CN111816338A - Health monitoring and fault positioning system and method for nuclear power plant information system - Google Patents
Health monitoring and fault positioning system and method for nuclear power plant information system Download PDFInfo
- Publication number
- CN111816338A CN111816338A CN202010512141.7A CN202010512141A CN111816338A CN 111816338 A CN111816338 A CN 111816338A CN 202010512141 A CN202010512141 A CN 202010512141A CN 111816338 A CN111816338 A CN 111816338A
- Authority
- CN
- China
- Prior art keywords
- nuclear power
- power plant
- data
- monitored
- 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 31
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000003745 diagnosis Methods 0.000 claims abstract description 56
- 238000012549 training Methods 0.000 claims abstract description 45
- 230000002159 abnormal effect Effects 0.000 claims abstract description 23
- 230000005856 abnormality Effects 0.000 claims abstract description 10
- 238000000513 principal component analysis Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 2
- 238000005094 computer simulation Methods 0.000 claims 1
- 230000004044 response Effects 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G21—NUCLEAR PHYSICS; NUCLEAR ENGINEERING
- G21D—NUCLEAR POWER PLANT
- G21D3/00—Control of nuclear power plant
- G21D3/04—Safety arrangements
- G21D3/06—Safety arrangements responsive to faults within the plant
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G21—NUCLEAR PHYSICS; NUCLEAR ENGINEERING
- G21D—NUCLEAR POWER PLANT
- G21D3/00—Control of nuclear power plant
- G21D3/001—Computer implemented control
-
- 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
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Plasma & Fusion (AREA)
- High Energy & Nuclear Physics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Emergency Management (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of fault diagnosis, and particularly discloses a system and a method for health monitoring and fault positioning of a nuclear power plant information system. The system comprises a bottom layer data acquisition module, a diagnosis model training module and an abnormality diagnosis module, wherein the bottom layer data acquisition module is connected with the diagnosis model training module and provides training data of the nuclear power plant information system in different time periods for the diagnosis model training module; the diagnostic model training module can run a diagnostic model, can monitor monitored data of the nuclear power plant information system in real time, and transmits the monitored data to the abnormal diagnostic module connected with the diagnostic model training module to perform abnormal state feedback when the parameters are abnormal. The method can obtain the actual operation condition closer to the system by using the fault diagnosis model, is suitable for the actual operation state and management of the nuclear power information system, can quickly locate the fault, shortens the fault response time and effectively improves the working efficiency.
Description
Technical Field
The invention belongs to the technical field of fault diagnosis, and particularly relates to a system and a method for health monitoring and fault positioning of a nuclear power plant information system.
Background
With the continuous development of the information construction of the nuclear power plant, the daily operation and maintenance work of an information system is more and more complex. The user uses only the application system itself, but also supports the running of the application system, such as an operating system, a database, a network environment, middleware and the like. Once the system fails, the time cost for manually performing fault diagnosis is too high. If the machine learning technology is adopted, the computer judges the fault source or reduces the range of the fault source, so that the diagnosis efficiency is greatly improved.
Disclosure of Invention
The invention aims to provide a system and a method for health monitoring and fault positioning of a nuclear power plant information system, and solves the problems that the nuclear power plant information system has high fault diagnosis time cost and is difficult to determine a fault source.
The technical scheme of the invention is as follows: a health monitoring and fault positioning system for a nuclear power plant information system comprises a bottom layer data acquisition module, a diagnosis model training module and an abnormity diagnosis module, wherein the bottom layer data acquisition module is connected with the diagnosis model training module and provides training data of the nuclear power plant information system in different time periods for the diagnosis model training module; the diagnostic model training module can run a diagnostic model, can monitor monitored data of the nuclear power plant information system in real time, and transmits the monitored data to the abnormal diagnostic module connected with the diagnostic model training module to perform abnormal state feedback when the parameters are abnormal.
The diagnostic model running in the diagnostic model training module is formed by performing calculation modeling on the monitored system data acquired by the bottom data acquisition module through a Principal Component Analysis (PCA) method and an isolated forest algorithm and combining technical indexes of the monitored system.
After the training of the diagnostic model training module is completed, the monitored data obtained from the bottom data acquisition module is input into the diagnostic model in real time for comparison, and if the data exceeds a threshold value within a period of time, the system is judged to be abnormal.
The abnormity diagnosis module is also connected with an early warning feedback module, and the early warning feedback module can feed back and push the abnormal parameter information monitored and identified by the abnormity diagnosis module to a corresponding processing system and a manager.
A health monitoring and fault locating method for a nuclear power plant information system comprises the following steps:
s1, determining information and parameters required to be monitored by the nuclear power plant information system;
s2, training a nuclear power plant information system diagnosis model;
s2.1, selecting data for diagnostic model training;
s2.2, establishing a fault diagnosis model of the nuclear power information system;
carrying out dimensionality reduction on the collected training data at different time periods by using a Principal Component Analysis (PCA) method, constructing a model by adopting an isolated forest algorithm, and combining technical indexes of a nuclear power plant information system to obtain a fault diagnosis model;
and S3, monitoring the data of the nuclear power plant information system in real time, and monitoring the system abnormality by using a fault diagnosis model.
The method for monitoring the abnormality of the nuclear power plant information system in real time comprises the following steps of:
monitoring data of an information system of the nuclear power plant in real time, and substituting various data of monitored operation into a fault diagnosis model of a corresponding time period for matching;
if the contact time of a certain parameter or parameters exceeds a threshold value, the abnormity of the monitored system is judged.
The method for monitoring the system abnormality by using the fault diagnosis model further comprises the steps of transmitting the abnormal parameters to a system foreground and sending out early warning information.
The information and parameters required to be monitored by the nuclear power plant information system specifically include:
determining information of an information system server to be monitored, wherein the information comprises a server name, a server IP (Internet protocol), and the like, and selecting a parameter item to be monitored;
determining information of an information system database to be monitored, wherein the information comprises a database host name, a port number, a user name and a password, and selecting corresponding detection parameter items;
determining the web server information to be monitored on the server, and selecting the corresponding monitored parameter item.
The data for the diagnostic model training specifically includes;
selecting nuclear power plant information data of different time periods as diagnosis model training data of different time periods according to the use condition of a monitored system; the data rotation comprises CPU, memory, disk, network, process, database user connection, user process, database session, database execution SQL, database log file, web container, project information, thread pool, JVM parameter data.
The invention has the following remarkable effects: the system and the method for health monitoring and fault positioning of the nuclear power plant information system can obtain the actual operation condition closer to the system by using the fault diagnosis model, are suitable for the actual operation state and management of the nuclear power plant information system, can quickly position the fault, shorten the fault response time and effectively improve the working efficiency.
Drawings
Fig. 1 is a schematic diagram of a health monitoring and fault locating system of a nuclear power plant information system according to the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and the embodiments.
As shown in fig. 1, a system for health monitoring and fault location of a nuclear power plant information system includes a bottom layer data acquisition module, a diagnosis model training module, an abnormality diagnosis module and an early warning feedback module, wherein the bottom layer data acquisition module is connected with the diagnosis model training module, and acquires data on an operating system, a database and a web server in the nuclear power plant information system by using the bottom layer data acquisition module, and transmits the acquired data to the diagnosis model training module for diagnosis model training; the data collected by the bottom data collection module comprises data of multiple dimensions such as a CPU, a memory, a disk, a database session, a database SQL, a web container, a JVM and the like; the diagnostic model training module is a time period training module, for example, the first 2000 pieces of data extracted in each set time period are used as a calculation template, a PCA principal component analysis method and an isolation forest algorithm are used for calculation, and a diagnostic model is generated according to the technical indexes of the existing nuclear power information system; the abnormity diagnosis module is connected with the diagnosis module training module and used for judging whether the nuclear power plant information system is abnormal or not, specifically, after the diagnosis model in the diagnosis model training module is trained, data acquired from the bottom layer data acquisition module every second is input into the diagnosis model for comparison, if the data in a continuous period of time exceeds a threshold value, for example, the data in 3 continuous seconds exceeds the threshold value, the nuclear power plant information system is judged to be abnormal, abnormal information such as abnormal parameters and the like is submitted to a system foreground, early warning information is sent out by the early warning feedback module connected with the abnormity diagnosis module and is pushed to a corresponding system and a manager, for example, after the system diagnoses the abnormity, the abnormal information is pushed to a corresponding system operation and maintenance person in a short message form by the abnormity diagnosis module.
A health monitoring and fault locating method for a nuclear power plant information system specifically comprises the following steps:
step 1, determining information and parameters required to be monitored by a nuclear power plant information system;
determining information of an information system server to be monitored, wherein the information comprises a server name, a server IP (Internet protocol), and the like, and selecting a parameter item to be monitored;
determining information of an information system database to be monitored, wherein the information comprises a database host name, a port number, a user name and a password, and selecting corresponding detection parameter items;
determining web server information to be monitored on a server, and selecting corresponding monitored parameter items;
step 2, training a nuclear power plant information system diagnosis model;
step 2.1, selecting data for diagnostic model training;
selecting nuclear power plant information data of different time periods as diagnosis model training data of different time periods according to the use condition of a monitored system; the data rotation comprises parameter data such as a CPU, a memory, a disk, a network, a process, a database user connection, a user process, a database session, a database execution SQL, a database log file, a web container, project information, a thread pool, a JVM and the like;
step 2.2, establishing a fault diagnosis model of the nuclear power information system;
carrying out dimensionality reduction on the collected training data at different time periods by using a Principal Component Analysis (PCA) method, constructing a model by adopting an isolated forest algorithm, and combining technical indexes of a nuclear power plant information system to obtain a fault diagnosis model;
step 3, monitoring data of the nuclear power plant information system in real time, and monitoring system abnormality by using a fault diagnosis model;
step 3.1, monitoring data of the nuclear power plant information system in real time, and substituting various data of monitored operation into a fault diagnosis model in a corresponding time period for matching;
step 3.2, if a certain parameter or parameters are associated for a period of time and exceed a threshold value, judging that the monitored system is abnormal;
if one or more parameters exceed the threshold value for 3 seconds continuously, judging that the monitored system is abnormal;
and 3.3, transmitting the abnormal parameters to a system foreground and sending out early warning information.
Claims (9)
1. A health monitoring and fault positioning system for a nuclear power plant information system is characterized by comprising a bottom layer data acquisition module, a diagnosis model training module and an abnormity diagnosis module, wherein the bottom layer data acquisition module is connected with the diagnosis model training module and provides training data of the nuclear power plant information system in different time periods for the diagnosis model training module; the diagnostic model training module can run a diagnostic model, can monitor monitored data of the nuclear power plant information system in real time, and transmits the monitored data to the abnormal diagnostic module connected with the diagnostic model training module to perform abnormal state feedback when the parameters are abnormal.
2. The system of claim 1, wherein the diagnostic model run in the diagnostic model training module is formed by performing computational modeling on the monitored system data acquired by the underlying data acquisition module through PCA principal component analysis and isolated forest algorithm, and combining technical indicators of the monitored system.
3. The system of claim 1, wherein the diagnostic model training module inputs the monitored data obtained from the underlying data acquisition module to the diagnostic model in real time for comparison after training is completed, and determines that the system is abnormal if the data exceeds a threshold value within a period of time.
4. The system for health monitoring and fault location of nuclear power plant information systems according to claim 1, wherein the abnormality diagnosis module is further connected with an early warning feedback module, and the early warning feedback module can feed back and push the abnormal parameter information monitored and identified by the abnormality diagnosis module to corresponding processing systems and managers.
5. A health monitoring and fault locating method for a nuclear power plant information system is characterized by comprising the following steps:
s1, determining information and parameters required to be monitored by the nuclear power plant information system;
s2, training a nuclear power plant information system diagnosis model;
s2.1, selecting data for diagnostic model training;
s2.2, establishing a fault diagnosis model of the nuclear power information system;
carrying out dimensionality reduction on the collected training data at different time periods by using a Principal Component Analysis (PCA) method, constructing a model by adopting an isolated forest algorithm, and combining technical indexes of a nuclear power plant information system to obtain a fault diagnosis model;
and S3, monitoring the data of the nuclear power plant information system in real time, and monitoring the system abnormality by using a fault diagnosis model.
6. The method of claim 5, wherein the monitoring of the data of the nuclear power plant information system in real time and the monitoring of the system anomaly using the fault diagnosis model further comprises:
monitoring data of an information system of the nuclear power plant in real time, and substituting various data of monitored operation into a fault diagnosis model of a corresponding time period for matching;
if the contact time of a certain parameter or parameters exceeds a threshold value, the abnormity of the monitored system is judged.
7. The method for health monitoring and fault location of nuclear power plant information systems according to claim 5 or 6, wherein the step of monitoring the system abnormality by using the fault diagnosis model further comprises the steps of transmitting the abnormal parameters to a system foreground and issuing warning information.
8. The method for health monitoring and fault location of a nuclear power plant information system according to claim 5, wherein the information and parameters required to be monitored by the nuclear power plant information system specifically include:
determining information of an information system server to be monitored, wherein the information comprises a server name, a server IP (Internet protocol), and the like, and selecting a parameter item to be monitored;
determining information of an information system database to be monitored, wherein the information comprises a database host name, a port number, a user name and a password, and selecting corresponding detection parameter items;
determining the web server information to be monitored on the server, and selecting the corresponding monitored parameter item.
9. The method for health monitoring and fault location of a nuclear power plant information system according to claim 5, wherein the data trained by the diagnostic model specifically includes;
selecting nuclear power plant information data of different time periods as diagnosis model training data of different time periods according to the use condition of a monitored system; the data rotation comprises CPU, memory, disk, network, process, database user connection, user process, database session, database execution SQL, database log file, web container, project information, thread pool, JVM parameter data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010512141.7A CN111816338A (en) | 2020-06-08 | 2020-06-08 | Health monitoring and fault positioning system and method for nuclear power plant information system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010512141.7A CN111816338A (en) | 2020-06-08 | 2020-06-08 | Health monitoring and fault positioning system and method for nuclear power plant information system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111816338A true CN111816338A (en) | 2020-10-23 |
Family
ID=72845974
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010512141.7A Pending CN111816338A (en) | 2020-06-08 | 2020-06-08 | Health monitoring and fault positioning system and method for nuclear power plant information system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111816338A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004240642A (en) * | 2003-02-05 | 2004-08-26 | Hitachi Ltd | Maintenance support device for plant equipment |
CN105512812A (en) * | 2015-12-02 | 2016-04-20 | 中广核工程有限公司 | Nuclear power plant equipment fault early warning analysis method and system based on dynamic simulation model |
CN105551549A (en) * | 2015-12-07 | 2016-05-04 | 中广核工程有限公司 | Method and system for on-line monitoring of running state of nuclear power equipment |
CN106597965A (en) * | 2016-12-07 | 2017-04-26 | 中国船舶重工集团公司第七〇九研究所 | Nuclear power apparatus running state monitoring system and monitoring method |
CN107301884A (en) * | 2017-07-24 | 2017-10-27 | 哈尔滨工程大学 | A kind of hybrid nuclear power station method for diagnosing faults |
CN110738274A (en) * | 2019-10-26 | 2020-01-31 | 哈尔滨工程大学 | nuclear power device fault diagnosis method based on data driving |
-
2020
- 2020-06-08 CN CN202010512141.7A patent/CN111816338A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004240642A (en) * | 2003-02-05 | 2004-08-26 | Hitachi Ltd | Maintenance support device for plant equipment |
CN105512812A (en) * | 2015-12-02 | 2016-04-20 | 中广核工程有限公司 | Nuclear power plant equipment fault early warning analysis method and system based on dynamic simulation model |
CN105551549A (en) * | 2015-12-07 | 2016-05-04 | 中广核工程有限公司 | Method and system for on-line monitoring of running state of nuclear power equipment |
CN106597965A (en) * | 2016-12-07 | 2017-04-26 | 中国船舶重工集团公司第七〇九研究所 | Nuclear power apparatus running state monitoring system and monitoring method |
CN107301884A (en) * | 2017-07-24 | 2017-10-27 | 哈尔滨工程大学 | A kind of hybrid nuclear power station method for diagnosing faults |
CN110738274A (en) * | 2019-10-26 | 2020-01-31 | 哈尔滨工程大学 | nuclear power device fault diagnosis method based on data driving |
Non-Patent Citations (1)
Title |
---|
彭彬森 等: "核动力装置运行数据的特征提取方法研究", 《原子能科学技术》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102449567B (en) | Cloud computing as a basis for equipment health monitoring service | |
CN106371986A (en) | Log treatment operation and maintenance monitoring system | |
CN108199922B (en) | System and method for diagnosing and repairing network equipment and server faults | |
CN107995049A (en) | The transregional synchronous fault monitoring method of the power ampere whole district, device and system | |
CN103069749B (en) | The method and system of the isolation of the problem in virtual environment | |
CN110750377A (en) | Fault positioning method and device | |
CN113516244B (en) | Intelligent operation and maintenance method and device, electronic equipment and storage medium | |
CN109240851A (en) | A kind of autonomous type realization self-healing method and system of batch BMC | |
CN116125958A (en) | Intelligent factory fault diagnosis and decision-making system based on digital twinning | |
CN113949652B (en) | User abnormal behavior detection method and device based on artificial intelligence and related equipment | |
CN115114856A (en) | Intelligent manufacturing production line operation system based on digital twin | |
CN106649034B (en) | Visual intelligent operation and maintenance method and platform | |
KR20190081691A (en) | System and Method for Abnormality Monitoring by Using Machine Learning Algorithm | |
WO2024027487A1 (en) | Health degree evaluation method and apparatus based on intelligent operations and maintenance scene | |
CN112988843A (en) | SMT chip mounter fault management and diagnosis system based on SQL Server database | |
CN117220917A (en) | Network real-time monitoring method based on cloud computing | |
CN115222181B (en) | Robot operation state monitoring system and method | |
CN111816338A (en) | Health monitoring and fault positioning system and method for nuclear power plant information system | |
CN116468423A (en) | Operation and maintenance emergency coordination method, system and terminal equipment | |
CN116205624A (en) | Equipment operation management method based on digital twin and related products | |
CN112069031B (en) | Abnormality query method, device, equipment and computer readable storage medium | |
CN113868094A (en) | Big data abnormal information monitoring system | |
CN112711508A (en) | Intelligent operation and maintenance service system facing large-scale client system | |
CN111209131B (en) | Method and system for determining faults of heterogeneous system based on machine learning | |
CN117391675B (en) | Data center infrastructure operation and maintenance management method |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201023 |
|
RJ01 | Rejection of invention patent application after publication |