CN113538171A - Power station safety monitoring system - Google Patents
Power station safety monitoring system Download PDFInfo
- Publication number
- CN113538171A CN113538171A CN202111072229.2A CN202111072229A CN113538171A CN 113538171 A CN113538171 A CN 113538171A CN 202111072229 A CN202111072229 A CN 202111072229A CN 113538171 A CN113538171 A CN 113538171A
- Authority
- CN
- China
- Prior art keywords
- power station
- monitoring data
- hidden danger
- data
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 137
- 238000003062 neural network model Methods 0.000 claims abstract description 42
- 230000008030 elimination Effects 0.000 claims abstract description 31
- 238000003379 elimination reaction Methods 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000013528 artificial neural network Methods 0.000 claims abstract description 3
- 238000005457 optimization Methods 0.000 claims description 16
- 238000012790 confirmation Methods 0.000 claims description 15
- 230000000694 effects Effects 0.000 claims description 15
- 238000007689 inspection Methods 0.000 claims description 13
- 238000011156 evaluation Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 8
- 230000001960 triggered effect Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 5
- 239000011435 rock Substances 0.000 description 3
- 238000011144 upstream manufacturing Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Water Supply & Treatment (AREA)
- Mathematical Physics (AREA)
- Public Health (AREA)
- Bioethics (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a power station safety monitoring system, which comprises a first acquisition module, a second acquisition module, a first analysis module and a second analysis module, wherein the first acquisition module is used for acquiring power station safety case data; the first analysis module is used for analyzing historical power station monitoring data in the power station safety case data, extracting hidden danger factors, taking the hidden danger factors and corresponding accident types as input of a neural network model, and pre-training the neural network model; the second acquisition module is used for acquiring real-time power station monitoring data; the second analysis module is used for processing the real-time power station monitoring data by using the pre-trained neural network, obtaining potential safety hazard information and generating a potential safety hazard elimination strategy according to the potential safety hazard information. The system can analyze potential safety hazards which may exist according to real-time monitoring data which are not directly related to safety accidents and generate corresponding potential safety hazard removing strategies, and assists workers to rapidly investigate and remove the potential safety hazards, so that stable operation of the power station is guaranteed.
Description
Technical Field
The invention relates to the technical field of power station management systems, in particular to a power station safety monitoring system.
Background
Along with the construction and development of intelligent power stations, the power stations put forward higher requirements on safety management and control in different stages of construction, operation and maintenance. At present, various field monitoring systems are installed in most power stations, but the systems usually only pay attention to data directly related to the operation of the power stations, such as the operation conditions of power station equipment, and give an alarm when abnormal data are monitored, that is, the systems can only give an alarm when a fault occurs, and do not pay attention to data reflecting the existence of potential safety hazards and possibly causing the fault or accident, for example, upstream continuous rainstorm may cause the water level of a reservoir of a downstream power station to rise, the water storage pressure to increase, and possibly cause dam break. The existing power station safety monitoring system cannot analyze potential safety hazards possibly existing according to the obtained monitoring data, so that the potential safety hazards can be further developed into faults or accidents, and the stable operation of the power station is seriously threatened.
Disclosure of Invention
In view of the above, the present invention is directed to a safety monitoring system for a power plant, which overcomes or at least partially solves the above-mentioned problems of the prior art.
In order to achieve the above object, the present invention provides a power station safety monitoring system, which includes a first acquisition module, a second acquisition module, a first analysis module and a second analysis module, wherein the first acquisition module is connected to the first analysis module, the second acquisition module is connected to the second analysis module,
the first acquisition module is used for acquiring power station safety case data, and the power station safety case data comprise accident types, accident reason information and historical power station monitoring data;
the first analysis module is used for analyzing historical power station monitoring data in the power station safety case data, extracting hidden danger factors in the historical power station monitoring data, using the hidden danger factors and corresponding accident types as input of a neural network model, and pre-training the neural network model;
the second acquisition module is used for acquiring real-time power station monitoring data, and the historical power station monitoring data and the real-time power station monitoring data respectively comprise power station equipment monitoring data, power station environment monitoring data and power station scheduling record data;
the second analysis module is used for processing the real-time power station monitoring data by using the pre-trained neural network, obtaining potential safety hazard information and generating a potential safety hazard elimination strategy according to the potential safety hazard information.
Further, the first obtaining module includes:
the first acquisition submodule is used for acquiring the safety case data of the power station by connecting the database through an internal network;
and the second acquisition submodule is used for connecting a third-party site through an external network to acquire the safety case data of the power station.
Further, the first analysis module specifically includes:
the extraction submodule is used for analyzing historical power station monitoring data in the power station safety case data and extracting hidden danger factors in the historical power station monitoring data;
the preprocessing submodule is used for dividing the hidden danger factors and the corresponding accident types into a training set and a testing set;
and the pre-training sub-module is used for inputting the training set into the neural network model to train the neural network model and inputting the test set into the neural network model to confirm the training effect.
Further, the second obtaining module includes:
the third acquisition submodule is used for connecting the sensor equipment deployed at each position of the power station and acquiring the power station operation monitoring data acquired by the sensor equipment;
the fourth acquisition submodule is used for acquiring the ambient environment information of the power station from a plurality of data sources to acquire the ambient monitoring data of the power station, wherein the data sources comprise an ambient monitoring sensor, a meteorological monitoring station and a third-party site which are deployed around the power station;
and the recording submodule is used for recording the power station scheduling operation instruction through the internal network so as to obtain power station scheduling instruction data.
Further, the power station operation monitoring data acquired by the third acquisition sub-module is encrypted power station operation monitoring data, and the third acquisition sub-module includes:
the identification submodule is used for identifying whether the received power station operation monitoring data is sent by the new sensor equipment, if so, the first decryption submodule is triggered, and if not, the second decryption submodule is triggered;
the first decryption submodule is used for acquiring a preset first key to decrypt the power station operation monitoring data;
and the second decryption submodule is used for acquiring the historical power station operation monitoring data, generating a data change trend curve graph according to the historical power station operation monitoring data, performing hash operation according to the data change trend curve graph to generate a unique identification code, generating a second key by taking the unique identification code as a parameter of a preset key algorithm, and decrypting the power station operation monitoring data through the second key.
Further, the second analysis module comprises:
the hidden danger analysis submodule is used for inputting the real-time power station monitoring data into a pre-trained neural network model for processing, and the neural network model classifies the hidden danger factors in the real-time power station monitoring data by analyzing the hidden danger factors to obtain potential safety hazard information generated by safety accidents which can be caused by the corresponding hidden danger factors;
and the strategy generation sub-module is used for querying a preset hidden danger elimination strategy database by taking the potential safety hazard information as a query condition to acquire a hidden danger elimination strategy corresponding to the potential safety hazard information.
Furthermore, the system also comprises an inspection terminal and an optimization module, wherein the inspection terminal is respectively connected with the optimization module and the second analysis module,
the inspection terminal is used for acquiring the hidden danger elimination strategy from the second analysis module and sending hidden danger confirmation information and strategy implementation results input by inspection personnel to the optimization module;
the optimization module is used for identifying and matching the hidden danger confirmation information and the potential safety hazard information generated by the second analysis module, and if the hidden danger confirmation information is not matched with the potential safety hazard information, optimizing and updating the neural network model according to the hidden danger confirmation information; and if the hidden danger confirmation information is matched with the potential safety hazard information, performing effect evaluation on the hidden danger elimination strategy according to the strategy implementation result.
Further, the optimization module is specifically configured to determine that the policy implementation result is a positive result or a negative result, and when the policy implementation result is the positive result, promote an effect evaluation level of the corresponding hidden danger elimination policy; and when the strategy implementation result is a negative result, reducing the effect evaluation grade of the corresponding hidden danger elimination strategy.
Compared with the prior art, the invention has the beneficial effects that:
according to the power station safety monitoring system, the first acquisition module is used for acquiring power station safety case data, the first analysis module is used for extracting hidden danger factors in indirect accident reason information in the power station safety case data, the second analysis module is used for inputting real-time power station monitoring data acquired by the second acquisition module into the neural network model after the neural network model is trained through the hidden danger factors, classification and identification are carried out on the basis of the real-time power station monitoring data to acquire potential safety hazard information, and further a hidden danger elimination strategy is generated according to the potential safety hazard information, so that the system can analyze potential safety hazards which possibly exist according to some real-time monitoring data which are not directly related to accidents and generate a corresponding hidden danger elimination strategy, and workers are assisted to quickly troubleshoot and eliminate the potential safety hazards, and stable operation of a power station is guaranteed.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is apparent that the drawings in the following description are only preferred embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without inventive efforts.
Fig. 1 is a schematic view of an overall structure of a power station safety monitoring system according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of an overall structure of a first obtaining module according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of an overall structure of a first analysis module according to an embodiment of the present invention.
Fig. 4 is a schematic diagram of an overall structure of a second obtaining module according to an embodiment of the present invention.
Fig. 5 is a schematic diagram of an overall structure of a second analysis module according to an embodiment of the present invention.
Fig. 6 is a schematic diagram of an overall structure of a power station safety monitoring system according to another embodiment of the present invention.
In the figure, 1 a first obtaining module, 101 a first obtaining submodule, 102 a second obtaining submodule, 2 a second obtaining module, 201 a third obtaining submodule, 2011 a recognition submodule, 2012 a first decryption submodule, 2013 a second decryption submodule, 202 a fourth obtaining submodule, 203 a recording submodule, 3 a first analysis module, 301 an extraction submodule, 302 a preprocessing submodule, 303 a pre-training submodule, 4 a second analysis module, 401 a hidden danger analysis submodule, 402 a strategy generating submodule, 5 a routing inspection terminal and 6 an optimization module.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, the illustrated embodiments are provided to illustrate the invention and not to limit the scope of the invention.
Referring to fig. 1, the present embodiment provides a power station safety monitoring system, the system includes a first obtaining module 1, a second obtaining module 2, a first analyzing module 3, and a second analyzing module 4, where the first obtaining module 1 is connected to the first analyzing module 3, and the second obtaining module 2 is connected to the second analyzing module 4.
The first acquisition module 1 is used for acquiring power station safety case data, wherein the power station safety case data comprise accident types, accident reason information and historical power station monitoring data. Illustratively, the accident type is used to describe a specific type of power station safety accident or fault, such as reservoir dam collapse, transformer fire, etc. The accident reason information is used for describing reasons directly causing power station safety accidents, for example, the reason directly causing reservoir dam collapse is that reservoir water level is too high, and the reason directly causing transformer fire is that temperature rise is caused by transformer overload operation to cause poor insulation. The historical power station monitoring data is the power station monitoring data when the power station safety accident happens and in a period of time before the power station safety accident happens.
The first analysis module 3 is used for analyzing historical power station monitoring data in the power station safety case data, extracting hidden danger factors in the historical power station monitoring data, taking the hidden danger factors and corresponding accident types as input of a neural network model, and pre-training the neural network model. The hidden danger factors are monitoring data related to accidents in historical power station monitoring data, for example, in a safety accident that a transformer is on fire, the historical power station monitoring data monitors that the humidity and the temperature of the air around the power station are high in a period of time before the transformer is on fire, so that the transformer is insulated, damped, short-circuited and on fire occurs, and the air humidity and the temperature data in the historical power station monitoring data are the hidden danger factors.
The second acquisition module 2 is used for acquiring real-time power station monitoring data, and the historical power station monitoring data and the real-time power station monitoring data comprise power station equipment monitoring data, power station environment monitoring data and power station scheduling record data.
The second analysis module 4 is used for processing the real-time power station monitoring data by using the pre-trained neural network model, obtaining potential safety hazard information, and generating a potential safety hazard elimination strategy according to the potential safety hazard information.
In the embodiment, the system firstly acquires the power station safety case data through the first acquisition module 1, extracts hidden danger factors in historical power station monitoring data of the power station safety case data through the first analysis module 3, and pre-trains the neural network model based on the hidden danger factors and corresponding accident types. The real-time power station monitoring data are acquired through the second acquisition module 2, the real-time power station monitoring data are input into the pre-trained neural network model through the second analysis module 4 to be processed, the neural network model acquires potential safety hazard information through classifying and identifying the real-time power station monitoring data, a potential safety hazard removing strategy can be further generated according to the potential safety hazard information, and a worker can rapidly check and remove the potential safety hazard according to the potential safety hazard information and the potential safety hazard removing strategy, so that stable operation of the power station is guaranteed.
As an alternative implementation, referring to fig. 2, the first obtaining module 1 includes a first obtaining submodule 101 and a second obtaining submodule 102.
The first obtaining submodule 101 is configured to obtain power station security case data by connecting to a database through an internal network. The database is used for storing relevant data of all safety cases which have occurred in the power station.
The second obtaining submodule 102 is configured to connect to a third-party site through an external network to obtain the power station security case data.
In this embodiment, the first obtaining module 1 can obtain not only the safety case data that has occurred in the power station, but also more safety case data from the third-party site through the external network, so that the obtained safety case data of the power station can cover various situations as much as possible, and the classification performance of the neural network model can be improved in the subsequent steps.
As an alternative implementation, referring to fig. 3, the first analysis module 3 specifically includes an extraction sub-module 301, a pre-processing sub-module 302, and a pre-training sub-module 303.
The extraction submodule 301 is configured to analyze historical power station monitoring data in the power station safety case data, and extract hidden danger factors in the historical power station monitoring data.
For example, one piece of power grid safety case data may include multiple types of historical power station monitoring data, wherein part of the historical power station monitoring data is not logically associated with the occurrence of the power grid safety accident, and part of the historical power station monitoring data is more logically associated with the occurrence of the power grid safety accident. When hidden danger factors in historical power station monitoring data are extracted, the historical power station monitoring data of various types of power grid safety cases with the same accident type can be subjected to statistical analysis, the historical power station monitoring data which are not logically related to the power station safety accident are screened, the rest historical power station monitoring data are screened, and the power station monitoring data which are highly logically related to the power station safety accident are screened out to serve as the hidden danger factors.
The preprocessing submodule 302 is configured to divide the hidden danger factors and the accident types corresponding to the hidden danger factors into a training set and a test set.
The pre-training submodule 303 is configured to input a training set into the neural network model to train the neural network model, and input a test set into the neural network model to confirm a training effect of the neural network model. Exemplarily, after training the neural network model through the training set, the hidden danger factors in the test set are input into the neural network model, whether the training effect of the neural network model reaches the expectation is judged according to the classification and recognition result of the neural network model in the test set, and if the training effect of the neural network model does not reach the expectation, the training set is used for carrying out iterative training on the neural network model.
As an alternative implementation, referring to fig. 4, the second obtaining module 2 includes a third obtaining submodule 201, a fourth obtaining submodule 202 and a recording submodule 203.
The third obtaining submodule 201 is configured to connect sensor devices deployed at various places of the power station, and obtain power station operation monitoring data collected by the sensor devices. The power station operation monitoring data comprises operation data of power station buildings, power generation equipment, power transformation equipment, power transmission equipment and the like.
The fourth obtaining sub-module 202 is configured to obtain the environmental information around the power station from multiple data sources to obtain the environmental monitoring data of the power station, where the data sources include an environmental monitoring sensor, a weather monitoring station, and a third-party site deployed around the power station. The environment monitoring sensor can be a temperature sensor, a humidity sensor and a seismic sensor. The third-party site can be a network site for monitoring and externally distributing related weather and geological change information at the upstream and periphery of the power station.
The recording submodule 203 is configured to record a power station scheduling operation instruction through an internal network to obtain power station scheduling instruction data.
As an optional implementation manner, the power station operation monitoring data acquired by the third acquisition sub-module 201 is encrypted power station operation monitoring data, that is, before each sensor device connected to the third acquisition sub-module 201 sends the power station operation monitoring data to the third acquisition sub-module 201, the power station operation monitoring data is encrypted.
Illustratively, when the sensor device first sends the power station operation monitoring data to the third obtaining sub-module 201, the power station operation monitoring data is encrypted by a first key preset by the third obtaining sub-module 201 and then sent to the third obtaining sub-module 201; if the sensor device does not send the power station operation monitoring data to the third obtaining sub-module 201 for the first time, the sensor generates a data change trend graph according to the historical power station operation monitoring data that was sent to the third obtaining sub-module 201, performs hash operation according to the data change trend graph to generate a corresponding unique identification code, calculates the unique identification code as an input parameter of a preset key algorithm to generate a second key, encrypts the power station operation monitoring data through the second key, and sends the encrypted data to the third obtaining sub-module 201.
Correspondingly, the third obtaining submodule 201 specifically includes an identification submodule 2011, a first decryption submodule 2012 and a second decryption submodule 2013.
The identification submodule 2011 is configured to identify whether the received power station operation monitoring data is sent by a new sensor device, if so, trigger the first decryption submodule 2012, and otherwise trigger the second decryption submodule 2013. I.e. sensor devices that have not previously sent data to the third acquisition submodule 201.
The first decryption sub-module 2012 is configured to obtain a preset first key when being triggered to decrypt the encrypted power station operation monitoring data.
The second decryption submodule 2013 is configured to, when triggered, acquire historical power station operation monitoring data sent by a sensor device sending encrypted power station operation monitoring data in the past, generate a data change trend graph according to the historical power station operation monitoring data, perform hash operation according to the data change trend graph to generate a unique identification code, generate a second key by using the unique identification code as a parameter of a preset key algorithm, and decrypt the encrypted power station operation monitoring data through the second key.
In this embodiment, when the sensor device continuously sends the power station operation monitoring data to the third obtaining sub-module 201, the unique key can be generated by the historical power station monitoring data transmitted between the two parties in the past to encrypt the power station operation monitoring data, so that the security and confidentiality of the power station operation monitoring data are protected. The second key changes in each transmission, and because the monitored data of different sensor devices are different, the second keys corresponding to different sensor devices are different, so that the difficulty of key cracking is further improved.
In other embodiments, when the fourth obtaining sub-module 202 obtains the environmental information around the power station from different data sources, the above encryption method may also be used to encrypt the power station environmental monitoring data.
As an alternative implementation, referring to fig. 5, the second analysis module 4 includes a hidden danger analysis sub-module 401 and a strategy generation sub-module 402.
The hidden danger analysis submodule 401 is configured to input real-time power station monitoring data into a pre-trained neural network model for processing, and the neural network model classifies the real-time power station monitoring data by analyzing hidden danger factors in the real-time power station monitoring data, so as to obtain potential safety hazard information generated by a safety accident which can be caused by the corresponding hidden danger factors.
The strategy generation sub-module 402 is configured to query a preset hidden danger elimination strategy database with the potential safety hazard information as a query condition, and obtain a hidden danger elimination strategy corresponding to the potential safety hazard information.
In the embodiment, the pre-trained neural network model can classify and identify hidden danger factors in various types of real-time power station monitoring data, so that corresponding potential safety hazard information is obtained. For example, when the real-time power station monitoring data includes "mud-rock flow occurs in the XX county upstream", the neural network model identifies the hidden danger factor of the mud-rock flow, generates corresponding potential safety hazard information "the power station may be influenced by the mud-rock flow", queries a corresponding hidden danger elimination strategy in a hidden danger elimination strategy database according to the potential safety hazard information, and assists in guiding a worker to take measures as soon as possible to eliminate or reduce negative influences possibly caused by the hidden danger through the hidden danger elimination strategy.
As an alternative implementation, referring to fig. 6, the system further includes an inspection terminal 5 and an optimization module 6, where the inspection terminal 5 is connected to the optimization module 6 and the second analysis module 4, respectively.
And the inspection terminal 5 is used for acquiring the hidden danger elimination strategy from the second analysis module 4 and sending the hidden danger confirmation information and the strategy implementation result input by the inspection personnel to the optimization module 6.
The optimization module is used for identifying and matching the hidden danger confirmation information and the potential safety hazard information generated by the second analysis module, and if the hidden danger confirmation information is not matched with the potential safety hazard information, optimizing and updating the neural network model according to the hidden danger confirmation information; and if the hidden danger confirmation information is matched with the potential safety hazard information, performing effect evaluation on the hidden danger elimination strategy according to the strategy implementation result.
Illustratively, the optimization module 6 is specifically configured to determine that the policy implementation result is a positive result or a negative result, and when the policy implementation result is a positive result, promote an effect evaluation level of a corresponding hidden danger elimination policy; and when the strategy implementation result is a negative result, reducing the effect evaluation grade of the corresponding hidden danger elimination strategy. The hidden danger elimination strategy database may store a plurality of hidden danger elimination strategies corresponding to the same potential safety hazard information, and when the hidden danger elimination strategy database is queried according to the potential safety hazard information, the hidden danger elimination strategy with a higher effect evaluation level may be preferentially selected.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. A power station safety monitoring system is characterized by comprising a first acquisition module, a second acquisition module, a first analysis module and a second analysis module, wherein the first acquisition module is connected with the first analysis module, the second acquisition module is connected with the second analysis module,
the first acquisition module is used for acquiring power station safety case data, and the power station safety case data comprise accident types, accident reason information and historical power station monitoring data;
the first analysis module is used for analyzing historical power station monitoring data in the power station safety case data, extracting hidden danger factors in the historical power station monitoring data, using the hidden danger factors and corresponding accident types as input of a neural network model, and pre-training the neural network model;
the second acquisition module is used for acquiring real-time power station monitoring data, and the historical power station monitoring data and the real-time power station monitoring data respectively comprise power station equipment monitoring data, power station environment monitoring data and power station scheduling record data;
the second analysis module is used for processing the real-time power station monitoring data by using the pre-trained neural network, obtaining potential safety hazard information and generating a potential safety hazard elimination strategy according to the potential safety hazard information.
2. The power station safety monitoring system of claim 1, wherein the first acquisition module comprises:
the first acquisition submodule is used for acquiring the safety case data of the power station by connecting the database through an internal network;
and the second acquisition submodule is used for connecting a third-party site through an external network to acquire the safety case data of the power station.
3. The power station safety monitoring system according to claim 1, wherein the first analysis module specifically comprises:
the extraction submodule is used for analyzing historical power station monitoring data in the power station safety case data and extracting hidden danger factors in the historical power station monitoring data;
the preprocessing submodule is used for dividing the hidden danger factors and the corresponding accident types into a training set and a testing set;
and the pre-training sub-module is used for inputting the training set into the neural network model to train the neural network model and inputting the test set into the neural network model to confirm the training effect.
4. The plant safety monitoring system of claim 1, wherein the second acquisition module comprises:
the third acquisition submodule is used for connecting the sensor equipment deployed at each position of the power station and acquiring the power station operation monitoring data acquired by the sensor equipment;
the fourth acquisition submodule is used for acquiring the ambient environment information of the power station from a plurality of data sources to acquire the ambient monitoring data of the power station, wherein the data sources comprise an ambient monitoring sensor, a meteorological monitoring station and a third-party site which are deployed around the power station;
and the recording submodule is used for recording the power station scheduling operation instruction through the internal network so as to obtain power station scheduling instruction data.
5. The power station safety monitoring system according to claim 4, wherein the power station operation monitoring data acquired by the third acquiring sub-module is encrypted power station operation monitoring data, and the third acquiring sub-module comprises:
the identification submodule is used for identifying whether the received power station operation monitoring data is sent by the new sensor equipment, if so, the first decryption submodule is triggered, and if not, the second decryption submodule is triggered;
the first decryption submodule is used for acquiring a preset first key to decrypt the power station operation monitoring data;
and the second decryption submodule is used for acquiring the historical power station operation monitoring data, generating a data change trend curve graph according to the historical power station operation monitoring data, performing hash operation according to the data change trend curve graph to generate a unique identification code, generating a second key by taking the unique identification code as a parameter of a preset key algorithm, and decrypting the power station operation monitoring data through the second key.
6. The plant safety monitoring system of claim 1, wherein the second analysis module comprises:
the hidden danger analysis submodule is used for inputting the real-time power station monitoring data into a pre-trained neural network model for processing, and the neural network model classifies the hidden danger factors in the real-time power station monitoring data by analyzing the hidden danger factors to obtain potential safety hazard information generated by safety accidents which can be caused by the corresponding hidden danger factors;
and the strategy generation sub-module is used for querying a preset hidden danger elimination strategy database by taking the potential safety hazard information as a query condition to acquire a hidden danger elimination strategy corresponding to the potential safety hazard information.
7. The power station safety monitoring system according to claim 1, characterized in that the system further comprises an inspection terminal and an optimization module, the inspection terminal is respectively connected with the optimization module and the second analysis module,
the inspection terminal is used for acquiring the hidden danger elimination strategy from the second analysis module and sending hidden danger confirmation information and strategy implementation results input by inspection personnel to the optimization module;
the optimization module is used for identifying and matching the hidden danger confirmation information and the potential safety hazard information generated by the second analysis module, and if the hidden danger confirmation information is not matched with the potential safety hazard information, optimizing and updating the neural network model according to the hidden danger confirmation information; and if the hidden danger confirmation information is matched with the potential safety hazard information, performing effect evaluation on the hidden danger elimination strategy according to the strategy implementation result.
8. The power station safety monitoring system according to claim 7, wherein the optimization module is specifically configured to determine whether the policy implementation result is a positive result or a negative result, and when the policy implementation result is a positive result, promote an effect evaluation level of a corresponding hidden danger elimination policy; and when the strategy implementation result is a negative result, reducing the effect evaluation grade of the corresponding hidden danger elimination strategy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111072229.2A CN113538171A (en) | 2021-09-14 | 2021-09-14 | Power station safety monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111072229.2A CN113538171A (en) | 2021-09-14 | 2021-09-14 | Power station safety monitoring system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113538171A true CN113538171A (en) | 2021-10-22 |
Family
ID=78092498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111072229.2A Pending CN113538171A (en) | 2021-09-14 | 2021-09-14 | Power station safety monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113538171A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116306223A (en) * | 2023-01-09 | 2023-06-23 | 浪潮智慧科技有限公司 | Hydraulic engineering monitoring method, equipment and medium |
| CN118095845A (en) * | 2024-02-23 | 2024-05-28 | 中国华能集团清洁能源技术研究院有限公司 | Safety hazard management method and system, electronic equipment, and storage medium |
| CN118508616A (en) * | 2024-07-18 | 2024-08-16 | 湖南大学 | Aerial hidden danger monitoring method and system for substation based on low-orbit satellite Internet |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090234757A1 (en) * | 2008-03-13 | 2009-09-17 | Ben Tarbell | Renewable energy system monitor |
| CN103679293A (en) * | 2013-12-20 | 2014-03-26 | 长园深瑞继保自动化有限公司 | Intelligent substation warning and aid decision making system |
| CN107016507A (en) * | 2017-04-07 | 2017-08-04 | 国网技术学院 | Electric network fault method for tracing based on data mining technology |
| CN110175756A (en) * | 2019-05-07 | 2019-08-27 | 岭澳核电有限公司 | Nuclear power station information system operational safety method for early warning, device, equipment and medium |
| CN111970109A (en) * | 2020-08-13 | 2020-11-20 | 山东英信计算机技术有限公司 | Data transmission method and system |
| CN112053537A (en) * | 2020-09-29 | 2020-12-08 | 深圳市建筑装饰(集团)有限公司 | Intelligent epidemic prevention monitoring response system and monitoring response method thereof |
| CN112966552A (en) * | 2021-01-29 | 2021-06-15 | 山东信通电子股份有限公司 | Routine inspection method and system based on intelligent identification |
-
2021
- 2021-09-14 CN CN202111072229.2A patent/CN113538171A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090234757A1 (en) * | 2008-03-13 | 2009-09-17 | Ben Tarbell | Renewable energy system monitor |
| CN103679293A (en) * | 2013-12-20 | 2014-03-26 | 长园深瑞继保自动化有限公司 | Intelligent substation warning and aid decision making system |
| CN107016507A (en) * | 2017-04-07 | 2017-08-04 | 国网技术学院 | Electric network fault method for tracing based on data mining technology |
| CN110175756A (en) * | 2019-05-07 | 2019-08-27 | 岭澳核电有限公司 | Nuclear power station information system operational safety method for early warning, device, equipment and medium |
| CN111970109A (en) * | 2020-08-13 | 2020-11-20 | 山东英信计算机技术有限公司 | Data transmission method and system |
| CN112053537A (en) * | 2020-09-29 | 2020-12-08 | 深圳市建筑装饰(集团)有限公司 | Intelligent epidemic prevention monitoring response system and monitoring response method thereof |
| CN112966552A (en) * | 2021-01-29 | 2021-06-15 | 山东信通电子股份有限公司 | Routine inspection method and system based on intelligent identification |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116306223A (en) * | 2023-01-09 | 2023-06-23 | 浪潮智慧科技有限公司 | Hydraulic engineering monitoring method, equipment and medium |
| CN116306223B (en) * | 2023-01-09 | 2023-09-22 | 浪潮智慧科技有限公司 | Hydraulic engineering monitoring method, equipment and medium |
| CN118095845A (en) * | 2024-02-23 | 2024-05-28 | 中国华能集团清洁能源技术研究院有限公司 | Safety hazard management method and system, electronic equipment, and storage medium |
| CN118508616A (en) * | 2024-07-18 | 2024-08-16 | 湖南大学 | Aerial hidden danger monitoring method and system for substation based on low-orbit satellite Internet |
| CN118508616B (en) * | 2024-07-18 | 2024-09-17 | 湖南大学 | Aerial hidden danger monitoring method and system for substation based on low-orbit satellite Internet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113538171A (en) | Power station safety monitoring system | |
| US10452845B2 (en) | Generic framework to detect cyber threats in electric power grid | |
| CN109241989B (en) | A method and system for restoration of smart substation intrusion scenarios based on spatio-temporal similarity matching | |
| CN107994539A (en) | A kind of distribution line failure detecting system based on Cloud Server | |
| CN118333411A (en) | Safety production accident hidden danger early warning system based on artificial intelligence | |
| CN108734201B (en) | Classification method and system for experience feedback events of nuclear power plant based on hierarchical reason analysis method | |
| CN112333241A (en) | Intelligent security system based on big data service | |
| CN110768846A (en) | Intelligent substation network safety protection system | |
| CN116781430A (en) | Network information security system and method for gas pipe network | |
| CN118015798A (en) | A method and system for real-time monitoring of electrical safety hazards of electrical equipment | |
| CN117439916A (en) | Network security test evaluation system and method | |
| CN118093793B (en) | Digital archive storage intelligent management system based on data analysis | |
| CN112488336A (en) | Power grid fault processing method and system used in extreme weather | |
| CN117935519B (en) | Gas detection alarm system | |
| CN119211000A (en) | A power communication network fault prediction and diagnosis system | |
| CN111145393A (en) | Method and system for monitoring abnormal operation of electric intelligent lock | |
| CN116823220A (en) | A cable operation status monitoring platform and equipment | |
| CN118228274A (en) | A data security diagnosis method for dispatching automation system | |
| CN119651923A (en) | A substation control system based on cloud control and local area network | |
| CN103812676A (en) | Apparatus and method for realizing log data real-time association | |
| CN110674193A (en) | A fault information modeling method for relay protection in smart substations | |
| CN117375216A (en) | Intelligent verification method of power grid operating status based on data security | |
| CN116614258A (en) | Network danger prediction model of security situation awareness system | |
| CN115765151A (en) | A safety operation and maintenance management method and system for substation secondary equipment | |
| Zhao et al. | Analysis and Application of intelligent Power Control System Cyber Security Situation Awareness Based on Wavelet Neural Network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |