WO2024098668A1 - Procédé et appareil de diagnostic d'anomalie basés sur la 5g pour dispositif à énergie nucléaire, et dispositif informatique - Google Patents

Procédé et appareil de diagnostic d'anomalie basés sur la 5g pour dispositif à énergie nucléaire, et dispositif informatique Download PDF

Info

Publication number
WO2024098668A1
WO2024098668A1 PCT/CN2023/088970 CN2023088970W WO2024098668A1 WO 2024098668 A1 WO2024098668 A1 WO 2024098668A1 CN 2023088970 W CN2023088970 W CN 2023088970W WO 2024098668 A1 WO2024098668 A1 WO 2024098668A1
Authority
WO
WIPO (PCT)
Prior art keywords
historical
sensor data
standard deviation
data
abnormal
Prior art date
Application number
PCT/CN2023/088970
Other languages
English (en)
Chinese (zh)
Inventor
郭承旺
钟质飞
郭伟
吕跃跃
范建超
熊国华
方郁
Original Assignee
中广核研究院有限公司
中国广核集团有限公司
中国广核电力股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 中广核研究院有限公司, 中国广核集团有限公司, 中国广核电力股份有限公司 filed Critical 中广核研究院有限公司
Publication of WO2024098668A1 publication Critical patent/WO2024098668A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3447—Performance evaluation by modeling
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E30/00—Energy generation of nuclear origin

Definitions

  • the present application relates to the field of nuclear power technology, and in particular to a 5G-based nuclear power equipment abnormality diagnosis method, device and computer equipment.
  • Nuclear power plants use the heat energy of nuclear reactors to supply electricity. How to ensure the safe and stable operation of nuclear power plants is the most concerned issue in the field of nuclear power technology. In order to ensure the safe and stable operation of nuclear power plants, it is particularly important to diagnose abnormalities in the operating status of nuclear power equipment.
  • the operating parameters of nuclear power equipment are mainly collected through sensors, and experienced experts are relied upon to diagnose and analyze the collected sensor data to determine whether there is any abnormality in the nuclear power equipment, thereby diagnosing the operating status of the nuclear power equipment.
  • the present application provides a 5G-based nuclear power equipment abnormality diagnosis method.
  • the method comprises:
  • Acquire sensor data of nuclear power equipment at each moment in a preset time period perform dimensionality reduction processing on the sensor data, and calculate the maximum value and standard deviation of the sensor data after dimensionality reduction processing;
  • the following conditions include that the maximum value is greater than a preset maximum value threshold and the standard deviation is greater than a preset standard deviation threshold, then the sensor data after the dimensionality reduction processing is determined to be abnormal data, and the diagnosis result of the abnormality of the nuclear power equipment is obtained according to the abnormal data;
  • the calculating of the maximum value and standard deviation of the sensor data after the dimension reduction process includes:
  • the average value of the sensor data after the dimensionality reduction processing is obtained by adding up all the square root values and dividing by the number of sensor data.
  • the standard deviation of the sensor data after the dimensionality reduction processing is calculated using the average value.
  • the present application also provides a 5G-based nuclear power equipment abnormality diagnosis device.
  • the device includes:
  • a data calculation module is used to obtain sensor data of nuclear power equipment at each moment in a preset time period, perform dimensionality reduction processing on the sensor data, and calculate the maximum value and standard deviation of the sensor data after dimensionality reduction processing;
  • An abnormality diagnosis module used for determining that the sensor data after the dimension reduction processing is abnormal data if any one of the following conditions is met, wherein the following conditions include that the maximum value is greater than a preset maximum value threshold and the standard deviation is greater than a preset standard deviation threshold, and obtaining a diagnosis result of the abnormality of the nuclear power equipment according to the abnormal data;
  • the data calculation module includes:
  • a maximum value calculation unit used to calculate the square root of the sum of squares of the sensor data after the dimensionality reduction processing corresponding to each moment in the preset time period, and determine the maximum value of the square root values corresponding to each moment as the maximum value of the sensor data after the dimensionality reduction processing;
  • the standard deviation calculation unit is used to add all the square root values and divide them by the number of sensor data to obtain the average value of the sensor data after the dimensionality reduction processing, and use the average value to calculate the standard deviation of the sensor data after the dimensionality reduction processing.
  • the present application further provides a computer device.
  • the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:
  • Acquire sensor data of nuclear power equipment at each moment in a preset time period perform dimensionality reduction processing on the sensor data, and calculate the maximum value and standard deviation of the sensor data after dimensionality reduction processing;
  • the following conditions include that the maximum value is greater than a preset maximum value threshold and the standard deviation is greater than a preset standard deviation threshold, then the sensor data after the dimensionality reduction processing is determined to be abnormal data, and the diagnosis result of the abnormality of the nuclear power equipment is obtained according to the abnormal data;
  • the calculating of the maximum value and standard deviation of the sensor data after the dimension reduction process includes:
  • the average value of the sensor data after the dimensionality reduction processing is obtained by adding up all the square root values and dividing by the number of sensor data.
  • the standard deviation of the sensor data after the dimensionality reduction processing is calculated using the average value.
  • the present application further provides a computer-readable storage medium.
  • the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:
  • Acquire sensor data of nuclear power equipment at each moment in a preset time period perform dimensionality reduction processing on the sensor data, and calculate the maximum value and standard deviation of the sensor data after dimensionality reduction processing;
  • the following conditions include that the maximum value is greater than a preset maximum value threshold and the standard deviation is greater than a preset standard deviation threshold, then the sensor data after the dimensionality reduction processing is determined to be abnormal data, and the diagnosis result of the abnormality of the nuclear power equipment is obtained according to the abnormal data;
  • the calculating of the maximum value and standard deviation of the sensor data after the dimension reduction processing includes:
  • the average value of the sensor data after the dimensionality reduction processing is obtained by adding up all the square root values and dividing by the number of sensor data.
  • the standard deviation of the sensor data after the dimensionality reduction processing is calculated using the average value.
  • the present application further provides a computer program product.
  • the computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:
  • Acquire sensor data of nuclear power equipment at each moment in a preset time period perform dimensionality reduction processing on the sensor data, and calculate the maximum value and standard deviation of the sensor data after dimensionality reduction processing;
  • the following conditions include that the maximum value is greater than a preset maximum value threshold and the standard deviation is greater than a preset standard deviation threshold, then the sensor data after the dimensionality reduction processing is determined to be abnormal data, and the diagnosis result of the abnormality of the nuclear power equipment is obtained according to the abnormal data;
  • the calculating of the maximum value and standard deviation of the sensor data after the dimension reduction process includes:
  • the average value of the sensor data after the dimensionality reduction processing is obtained by adding up all the square root values and dividing by the number of sensor data.
  • the standard deviation of the sensor data after the dimensionality reduction processing is calculated using the average value.
  • FIG1 is a schematic diagram of a flow chart of a 5G-based nuclear power equipment abnormality diagnosis method provided in an embodiment of the present application;
  • FIG2 is a schematic diagram of a flow chart of a method for obtaining a preset maximum value threshold and a preset standard deviation threshold in one embodiment
  • FIG3 is a schematic diagram of a process of obtaining a trained abnormality diagnosis network model in one embodiment
  • FIG4 is a schematic diagram of a process of diagnosing abnormal data using a network model in one embodiment
  • FIG5 is a schematic diagram of a process flow of a network model diagnosing normal data in one embodiment
  • FIG6 is a structural block diagram of a 5G-based nuclear power equipment abnormality diagnosis system provided in an embodiment of the present application.
  • FIG7 is a structural block diagram of a 5G-based nuclear power equipment abnormality diagnosis device provided in an embodiment of the present application.
  • FIG8 is an internal structure diagram of a computer device provided in an embodiment of the present application.
  • a 5G-based nuclear power equipment abnormality diagnosis method takes the method applied to a computer device as an example. It can be understood that the method can also be applied to a server, and can also be applied to a system including a computer device and a server, and is implemented through the interaction between the computer device and the server.
  • FIG1 is a flow chart of a 5G-based nuclear power equipment abnormality diagnosis method provided in an embodiment of the present application. The method is applied to a computer device or a server. In one embodiment, as shown in FIG1 , the method includes the following steps:
  • sensor data is data collected by using corresponding sensors to collect various parameters of the nuclear power equipment itself or the environment in which the nuclear power equipment is located.
  • Sensor data includes temperature, vibration, pressure, flow, etc.
  • the steam turbine of nuclear power equipment the steam turbine generates electricity by driving the impeller to rotate through steam.
  • the pressure value of the steam on the impeller is collected through the pressure sensor, and this pressure value is the sensor data.
  • principal component analysis can be used to perform dimensionality reduction processing on sensor data
  • independent component analysis can also be used to perform dimensionality reduction processing on sensor data. There is no limitation to this.
  • the sensor data collected for T minutes is ⁇ x 1 ,x 2 ,...,x T ⁇ , where x T is the sensor data collected at time T.
  • the sensor data is reduced in dimension using principal component analysis, so that the dimension of the sensor data at each moment is reduced to n.
  • the sensor data at moment t after dimensionality reduction is
  • a method for calculating the maximum value and standard deviation of the sensor data after dimensionality reduction processing is to calculate the square root of the sum of squares of the sensor data after dimensionality reduction processing corresponding to each moment within a preset time period, and determine the maximum value of the square root values corresponding to each moment as the maximum value of the sensor data after dimensionality reduction processing; add all square root values and divide them by the number of sensor data to obtain the average value of the sensor data after dimensionality reduction processing, and use the average value to calculate the standard deviation of the sensor data after dimensionality reduction processing.
  • the square root of the sum of squares of the sensor data at time t after dimensionality reduction is The maximum value of the square root values corresponding to each moment is determined as the maximum value of the sensor data after the dimensionality reduction processing;
  • the average value of the sensor data after dimensionality reduction is The formula for calculating the standard deviation ⁇ of the sensor data after dimensionality reduction using the average value u is:
  • the 5G-based nuclear power equipment abnormality diagnosis method obtains the sensor data of the nuclear power equipment at each moment within a preset time period, performs dimensionality reduction processing on the sensor data, and calculates the maximum value and standard deviation of the sensor data after dimensionality reduction processing; if the maximum value is greater than the preset maximum value threshold and the standard deviation is greater than the preset standard deviation threshold, the sensor data after dimensionality reduction processing is determined to be abnormal data, and the abnormal diagnosis result of the nuclear power equipment is obtained according to the abnormal data.
  • the present application collects sensor data, and because the collected sensor data has data interference and the data volume is large, the dimensionality reduction processing of the sensor data can reduce the data volume, improve the efficiency of abnormal diagnosis of nuclear power equipment, and can also eliminate the redundant data interference in the sensor data, further calculate the maximum value and standard deviation of the sensor data after dimensionality reduction processing, compare the maximum value with the preset maximum value threshold, and the standard deviation with the preset standard deviation threshold, and judge whether the sensor data after dimensionality reduction processing is abnormal data according to the comparison result, thereby improving the accuracy and efficiency of abnormal diagnosis of nuclear power equipment.
  • FIG2 a flow chart of a method for obtaining a preset maximum value threshold and a preset standard deviation threshold is shown in FIG2 , and includes the following steps:
  • historical normal sensor data is data collected by using sensors to collect various parameters of the nuclear power equipment itself or the environment in which the nuclear power equipment is located when the nuclear power equipment is operating normally.
  • Historical normal sensor data includes historical normal temperature, historical normal vibration, historical normal pressure, and historical normal flow.
  • the steam turbine of nuclear power equipment As an example, the steam turbine generates electricity by driving the impeller to rotate by steam.
  • the historical normal flow value of steam collected by the flow sensor is the historical normal sensor data.
  • each historical normal sensor data can be processed by principal component analysis, and each historical normal sensor data can also be processed by independent component analysis, which is not limited.
  • the method of calculating the historical maximum value and historical standard deviation of the historical normal sensor data after dimensionality reduction processing is the same as the method of calculating the maximum value and standard deviation of the sensor data after dimensionality reduction processing in step S101, and reference can be made to the above description of the method of calculating the maximum value and standard deviation of the sensor data after dimensionality reduction processing in step S101.
  • multiple historical maximum values conform to normal distribution, so as to obtain the historical maximum expected value ⁇ 1 and the historical maximum standard deviation value ⁇ 1 among the multiple historical maximum values, and the preset maximum value threshold is calculated by the following first threshold formula, which is ⁇ 1 +3 ⁇ 1 .
  • the preset standard deviation threshold is calculated by the following second threshold formula, which is ⁇ 2 +3 ⁇ 2 .
  • Obtaining a preset maximum value threshold and a preset standard deviation threshold, comparing the maximum value with the preset maximum value threshold, and the standard deviation with the preset standard deviation threshold, and judging whether the sensor data after dimensionality reduction processing is abnormal data based on the comparison result can improve the efficiency and accuracy of abnormal diagnosis of nuclear power equipment.
  • the nuclear power equipment when the diagnosis result of the nuclear power equipment is abnormal, the nuclear power equipment is replaced by the spare nuclear power equipment.
  • the abnormal nuclear power equipment can be replaced in time, so as not to affect the normal operation of the nuclear power plant, enhance the ability to handle abnormal situations, and improve practicality.
  • a flow chart of obtaining a trained abnormality diagnosis network model includes the following contents:
  • historical abnormal sensor data refers to data collected by sensors from various parameters of nuclear power equipment itself or the environment in which the nuclear power equipment is located when the nuclear power equipment is operating abnormally
  • historical normal sensor data refers to data collected by sensors from various parameters of nuclear power equipment itself or the environment in which the nuclear power equipment is located when the nuclear power equipment is operating normally.
  • Historical abnormal sensor data includes historical abnormal temperature, historical abnormal vibration, historical abnormal pressure, and historical abnormal flow.
  • the method of marking the historical abnormal sensor data and the historical normal sensor data respectively may be to mark the historical abnormal sensor data with a first preset mark value and mark the historical normal sensor data with a second preset mark value. For example, mark the historical abnormal sensor data as 0 and mark the historical normal sensor data as 1.
  • the abnormal data type is the data type corresponding to the event category that specifically causes the abnormal data
  • the normal data type is the data type corresponding to the normal data.
  • the abnormal data types can be Class A and Class B. Class A indicates bearing wear of nuclear power equipment, and Class B indicates pipeline rupture of nuclear power equipment.
  • the initial abnormal diagnosis network model can be a full neural network model or a convolutional neural network model, which is not limited here. The initial abnormal diagnosis network model is trained to obtain a trained abnormal diagnosis network model, which can ensure the accuracy of the output results when using the trained abnormal diagnosis network model.
  • the trained abnormal diagnosis network model is used to diagnose the abnormal data again.
  • the flow chart of the model for abnormal data diagnosis is shown in Figure 4, which includes the following steps:
  • the method of marking abnormal data can be to mark the abnormal data with a preset abnormal marking value. For example, if the preset abnormal marking value is 0, the sensor data at time t after the dimensionality reduction process is abnormal data, then the marked abnormal data is
  • the preset diagnosis and maintenance database is a database set in advance for proposing corresponding maintenance plans for each abnormal data type. Using the maintenance plan to repair nuclear power equipment can put the repaired nuclear power equipment back into use, avoiding the waste of nuclear power equipment resources.
  • Using the sensor data corresponding to the normal data type as the historical normal sensor data to update the preset maximum value threshold and the preset standard deviation threshold can ensure the accuracy of the threshold setting and improve the accuracy of abnormal diagnosis of nuclear power equipment.
  • FIG5 is a schematic diagram of a process of diagnosing normal data by a network model in one embodiment, as shown in FIG5 , including the following steps:
  • the normal data can be marked by using a preset normal mark value. For example, if the preset normal mark value is 1, the sensor data at time t after the dimensionality reduction process is normal data, then the marked normal data is
  • the preset diagnosis and maintenance database is a database set in advance for proposing corresponding maintenance plans for each abnormal data type. Using the maintenance plan to repair nuclear power equipment can put the repaired nuclear power equipment back into use, avoiding the waste of nuclear power equipment resources.
  • Using the sensor data corresponding to the normal data type as the historical normal sensor data to update the preset maximum value threshold and the preset standard deviation threshold can ensure the accuracy of the threshold setting and improve the accuracy of abnormal diagnosis of nuclear power equipment.
  • FIG6 is a structural block diagram of a 5G-based nuclear power equipment abnormality diagnosis system provided in an embodiment of the present application.
  • the 5G-based nuclear power equipment abnormality diagnosis system includes a sensor data acquisition module, an edge processing module, and a cloud processing module. Among them, the sensor data acquisition module and the edge processing module transmit data through the 5G wireless network, the edge processing module processes data through the edge server, the cloud processing module processes data through the cloud server, and the edge processing module and the cloud processing module transmit data through Ethernet.
  • the sensor data acquisition module is used to collect sensor data of nuclear power equipment, and transmit the collected sensor data to the edge processing module through the 5G wireless network for processing.
  • the edge processing module is used to receive the collected sensor data, process the collected sensor data, perform pre-diagnosis using the processed sensor data, and transmit the pre-diagnosis results, processed sensor data, and collected sensor data to the cloud processing module through Ethernet.
  • the cloud processing module is used to receive the pre-diagnosis results, processed sensor data, and collected sensor data, and perform re-diagnosis on the processed sensor data and collected sensor data.
  • the edge processing module includes an edge data receiving unit, a pre-diagnosis unit, an edge data storage unit and an edge data sending unit.
  • the cloud processing module includes a cloud data receiving unit, a cloud diagnosis unit and a cloud data storage unit.
  • the process of applying the system to the interaction between edge servers and cloud servers to realize a 5G-based nuclear power equipment abnormality diagnosis method is described in detail.
  • the sensor data acquisition module is used to obtain the sensor data of the nuclear power equipment at each moment within a preset time period.
  • the edge data receiving unit is used to receive the sensor data of the nuclear power equipment at each moment within a preset time period.
  • the pre-diagnosis unit is used to perform dimensionality reduction processing on the sensor data, calculate the maximum value and standard deviation of the sensor data after dimensionality reduction processing, compare the maximum value with the preset maximum value threshold, and the standard deviation with the preset standard deviation threshold, and judge whether the sensor data after dimensionality reduction processing is abnormal data or normal data according to the comparison result, and mark them respectively; in the case that the sensor data after dimensionality reduction processing is abnormal data, the corresponding standby nuclear power equipment information is queried in the preset emergency standby equipment library, and the abnormal nuclear power equipment is replaced with the standby nuclear power equipment.
  • the edge data storage unit is used to store the preset maximum value threshold, the preset standard deviation threshold and the preset emergency standby equipment library.
  • the edge data sending unit is used to transmit the marked sensor data and the collected sensor data to the cloud processing module.
  • the cloud data receiving unit is used to receive the labeled sensor data and the collected sensor data.
  • the cloud diagnosis unit is used to input the labeled sensor data and the collected sensor data into the trained abnormal diagnosis network model, and output the corresponding abnormal data type and normal data type; when the output is the abnormal data type, the corresponding maintenance plan is queried in the preset diagnosis and maintenance library, and the nuclear power equipment is repaired using the maintenance plan.
  • the cloud data storage unit is used to store historical normal sensor data, historical abnormal sensor data, the trained abnormal diagnosis network model and the preset diagnosis and maintenance library.
  • the 5G-based nuclear power equipment abnormality diagnosis system obtains the sensor data of the nuclear power equipment at each moment in a preset time period, performs dimensionality reduction processing on the sensor data, and calculates the maximum value and standard deviation of the sensor data after dimensionality reduction processing; if the maximum value is greater than the preset maximum value threshold and the standard deviation is greater than the preset standard deviation threshold, the sensor data after dimensionality reduction processing is determined to be abnormal data, and the diagnosis result of the abnormality of the nuclear power equipment is obtained according to the abnormal data.
  • the present application collects sensor data, and because the collected sensor data has data interference and the data volume is large, the dimensionality reduction processing of the sensor data can reduce the data volume, improve the efficiency of abnormal diagnosis of nuclear power equipment, and can also eliminate the redundant data interference in the sensor data, further calculate the maximum value and standard deviation of the sensor data after dimensionality reduction processing, compare the maximum value with the preset maximum value threshold, and the standard deviation with the preset standard deviation threshold, and judge whether the sensor data after dimensionality reduction processing is abnormal data according to the comparison result, thereby improving the accuracy and efficiency of abnormal diagnosis of nuclear power equipment.
  • the system uses edge servers to process the collected sensor data and pre-diagnose the processed sensor data, reducing the unreliability of remote data transmission and the operation and maintenance costs of remote data transmission.
  • the cloud server has powerful computing power, which ensures the accuracy of data processing and improves the accuracy of abnormal diagnosis of nuclear power equipment.
  • steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
  • the embodiment of the present application also provides a 5G-based nuclear power equipment abnormality diagnosis device for implementing the above-mentioned 5G-based nuclear power equipment abnormality diagnosis method.
  • the implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more 5G-based nuclear power equipment abnormality diagnosis device embodiments provided below can refer to the limitations of the 5G-based nuclear power equipment abnormality diagnosis method above, and will not be repeated here.
  • FIG. 7 is a structural block diagram of a 5G-based nuclear power equipment abnormality diagnosis device provided in an embodiment of the present application.
  • the device 700 includes: a data calculation module 701 and an abnormality diagnosis module 702, wherein:
  • the data calculation module 701 is used to obtain the sensor data of the nuclear power equipment at each time in a preset time period, perform dimensionality reduction processing on the sensor data, and calculate the maximum value and standard deviation of the sensor data after the dimensionality reduction processing;
  • the abnormality diagnosis module 702 is used to determine that the sensor data after dimensionality reduction processing is abnormal data if any one of the following conditions is met, including that the maximum value is greater than a preset maximum value threshold and the standard deviation is greater than a preset standard deviation threshold, and obtain the diagnosis result of the nuclear power equipment abnormality based on the abnormal data.
  • the 5G-based nuclear power equipment abnormality diagnosis device obtains the sensor data of the nuclear power equipment at each moment in a preset time period through a data calculation module, performs dimensionality reduction processing on the sensor data, and calculates the maximum value and standard deviation of the sensor data after dimensionality reduction processing; in the abnormality diagnosis module, if the maximum value is greater than the preset maximum value threshold and the standard deviation is greater than the preset standard deviation threshold, the sensor data after dimensionality reduction processing is determined to be abnormal data, and the diagnosis result of the nuclear power equipment abnormality is obtained based on the abnormal data.
  • this application collects and analyzes the collected sensor data through 5G.
  • Sensor data because the collected sensor data has data interference and the data volume is large, dimensionality reduction processing of the sensor data can reduce the data volume, improve the efficiency of abnormal diagnosis of nuclear power equipment, and eliminate redundant data interference in the sensor data.
  • the maximum value and standard deviation of the sensor data after dimensionality reduction processing are further calculated, and the maximum value is compared with the preset maximum value threshold, and the standard deviation is compared with the preset standard deviation threshold. According to the comparison results, it is determined whether the sensor data after dimensionality reduction processing is abnormal data, which improves the accuracy and efficiency of abnormal diagnosis of nuclear power equipment.
  • the data calculation module 701 includes:
  • a maximum value calculation unit used to calculate the square root of the sum of squares of the sensor data after dimensionality reduction processing corresponding to each moment in a preset time period, and determine the maximum value of the square root values corresponding to each moment as the maximum value of the sensor data after dimensionality reduction processing;
  • the standard deviation calculation unit is used to add all the square root values and divide them by the number of sensor data to obtain the average value of the sensor data after dimensionality reduction processing, and use the average value to calculate the standard deviation of the sensor data after dimensionality reduction processing.
  • the abnormality diagnosis module 702 includes:
  • a historical data acquisition unit is used to acquire historical normal sensor data collected by the nuclear power equipment in a normal state in multiple historical time periods, perform dimensionality reduction processing on each historical normal sensor data, and calculate the historical maximum value and historical standard deviation of the historical normal sensor data after the dimensionality reduction processing;
  • a maximum value threshold unit is used to obtain a historical maximum expected value and a historical maximum standard deviation value among multiple historical maximum values, and calculate a preset maximum value threshold using the historical maximum expected value and the historical maximum standard deviation value;
  • the standard deviation threshold unit is used to obtain the historical standard deviation expected value and the historical standard deviation standard deviation value from multiple historical standard deviations, and calculate the preset standard deviation threshold using the historical standard deviation expected value and the historical standard deviation standard deviation value.
  • the device 700 further includes:
  • the equipment replacement module is used to replace the nuclear power equipment with a spare nuclear power equipment when the diagnosis result of the nuclear power equipment is abnormal.
  • the device 700 further includes:
  • An abnormal input module is used to mark abnormal data and input the marked abnormal data into the trained abnormal diagnosis network model;
  • the first abnormal module is used to query the corresponding maintenance plan in the preset diagnosis and maintenance library according to the abnormal data type when the abnormal data type is output, and use the maintenance plan to repair the nuclear power equipment;
  • the first normal module is used to update a preset maximum value threshold and a preset standard deviation threshold using the sensing data corresponding to the normal data type when a normal data type is output.
  • the device 700 further includes:
  • the abnormality diagnosis module 702 is further used to determine that the sensor data after the dimension reduction processing is normal data if the maximum value is not greater than a preset maximum value threshold and the standard deviation is not greater than a preset standard deviation threshold;
  • a normal input module is used to label normal data and input the labeled normal data into the trained abnormal diagnosis network model;
  • the second abnormal module is used to query the corresponding maintenance plan in the preset diagnosis and maintenance library according to the abnormal data type when the abnormal data type is output, and use the maintenance plan to repair the nuclear power equipment;
  • the second normal module is used to update a preset maximum value threshold and a preset standard deviation threshold using the sensing data corresponding to the normal data type when a normal data type is output.
  • the device 700 further includes:
  • a historical data acquisition module is used to acquire historical abnormal sensor data and historical normal sensor data, and mark the historical abnormal sensor data and historical normal sensor data respectively;
  • the model training module is used to train the initial abnormal diagnosis network model with the marked historical abnormal sensor data and the marked historical normal sensor data as input and the corresponding abnormal data type and normal data type as output to obtain the trained abnormal diagnosis network model.
  • Each module in the above-mentioned 5G-based nuclear power equipment abnormality diagnosis device can be implemented in whole or in part by software, hardware and their combination.
  • Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.
  • a computer device which may be a terminal, and its internal structure diagram may be shown in FIG8.
  • the computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input device.
  • the processor, the memory, and the input/output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected via the input/output interface.
  • the computer device is connected to the system bus.
  • the processor of the computer device is used to provide computing and control capabilities.
  • the memory of the computer device includes a non-volatile storage medium and an internal memory.
  • the non-volatile storage medium stores an operating system and a computer program.
  • the internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium.
  • the input/output interface of the computer device is used to exchange information between the processor and the external device.
  • the communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through a 5G wireless network, WIFI, a mobile cellular network, NFC (near field communication) or other technologies.
  • a 5G-based nuclear power equipment abnormality diagnosis method is implemented.
  • the display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device.
  • the display screen can be a liquid crystal display screen or an electronic ink display screen
  • the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.
  • FIG. 8 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.
  • the specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
  • a computer device including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the 5G-based nuclear power equipment abnormality diagnosis method provided in the above embodiment are implemented:
  • Acquire sensor data of nuclear power equipment at each moment in a preset time period perform dimensionality reduction processing on the sensor data, and calculate the maximum value and standard deviation of the sensor data after dimensionality reduction processing;
  • the sensor data after dimensionality reduction processing is determined to be abnormal data, and the diagnosis result of the abnormality of the nuclear power equipment is obtained based on the abnormal data;
  • the average value of the sensor data after dimensionality reduction processing is obtained by adding up all the square root values and dividing by the number of sensor data.
  • the standard deviation of the sensor data after dimensionality reduction processing is calculated using the average value.
  • a corresponding maintenance plan is searched in a preset diagnosis and maintenance library according to the abnormal data type, and the nuclear power equipment is repaired using the maintenance plan;
  • the preset maximum value threshold and the preset standard deviation threshold are updated using the sensing data corresponding to the normal data type.
  • the sensor data after the dimensionality reduction processing is determined to be normal data
  • a corresponding maintenance plan is searched in a preset diagnosis and maintenance library according to the abnormal data type, and the nuclear power equipment is repaired using the maintenance plan;
  • the preset maximum value threshold and the preset standard deviation threshold are updated using the sensing data corresponding to the normal data type.
  • the initial abnormal diagnosis network model is trained to obtain the trained abnormal diagnosis network model.
  • a computer-readable storage medium on which a computer program is stored.
  • the steps of the 5G-based nuclear power equipment abnormality diagnosis method provided in the above embodiment are implemented:
  • Acquire sensor data of nuclear power equipment at each moment in a preset time period perform dimensionality reduction processing on the sensor data, and calculate the maximum value and standard deviation of the sensor data after dimensionality reduction processing;
  • the sensor data after dimensionality reduction processing is determined to be abnormal data, and the diagnosis result of the abnormality of the nuclear power equipment is obtained based on the abnormal data;
  • the average value of the sensor data after dimensionality reduction processing is obtained by adding up all the square root values and dividing by the number of sensor data.
  • the standard deviation of the sensor data after dimensionality reduction processing is calculated using the average value.
  • a corresponding maintenance plan is searched in a preset diagnosis and maintenance library according to the abnormal data type, and the nuclear power equipment is repaired using the maintenance plan;
  • the preset maximum value threshold and the preset standard deviation threshold are updated using the sensing data corresponding to the normal data type.
  • the sensor data after the dimensionality reduction processing is determined to be normal data
  • a corresponding maintenance plan is searched in a preset diagnosis and maintenance library according to the abnormal data type, and the nuclear power equipment is repaired using the maintenance plan;
  • the preset maximum value threshold and the preset standard deviation threshold are updated using the sensing data corresponding to the normal data type.
  • the initial abnormal diagnosis network model is trained to obtain the trained abnormal diagnosis network model.
  • a computer program product including a computer program, which, when executed by a processor, implements the steps of the 5G-based nuclear power equipment abnormality diagnosis method provided in the above embodiment:
  • Acquire sensor data of nuclear power equipment at each moment in a preset time period perform dimensionality reduction processing on the sensor data, and calculate the maximum value and standard deviation of the sensor data after dimensionality reduction processing;
  • the sensor data after dimensionality reduction processing is determined to be abnormal data, and the diagnosis result of the abnormality of the nuclear power equipment is obtained based on the abnormal data;
  • the average value of the sensor data after dimensionality reduction processing is obtained by adding up all the square root values and dividing by the number of sensor data.
  • the standard deviation of the sensor data after dimensionality reduction processing is calculated using the average value.
  • a corresponding maintenance plan is searched in a preset diagnosis and maintenance library according to the abnormal data type, and the nuclear power equipment is repaired using the maintenance plan;
  • the preset maximum value threshold and the preset standard deviation threshold are updated using the sensing data corresponding to the normal data type.
  • the sensor data after the dimensionality reduction processing is determined to be normal data
  • a corresponding maintenance plan is searched in a preset diagnosis and maintenance library according to the abnormal data type, and the nuclear power equipment is repaired using the maintenance plan;
  • the preset maximum value threshold and the preset standard deviation threshold are updated using the sensing data corresponding to the normal data type.
  • the initial abnormal diagnosis network model is trained to obtain the trained abnormal diagnosis network model.
  • any reference to memory, database or other media used in the embodiments provided in the present application may include at least one of non-volatile and volatile memory.
  • Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), Graphene Memory, etc.
  • Volatile memory may include Random Access Memory (RAM) or external cache memory, etc.
  • RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), etc.
  • the database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database.
  • Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto.
  • the processors involved in each embodiment provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., but are not limited thereto.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Marketing (AREA)
  • Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Strategic Management (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Computer Hardware Design (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Monitoring And Testing Of Nuclear Reactors (AREA)

Abstract

La présente demande concerne un procédé et un appareil de diagnostic d'anomalie basés sur la 5G pour un dispositif à énergie nucléaire, et un dispositif informatique. Le procédé consiste à : obtenir des données de détection d'un dispositif à énergie nucléaire à chaque moment pendant une période de temps prédéfinie, effectuer un traitement de réduction de dimension sur les données de détection, et calculer une valeur maximale et un écart-type des données de détection après un traitement de réduction de dimension ; et si l'une quelconque des conditions suivantes est satisfaite, déterminer que les données de détection après le traitement de réduction de dimension sont des données anormales, et obtenir, en fonction des données anormales, un résultat de diagnostic indiquant que le dispositif à énergie nucléaire est anormal, lesdites conditions suivantes comprenant que la valeur maximale est supérieure à un seuil de valeur maximale prédéfini, et l'écart-type est supérieur à un seuil d'écart-type prédéfini.
PCT/CN2023/088970 2022-11-08 2023-04-18 Procédé et appareil de diagnostic d'anomalie basés sur la 5g pour dispositif à énergie nucléaire, et dispositif informatique WO2024098668A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211392043.XA CN115617634A (zh) 2022-11-08 2022-11-08 基于5g的核电设备异常诊断方法、装置和计算机设备
CN202211392043.X 2022-11-08

Publications (1)

Publication Number Publication Date
WO2024098668A1 true WO2024098668A1 (fr) 2024-05-16

Family

ID=84878913

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/088970 WO2024098668A1 (fr) 2022-11-08 2023-04-18 Procédé et appareil de diagnostic d'anomalie basés sur la 5g pour dispositif à énergie nucléaire, et dispositif informatique

Country Status (2)

Country Link
CN (1) CN115617634A (fr)
WO (1) WO2024098668A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115617634A (zh) * 2022-11-08 2023-01-17 中广核研究院有限公司 基于5g的核电设备异常诊断方法、装置和计算机设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105791051A (zh) * 2016-03-25 2016-07-20 中国地质大学（武汉） 基于人工免疫和k均值聚类的无线传感网异常检测方法及系统
KR102051227B1 (ko) * 2018-09-07 2019-12-02 한국수력원자력 주식회사 원전 설비의 예측 진단 방법 및 시스템
CN111352794A (zh) * 2018-12-24 2020-06-30 鸿富锦精密工业(武汉)有限公司 异常检测方法、装置、计算机装置及存储介质
CN112488242A (zh) * 2020-12-18 2021-03-12 深圳供电局有限公司 电力计量终端异常检测方法、装置、计算机设备和介质
CN115617634A (zh) * 2022-11-08 2023-01-17 中广核研究院有限公司 基于5g的核电设备异常诊断方法、装置和计算机设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105791051A (zh) * 2016-03-25 2016-07-20 中国地质大学（武汉） 基于人工免疫和k均值聚类的无线传感网异常检测方法及系统
KR102051227B1 (ko) * 2018-09-07 2019-12-02 한국수력원자력 주식회사 원전 설비의 예측 진단 방법 및 시스템
CN111352794A (zh) * 2018-12-24 2020-06-30 鸿富锦精密工业(武汉)有限公司 异常检测方法、装置、计算机装置及存储介质
CN112488242A (zh) * 2020-12-18 2021-03-12 深圳供电局有限公司 电力计量终端异常检测方法、装置、计算机设备和介质
CN115617634A (zh) * 2022-11-08 2023-01-17 中广核研究院有限公司 基于5g的核电设备异常诊断方法、装置和计算机设备

Also Published As

Publication number Publication date
CN115617634A (zh) 2023-01-17

Similar Documents

Publication Publication Date Title
WO2020259421A1 (fr) Procédé et appareil de surveillance de système de service
US11037080B2 (en) Operational process anomaly detection
Lin et al. Reliability assessment of systems subject to dependent degradation processes and random shocks
Marino et al. A microgrid energy management system based on chance-constrained stochastic optimization and big data analytics
JP2018152052A (ja) 信頼性監視のためのシステムおよび方法
WO2022088632A1 (fr) Procédé, appareil, dispositif et support de suivi et d'analyse de données utilisateur
WO2024098668A1 (fr) Procédé et appareil de diagnostic d'anomalie basés sur la 5g pour dispositif à énergie nucléaire, et dispositif informatique
CN113823396A (zh) 医疗设备管理方法、装置、计算机设备和存储介质
JP6767203B2 (ja) 保守支援装置、保守支援方法およびコンピュータプログラム
CN104572795B (zh) 规则的自动生成和动态更新
Mittman et al. A hierarchical model for heterogenous reliability field data
US20230236590A1 (en) Method and system for providing maintenance service for recording medium included in electronic device
CN117235664A (zh) 配电通信设备的故障诊断方法、系统和计算机设备
US20180089637A1 (en) Framework for industrial asset repair recommendations
CN115471215B (zh) 一种业务流程处理方法及装置
CN115481767A (zh) 面向配电网检修的运行数据处理方法、装置和计算机设备
CN115827383A (zh) 数据异常监测方法和装置
CN114092275A (zh) 企业经营异常监测方法、装置、计算机设备和存储介质
US20200332773A1 (en) A prognostics and health management model for predicting wind turbine oil filter wear level
US20180189701A1 (en) Distributed cache cleanup for analytic instance runs processing operating data from industrial assets
CN113887676A (zh) 设备故障预警方法、装置、设备、介质和计算机程序产品
Sarker et al. Cp-sam: Cyber-power security assessment and resiliency analysis tool for distribution system
US10989626B2 (en) Systems, methods, and devices for performance monitoring of mechanical assemblies
US11281689B1 (en) Distributed interaction feature generation system
CN114154662A (zh) 运行系统的故障诊断方法、装置、计算机设备和存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23887370

Country of ref document: EP

Kind code of ref document: A1