CN118194142B - A post-earthquake repair engineering analysis method and system for smart pipe networks - Google Patents

Abstract

The present application discloses a post-earthquake repair engineering analysis method and system for smart pipe networks, which are used to improve the speed of post-earthquake smart pipe network repair. The post-earthquake repair engineering analysis method of the present application includes: receiving earthquake disaster alarms sent by disaster detection equipment; collecting downhole sensor data of underground pipelines within the jurisdiction area; analyzing the pipeline operation status according to the downhole sensor data; sending collection instructions to sub-intelligent manhole covers within a predetermined range, so that the sub-intelligent manhole covers collect and return downhole sensor data and spread the collection instructions; receiving downhole sensor data collected by sub-intelligent manhole covers in their respective jurisdiction areas; classifying and counting all downhole sensor data according to the pipeline ID of the underground pipeline to generate statistical results; marking data on an electronic map according to the location of the main intelligent manhole cover, the location of the sub-intelligent manhole cover and the statistical results; generating disaster conditions for at least one cluster area according to the operating status of each underground pipeline on the electronic map.

Description

A post-earthquake repair engineering analysis method and system for smart pipe networks

Technical Field

The embodiments of the present application relate to the field of smart pipe networks, and in particular, to a post-earthquake repair engineering analysis method and system for smart pipe networks.

Background Art

Urban integrated pipe network is an important part of urban construction. Strengthening the intelligent management of urban above-ground and underground pipe networks is of great significance to the healthy, safe and orderly development of cities. With the improvement of my country's urbanization level and the development of infrastructure, all cities have built large-scale and complex above-ground and underground integrated pipe network facilities, especially in the prosperous areas of the city center. Under each road, there are more than 20 underground pipelines such as water supply, drainage, gas, heat, electricity, and telecommunications. There is no efficient and suitable management method for the data of different underground lines. This makes it difficult to effectively integrate pipeline resources, resulting in frequent pipeline accidents, untimely emergency rescue, affecting the normal operation of the city, and the pipe network management has developed from extensive to intelligent.

Nowadays, the smart pipeline network is proposed to accurately detect and locate underground pipelines, implement monitoring and perception of pipeline damage and other faults, and build a comprehensive information platform system for the full life cycle management of underground pipelines, so as to timely warn and deal with abnormalities of underground pipelines to ensure the safety of people's lives and property. Its target is all underground pipelines from entering the city to serving the people's livelihood. Its main vein follows the urban road network (above ground and underground). The intelligent content includes a full life cycle integrated management system of accurate detection, underground identification, comprehensive perception and emergency linkage.

However, in the disaster-stricken areas where natural disasters such as earthquakes occur, the damage of underground pipelines inside the smart pipe network can easily cause the disaster-stricken areas to fall into the predicament of water shortage, power shortage, and gas shortage. In addition to a large amount of manpower and financial resources, post-earthquake repair work also requires a lot of material resources. It is very important to repair underground water pipelines, underground natural gas pipelines, power pipelines, and communication pipelines in the disaster-stricken areas in a timely manner. However, for the disaster-stricken areas, the repair of underground pipelines requires a lot of time to understand which pipelines are damaged, and it also takes a lot of time to determine the damaged parts. Under normal circumstances, traditional smart pipe networks can obtain pipeline operation data through sensors and upload them to the platform of the corresponding ownership unit. However, in the earthquake zone, communication facilities are often damaged, and the smart pipe network cannot communicate with the external connection. In addition, the sensors inside the pipeline may be damaged in the epicenter, which leads to a decrease in the repair speed of the post-earthquake smart pipe network.

Summary of the invention

Traditional underground pipelines need to use data cables for data transmission for data collection. Now, as an important part of the smart pipe network, smart manhole covers are innovative products that use modern scientific and technological means to improve the level of urban management and infrastructure management. Smart manhole covers are equipped with independent sensors, communication modules, controllers, etc. to form an independent intelligent system. They can not only realize real-time monitoring and data collection of information such as manhole cover status, surrounding environment, and traffic conditions, but also respond quickly to abnormal situations and make alarms and handle them in time. In addition, the smart manhole cover itself can operate independently. As the center of information transmission, compared with the information receiving device on the ground, the smart manhole cover can better collect data with the underground sensors. The most important thing is that ordinary manhole covers are widely distributed. After replacing them with smart manhole covers, the smart manhole covers can efficiently collect real-time data generated by sensors of underground pipe networks within a certain area through underground channels without the need to add exclusive data cables.

Based on the above-mentioned smart manhole cover, the present application discloses a post-earthquake repair engineering analysis method and system for smart pipe networks, which are used to improve the speed of post-earthquake smart pipe network repair.

The first aspect of the present application discloses a post-earthquake repair engineering analysis method for a smart pipe network, comprising:

The main terminal of the main intelligent manhole cover receives the earthquake disaster alarm sent by the disaster detection equipment;

The main terminal collects downhole sensor data of underground pipelines within the jurisdiction area;

The main terminal performs pipeline operation status analysis according to the downhole sensor data, generates pipeline area status data, and adds the pipeline area status data to the downhole sensor data;

The main terminal sends a collection instruction to the secondary intelligent manhole covers within a predetermined range, so that the secondary intelligent manhole covers within the predetermined range collect and return the downhole sensor data of the underground pipelines within their respective jurisdiction areas and spread the collection instruction;

The main terminal receives the underground sensor data collected by the secondary intelligent manhole covers in their respective jurisdiction areas;

The main terminal classifies and counts all the downhole sensor data according to the pipeline ID of the underground pipeline and generates statistical results;

The main terminal marks data on the electronic map according to the position of the main intelligent manhole cover, the position of the secondary intelligent manhole cover and the statistical results, so that the position distribution, normal operation section and abnormal operation section of each underground pipeline are displayed on the electronic map;

The master terminal generates a disaster situation for at least one cluster area according to the operation status of each underground pipeline on the electronic map.

Optionally, the main terminal performs pipeline operation status analysis based on downhole sensor data and generates pipeline area status data, including:

The main terminal determines the underground pipeline to be inspected that has no collected data based on the downhole sensor data;

The main terminal compares the normal historical records of the remaining pipelines in the database with the downhole sensor data for similarity, and determines the underground pipelines that are operating normally and those that are operating abnormally in the area;

The main terminal generates pipeline area status data based on the analysis of the underground pipelines to be inspected, the underground pipelines operating normally, and the underground pipelines operating abnormally.

Optionally, the downhole sensor data also includes damage point data;

After the main terminal analyzes the pipeline operation status according to the downhole sensor data and generates the pipeline area status data, the main terminal sends a collection instruction to the secondary intelligent manhole covers within a predetermined range, so that the secondary intelligent manhole covers within the predetermined range collect the downhole sensor data of the underground pipelines within their respective jurisdiction areas and spread the collection instruction. The post-earthquake repair engineering analysis method also includes:

When the underground pipelines with abnormal operation are transport pipes for transporting air and liquid, the main terminal uses the disaster damage point detection device to perform section detection on the underground pipelines with abnormal operation and generate detection results;

When the detection result shows that there is a damage point in the jurisdiction area, the main terminal uses the downhole image acquisition equipment to collect images of the underground pipeline with abnormal operation within the damage point range to obtain at least one pipeline shooting image;

The main terminal obtains a corresponding reference damaged image set of the underground pipeline with abnormal operation from the database according to the earthquake disaster alarm, wherein the reference damaged image set includes a camera image set and an infrared remote sensing camera image set, wherein the camera image set includes at least two pipeline damaged images of the underground pipeline with different damage conditions, and the infrared remote sensing camera image set includes at least two pipeline damaged images of the underground pipeline with different damage conditions;

The main terminal performs feature fusion on the pipeline photographed image and the pipeline damage image to generate at least one damage feature enhanced image;

The main terminal inputs at least one damaged feature enhanced image into a convolutional neural network recognition model for recognition analysis, and generates an analysis result;

The main terminal determines the damage situation with the highest probability according to the analysis results, and determines the shooting point of the pipeline image corresponding to the damage situation with the highest probability;

The main terminal determines the damage situation and shooting point with the highest probability as damage point data.

Optionally, the main terminal performs feature fusion on the pipeline photographed image and the pipeline damage image to generate at least one damage feature enhanced image, including:

The main terminal performs 1*1 convolution processing on the first pipeline damage image to generate damage label features;

The main terminal performs a 1*1 convolution operation on the image captured by the first pipeline to generate the captured convolution features;

The main terminal performs a regional pixel attention generation process and a channel multiplication process on the damaged label feature to generate a first processing feature;

The main terminal performs residual extraction and residual fusion processing on the first processing feature to generate a fusion residual;

The main terminal performs channel superposition of the fusion residual, the damaged label feature and the shooting convolution feature to generate a second processing feature;

The master terminal performs edge reconstruction on the second processing feature to generate a third processing feature;

The main terminal allocates attention to each neuron corresponding to the third processing feature, and screens out neurons whose attention is less than a first preset threshold, to generate a fourth processing feature;

The main terminal performs edge reconstruction on the fourth processing feature to generate enhancement parameters;

The main terminal restores and outputs the enhancement parameters to generate a damage feature enhanced image corresponding to the first pipeline captured image;

The main terminal performs feature fusion on each pipeline photographed image and pipeline damage image according to the above method to generate at least one damage feature enhanced image.

Optionally, when the underground pipeline with abnormal operation is a transport pipeline and a liquid transport pipeline, the main terminal uses a disaster damage point detection device to perform section detection on the underground pipeline with abnormal operation and generate detection results, including:

When the underground pipeline with abnormal operation is a transport pipeline and a liquid transport pipeline, the main terminal uses a disaster acoustic wave sensor to perform section detection on the underground pipeline with abnormal operation to generate first detection data;

The main terminal uses infrared remote sensing imaging equipment during disasters to perform section detection on the underground pipelines that are operating abnormally, and generates second detection data;

A detection result is generated according to the first detection data and the second detection data.

Optionally, after the main terminal generates a disaster situation for at least one cluster area according to the operation status of each underground pipeline on the electronic map, the post-earthquake repair engineering analysis method further includes:

The main terminal sends the disaster situation to the receiver of the smart pipe network;

When the main terminal does not obtain the successful reception notification sent by the receiver, the main terminal sends the disaster situation to the secondary intelligent manhole covers within the predetermined range, so that the secondary intelligent manhole covers within the predetermined range store the disaster situation and send the disaster situation to other receivers.

The second aspect of the present application discloses a post-earthquake repair engineering analysis method for a smart pipe network, comprising:

A first receiving unit, used for receiving an earthquake disaster alarm sent by a disaster detection device;

A collection unit, used to collect downhole sensor data of underground pipelines within the jurisdiction area;

A first generating unit, configured to perform pipeline operation status analysis according to downhole sensor data, generate pipeline area status data, and add the pipeline area status data to the downhole sensor data;

A first sending unit is used to send a collection instruction to the secondary intelligent manhole covers within a predetermined range, so that the secondary intelligent manhole covers within the predetermined range collect and return downhole sensor data of underground pipelines within their respective jurisdiction areas and spread the collection instruction;

The second receiving unit is used to receive the underground sensor data collected by the secondary intelligent manhole covers in their respective jurisdiction areas;

The second generating unit is used to classify and count all the downhole sensor data according to the pipeline ID of the underground pipeline to generate a statistical result;

A marking unit, used to mark data on an electronic map according to the position of the primary intelligent manhole cover, the position of the secondary intelligent manhole cover and the statistical results, so that the position distribution, normal operation section and abnormal operation section of each underground pipeline are displayed on the electronic map;

The third generating unit is used to generate a disaster situation for at least one cluster area according to the operating status of each underground pipeline on the electronic map.

Optionally, the first generating unit includes:

Determine the underground pipeline to be inspected without collected data based on the downhole sensor data;

Compare the normal historical records of the remaining pipelines in the database with the downhole sensor data for similarity, and determine the underground pipelines that are operating normally and those that are operating abnormally in the area;

Pipeline area status data is generated based on the analysis of underground pipelines to be inspected, underground pipelines operating normally, and underground pipelines operating abnormally.

Optionally, the downhole sensor data also includes damage point data;

After the first generating unit and before the first sending unit, the post-earthquake repair engineering analysis system further includes:

The fourth generating unit is used to perform section detection on the underground pipeline with abnormal operation by using the disaster damage point detection device when the underground pipeline with abnormal operation is a transport pipe and a liquid transport pipe, and generate a detection result;

The first acquisition unit is used to acquire images of the abnormal underground pipeline within the range of the damaged point using a downhole image acquisition device when the detection result shows that there is a damaged point in the jurisdiction area, and acquire at least one pipeline shooting image;

A second acquisition unit is used to acquire a corresponding reference damaged image set of the underground pipelines in abnormal operation from a database according to the earthquake disaster alarm, wherein the reference damaged image set includes a camera image set and an infrared remote sensing camera image set, wherein the camera image set includes at least two pipeline damaged images of the underground pipelines in different damage conditions, and the infrared remote sensing camera image set includes at least two pipeline damaged images of the underground pipelines in different damage conditions;

A fifth generating unit, configured to perform feature fusion on the captured pipeline image and the pipeline damage image to generate at least one damage feature enhanced image;

A sixth generating unit, used for inputting at least one damage feature enhanced image into a convolutional neural network recognition model for recognition analysis to generate an analysis result;

A first determination unit is used to determine the damage situation with the highest probability according to the analysis result, and determine the shooting point position of the pipeline image corresponding to the damage situation with the highest probability;

The second determining unit is used to determine the damage situation and shooting point with the highest probability as damage point data.

Optionally, the fifth generation unit includes:

Perform 1*1 convolution processing on the first pipeline damage image to generate damage label features;

Perform 1*1 convolution operation on the image captured by the first pipeline to generate the captured convolution features;

Performing a regional pixel attention generation process and a channel multiplication process on the damaged label feature to generate a first processing feature;

Performing residual extraction and residual fusion processing on the first processed features to generate fused residuals;

Channel-wise superposition of the fused residual, damaged label features, and shot convolution features to generate a second processing feature;

Reconstructing the edge of the second processing feature to generate a third processing feature;

Allocating attention to each neuron corresponding to the third processing feature, and screening out neurons whose attention is less than a first preset threshold, to generate a fourth processing feature;

Performing edge reconstruction on the fourth processing feature to generate enhancement parameters;

The enhancement parameters are restored and outputted to generate a damage feature enhanced image corresponding to the first pipeline captured image;

According to the above method, feature fusion is performed on each pipeline photographed image and pipeline damage image to generate at least one damage feature enhanced image.

Optionally, the fourth generating unit includes:

When the underground pipeline with abnormal operation is a transport pipe for air and a transport pipe for liquid, a disaster acoustic wave sensor is used to perform section detection on the underground pipeline with abnormal operation to generate first detection data;

Use disaster-time infrared remote sensing imaging equipment to conduct section inspection of underground pipelines that are operating abnormally, and generate second inspection data;

A detection result is generated according to the first detection data and the second detection data.

Optionally, after the third generation unit, the post-earthquake repair engineering analysis system further includes:

The second sending unit is used to send the disaster situation to the receiver of the smart pipe network;

The third sending unit is used to send the disaster situation to the secondary smart manhole covers within a predetermined range when the successful reception notification sent by the receiver is not obtained, so that the secondary smart manhole covers within the predetermined range store the disaster situation and send the disaster situation to other receivers.

The third aspect of the present application provides a data security transmission system based on a smart pipe network, comprising:

Processor, memory, input-output unit, and bus;

The processor is connected to the memory, the input and output unit, and the bus;

The memory stores a program, and the processor calls the program to execute the first aspect and any optional post-earthquake repair engineering analysis method for the smart pipe network of the first aspect.

The fourth aspect of the present application provides a computer-readable storage medium, on which a program is stored. When the program is executed on a computer, it executes the post-earthquake repair engineering analysis method of the smart pipeline network in the first aspect and any optional method in the first aspect.

It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

In this application, when the main terminal of the main intelligent manhole cover receives the earthquake disaster alarm sent by the disaster detection equipment, since the main intelligent manhole cover can operate independently of the smart pipe network system, the main terminal will collect the downhole sensor data of the underground pipeline within its own jurisdiction. The main terminal then analyzes the pipeline operation status based on the downhole sensor data and generates pipeline area status data. The downhole sensor data and pipeline area status data are collectively referred to as downhole sensor data. The main terminal sends a collection instruction to the secondary intelligent manhole cover within the predetermined range, so that the secondary intelligent manhole cover within the predetermined range collects and returns the downhole sensor data of the underground pipeline within their respective jurisdictions and spreads the collection instruction. The main terminal receives the downhole sensor data collected by the secondary intelligent manhole cover in their respective jurisdictions. The main terminal classifies and counts all the downhole sensor data according to the pipeline number ID of the underground pipeline and generates statistical results. The main terminal marks the data on the electronic map according to the position of the main intelligent manhole cover, the position of the secondary intelligent manhole cover and the statistical results, so that the electronic map displays the location distribution, normal operation section and abnormal operation section of each underground pipeline. The master terminal generates a disaster situation for at least one cluster area according to the operation status of each underground pipeline on the electronic map.

Through the widely distributed and independently operated intelligent manhole covers, the underground sensor data is collected and analyzed. Even if a few intelligent manhole covers are damaged, a large number of intelligent manhole covers can still collect data. When the intelligent manhole covers are collecting data under normal circumstances, they can collect data with the sensors of the underground pipelines. After the earthquake, as long as the sensors are not damaged, data collection can be carried out as usual. Secondly, even if the underground pipeline sensors in the current area are damaged, since the underground pipelines span multiple areas and there are a large number of branch parts, that is, the upstream part of the pipeline and the downstream part of the pipeline, there are sensors in the upstream part of the pipeline and the downstream part of the pipeline. The important thing is that there is an undamaged sensor, and the damage to the midstream pipeline can be analyzed. This is mainly due to the fact that the distribution of intelligence is as wide as that of the underground pipelines. The main terminal classifies and counts all the underground sensor data according to the pipeline ID of the underground pipeline, generates statistical results, and obtains the operation status of the pipeline, and marks the data on the electronic map, so that the operation status of each underground pipeline can be observed from the map, and the disaster situation can be generated for at least one cluster area. This type of data is stored in the smart manhole cover so that repair personnel can obtain relevant data to formulate repair strategies, greatly improving the speed of post-earthquake smart pipeline repair.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

FIG1 is a schematic diagram of a structure of the post-earthquake repair engineering analysis method of the present application;

FIG2 is a schematic diagram of an embodiment of the first stage of the post-earthquake restoration engineering analysis method of the present application;

FIG3 is a schematic diagram of an embodiment of the second stage of the post-earthquake restoration engineering analysis method of the present application;

FIG4 is a schematic diagram of an embodiment of the third stage of the post-earthquake repair engineering analysis method of the present application;

FIG5 is a schematic diagram of an embodiment of the fourth stage of the post-earthquake repair engineering analysis method of the present application;

FIG6 is a schematic diagram of an embodiment of the post-earthquake restoration engineering analysis system of the present application;

FIG7 is a schematic diagram of another embodiment of the post-earthquake restoration engineering analysis system of the present application;

FIG8 is a schematic diagram of another embodiment of the post-earthquake repair engineering analysis system of the present application.

DETAILED DESCRIPTION

In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and/or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and/or combinations thereof.

It should also be understood that the term “and/or” used in the specification and appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

In the prior art, in the disaster-stricken areas where natural disasters such as earthquakes occur, the underground pipelines inside the smart pipe network are damaged, which easily causes the disaster-stricken areas to fall into the predicament of water shortage, power shortage, gas shortage, etc., and the post-earthquake repair work requires not only a lot of manpower and financial resources, but also a lot of material resources. It is very important to repair underground water pipelines, underground natural gas pipelines, power pipelines, and communication pipelines in the disaster-stricken areas in a timely manner. However, for the disaster-stricken areas, the repair of underground pipelines requires a lot of time to understand which pipelines are damaged, and it also takes a lot of time to determine the damaged parts. Under normal circumstances, traditional smart pipe networks can obtain pipeline operation data through sensors and upload them to the platform of the corresponding ownership unit, but in the earthquake zone, communication facilities are often damaged, and the smart pipe network cannot communicate with the external connection, and the sensors inside the pipelines may be damaged in the epicenter, which leads to a decrease in the repair speed of the post-earthquake smart pipe network.

Based on this, the smart manhole cover of the present application is equipped with independent sensors, communication modules, controllers, etc. to form an independent intelligent system, which can not only realize real-time monitoring and data collection of information such as the manhole cover status, surrounding environment, and traffic conditions, but also can quickly respond to abnormal situations, and promptly alarm and process. And the smart manhole cover itself can operate independently. As the hub of information transmission, compared with the information receiving device on the ground, the smart manhole cover can better collect data with the underground sensors. The most important thing is that ordinary manhole covers are widely distributed. After replacing the smart manhole cover, the smart manhole cover can efficiently collect real-time data generated by sensors of underground pipe networks within a certain area through the underground channel without the need to add dedicated data lines.

Based on the above-mentioned smart manhole cover, the present application discloses a post-earthquake repair engineering analysis method and system for smart pipe networks, which are used to improve the speed of post-earthquake smart pipe network repair.

The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

The method of the present application can be applied to a server, a device, a terminal or other devices with logic processing capabilities, and the present application does not limit this. For the convenience of description, the following description is made by taking the execution subject as the main terminal as an example.

Referring to FIG. 1 , the present application provides an embodiment of a post-earthquake repair engineering analysis method for a smart pipe network, including:

101. The main terminal of the main intelligent manhole cover receives the earthquake disaster alarm sent by the disaster detection equipment;

In this embodiment, the main terminal is the control terminal on the main intelligent manhole cover. It should be noted that there are multiple intelligent manhole covers in a large area. Generally speaking, the intelligent manhole covers used in the central part with more underground pipelines have more functions, and they play a role in controlling other secondary intelligent manhole covers after the earthquake, but the identities of the main intelligent manhole cover and the secondary intelligent manhole cover can be converted to each other. When the main intelligent manhole cover is damaged in the epicenter, another intelligent manhole cover is needed as the core of the collection. When the main terminal of the main intelligent manhole cover receives the earthquake disaster alarm, the internal detection finds that there is damage, then other intelligent manhole covers in the coverage area can be allowed to take over the collection task instead. If the main terminal of the main intelligent manhole cover can no longer receive the earthquake disaster alarm, after receiving the earthquake disaster alarm, other secondary intelligent manhole covers will actively take over the collection task and become the main intelligent manhole cover when they send the earthquake disaster alarm to the main terminal of the main intelligent manhole cover but there is no response.

102. The main terminal collects downhole sensor data of underground pipelines within the jurisdiction area;

The main terminal collects downhole sensor data of underground pipelines within its exclusive jurisdiction based on the area it covers. This step is the same as before the earthquake. Even if no earthquake is detected, the daily function of the main intelligent manhole cover is to collect downhole sensor data of underground pipelines within the jurisdiction. The only difference is that after collection, the data needs to be classified and encrypted, and transmitted through specific receivers to the platform of the ownership unit.

At present, since the disaster information has been sent, in order to carry out rescue work in a timely manner, it is necessary to collect, analyze and save data on specific underground pipelines that are essential for life in the disaster area, so that front-line personnel can analyze the stored information in a timely manner and speed up the rescue and relief tasks.

103. The main terminal performs pipeline operation status analysis according to the downhole sensor data, generates pipeline area status data, and adds the pipeline area status data to the downhole sensor data;

After the master terminal collects the downhole sensor data of the underground pipeline in the jurisdiction area, the master terminal analyzes the pipeline operation status according to the downhole sensor data and generates pipeline area status data. For example, when the downhole sensor data shows that the flow rate of the underground water pipe is 0, it means that in the jurisdiction area, the underground water pipe has been damaged upstream or at this location, and there is a lack of water or no water downstream.

If it is a normal value, it means that the possibility of damage to the underground water pipe in this jurisdiction is small, and the focus can be on repairing other pipelines.

When there is no sensor data, it means that the water flow sensor of the underground water pipe is damaged and needs to be deduced through other upstream data or downstream data.

Downhole sensor data and pipeline area status data are collectively referred to as downhole sensor data.

104. The main terminal sends a collection instruction to the secondary intelligent manhole covers within a predetermined range, so that the secondary intelligent manhole covers within the predetermined range collect and return the downhole sensor data of the underground pipelines within their respective jurisdiction areas and spread the collection instruction;

The main terminal sends a collection instruction to the secondary intelligent manhole covers within the predetermined range, so that the secondary intelligent manhole covers within the predetermined range collect and return the underground sensor data of the underground pipelines within their respective jurisdictions and spread the collection instruction. Specifically, the main terminal sends the collection instruction in the coverage area, so that the surrounding intelligent manhole covers collect and analyze the underground sensor data and send it back to the main terminal. Secondly, the surrounding intelligent manhole covers will send instructions outward, so that the intelligent manhole covers in the entire disaster area can collect and analyze data.

105. The main terminal receives the underground sensor data collected by the secondary intelligent manhole covers in their respective jurisdiction areas;

106. The main terminal classifies and counts all the downhole sensor data according to the pipeline ID of the underground pipeline and generates statistical results;

When the main terminal receives the underground sensor data collected by the secondary smart manhole covers in their respective jurisdictions, it is necessary to uniformly summarize the data collected and analyzed by each smart manhole cover. Specifically, the data is classified according to the pipeline ID of the underground pipeline, and the collected data of each underground bus is analyzed as a whole to determine which area is damaged and which areas are intact. In addition, for areas where no data is collected, it is necessary to analyze the data of the upstream and downstream of the underground pipelines and finally generate statistical results.

107. The main terminal marks data on the electronic map according to the position of the main intelligent manhole cover, the position of the secondary intelligent manhole cover and the statistical results, so that the position distribution, normal operation section and abnormal operation section of each underground pipeline are displayed on the electronic map;

The main terminal marks the data on the electronic map according to the location of the main intelligent manhole cover, the location of the secondary intelligent manhole cover and the statistical results. That is, on the ground map, not only the location of the intelligent manhole cover is marked, but also the location of each underground pipeline in the smart pipe network and the operation status of each section are marked.

108. The main terminal generates a disaster situation for at least one cluster area according to the operation status of each underground pipeline on the electronic map.

The main terminal analyzes the underground pipelines of a village, town or county, and determines whether the water resource input, natural gas input and other necessary resource input in the area meet the minimum living security based on the operation of the underground pipelines. If not, the disaster situation is serious.

In this embodiment, when the main terminal of the main intelligent manhole cover receives the earthquake disaster alarm sent by the disaster detection equipment, since the main intelligent manhole cover can operate independently of the smart pipe network system, the main terminal will collect the downhole sensor data of the underground pipeline within its own jurisdiction. The main terminal then analyzes the pipeline operation status based on the downhole sensor data and generates pipeline area status data. The downhole sensor data and pipeline area status data are collectively referred to as downhole sensor data. The main terminal sends a collection instruction to the secondary intelligent manhole cover within the predetermined range, so that the secondary intelligent manhole cover within the predetermined range collects and returns the downhole sensor data of the underground pipeline within their respective jurisdictions and spreads the collection instruction. The main terminal receives the downhole sensor data collected by the secondary intelligent manhole cover in their respective jurisdictions. The main terminal classifies and counts all the downhole sensor data according to the pipeline ID of the underground pipeline and generates statistical results. The main terminal marks the data on the electronic map according to the location of the main intelligent manhole cover, the location of the secondary intelligent manhole cover and the statistical results, so that the location distribution, normal operation section and abnormal operation section of each underground pipeline are displayed on the electronic map. The master terminal generates a disaster situation for at least one cluster area according to the operation status of each underground pipeline on the electronic map.

Through the widely distributed and independently operated intelligent manhole covers, the underground sensor data is collected and analyzed. Even if a few intelligent manhole covers are damaged, a large number of intelligent manhole covers can still collect data. When the intelligent manhole covers are collecting data under normal circumstances, they can collect data with the sensors of the underground pipelines. After the earthquake, as long as the sensors are not damaged, data collection can be carried out as usual. Secondly, even if the underground pipeline sensors in the current area are damaged, since the underground pipelines span multiple areas and there are a large number of branch parts, that is, the upstream part of the pipeline and the downstream part of the pipeline, there are sensors in the upstream part of the pipeline and the downstream part of the pipeline. The important thing is that there is an undamaged sensor, and the damage to the midstream pipeline can be analyzed. This is mainly due to the fact that the distribution of intelligence is as wide as that of the underground pipelines. The main terminal classifies and counts all the underground sensor data according to the pipeline ID of the underground pipeline, generates statistical results, and obtains the operation status of the pipeline, and marks the data on the electronic map, so that the operation status of each underground pipeline can be observed from the map, and the disaster situation can be generated for at least one cluster area. This type of data is stored in the smart manhole cover so that repair personnel can obtain relevant data to formulate repair strategies, greatly improving the speed of post-earthquake smart pipeline repair.

Referring to FIG. 2 , FIG. 3 , FIG. 4 , and FIG. 5 , the present application provides another embodiment of a post-earthquake repair engineering analysis method for a smart pipe network, including:

201. The main terminal of the main intelligent manhole cover receives the earthquake disaster alarm sent by the disaster detection equipment;

202. The main terminal collects downhole sensor data of underground pipelines within the jurisdiction area;

Steps 201 to 202 in this embodiment are similar to steps 101 to 102 in the aforementioned embodiment, and are not described again here.

203. The main terminal determines the underground pipeline to be inspected that has no collected data according to the downhole sensor data;

204. The main terminal compares the normal historical records of the remaining pipelines in the database with the downhole sensor data for similarity, and determines the underground pipelines that are operating normally and the underground pipelines that are operating abnormally in the area;

205. The main terminal generates pipeline area status data according to the analysis of the underground pipeline to be inspected, the underground pipeline operating normally and the underground pipeline operating abnormally. The downhole sensor data and the pipeline area status data are collectively referred to as downhole sensor data;

In this embodiment, the main terminal determines the underground pipelines to be inspected that have no collected data based on the downhole sensor data, and first screens out the unknown underground pipelines. Next, the main terminal compares the normal historical records of the remaining pipelines in the database with the downhole sensor data for similarity, and determines the underground pipelines that are operating normally and the underground pipelines that are operating abnormally in the area. The main terminal generates pipeline area status data based on the analysis of the underground pipelines to be inspected, the underground pipelines that are operating normally, and the underground pipelines that are operating abnormally. If it is a water pipe, the flow rate and other data are compared, and the specific comparison is compared with the pre-earthquake data, which will not be repeated here.

206. When the underground pipeline with abnormal operation is a transport pipeline and a liquid transport pipeline, the main terminal uses a disaster acoustic wave sensor to perform section detection on the underground pipeline with abnormal operation to generate first detection data;

207. The main terminal uses the disaster-time infrared remote sensing imaging equipment to perform section detection on the underground pipeline with abnormal operation, and generates second detection data;

208. Generate a test result according to the first test data and the second test data;

For the transport pipes and liquid pipes that are prone to leakage, acoustic sensors and infrared remote sensing imaging equipment can be used to detect the damaged points. It should be noted that acoustic sensors and infrared remote sensing imaging equipment are only triggered when a disaster occurs, or when the pipeline is confirmed to be damaged. The two can operate independently and are only controlled by the smart manhole cover.

When the underground pipelines that are operating abnormally are air transport pipes and liquid transport pipes, the main terminal uses disaster-time acoustic wave sensors to perform section detection on the underground pipelines that are operating abnormally to generate first detection data. The main terminal uses disaster-time infrared remote sensing imaging equipment to perform section detection on the underground pipelines that are operating abnormally to generate second detection data. The detection results are generated based on the first detection data and the second detection data to achieve the function of double insurance.

209. When the detection result shows that there is a damage point in the jurisdiction area, the main terminal uses the downhole image acquisition equipment to collect images of the underground pipeline with abnormal operation within the range of the damage point, and obtains at least one pipeline shooting image;

210. The main terminal obtains a corresponding reference damaged image set of the underground pipeline in abnormal operation from a database according to the earthquake disaster alarm, wherein the reference damaged image set includes a camera image set and an infrared remote sensing camera image set, wherein the camera image set includes at least two pipeline damaged images of the underground pipeline in different damage conditions, and the infrared remote sensing camera image set includes at least two pipeline damaged images of the underground pipeline in different damage conditions;

In this embodiment, when the detection result shows that there is a damage point in the jurisdiction area, if there is maintenance equipment in the area, the damage point can be actively confirmed, and the main terminal uses the downhole image acquisition equipment to collect images of the abnormal underground pipeline in the range of the damage point to obtain at least one pipeline shooting image. The downhole image acquisition equipment includes ordinary cameras and infrared remote sensing cameras.

The main terminal obtains the corresponding reference damaged image set of the abnormally operating underground pipeline from the database according to the earthquake disaster alarm. The reference damaged image set includes a camera-shot image set and an infrared remote sensing camera image set. The camera-shot image set includes at least two pipeline damaged images of underground pipelines in different damage conditions. The infrared remote sensing camera image set includes at least two pipeline damaged images of underground pipelines in different damage conditions. In a lightless environment, infrared remote sensing cameras and infrared remote sensing camera image sets are mainly used. When there is an available light source, ordinary cameras and camera-shot image sets are used.

It should be noted that both can be used together.

211. The main terminal performs 1*1 convolution processing on the first pipeline damage image to generate a damage label feature;

212. The main terminal performs a 1*1 convolution operation on the image captured by the first pipeline to generate a captured convolution feature;

213. The main terminal performs a regional pixel attention generation process and a channel multiplication process on the damaged label feature to generate a first processing feature;

214. The main terminal performs residual extraction and residual fusion processing on the first processing feature to generate a fusion residual;

215. The main terminal performs channel superposition on the fusion residual, the damaged label feature and the shooting convolution feature to generate a second processing feature;

216. The master terminal performs edge reconstruction on the second processing feature to generate a third processing feature;

217. The main terminal allocates attention to each neuron corresponding to the third processing feature, and screens out neurons whose attention is less than a first preset threshold, to generate a fourth processing feature;

218. The main terminal performs edge reconstruction on the fourth processing feature to generate an enhancement parameter;

219. The main terminal restores and outputs the enhancement parameters to generate a damage feature enhanced image corresponding to the first pipeline captured image;

220. The main terminal performs feature fusion on each pipeline photographed image and pipeline damage image according to the above method to generate at least one damage feature enhanced image;

In this embodiment, the main terminal performs 1*1 convolution processing on the first pipeline damage image to generate a damage label feature. The main terminal performs 1*1 convolution operation on the first pipeline shooting image to generate a shooting convolution feature.

The main terminal performs regional pixel attention generation processing and channel multiplication processing on the damaged label feature to generate a first processing feature. Specifically, the main terminal performs regional pixel attention generation processing and channel multiplication processing on the damaged label feature to generate a first processing feature. Specifically, the main terminal can use the regional pixel attention module RPA to perform regional pixel attention generation processing and channel multiplication processing on the fourth superposition feature. The regional pixel attention module RPA in this step includes a BatchNorm-DefConv-ReLU, a BatchNorm-DefConv, a SigMoid function module and a bilinear interpolation module. BatchNorm-DefConv-ReLU, BatchNorm-DefConv, SigMoid function module and bilinear interpolation module are connected in series in sequence. The BatchNorm-DefConv-ReLU layer and the BatchNorm-DefConv layer here are both commonly used feature processing layers in convolutional neural networks. The SigMoid function is a known function, and the bilinear interpolation operation method is also a known algorithm. The regional pixel attention module RPA is the first attention mechanism. Since a weight is assigned to each regional pixel of the damaged label feature, the neural network model pays more attention to the area with obvious splicing features.

The main terminal performs residual extraction and residual fusion processing on the first processing feature to generate a fused residual. This step can reduce changes to the original image.

The main terminal performs residual extraction on the first processing feature to generate a first residual, then performs residual extraction on the first residual to generate a second residual, then performs residual extraction on the second residual to generate a third residual, and finally fuses the three residuals according to a preset superposition coefficient to generate a final fused residual.

The main terminal performs channel superposition of the fusion residual, the damaged label feature and the shooting convolution feature to generate a second processing feature. The main terminal performs edge reconstruction on the second processing feature to generate a third processing feature.

The main terminal allocates attention to each neuron corresponding to the third processing feature, and screens out neurons whose attention is less than the first preset threshold to generate a fourth processing feature. Specifically, the main terminal allocates attention to each neuron corresponding to the third processing feature, and screens out neurons whose attention is less than the first preset threshold to generate a fourth processing feature, the purpose of which is to eliminate some invalid neurons.

The terminal reconstructs the edge of the fourth processing feature, generates an enhancement parameter, restores and outputs the enhancement parameter, and generates a damage feature enhanced image corresponding to the first pipeline captured image, which is specifically restored and outputted through the output module Conv_out. And according to the above method, feature fusion is performed on each pipeline captured image and pipeline damage image to generate a corresponding damage feature enhanced image.

221. The main terminal inputs at least one damage feature enhanced image into a convolutional neural network recognition model for recognition analysis, and generates an analysis result;

222. The main terminal determines the damage situation with the highest probability according to the analysis result, and determines the shooting point of the pipeline image corresponding to the damage situation with the highest probability;

223. The main terminal determines the damage situation and shooting point with the highest probability as damage point data;

The main terminal inputs at least one damage feature enhanced image into the convolutional neural network recognition model for recognition analysis and generates analysis results. The convolutional neural network recognition model here is a trained model trained on some specific pipeline damage images. The main terminal determines the damage with the highest probability based on the analysis results of all images, and determines the shooting point of the pipeline image corresponding to the damage with the highest probability. The location sends the corresponding damage, and the shooting position corresponding to this image is determined as the damage point. If the highest probability is less than the preset 20%, it means that the damage at this location may come from upstream and cannot be detected in this jurisdiction.

224. The main terminal sends a collection instruction to the secondary intelligent manhole covers within the predetermined range, so that the secondary intelligent manhole covers within the predetermined range collect and return the downhole sensor data of the underground pipelines within their respective jurisdiction areas and spread the collection instruction;

225. The main terminal receives the underground sensor data collected by the secondary intelligent manhole covers in their respective jurisdiction areas;

226. The main terminal classifies and counts all the downhole sensor data according to the pipeline ID of the underground pipeline and generates statistical results;

227. The main terminal marks data on the electronic map according to the position of the main intelligent manhole cover, the position of the secondary intelligent manhole cover and the statistical results, so that the position distribution, normal operation section and abnormal operation section of each underground pipeline are displayed on the electronic map;

228. The master terminal generates a disaster situation for at least one cluster area according to the operation status of each underground pipeline on the electronic map;

Steps 224 to 228 in this embodiment are similar to steps 104 to 108 in the aforementioned embodiment and are not described again here.

229. The main terminal sends the disaster situation to the receiver of the smart pipe network;

230. When the main terminal does not obtain the successful reception notification sent by the receiver, the main terminal sends the disaster situation to the secondary intelligent manhole covers within the predetermined range, so that the secondary intelligent manhole covers within the predetermined range store the disaster situation and send the disaster situation to other receivers.

The terminal main terminal sends the disaster situation to the receiver of the smart pipe network. However, if the transmission fails due to damage to the communication network or other reasons, the main terminal sends the disaster situation to the secondary smart manhole covers within the predetermined range, so that the secondary smart manhole covers within the predetermined range can store the disaster situation and send the disaster situation to other receivers, that is, spread it outward. If none of them can be sent, the data will be saved inside the smart manhole cover and wait for rescue personnel to obtain it.

In this embodiment, when the main terminal of the main intelligent manhole cover receives the earthquake disaster alarm sent by the disaster detection equipment, since the main intelligent manhole cover can operate independently of the smart pipe network system, the main terminal will collect the downhole sensor data of the underground pipelines within its own jurisdiction. The main terminal determines the underground pipelines to be inspected for which no data has been collected based on the downhole sensor data. The main terminal compares the normal historical records of the remaining pipelines in the database with the downhole sensor data for similarity, and determines the underground pipelines that are operating normally and the underground pipelines that are operating abnormally in the area. The main terminal generates pipeline area status data based on the analysis of the underground pipelines to be inspected, the underground pipelines that are operating normally, and the underground pipelines that are operating abnormally. The downhole sensor data and the pipeline area status data are collectively referred to as downhole sensor data.

When the underground pipeline with abnormal operation is a transport pipeline and a liquid transport pipeline, the main terminal uses a disaster acoustic wave sensor to perform section detection on the underground pipeline with abnormal operation and generates first detection data. The main terminal uses a disaster infrared remote sensing imaging device to perform section detection on the underground pipeline with abnormal operation and generates second detection data. A detection result is generated according to the first detection data and the second detection data. When the detection result shows that there is a damage point in the jurisdiction area, the main terminal uses a downhole image acquisition device to collect images of the underground pipeline with abnormal operation within the damage point range and obtains at least one pipeline shooting image. The main terminal obtains the corresponding reference damage image set of the underground pipeline with abnormal operation from the database according to the earthquake disaster alarm. The reference damage image set includes a camera shooting image set and an infrared remote sensing camera image set. The camera shooting image set includes at least two pipeline damage images with different damage conditions of the underground pipeline, and the infrared remote sensing camera image set includes at least two pipeline damage images with different damage conditions of the underground pipeline. The main terminal performs 1*1 convolution processing on the first pipeline damage image to generate a damage label feature. The main terminal performs 1*1 convolution operation on the first pipeline shooting image to generate a shooting convolution feature. The main terminal performs regional pixel attention generation processing and channel multiplication processing on the damaged label feature to generate a first processing feature. The main terminal performs residual extraction and residual fusion processing on the first processing feature to generate a fused residual. The main terminal performs channel superposition on the fused residual, the damaged label feature and the shooting convolution feature to generate a second processing feature. The main terminal performs edge reconstruction on the second processing feature to generate a third processing feature. The main terminal allocates attention to each neuron corresponding to the third processing feature, and screens out neurons whose attention is less than a first preset threshold to generate a fourth processing feature. The main terminal performs edge reconstruction on the fourth processing feature to generate an enhancement parameter. The main terminal restores and outputs the enhancement parameter to generate a damage feature enhanced image corresponding to the first pipeline shooting image. The main terminal performs feature fusion on each pipeline shooting image and pipeline damage image according to the above method to generate at least one damage feature enhanced image. The main terminal inputs at least one damage feature enhanced image into the convolutional neural network recognition model for recognition analysis to generate an analysis result. The main terminal determines the damage situation with the highest probability based on the analysis result, and determines the shooting point position of the pipeline image corresponding to the damage situation with the highest probability. The main terminal determines the damage situation and shooting point with the highest probability as damage point data.

The main terminal sends a collection instruction to the secondary intelligent manhole covers within the predetermined range, so that the secondary intelligent manhole covers within the predetermined range collect and transmit back the downhole sensor data of the underground pipelines in their respective jurisdictions and spread the collection instructions. The main terminal receives the downhole sensor data collected by the secondary intelligent manhole covers in their respective jurisdictions. The main terminal classifies and counts all the downhole sensor data according to the pipeline ID of the underground pipeline and generates statistical results. The main terminal marks the data on the electronic map according to the location of the main intelligent manhole cover, the location of the secondary intelligent manhole cover and the statistical results, so that the location distribution, normal operating sections and abnormal operating sections of each underground pipeline are displayed on the electronic map. The main terminal generates a disaster situation for at least one cluster area according to the operating status of each underground pipeline on the electronic map.

The main terminal sends the disaster situation to the receiver of the smart pipe network. When the main terminal does not obtain the successful reception notification sent by the receiver, the main terminal sends the disaster situation to the secondary smart manhole covers within the predetermined range, so that the secondary smart manhole covers within the predetermined range store the disaster situation and send the disaster situation to other receivers.

Through the widely distributed and independently operated intelligent manhole covers, the underground sensor data is collected and analyzed. Even if a few intelligent manhole covers are damaged, a large number of intelligent manhole covers can still collect data. When the intelligent manhole covers are collecting data under normal circumstances, they can collect data with the sensors of the underground pipelines. After the earthquake, as long as the sensors are not damaged, data collection can be carried out as usual. Secondly, even if the underground pipeline sensors in the current area are damaged, since the underground pipelines span multiple areas and there are a large number of branch parts, that is, the upstream part of the pipeline and the downstream part of the pipeline, there are sensors in the upstream part of the pipeline and the downstream part of the pipeline. The important thing is that there is an undamaged sensor, and the damage to the midstream pipeline can be analyzed. This is mainly due to the fact that the distribution of intelligence is as wide as that of the underground pipelines. The main terminal classifies and counts all the underground sensor data according to the pipeline ID of the underground pipeline, generates statistical results, and obtains the operation status of the pipeline, and marks the data on the electronic map, so that the operation status of each underground pipeline can be observed from the map, and the disaster situation can be generated for at least one cluster area. This type of data is stored in the smart manhole cover so that repair personnel can obtain relevant data to formulate repair strategies, greatly improving the speed of post-earthquake smart pipeline repair.

Please refer to FIG6 . The present application provides an embodiment of a post-earthquake repair engineering analysis system for a smart pipe network, including:

The first receiving unit 601 is used to receive the earthquake disaster alarm sent by the disaster detection equipment;

The acquisition unit 602 is used to acquire downhole sensor data of underground pipelines within the jurisdiction area;

A first generating unit 603 is used to analyze the pipeline operation status according to the downhole sensor data, generate pipeline area status data, and add the pipeline area status data to the downhole sensor data;

The first sending unit 604 is used to send a collection instruction to the secondary intelligent manhole covers within a predetermined range, so that the secondary intelligent manhole covers within the predetermined range collect and return the downhole sensor data of the underground pipelines within their respective jurisdiction areas and spread the collection instruction;

The second receiving unit 605 is used to receive the underground sensor data collected by the secondary intelligent manhole covers in their respective jurisdiction areas;

The second generating unit 606 is used to classify and count all the downhole sensor data according to the pipeline ID of the underground pipeline to generate a statistical result;

The marking unit 607 is used to mark data on the electronic map according to the position of the primary intelligent manhole cover, the position of the secondary intelligent manhole cover and the statistical results, so that the position distribution, normal operation section and abnormal operation section of each underground pipeline are displayed on the electronic map;

The third generating unit 608 is used to generate a disaster situation for at least one cluster area according to the operation status of each underground pipeline on the electronic map.

Please refer to FIG. 7 . The present application provides another embodiment of a post-earthquake repair engineering analysis system for a smart pipe network, including:

The first receiving unit 701 is used to receive the earthquake disaster alarm sent by the disaster detection equipment;

The acquisition unit 702 is used to acquire downhole sensor data of underground pipelines within the jurisdiction area;

The first generating unit 703 is used to analyze the pipeline operation status according to the downhole sensor data and generate pipeline area status data. The downhole sensor data and the pipeline area status data are collectively referred to as downhole sensor data;

Optionally, the first generating unit 703 includes:

Determine the underground pipeline to be inspected without collected data based on the downhole sensor data;

Compare the normal historical records of the remaining pipelines in the database with the downhole sensor data for similarity, and determine the underground pipelines that are operating normally and those that are operating abnormally in the area;

Pipeline area status data is generated based on the analysis of underground pipelines to be inspected, underground pipelines operating normally, and underground pipelines operating abnormally.

The fourth generating unit 704 is used to perform section detection on the underground pipeline with abnormal operation by using the disaster damage point detection device when the underground pipeline with abnormal operation is a transport pipe and a liquid transport pipe, and generate a detection result;

Optionally, the fourth generating unit 704 includes:

When the underground pipeline with abnormal operation is a transport pipe for air and a transport pipe for liquid, a disaster acoustic wave sensor is used to perform section detection on the underground pipeline with abnormal operation to generate first detection data;

Use disaster-time infrared remote sensing imaging equipment to conduct section inspection of underground pipelines that are operating abnormally, and generate second inspection data;

A detection result is generated according to the first detection data and the second detection data.

The first acquisition unit 705 is used to acquire at least one pipeline photographed image by using a downhole image acquisition device to acquire images of the abnormal underground pipeline within the range of the damaged point when the detection result shows that there is a damaged point in the jurisdiction area;

The second acquisition unit 706 is used to acquire a corresponding reference damaged image set of the underground pipelines in abnormal operation from the database according to the earthquake disaster alarm, wherein the reference damaged image set includes a camera image set and an infrared remote sensing camera image set, wherein the camera image set includes at least two pipeline damaged images of the underground pipelines in different damage conditions, and the infrared remote sensing camera image set includes at least two pipeline damaged images of the underground pipelines in different damage conditions;

A fifth generating unit 707 is used to perform feature fusion on the pipeline photographed image and the pipeline damage image to generate at least one damage feature enhanced image;

Optionally, the fifth generating unit 707 includes:

Perform 1*1 convolution processing on the first pipeline damage image to generate damage label features;

Perform 1*1 convolution operation on the image captured by the first pipeline to generate the captured convolution features;

Performing a regional pixel attention generation process and a channel multiplication process on the damaged label feature to generate a first processing feature;

Performing residual extraction and residual fusion processing on the first processed features to generate fused residuals;

Channel-wise superposition of the fused residual, damaged label features, and shot convolution features to generate a second processing feature;

Reconstructing the edge of the second processing feature to generate a third processing feature;

Allocating attention to each neuron corresponding to the third processing feature, and screening out neurons whose attention is less than a first preset threshold, to generate a fourth processing feature;

Performing edge reconstruction on the fourth processing feature to generate enhancement parameters;

The enhancement parameters are restored and outputted to generate a damage feature enhanced image corresponding to the first pipeline captured image;

According to the above method, feature fusion is performed on each pipeline photographed image and pipeline damage image to generate at least one damage feature enhanced image.

A sixth generating unit 708, configured to input at least one damage feature enhanced image into a convolutional neural network recognition model for recognition analysis and generate an analysis result;

The first determining unit 709 is used to determine the damage situation with the highest probability according to the analysis result, and determine the shooting point of the pipeline image corresponding to the damage situation with the highest probability;

The second determining unit 710 is used to determine the damage situation and shooting point with the highest probability as damage point data.

The first sending unit 711 is used to send a collection instruction to the secondary intelligent manhole covers within a predetermined range, so that the secondary intelligent manhole covers within the predetermined range collect and return the downhole sensor data of the underground pipelines within their respective jurisdiction areas and spread the collection instruction;

The second receiving unit 712 is used to receive the underground sensor data collected by the secondary intelligent manhole covers in their respective jurisdiction areas;

The second generating unit 713 is used to classify and count all the downhole sensor data according to the pipeline ID of the underground pipeline to generate a statistical result;

The marking unit 714 is used to mark data on the electronic map according to the position of the primary intelligent manhole cover, the position of the secondary intelligent manhole cover and the statistical results, so that the position distribution, normal operation section and abnormal operation section of each underground pipeline are displayed on the electronic map;

The third generating unit 715 is used to generate a disaster situation for at least one cluster area according to the operation status of each underground pipeline on the electronic map;

The second sending unit 716 is used to send the disaster situation to the receiver of the smart pipe network;

The third sending unit 717 is used to send the disaster situation to the secondary smart manhole covers within the predetermined range when the successful reception notification sent by the receiver is not obtained, so that the secondary smart manhole covers within the predetermined range store the disaster situation and send the disaster situation to other receivers.

Please refer to FIG8 . The present application provides a data security transmission system based on a smart pipe network, including:

Processor 801 , memory 802 , input-output unit 803 , and bus 804 .

The processor 801 is connected to the memory 802 , the input and output unit 803 , and the bus 804 .

The memory 802 stores a program, and the processor 801 calls the program to execute the post-earthquake repair engineering analysis method shown in FIG. 1 , FIG. 2 , FIG. 3 , FIG. 4 , and FIG. 5 .

The present application provides a computer-readable storage medium on which a program is stored. When the program is executed on a computer, the post-earthquake repair engineering analysis method shown in Figures 1, 2, 3, 4 and 5 is performed.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk and other media that can store program code.

Claims (5)

1. A post-earthquake repair engineering analysis method for a smart pipe network, comprising: The main terminal of the main intelligent manhole cover receives the earthquake disaster alarm sent by the disaster detection equipment; The master terminal collects downhole sensor data of underground pipelines within the jurisdiction area; The main terminal determines the underground pipeline to be inspected that has no collected data according to the downhole sensor data; The main terminal compares the normal historical records of the remaining pipelines in the database with the downhole sensor data for similarity, and determines the underground pipelines that are operating normally and the underground pipelines that are operating abnormally in the area; The main terminal generates pipeline area status data according to the analysis of the underground pipeline to be inspected, the underground pipeline operating normally and the underground pipeline operating abnormally, and adds the pipeline area status data to the downhole sensor data; When the underground pipeline with abnormal operation is a transport pipe for air and a transport pipe for liquid, the main terminal uses a disaster acoustic wave sensor to perform section detection on the underground pipeline with abnormal operation to generate first detection data; The main terminal uses the disaster infrared remote sensing imaging equipment to perform section detection on the abnormally operating underground pipeline to generate second detection data; generating a detection result according to the first detection data and the second detection data; When the detection result shows that there is a damage point in the jurisdiction area, the main terminal uses the downhole image acquisition equipment to collect images of the abnormal underground pipeline within the damage point range to obtain at least one pipeline shooting image; The master terminal obtains a corresponding reference damaged image set of the abnormally operating underground pipeline from the database according to the earthquake disaster alarm, wherein the reference damaged image set includes a camera image set and an infrared remote sensing camera image set, wherein the camera image set includes at least two pipeline damaged images of underground pipelines in different damage conditions, and the infrared remote sensing camera image set includes at least two pipeline damaged images of underground pipelines in different damage conditions; The main terminal performs feature fusion on the captured pipeline image and the pipeline damage image to generate at least one damage feature enhanced image; The main terminal inputs at least one damage feature enhanced image into a convolutional neural network recognition model for recognition analysis to generate an analysis result; The main terminal determines the damage condition with the highest probability according to the analysis result, and determines the shooting point of the pipeline image corresponding to the damage condition with the highest probability; The main terminal determines the damage situation with the highest probability and the shooting point as damage point data; The main terminal sends a collection instruction to the secondary intelligent manhole covers within a predetermined range, so that the secondary intelligent manhole covers within the predetermined range collect and return downhole sensor data of underground pipelines within their respective jurisdiction areas and spread the collection instruction; The master terminal receives the underground sensor data collected by the secondary intelligent manhole covers in their respective jurisdiction areas; The main terminal classifies and counts all the downhole sensor data according to the pipeline ID of the underground pipeline to generate statistical results; The main terminal marks data on the electronic map according to the position of the main intelligent manhole cover, the position of the secondary intelligent manhole cover and the statistical result, so that the position distribution, normal operation section and abnormal operation section of each underground pipeline are displayed on the electronic map; The master terminal generates a disaster situation for at least one cluster area according to the operating status of each underground pipeline on the electronic map. 2. The post-earthquake repair engineering analysis method according to claim 1, characterized in that the main terminal performs feature fusion on the pipeline photographed image and the pipeline damage image to generate at least one damage feature enhanced image, comprising: The main terminal performs 1*1 convolution processing on the first pipeline damage image to generate a damage label feature; The main terminal performs a 1*1 convolution operation on the first pipeline captured image to generate a captured convolution feature; The main terminal performs a regional pixel attention generation process and a channel multiplication process on the damaged label feature to generate a first processing feature; The main terminal performs residual extraction and residual fusion processing on the first processing feature to generate a fusion residual; The main terminal performs channel superposition on the fusion residual, the damaged label feature and the shooting convolution feature to generate a second processing feature; The master terminal performs edge reconstruction on the second processing feature to generate a third processing feature; The master terminal allocates attention to each neuron corresponding to the third processing feature, and screens out neurons whose attention is less than a first preset threshold, to generate a fourth processing feature; The master terminal performs edge reconstruction on the fourth processing feature to generate an enhancement parameter; The main terminal restores and outputs the enhancement parameters to generate a damage feature enhanced image corresponding to the first pipeline captured image; The main terminal performs feature fusion on each of the photographed pipeline images and the pipeline damage image according to the above method to generate at least one damage feature enhanced image. 3. The post-earthquake repair engineering analysis method according to any one of claims 1 to 2, characterized in that after the master terminal generates a disaster situation for at least one cluster area according to the operating status of each underground pipeline on the electronic map, the post-earthquake repair engineering analysis method further comprises: The main terminal sends the disaster situation to a receiver of the smart pipe network; When the main terminal does not obtain the successful reception notification sent by the receiver, the main terminal sends the disaster situation to the secondary smart manhole covers within the predetermined range, so that the secondary smart manhole covers within the predetermined range store the disaster situation and send the disaster situation to other receivers. 4. A post-earthquake repair engineering analysis system for a smart pipe network, characterized by comprising: A first receiving unit, used for receiving an earthquake disaster alarm sent by a disaster detection device; A collection unit, used to collect downhole sensor data of underground pipelines within the jurisdiction area; A first generating unit, configured to perform pipeline operation status analysis according to the downhole sensor data, generate pipeline area status data, and add the pipeline area status data to the downhole sensor data; The first generation unit comprises: Determine the underground pipeline to be inspected without collected data according to the downhole sensor data; Comparing the normal historical records of the remaining pipelines in the database with the downhole sensor data for similarity, and determining the underground pipelines that are operating normally and the underground pipelines that are operating abnormally in the area; Generate pipeline area status data according to the analysis of the underground pipeline to be inspected, the underground pipeline operating normally, and the underground pipeline operating abnormally; a fourth generating unit, configured to, when the underground pipeline with abnormal operation is a transport pipe for transporting air and a transport pipe for transporting liquid, use a disaster damage point detection device to perform section detection on the underground pipeline with abnormal operation and generate a detection result; The fourth generation unit comprises: When the underground pipeline with abnormal operation is a transport pipe for air and a transport pipe for liquid, a disaster acoustic wave sensor is used to perform section detection on the underground pipeline with abnormal operation to generate first detection data; Use disaster-time infrared remote sensing imaging equipment to conduct section inspection of underground pipelines that are operating abnormally, and generate second inspection data; generating a detection result according to the first detection data and the second detection data; A first acquisition unit is used to acquire images of the abnormally operating underground pipeline within the range of the damaged point using a downhole image acquisition device when the detection result shows that there is a damaged point within the jurisdiction, and acquire at least one pipeline shooting image; a second acquisition unit, configured to acquire, from the database according to the earthquake disaster alarm, a corresponding reference damaged image set of the underground pipeline in abnormal operation, wherein the reference damaged image set includes a camera-photographed image set and an infrared remote sensing camera image set, wherein the camera-photographed image set includes at least two pipeline damaged images of underground pipelines in different damage conditions, and the infrared remote sensing camera image set includes at least two pipeline damaged images of underground pipelines in different damage conditions; a fifth generating unit, configured to perform feature fusion on the photographed pipeline image and the pipeline damage image to generate at least one damage feature enhanced image; A sixth generating unit, used for inputting at least one damage feature enhanced image into a convolutional neural network recognition model for recognition analysis to generate an analysis result; A first determination unit, configured to determine the damage condition with the highest probability according to the analysis result, and determine a shooting point of the pipeline image corresponding to the damage condition with the highest probability; A second determining unit is used to determine the damage situation and shooting point with the highest probability as damage point data; A first sending unit is used to send a collection instruction to the secondary intelligent manhole covers within a predetermined range, so that the secondary intelligent manhole covers within the predetermined range collect and return downhole sensor data of underground pipelines within their respective jurisdiction areas and spread the collection instruction; The second receiving unit is used to receive the underground sensor data collected by the secondary intelligent manhole covers in their respective jurisdiction areas; A second generating unit is used to classify and count all the downhole sensor data according to the pipeline ID of the underground pipeline to generate a statistical result; a marking unit, used for marking data on an electronic map according to the position of the primary intelligent manhole cover, the position of the secondary intelligent manhole cover and the statistical results, so that the position distribution, normal operation section and abnormal operation section of each underground pipeline are displayed on the electronic map; The third generating unit is used to generate a disaster situation for at least one cluster area according to the operating status of each underground pipeline on the electronic map. 5. The post-earthquake repair engineering analysis system according to claim 4, characterized in that the fifth generation unit comprises: Performing 1*1 convolution processing on the first pipeline damage image to generate a damage label feature; Performing a 1*1 convolution operation on the first pipeline captured image to generate a captured convolution feature; Performing a regional pixel attention generation process and a channel multiplication process on the damaged label feature to generate a first processing feature; Performing residual extraction and residual fusion processing on the first processing features to generate fused residuals; Channel-superimposing the fusion residual, the damaged label feature and the shooting convolution feature to generate a second processing feature; Performing edge reconstruction on the second processing feature to generate a third processing feature; Allocating attention to each neuron corresponding to the third processing feature, and screening out neurons whose attention is less than a first preset threshold, to generate a fourth processing feature; Performing edge reconstruction on the fourth processing feature to generate enhancement parameters; The enhancement parameters are restored and output to generate a damage feature enhanced image corresponding to the first pipeline captured image; According to the above method, feature fusion is performed on each of the photographed pipeline images and the pipeline damage image to generate at least one damage feature enhanced image.