CN114353886A - A method and system for detecting fault points in urban drainage pipe network - Google Patents

Abstract

The invention discloses a method and a system for detecting a fault point of a municipal drainage pipe network, which relate to the technical field of fault position detection. And calculating the difference value of the flow mean value curve in the period to be detected and the historical flow mean value curve in the corresponding period, and judging the position of a fault area and the fault point according to the obtained flow error curve. The technical scheme of the invention can make the detection result more accurate and reduce errors caused by flow characteristics at different time intervals. And can reduce a large amount of instrument cost.

Description

A method and system for detecting fault points in urban drainage pipe network

technical field

The invention relates to the technical field of fault location detection, and more particularly to a method and system for fault location detection of an urban drainage pipe network.

Background technique

Urban drainage pipelines ensure the discharge of residential wastewater and natural precipitation, and are important infrastructure for maintaining community operations. Once the drainage pipeline fails, it will often lead to road surface water, ground storage water, and even reverse backflow, which will seriously affect the traffic and life order of the community, and may cause accidents such as vehicle flooding. There are also hidden health risks and building quality problems. risk.

Existing drainage pipes are usually laid underground, and are generally cleaned and inspected manually by area on a regular basis. However, on the one hand, this method cannot effectively determine the fault location, and the carpet cleaning cost is high, which is very inconvenient. On the other hand, it is more expensive. In many cases, the pipelines in the area are cleaned and tested after an accident has occurred, and it is impossible to detect whether a fault occurs and the location of the fault point in real time during the drainage process.

It can be seen that the existing technology is difficult to detect the fault point of the pipeline, which leads to the failure to repair the pipeline in a timely and effective manner, and increases the cost. Therefore, how to provide a system that can detect whether the drainage pipeline fails and the location of the fault point in real time during the drainage process is a problem. Problems that those skilled in the art need to solve urgently.

SUMMARY OF THE INVENTION

In view of this, the present invention provides a method and system for detecting a fault point of an urban drainage pipe network.

In order to achieve the above object, the present invention provides the following technical solutions:

A method for detecting fault points in an urban drainage pipe network, comprising the following steps:

Step 1: Classify all nodes in the drainage network according to the node properties, and obtain a classified node set;

Step 2: Select a representative node in each type of node set as a monitoring point;

Step 3: Obtain historical flow data at the monitoring point, classify the historical flow data according to different time periods, and obtain multiple historical flow data sets;

Step 4. According to each historical flow data set, taking the monitoring point as the abscissa and the flow data as the ordinate, draw the historical flow mean curve corresponding to each period;

Step 5: Collect the flow data at the monitoring point during the period to be detected;

Step 6, draw the flow mean curve of the period to be detected;

Step 7: Calculate the flow error curve of the to-be-detected period according to the flow mean value curve of the to-be-detected period and the historical flow mean value curve of the corresponding period;

Step 8: Obtain the position section of the error curve in the period to be detected that exceeds the preset error threshold, and obtain the fault section where the fault point is located;

Step 9: According to the fault section, obtain the first monitoring point located in the fault section, check the pipeline around the monitoring point, and obtain the accurate fault point position.

Optionally, in the first step, the properties of the nodes include water pressure, flow, and the like.

Optionally, in the first step, a fuzzy clustering method is used to classify the nodes.

Optionally, in the second step, the TF-IDF algorithm is used to extract each category of node sets to obtain representative nodes in each category.

Optionally, in each of the steps, a water flow sensor is used to obtain flow data.

Optionally, the specific steps of the step 4 are:

Step 4.1. Let the historical flow data set of the ith period be Ai, take the monitoring point as the abscissa and the flow data as the ordinate, and draw the historical flow curves corresponding to different collection moments in the ith period;

Step 4.2. According to a plurality of historical flow curves, average the flow data of each monitoring point to obtain the average historical flow curve of the i-th period.

Optionally, the specific steps of the step 6 are:

Step 6.1. Draw multiple flow curves according to the collected flow data during the period to be detected according to different collection times;

Step 6.2: Calculate the average of the flow data of each monitoring point according to the multiple flow curves of the period to be detected, to obtain the mean curve of the flow of the period to be detected.

Optionally, in the step 9, the first monitoring point located in the fault section refers to the first monitoring point in the fault section in the sequential direction according to the direction of water flow in the drainage pipe network. point.

An urban drainage pipe network fault point detection system, comprising:

The node classification module of the drainage pipe network is used to classify all the nodes in the drainage pipe network according to the node properties, and obtain the classified node set;

The monitoring point selection module is used to select a representative node in each type of node set as a monitoring point;

The historical flow data classification module is used to obtain the historical flow data at the monitoring point, classify the historical flow data according to different time periods, and obtain a plurality of historical flow data sets;

The historical flow average curve acquisition module is used to draw the historical flow average curve corresponding to each period according to each historical flow data set, taking the monitoring point as the abscissa and the flow data as the ordinate;

The flow data acquisition module during the period to be detected is used to collect the flow data at the monitoring points during the period to be detected;

A flow average curve acquisition module in the period to be detected, which is used to draw the average flow curve of the period to be detected;

a flow error curve acquisition module, configured to calculate and obtain the flow error curve of the to-be-detected period according to the flow mean value curve of the to-be-detected period and the historical flow mean value curve of the corresponding period;

The fault section determination module is used to obtain the position section that exceeds the preset error threshold in the error curve of the to-be-detected period, and obtain the fault section where the fault point is located;

The fault point determination module is used for obtaining the first monitoring point located in the fault section according to the fault section, and checking the pipeline around the monitoring point to obtain the accurate fault point position.

As can be seen from the above technical solutions, the present disclosure provides a method and system for detecting fault points in an urban drainage pipe network, which has the following beneficial effects compared with the prior art:

The invention classifies and filters all nodes in the drainage pipe network, obtains representative nodes in each category as monitoring points, obtains historical flow data at the monitoring points, divides the collected data into time periods, and then draws The historical traffic mean curve corresponding to each period is obtained. Calculate the difference between the flow average curve in the period to be detected and the historical flow average curve in the corresponding period, and judge the fault area and fault point according to the obtained flow error curve. By dividing the time period, the present invention can compare the flow mean value curve of the period to be detected with the historical flow mean value curve of the corresponding period to obtain the detection result, so that the detection result is more accurate and the error caused by the flow characteristics of different time periods is reduced. . In addition, the selection of representative monitoring points can ensure accurate detection results and reduce instrument costs.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only It is an embodiment of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to the provided drawings without creative work.

Fig. 1 is the method step flow chart of the present invention;

FIG. 2 is a schematic diagram of the system structure of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

The embodiment of the present invention discloses a method for detecting a fault point of an urban drainage pipe network. Referring to FIG. 1 , the method includes the following steps:

Step 1: Use the fuzzy clustering method to classify all the nodes in the drainage network according to the water pressure value and the flow value, and obtain the classified node set.

Step 2: Use the TF-IDF algorithm to extract each type of node set, and select a representative node in each type of node set as a monitoring point; by selecting a monitoring point, while ensuring the acquisition of representative traffic data, Ensure the comprehensiveness of fault point detection, reduce the number of water flow sensors, and reduce detection costs.

Step 3: Obtain historical flow data at the monitoring point, classify the historical flow data according to different time periods, and obtain multiple historical flow data sets A1, A2, ..., An, where n is the number of divided time periods.

In a specific embodiment, a statistical method may be used for the division of time periods, and time periods are divided according to characteristics of traffic at different times. It is required that in each period, the difference of flow data should be controlled within a preset range.

Step 4. According to each historical flow data set, taking the monitoring point as the abscissa and the flow data as the ordinate, draw the historical flow mean curve corresponding to each period;

The specific steps are:

Step 4.1. Let the historical flow data set of the ith period be Ai, take the monitoring point as the abscissa and the flow data as the ordinate, draw the historical flow curves Si1, Si2, .. ., Sim, m is the number of collection moments in the ith period;

Step 4.2, according to a plurality of historical flow curves Si1, Si2, .

Step 5: Collect the flow data at the monitoring point during the period to be detected;

Step 6. Draw the flow mean curve Fi in the period to be detected;

The specific steps are:

Step 6.1. Draw multiple flow curves according to the collected flow data during the period to be detected according to different collection times;

Step 6.2: Calculate the average of the flow data of each monitoring point according to the multiple flow curves of the period to be detected, to obtain the mean curve of the flow of the period to be detected.

Step 7: According to the flow mean curve Fi of the period to be detected and the historical flow mean curve Si of the corresponding period, the flow data of each monitoring point is calculated to obtain the difference value, and the flow error curve Mi of the period to be detected is calculated;

Step 8: Obtain the position section of the error curve Mi in the period to be detected that exceeds the preset error threshold, and obtain the fault section where the fault point is located; if there is no section that exceeds the preset error threshold, it means that the drainage pipeline during the period to be detected No failure occurred.

Step 9: According to the fault section, obtain the first monitoring point located in the fault section, check the pipeline around the monitoring point, and obtain the accurate fault point position. The first monitoring point in the fault section refers to the first monitoring point in the fault section in the sequential direction according to the direction of water flow in the drainage pipe network.

In each of the steps, flow data is acquired using a water flow sensor.

In the process of implementing the above method, it is first necessary to set a water flow sensor at each node of the drainage network to obtain historical flow data at each node. After the historical flow mean curve is obtained, it is only necessary to set the water flow sensor at the monitoring point. When detecting the fault point in the period to be detected, the flow data at each monitoring point can be obtained.

It is worth noting that when it is necessary to obtain the fault point at the current moment, step 6 does not need to calculate the mean value, but only needs to draw the flow curve at the current moment, and calculate the difference between the flow curve at the current moment and the historical flow mean curve Si. , obtain the flow error curve at the current moment, and then proceed to step 8 to perform subsequent steps.

The embodiment of the present invention also discloses a system for detecting fault points in an urban drainage pipe network, referring to FIG. 2 , including:

The node classification module of the drainage pipe network is used to classify all the nodes in the drainage pipe network according to the node properties, and obtain the classified node set;

The monitoring point selection module is used to select a representative node in each type of node set as a monitoring point;

The historical flow data classification module is used to obtain the historical flow data at the monitoring point, classify the historical flow data according to different time periods, and obtain a plurality of historical flow data sets;

The historical flow average curve acquisition module is used to draw the historical flow average curve corresponding to each period according to each historical flow data set, taking the monitoring point as the abscissa and the flow data as the ordinate;

The flow data acquisition module during the period to be detected is used to collect the flow data at the monitoring points during the period to be detected;

A flow average curve acquisition module in the period to be detected, which is used to draw the average flow curve of the period to be detected;

a flow error curve acquisition module, configured to calculate and obtain the flow error curve of the to-be-detected period according to the flow mean value curve of the to-be-detected period and the historical flow mean value curve of the corresponding period;

The fault section determination module is used to obtain the position section that exceeds the preset error threshold in the error curve of the to-be-detected period, and obtain the fault section where the fault point is located;

The fault point determination module is used for obtaining the first monitoring point located in the fault section according to the fault section, and checking the pipeline around the monitoring point to obtain the accurate fault point position.

The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the various embodiments can be referred to each other. As for the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant part can be referred to the description of the method.

The above description of the disclosed embodiments enables any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (9)

1. a method for detecting the fault point of an urban drainage network, is characterized in that, comprises the following steps: Step 1: Classify all nodes in the drainage network according to the node properties, and obtain a classified node set; Step 2: Select a representative node in each type of node set as a monitoring point; Step 3: Obtain historical flow data at the monitoring point, classify the historical flow data according to different time periods, and obtain multiple historical flow data sets; Step 4. According to each historical flow data set, taking the monitoring point as the abscissa and the flow data as the ordinate, draw the historical flow mean curve corresponding to each period; Step 5: Collect the flow data at the monitoring point during the period to be detected; Step 6, draw the flow mean curve of the period to be detected; Step 7: Calculate the flow error curve of the to-be-detected period according to the flow mean value curve of the to-be-detected period and the historical flow mean value curve of the corresponding period; Step 8: Obtain the position section of the error curve in the period to be detected that exceeds the preset error threshold, and obtain the fault section where the fault point is located; Step 9: According to the fault section, obtain the first monitoring point located in the fault section, check the pipeline around the monitoring point, and obtain the accurate fault point position. 2 . The method for detecting a fault point of an urban drainage pipe network according to claim 1 , wherein in the first step, the properties of the nodes include water pressure and flow. 3 . 3 . The method for detecting fault points in an urban drainage pipe network according to claim 1 , wherein, in the first step, the nodes are classified using a fuzzy clustering method. 4 . 4. The method for detecting a fault point in an urban drainage network according to claim 1, wherein in the second step, a TF-IDF algorithm is used to extract each type of node set, to obtain the representative node. 5 . The method for detecting a fault point in an urban drainage pipe network according to claim 1 , wherein the flow data is obtained by using a water flow sensor. 6 . 6. The method for detecting a fault point of an urban drainage pipe network according to claim 1, wherein the specific steps of the fourth step are: Step 4.1. Let the historical flow data set of the ith period be Ai, take the monitoring point as the abscissa and the flow data as the ordinate, and draw the historical flow curves corresponding to different collection moments in the ith period; Step 4.2. According to a plurality of historical flow curves, average the flow data of each monitoring point to obtain the average historical flow curve of the i-th period. 7. The method for detecting a fault point of an urban drainage pipe network according to claim 1, wherein the specific steps of the step 6 are: Step 6.1. Draw multiple flow curves according to the collected flow data during the period to be detected according to different collection times; Step 6.2: Calculate the average of the flow data of each monitoring point according to the multiple flow curves of the period to be detected, to obtain the mean curve of the flow of the period to be detected. 8 . The method for detecting a fault point in an urban drainage pipe network according to claim 1 , wherein, in the step 9, the first monitoring point located in the fault section refers to, according to the The water flow direction is the sequence direction, the first monitoring point in the fault section in the sequence direction. 9. An urban drainage pipe network fault point detection system, characterized in that, comprising: The node classification module of the drainage pipe network is used to classify all the nodes in the drainage pipe network according to the node properties, and obtain the classified node set; The monitoring point selection module is used to select a representative node in each type of node set as a monitoring point; The historical flow data classification module is used to obtain the historical flow data at the monitoring point, classify the historical flow data according to different time periods, and obtain a plurality of historical flow data sets; The historical flow average curve acquisition module is used to draw the historical flow average curve corresponding to each period according to each historical flow data set, taking the monitoring point as the abscissa and the flow data as the ordinate; The flow data acquisition module during the period to be detected is used to collect the flow data at the monitoring points during the period to be detected; A flow average curve acquisition module in the period to be detected, which is used to draw the average flow curve of the period to be detected; a flow error curve acquisition module, configured to calculate and obtain the flow error curve of the to-be-detected period according to the flow mean value curve of the to-be-detected period and the historical flow mean value curve of the corresponding period; The fault section determination module is used to obtain the position section that exceeds the preset error threshold in the error curve of the to-be-detected period, and obtain the fault section where the fault point is located; The fault point determination module is used for obtaining the first monitoring point located in the fault section according to the fault section, and checking the pipeline around the monitoring point to obtain the accurate fault point position.

Images