CN115392782A - Method and system for monitoring and diagnosing health state of process system of nuclear power plant - Google Patents
Method and system for monitoring and diagnosing health state of process system of nuclear power plant Download PDFInfo
- Publication number
- CN115392782A CN115392782A CN202211156882.1A CN202211156882A CN115392782A CN 115392782 A CN115392782 A CN 115392782A CN 202211156882 A CN202211156882 A CN 202211156882A CN 115392782 A CN115392782 A CN 115392782A
- Authority
- CN
- China
- Prior art keywords
- data
- health
- operation data
- power plant
- nuclear power
- 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.)
- Withdrawn
Links
- 230000036541 health Effects 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 66
- 230000008569 process Effects 0.000 title claims abstract description 32
- 238000012544 monitoring process Methods 0.000 title claims abstract description 23
- 230000002159 abnormal effect Effects 0.000 claims abstract description 36
- 238000001514 detection method Methods 0.000 claims abstract description 28
- 238000011156 evaluation Methods 0.000 claims abstract description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 37
- 238000013528 artificial neural network Methods 0.000 claims description 13
- 238000013527 convolutional neural network Methods 0.000 claims description 11
- 238000003066 decision tree Methods 0.000 claims description 9
- 230000003862 health status Effects 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 8
- 238000012706 support-vector machine Methods 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 description 14
- 238000012795 verification Methods 0.000 description 5
- 238000007635 classification algorithm Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000000007 visual effect 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
-
- 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
Abstract
The invention discloses a method and a system for monitoring and diagnosing the health state of a process system of a nuclear power plant, belonging to the technical field of health state monitoring of the nuclear power plant and comprising the following steps: acquiring operation data of a nuclear power plant; identifying the operation data by adopting a power step identification model, and determining the working condition of the operation data; according to the working conditions, carrying out anomaly detection on the operation data through an anomaly detection identification model to obtain anomaly data in the operation data; fault recognition is carried out on the abnormal data, and a fault recognition result is obtained; and evaluating the health state of the system according to the operation data to obtain the health state evaluation result of the system. The system fault can be accurately detected, and the health state of the system can be evaluated.
Description
Technical Field
The invention relates to the technical field of health state monitoring, in particular to a method and a system for monitoring and diagnosing the health state of a process system of a nuclear power plant.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
In the operation process of the nuclear power plant process system, an effective method is needed to monitor and diagnose the system operation state and the state of key items, so that the supervision of the system is realized, real, clear and complete system state information is provided, the premise that the actual operation conditions of the system and equipment are mastered and correct decisions are made is provided, and the guarantee that the whole nuclear power plant can safely and stably operate is also provided.
The traditional method for monitoring and diagnosing the running state of the nuclear power plant process system is a threshold value monitoring method, although the method can provide the state that the monitored parameters deviate from normal running for an operator, the reason and the development trend of abnormal running parameters are difficult to provide, and the operator is difficult to pre-judge and timely diagnose system faults and equipment performance.
The fault classification is an important link in the system detection process, and it is crucial to adopt an appropriate classification algorithm. The traditional classification algorithm comprises a naive Bayes algorithm, a decision tree algorithm, a support vector machine algorithm, a K nearest neighbor algorithm and the like. In the actual operation process of the nuclear power plant, the nuclear power plant is in a normal operation state for a long time, the difference between abnormal fault data of the system is very small, and the normal classification algorithm cannot well identify the difference, so that the fault detection of the process system is inaccurate.
Disclosure of Invention
The invention provides a method and a system for monitoring and diagnosing the health state of a process system of a nuclear power plant in order to solve the problems, wherein when fault identification is carried out through a CNN neural network algorithm, a data whole of a period of time is intercepted and used as a picture as input, the characteristics are richer than a single point, the characteristic difference is easier to identify, and the fault can be accurately identified under the condition of small fault data difference, so that the fault identification accuracy is greatly improved.
In order to realize the purpose, the invention adopts the following technical scheme:
in a first aspect, a method for monitoring and diagnosing a health status of a process system of a nuclear power plant is provided, which includes:
acquiring operation data of a nuclear power plant;
identifying the operation data by adopting a power step identification model, and determining the working condition of the operation data;
according to the working conditions, carrying out anomaly detection on the operation data through an anomaly detection identification model to obtain anomaly data in the operation data;
carrying out fault identification on the abnormal data to obtain a fault identification result;
and evaluating the health state of the system according to the operation data to obtain the health state evaluation result of the system.
In a second aspect, a system for monitoring and diagnosing a health status of a process system of a nuclear power plant is provided, comprising:
the data acquisition module is used for acquiring the operation data of the nuclear power plant;
the power plant operation condition identification module is used for identifying the operation data by adopting a power step identification model and determining the operation condition of the operation data;
the system anomaly detection and identification module is used for carrying out anomaly detection on the operation data through an anomaly detection and identification model according to the working conditions to obtain the anomaly data in the operation data;
the fault identification module is used for carrying out fault identification on the abnormal data to obtain a fault identification result;
and the system health state evaluation module is used for evaluating the health state of the system according to the operation data to obtain the health state evaluation result of the system.
In a third aspect, an electronic device is provided, comprising a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the steps of a method for monitoring and diagnosing a health status of a nuclear power plant process system.
In a fourth aspect, a computer readable storage medium is provided for storing computer instructions that, when executed by a processor, perform the steps of a method for monitoring and diagnosing a health state of a process system of a nuclear power plant.
Compared with the prior art, the invention has the beneficial effects that:
1. the method can accurately identify the faults of the nuclear power plant process system, can evaluate the health state of the system according to the identified fault result, and improves the safety of the nuclear power plant.
2. The method and the device have the advantages that when fault identification is carried out, the abnormal data in a period of time is obtained, the abnormal data in the period of time is formed into a picture to be used as the input of the CNN neural network, fault identification is carried out, the characteristics are richer than those of a single point, the characteristic difference is easier to identify, the fault can be accurately identified under the condition that the fault data difference is small, and the fault identification accuracy is greatly improved.
3. The invention can monitor the running condition of the system in real time, thereby greatly improving the working efficiency of identifying the abnormal state of the system; the health condition of the process system can be calculated in real time, different levels of early warning information are provided, and the safety and reliability of the system are effectively improved; and a visual interface is also provided, so that the health data of each process system can be displayed on line in real time, and the health condition of the system and the safety level of the nuclear power plant can be conveniently and quickly known by different professionals.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, are included to provide a further understanding of the application, and the description of the exemplary embodiments and illustrations of the application are intended to explain the application and are not intended to limit the application.
FIG. 1 is a flow chart of the method disclosed in example 1.
Detailed Description
The invention is further described with reference to the following figures and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example 1
In this embodiment, a method for health status monitoring and diagnosis of a nuclear power plant process system is disclosed, as shown in fig. 1, including:
acquiring operation data of a nuclear power plant;
identifying the operation data by adopting a power step identification model, and determining the working condition of the operation data;
according to the working conditions, carrying out anomaly detection on the operation data through an anomaly detection identification model, identifying whether the operation data is abnormal or not, and obtaining abnormal data in the operation data;
carrying out fault identification on the abnormal data to obtain a fault identification result;
and evaluating the health state of the system according to the operation data to obtain the health state evaluation result of the system.
The steps are introduced as follows:
the method comprises the steps that due to the fact that the obtained nuclear power plant operation data have different dimensions, when the working condition of the operation data is determined, the nuclear power plant operation data are preprocessed, and the preprocessing comprises data normalization, data dimension reduction and the like; secondly, recognizing the preprocessed data by adopting a power step recognition model, and determining the working condition of the operation data.
The power step identification model is obtained by selecting an algorithm model with the optimal operation data identification effect from a decision tree algorithm model, an ensemble learning algorithm model, a support vector machine algorithm model and a neural network model. The specific process is as follows: the method comprises the steps of obtaining existing nuclear power plant operation data samples, carrying out classification marking on the existing nuclear power plant operation data samples according to power plant operation conditions to obtain a training data set, dividing the training data set into a training set and a verification set, respectively training a constructed decision tree algorithm model, an integrated learning algorithm model, a support vector machine algorithm model and a neural network model through the training set, carrying out effect verification on each trained model through the verification set, and selecting a model with the optimal classification effect from the trained decision tree algorithm model, the integrated learning algorithm model, the support vector machine algorithm model and the neural network model as a power step recognition model.
Because the health data is less during actual operation, normal sample data needs to be expanded, 80% of sample data in a training data set is used as training data, 20% of the sample data is used as test data, and a trained model is applied to the working condition prediction of real-time operation data.
When the decision tree algorithm model is trained, the parameters are default values, and the common parameters are as follows:
criterion uses gini (cart algorithm);
the method comprises the following steps that (1) splitter (feature division), best is used by default when the sample size is not large, the optimal points are found in all division points of the features, and random randomly finds local optimal points in partial division points;
max _ depth (maximum depth of decision tree), the default is when None is suitable for a small number of samples or features, if the number of samples is large or the number of features is large, a numerical value is set to limit the depth of the tree, and the overfitting problem is solved between 10 and 100 values;
min _ samples _ split (the minimum number of samples required by the internal nodes in the division), the default value is 2, if int, the incoming value is used as the minimum number of samples, and if float, the float number of samples is used as the minimum number of samples;
min _ samples _ leaf (minimum number of samples of leaf node), if int, taking the incoming value as the minimum number of samples, if float, taking float as the minimum number of samples, this value limits the minimum number of samples of leaf node, if the number of certain leaf node is less than the number of samples, then it will be pruned together with brother node;
max _ features (the maximum number of features considered when partitioning a data set), int represents the maximum number of features at each partition, and float represents a percentage.
And according to the working conditions, performing anomaly detection on the operation data through an anomaly detection identification model, identifying whether the operation data is abnormal or not, and acquiring abnormal data in the operation data.
The abnormal detection and identification model is obtained by selecting an algorithm with the optimal abnormal data detection effect from a decision tree, ensemble learning, a support vector machine and a neural network algorithm and constructing the algorithm.
Adopting a CNN neural network algorithm to carry out fault identification on abnormal data to obtain a fault identification result, specifically: acquiring abnormal data of continuous set time periods, and generating a gray scale map from all the abnormal data; and identifying the gray level image by adopting a CNN neural network algorithm to obtain a fault identification result.
Because the single point has limited characteristics, when the data of the single point is adopted for fault identification, the accuracy of the fault identification cannot be ensured, so that the abnormal data of continuous set time periods are collected when the fault identification is carried out; and normalizing the abnormal data of the time period, drawing the data of all dimensions on a graph to generate a gray graph, identifying faults of the gray graph, and determining the fault types.
The CNN neural network algorithm model is structured as follows: the system is composed of 3 convolution layers with convolution kernel size of 3, 3 batch normalization layers, 3 activation layers, 2 pooling layers with rectangular region size of 2, 1 full connection layer, 1 softmax layer for normalizing output of the full connection layer and 1 classification layer.
Wherein, the parameters involved are:
plots: a default value (none) indicates that no progress is shown during training and 'training-progress' shows training progress;
verbose: true indicates that the training progress information is displayed in the command window, while false does not;
validationrequest: 50 (default) or other value, representing the number of iterations between the verification metric values;
ValidationData: data for verifying network performance, i.e., a verification set;
MaxEpochr: a maximum number of iterations for training;
solverName: a solver is specified.
When the CNN neural network algorithm model is trained, 80% of data of the data samples are used as training samples for training the model, and 20% of data are used as test samples for testing the model. And training the CNN neural network algorithm model through abnormal data in the data sample, and using the trained CNN neural network algorithm model for fault diagnosis of the abnormal data.
And (3) evaluating the health state of the system according to the operation data, specifically:
clustering the obtained operation data according to the working conditions to obtain operation data of each type;
calculating the distance between each type of operation data and the health baseline;
the health status of the system is determined from the distance.
The acquisition process of the healthy baseline is as follows:
acquiring health data of an existing nuclear power plant under multiple operating conditions;
clustering the health data according to working conditions to obtain multiple types of health data;
and determining the central point of each type of health data, and connecting the central points of all the health data to form a health baseline.
The method comprises the following specific steps:
the method comprises the steps of obtaining health data of the existing nuclear power plant under all operating conditions, integrating the health data under each operating condition on one table, if the data volume is small, expanding samples, using a PCA algorithm to normalize and reduce the dimension of the health data, using a Kmeans clustering algorithm to cluster the health data according to the operating conditions to obtain multiple types of health index sequences, clustering the data of the n operating conditions into n clusters to obtain n types of health index sequences, wherein each type of health index sequence belongs to the same operating condition. And calculating the central points and the radii of the n clusters as baseline models, and connecting all the central points to form a healthy baseline.
Calculating the distance between each type of operation data and the central point of the health data under the same working condition, and determining a health index according to the distance;
and identifying the health index to determine the health state of the system.
The health index interval is 0-1, 0 represents that the distance from the health baseline is very close, 1 represents that the distance from the health baseline is very far, and the farther the distance from the center is, the more serious the system fault degree is.
According to the method for monitoring and diagnosing the health state of the nuclear power plant process system, faults of the nuclear power plant process system can be accurately identified, the health state of the system can be evaluated according to operation data, and the safety of a nuclear power plant is improved; when fault identification is carried out, abnormal data of a period of time is obtained, the abnormal data of the period of time is formed into a picture to be used as input of a CNN neural network, the features are richer than single points, the feature difference is easier to identify, the fault can be accurately identified under the condition of small difference of the fault data, the accuracy rate of fault identification is greatly improved, in addition, when the abnormal data of working condition identification and operation data are detected, the optimal model selection is carried out on a power step identification model and an abnormal detection identification model, and the selected model is optimal in the working condition identification effect and the abnormal data detection effect.
The method disclosed by the embodiment can monitor the running condition of the system in real time, and greatly improves the working efficiency of identifying the abnormal state of the system; the health condition of the process system can be calculated in real time, different levels of early warning information are provided, and the safety and reliability of the system are effectively improved.
Example 2
In this embodiment, a system for monitoring and diagnosing a health status of a nuclear power plant process system is disclosed, comprising:
the data acquisition module is used for acquiring the operating data of the nuclear power plant;
the power plant operation condition identification module is used for identifying the operation data by adopting a power step identification model and determining the operation condition of the operation data;
the system anomaly detection and identification module is used for carrying out anomaly detection on the operation data through an anomaly detection and identification model according to the working conditions to obtain the anomaly data in the operation data;
the fault identification module is used for carrying out fault identification on the abnormal data to obtain a fault identification result;
and the system health state evaluation module is used for evaluating the health state of the system according to the operation data to obtain the health state evaluation result of the system.
Further comprising: and the display module is used for displaying the operation data, the working condition of the operation data, the detection result of the operation data and the health state evaluation result of the system.
Example 3
In this embodiment, an electronic device is disclosed, comprising a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the steps of the method for monitoring and diagnosing the health status of a nuclear power plant process system disclosed in embodiment 1.
Example 4
In this embodiment, a computer readable storage medium is disclosed for storing computer instructions that, when executed by a processor, perform the steps of a method for monitoring and diagnosing a health state of a nuclear power plant process system as disclosed in embodiment 1.
Finally, it should be noted that: although the present invention has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (10)
1. A method for monitoring and diagnosing the state of health of a nuclear power plant process system is characterized by comprising the following steps:
acquiring operation data of a nuclear power plant;
identifying the operation data by adopting a power step identification model, and determining the working condition of the operation data;
according to the working conditions, carrying out anomaly detection on the operation data through an anomaly detection identification model to obtain the anomaly data in the operation data;
carrying out fault identification on the abnormal data to obtain a fault identification result;
and evaluating the health state of the system according to the operation data to obtain a health state evaluation result of the system.
2. The method for monitoring and diagnosing the health of a nuclear power plant process system of claim 1, wherein the power step identification model is constructed by selecting an algorithm model having an optimal identification effect on the operational data from a decision tree algorithm model, an ensemble learning algorithm model, a support vector machine algorithm model and a neural network model;
the abnormal detection and identification model is obtained by selecting an algorithm with the optimal abnormal data detection effect from a decision tree, ensemble learning, a support vector machine and a neural network algorithm and constructing the algorithm.
3. The method of claim 1, wherein a CNN neural network algorithm is used to perform fault recognition on the abnormal data to obtain a fault recognition result.
4. The method of claim 3, wherein the fault identification result is obtained by:
acquiring abnormal data of continuous set time periods, and generating a gray scale map from all the abnormal data; and identifying the gray level image by adopting a CNN neural network algorithm to obtain a fault identification result.
5. The method of claim 1, wherein the health of the system is assessed based on operational data, specifically:
clustering the acquired operation data according to the working conditions to acquire operation data of each type;
calculating the distance between each type of operation data and the health baseline;
the health status of the system is determined from the distance.
6. The method of claim 5, wherein the health data is obtained for a plurality of operating conditions of an existing nuclear power plant;
clustering the health data according to working conditions to obtain multiple types of health data;
and determining the central point of each type of health data, and connecting the central points of all the health data to form a health baseline.
7. The method of claim 6, wherein the distance between each type of operating data and the center point of the same operating condition health data is calculated, a health indicator is determined based on the distance, the health indicator is identified, and the health status of the system is determined.
8. A nuclear power plant process system health monitoring and diagnostic system, comprising:
the data acquisition module is used for acquiring the operation data of the nuclear power plant;
the power plant operation condition identification module is used for identifying the operation data by adopting a power step identification model and determining the operation condition of the operation data;
the system anomaly detection and identification module is used for carrying out anomaly detection on the operation data through an anomaly detection and identification model according to the working conditions to obtain the anomaly data in the operation data;
the fault identification module is used for carrying out fault identification on the abnormal data to obtain a fault identification result;
and the system health state evaluation module is used for evaluating the health state of the system according to the operation data to obtain the health state evaluation result of the system.
9. An electronic device comprising a memory and a processor and computer instructions stored on the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the steps of a method for monitoring and diagnosing the health of a nuclear power plant process system as recited in any one of claims 1 to 7.
10. A computer readable storage medium storing computer instructions which, when executed by a processor, perform the steps of a method for monitoring and diagnosing health of a nuclear power plant process system as recited in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211156882.1A CN115392782A (en) | 2022-09-22 | 2022-09-22 | Method and system for monitoring and diagnosing health state of process system of nuclear power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211156882.1A CN115392782A (en) | 2022-09-22 | 2022-09-22 | Method and system for monitoring and diagnosing health state of process system of nuclear power plant |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115392782A true CN115392782A (en) | 2022-11-25 |
Family
ID=84126308
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211156882.1A Withdrawn CN115392782A (en) | 2022-09-22 | 2022-09-22 | Method and system for monitoring and diagnosing health state of process system of nuclear power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115392782A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116204779A (en) * | 2023-04-19 | 2023-06-02 | 中能建数字科技集团有限公司 | Method, system and readable storage medium for judging operation state of energy storage salt cavern |
| CN117554737A (en) * | 2024-01-11 | 2024-02-13 | 深圳市美顺和电子有限公司 | Health condition detection method and system of vehicle-mounted charger |
-
2022
- 2022-09-22 CN CN202211156882.1A patent/CN115392782A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116204779A (en) * | 2023-04-19 | 2023-06-02 | 中能建数字科技集团有限公司 | Method, system and readable storage medium for judging operation state of energy storage salt cavern |
| CN116204779B (en) * | 2023-04-19 | 2023-09-05 | 中能建数字科技集团有限公司 | Method, system and readable storage medium for judging operation state of energy storage salt cavern |
| CN117554737A (en) * | 2024-01-11 | 2024-02-13 | 深圳市美顺和电子有限公司 | Health condition detection method and system of vehicle-mounted charger |
| CN117554737B (en) * | 2024-01-11 | 2024-03-26 | 深圳市美顺和电子有限公司 | Health condition detection method and system of vehicle-mounted charger |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220283576A1 (en) | Automatic diagnosis method, system and storage medium for equipment | |
| CN115392782A (en) | Method and system for monitoring and diagnosing health state of process system of nuclear power plant | |
| CN113255848B (en) | Water turbine cavitation sound signal identification method based on big data learning | |
| CN110738274A (en) | nuclear power device fault diagnosis method based on data driving | |
| US11669080B2 (en) | Abnormality detection device, abnormality detection method, and program | |
| CN112528519A (en) | Method, system, readable medium and electronic device for engine quality early warning service | |
| CN116450399B (en) | Fault diagnosis and root cause positioning method for micro service system | |
| CN109298633A (en) | Chemical production process fault monitoring method based on adaptive piecemeal Non-negative Matrix Factorization | |
| CN115187832A (en) | Energy system fault diagnosis method based on deep learning and gram angular field image | |
| CN113760670A (en) | Cable joint abnormity early warning method and device, electronic equipment and storage medium | |
| JP2019028834A (en) | Abnormal value diagnostic device, abnormal value diagnostic method, and program | |
| CN114118219A (en) | Data-driven real-time abnormal detection method for health state of long-term power-on equipment | |
| CN116702076A (en) | Small sample migration learning fault diagnosis method, system, computer and storage medium based on CNN feature fusion | |
| CN117034143B (en) | Distributed system fault diagnosis method and device based on machine learning | |
| CN113918433A (en) | Adaptive intelligent network equipment performance index abnormity detection device and method | |
| JP2020071624A (en) | Abnormality diagnosing apparatus, abnormality diagnosing method and program | |
| CN115729761B (en) | Hard disk fault prediction method, system, equipment and medium | |
| CN116821804A (en) | Fracturing pump check valve fault on-line monitoring method based on multi-feature fusion | |
| CN111079348B (en) | Method and device for detecting slowly-varying signal | |
| CN115099828A (en) | Oil failure diagnosis tracing method and system based on multi-index monitoring | |
| CN114528942A (en) | Construction method of data sample library of engineering machinery, failure prediction method and engineering machinery | |
| KR20230075150A (en) | Method for managing system health | |
| CN114137915A (en) | Fault diagnosis method for industrial equipment | |
| CN111160454B (en) | Quick change signal detection method and device | |
| CN116738352B (en) | Method and device for classifying abnormal rod cells of retinal vascular occlusion disease |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: No. 29 Hong Cao Road, Xuhui District, Shanghai Applicant after: Shanghai Nuclear Engineering Research and Design Institute Co.,Ltd. Address before: No. 29 Hong Cao Road, Xuhui District, Shanghai Applicant before: SHANGHAI NUCLEAR ENGINEERING RESEARCH & DESIGN INSTITUTE Co.,Ltd. |
|
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20221125 |