CN117874612A - Power system equipment model anomaly detection method based on artificial intelligence - Google Patents
Power system equipment model anomaly detection method based on artificial intelligence Download PDFInfo
- Publication number
- CN117874612A CN117874612A CN202410011534.8A CN202410011534A CN117874612A CN 117874612 A CN117874612 A CN 117874612A CN 202410011534 A CN202410011534 A CN 202410011534A CN 117874612 A CN117874612 A CN 117874612A
- Authority
- CN
- China
- Prior art keywords
- model
- fault
- data
- power system
- neural network
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 47
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 61
- 238000003745 diagnosis Methods 0.000 claims abstract description 43
- 238000013528 artificial neural network Methods 0.000 claims abstract description 28
- 230000005856 abnormality Effects 0.000 claims abstract description 27
- 238000003062 neural network model Methods 0.000 claims abstract description 22
- 238000013145 classification model Methods 0.000 claims abstract description 14
- 230000002159 abnormal effect Effects 0.000 claims description 32
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 8
- 238000012423 maintenance Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 210000002569 neuron Anatomy 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 210000005036 nerve Anatomy 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 6
- 238000004422 calculation algorithm Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000004590 computer program Methods 0.000 description 8
- 239000002131 composite material Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000003860 storage Methods 0.000 description 4
- 230000002708 enhancing effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06N3/088—Non-supervised learning, e.g. competitive learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides an artificial intelligence-based power system equipment model anomaly detection method, which is characterized in that a traditional power special model is enhanced by combining unsupervised learning with a neural network model, and a fault classification model is constructed by a narrow-sense neural network, so that accurate fault classification diagnosis of power equipment can be realized. Finally, the fault detection method based on artificial intelligence can realize on-line fault diagnosis and timely early warning and process the fault problem of the power system equipment. The invention uses the artificial intelligence algorithm and technology of the front edge, and has the advantages of high identification accuracy and strong fault diagnosis capability. The method can be applied to the fields of abnormality detection, online fault diagnosis and the like of the power system, and improves the safety stability and reliability of the power system.
Description
Technical Field
The invention relates to the technical field of intelligent detection of power systems, in particular to an artificial intelligence-based power system equipment model anomaly detection method.
Background
The power system is an important infrastructure for guaranteeing power supply in the modern society, and the normal operation of the equipment model is critical to the stability and reliability of the power system. However, due to the complexity and variability of the power equipment, equipment models may be abnormal during operation, resulting in power system failures and blackouts. The traditional power equipment model abnormality detection method mainly relies on a manual or regularized mode, and whether the equipment model is abnormal or not is judged manually. The method has the following problems: firstly, the manual judgment is easily influenced by subjective factors, and the complex abnormal situation can not be accurately judged; secondly, the regularized method is difficult to cover all possible abnormal situations, and can not be found in time for the novel fault mode.
Disclosure of Invention
Aiming at the problems that the traditional power equipment model abnormality detection method is easily influenced by subjective factors and the complicated abnormality situation can not be accurately judged, the invention provides the power system equipment model abnormality detection method based on artificial intelligence. The traditional power special model is enhanced by combining the unsupervised learning and the neural network model, and the fault classification model is constructed by the narrow-definition neural network, so that the accurate fault classification diagnosis of the power equipment can be realized. Finally, the fault detection method based on artificial intelligence can realize on-line fault diagnosis and timely early warning and process the fault problem of the power system equipment. The invention uses the artificial intelligence algorithm and technology of the front edge, and has the advantages of high identification accuracy and strong fault diagnosis capability. The method can be applied to the fields of abnormality detection, online fault diagnosis and the like of the power system, and improves the safety stability and reliability of the power system.
The present invention first proposes a neural network model for enhancing and utilizing parameters collected from anomaly data recognition. The neural network model estimates sample data based on decision scores and is able to distinguish anomalies in the composite dataset. And constructing a fault classification model, and classifying fault states based on the supervised learning model by using a narrow neural network. Through training the known fault samples, the model can accurately classify different types of fault states, and powerful support is provided for fault diagnosis. Finally, a fault detection method based on artificial intelligence is provided, namely fault detection is carried out by utilizing an abnormal detection result of the power equipment model. By combining the results of the unsupervised learning and the supervised learning, the method can accurately detect the abnormality of the power system equipment, discover potential fault problems in time and provide references for on-line fault diagnosis. By introducing an unsupervised learning and neural network model, the traditional power special model can be enhanced, and the detection of an abnormal model can be realized. Meanwhile, a fault classification model is constructed by utilizing the narrow neural network, so that support is provided for accurate and efficient fault diagnosis.
The invention adopts the following technical scheme:
the method for detecting the abnormality of the power system equipment model based on the artificial intelligence is characterized by comprising the following steps of:
step S1: acquiring historical data and real-time data of an electric power system equipment model, and taking the historical data and the real-time data as input data for constructing the electric power system equipment model; and cleaning and preprocessing the data to improve the quality and accuracy of the data;
step S2: training and feature learning are carried out on the power system equipment model data by using an unsupervised learning method, relevant features in the data are extracted, and a basic feature space of the model is established; grouping the data based on an unsupervised learning method, thereby finding abnormal samples in the data;
step S3: constructing a neural network model based on decision scores, and accurately identifying abnormal samples in the power equipment model; the neural network model outputs decision scores by inputting sample data and training by using a training set, and the abnormality degree of the sample data is estimated;
step S4: adopting a supervised learning method to construct a fault classification model based on a narrow neural network; training by using known power equipment fault samples, so that the model can accurately classify the power equipment fault samples into different fault types, thereby providing support for online fault diagnosis;
step S5: combining unsupervised learning and neural network classification results to realize fault detection based on artificial intelligence; inputting sample data in the power equipment model into a neural network model, judging whether the sample data is abnormal or not through decision scores and results of a fault classification model, and performing fault classification diagnosis;
step S6: and triggering a corresponding alarm mechanism according to the results of abnormality detection and fault diagnosis.
The mechanism can send the alarm information to maintenance personnel, and the maintenance personnel can timely process the fault problem of the power equipment according to the alarm information, so that the safe and stable operation of the power system is ensured.
Further, in step S1, the normalization processing is performed on the model data of the power system equipment, so as to ensure that different types of data have the same dimension, and improve the training and prediction effects of the model.
Further, in step S2, the unsupervised learning method includes evaluating model training and selecting an optimal model to ensure that the selected model is capable of high accuracy and robustness in anomaly detection and fault diagnosis tasks.
Further, in step S3, the constructed neural network model includes an input layer, a hidden layer, and an output layer; the hidden layer includes a plurality of neurons and uses an activation function to non-linearly transform the output of each neuron.
Further, in step S5, the sample data is classified into a normal state, a potential fault state and a known fault state according to the abnormal score and the classification result of the power equipment model data, thereby providing maintenance personnel with more specific and accurate fault information.
Further, the constructed neural network framework is shown as follows:
wherein β represents a weighted model from an initial layer to a next layer of the neural network, α represents a matrix deviation, γ represents an output matrix of the optimization method, M represents the number of source data samples, and X m Representing a sequence of source data samples;
by changing the objective function of the specific nerve model, the beta enhancement of the gamma sum is realized based on an optimization method while the alpha of the gamma sum is enhanced independently:
similarly, enhancement of α is achieved by:
further, the goals of the neural network are as follows:
wherein the method comprises the steps ofIs the node in layer i for activation, +.>A j-th layer weighting matrix from i-th layer to i+1-th layer, y i Is a bias matrix for use in each stage; the initial sample is identified as a at the initial stage j And the score for output and hidden layer i-1 is identified as a j The method comprises the steps of carrying out a first treatment on the surface of the The weighting matrix h and the bias matrix y are enhanced with a neural network system based on an sigmoid start-up function.
The traditional power special model is enhanced by combining the unsupervised learning and the neural network model, and the fault classification model is constructed by the narrow-sense neural network, so that the accurate fault classification diagnosis of the power equipment can be realized; finally, the fault detection method based on artificial intelligence can realize on-line fault diagnosis, and timely early warning and processing the fault problem of the power system equipment; the invention applies the artificial intelligence algorithm and technology of the front edge, and has the advantages of high identification accuracy and strong fault diagnosis capability; the method can be applied to the fields of abnormality detection, online fault diagnosis and the like of the power system, and improves the safety stability and reliability of the power system.
In the scheme provided by the invention, a neural network model based on decision scores is provided for enhancing and utilizing parameters collected from abnormal data identification. The neural network model distinguishes abnormal samples in the composite data set by estimating decision scores of the sample data, so that abnormal data can be effectively identified, and the accuracy of abnormal detection is improved.
Further, a fault classification model is constructed, and fault states are classified by using a narrow neural network based on a supervised learning model. The model can accurately classify different types of fault states by training known fault samples, and provides support for online fault diagnosis.
Further, an artificial intelligence-based fault detection method is provided, namely fault detection is performed by using an abnormal detection result of the power equipment model. By combining the results of the unsupervised learning and the supervised learning, the method can accurately detect the abnormality of the power system equipment, discover potential fault problems in time and provide references for on-line fault diagnosis.
Compared with the prior art, the invention and the preferable scheme thereof have the following beneficial effects:
1. by introducing an unsupervised learning and neural network combined mode, the equipment model in the power system can be accurately detected in an abnormality mode. By utilizing the decision score of the neural network model, the abnormal samples in the composite data set are effectively distinguished, and the accuracy of abnormal detection is improved.
2. By constructing a fault classification model based on supervised learning, the fault states of the power equipment can be accurately classified. The model can be trained according to known fault samples, realizes classification diagnosis of different types of faults, and provides support for online fault diagnosis.
3. By combining the results of unsupervised learning and supervised learning, the fault detection method based on artificial intelligence is realized. The method can timely find out the abnormal condition of the power system equipment and provide reference for on-line fault diagnosis. The potential fault problems can be early warned and handled by timely fault detection and diagnosis, and the safety and stability of the power system are improved.
4. And the historical data and the real-time data of the power system equipment model are utilized to carry out abnormality detection and fault diagnosis, so that the functions of automation and real-time monitoring are realized. The state change of the power equipment can be monitored in time, potential fault problems can be found in advance, and faults and power failure accidents of the power system are avoided.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objects and other advantages of the invention may be realized and obtained by means of the instrumentalities and combinations particularly pointed out in the specification.
Drawings
The invention is described in further detail below with reference to the attached drawings and detailed description:
FIG. 1 is a flowchart of an artificial intelligence-based power system equipment model anomaly detection method in an embodiment of the invention.
Fig. 2 is a fault detection framework based on abnormal data monitoring of power system equipment according to an embodiment of the present invention.
Detailed Description
Hereinafter, specific embodiments of the present application will be described in detail with reference to the accompanying drawings, and according to these detailed descriptions, those skilled in the art can clearly understand the present application and can practice the present application. Features from various embodiments may be combined to obtain new implementations or to replace certain features from certain embodiments to obtain other preferred implementations without departing from the principles of the present application.
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 in accordance with the present application. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
In order to make the features and advantages of the present patent more comprehensible, embodiments accompanied with figures are described in detail below:
it is to be noted that unless otherwise defined, technical or scientific terms used herein should be taken in a general sense as understood by one of ordinary skill in the art to which the present invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
As shown in fig. 1 and 2, the invention provides an artificial intelligence-based power system equipment model anomaly detection method. The traditional power special model is enhanced by combining the unsupervised learning and the neural network model, and the fault classification model is constructed by the narrow-definition neural network, so that the accurate fault classification diagnosis of the power equipment can be realized. Finally, the fault detection method based on artificial intelligence can realize on-line fault diagnosis and timely early warning and process the fault problem of the power system equipment. The invention uses the artificial intelligence algorithm and technology of the front edge, and has the advantages of high identification accuracy and strong fault diagnosis capability. The method can be applied to the fields of abnormality detection, online fault diagnosis and the like of the power system, and improves the safety stability and reliability of the power system.
In the present embodiment, first, the history data and the real-time data of the power system equipment model are collected. And cleaning and preprocessing the acquired data, namely removing abnormal values, filling the missing values, and carrying out data normalization processing to enable the data of different types to have the same dimension.
Further, an unsupervised learning method is adopted to train and learn the characteristics of the power system equipment model data, and relevant characteristics in the data are extracted. And constructing a neural network model based on the decision score, wherein the model can distinguish abnormal samples in the composite data set by estimating the decision score of the abnormal data. The neural network model may be used to augment and utilize parameters collected from an unsupervised-based model that is subject to anomaly identification, estimate sample data based on decision scores to distinguish anomalies in the composite dataset, where the conclusion limit between anomalies and normals is nonlinear. The neural network framework constructed herein is shown by the following formula:
beta represents a weighted model from an initial layer to a next layer of the neural network, alpha represents a matrix deviation, gamma represents an output matrix of the optimization method, M represents the number of source data samples, and X m Representing a sequence of source data samples.
By changing the objective function of the specific nerve model, the beta enhancement of gamma and alpha can be realized based on an optimization method while the gamma and alpha are enhanced independently:
similarly, enhancement of α can be achieved by:
further, based on the supervised learning model, fault conditions are classified using a narrow neural network. The method belongs to an artificial intelligence method, and trains a computer framework on a result sample featuring a certain type of output. The neural network-based model proposed by the present invention outputs continuous changes on the basis of unrecognized fault detection, so that the enhanced framework learns and evaluates the recognized faults by using the algorithm. The goals of the neural network are as follows
Wherein the method comprises the steps ofIs the node in layer i for activation, +.>A j-th layer weighting matrix from i-th layer to i+1-th layer, y i Is the bias matrix for each stage. The initial sample is identified as (a) at the initial stage j ) And the score for output and hidden layer (i-1) is identified as a j . The weighting matrix h and the bias matrix y are enhanced with a neural network system based on an sigmoid start-up function. The fault classification model is constructed by the method, and the fault state is classified by using the narrow neural network based on the supervised learning model. The model can accurately classify different types of fault states by training known fault samples, and provides support for online fault diagnosis.
Further, an artificial intelligence-based fault detection method is provided, namely fault detection is performed by using an abnormal detection result of the power equipment model. By combining the results of the unsupervised learning and the supervised learning, the method can accurately detect the abnormality of the power system equipment, discover potential fault problems in time and provide references for on-line fault diagnosis.
Further, by combining the results of unsupervised learning and supervised learning, an artificial intelligence-based fault detection method is realized, so that accurate fault classification diagnosis of the power equipment is realized. The method can timely find out the abnormal condition of the power system equipment and provide reference for on-line fault diagnosis. And triggering a corresponding alarm mechanism according to the results of abnormality detection and fault diagnosis, and sending alarm information to maintenance personnel.
The application principle of the invention is as follows: historical data and real-time data, including current, voltage, power, etc., are collected and prepared from the power equipment as input data for constructing a power equipment model. And the data is subjected to cleaning, normalization and sampling treatment by using a data preprocessing method, so that the data quality is improved. And (3) adopting an unsupervised learning method, and constructing a power equipment model by training power equipment model data and extracting relevant characteristics thereof. The unsupervised learning method can automatically learn features from data and establish related feature models. A neural network model based on the decision scores is constructed for enhancing and utilizing the parameters collected from the anomaly data identification. The neural network model can distinguish abnormal samples in the composite data set by estimating the decision score of the sample data, and improves the accuracy of abnormal detection. The fault classification model is constructed based on the narrow neural network, so that different types of fault states can be accurately classified. The model can accurately classify different types of fault states by training by using known fault samples, and provides support for online fault diagnosis. By combining the results of unsupervised learning and supervised learning, the fault detection method based on artificial intelligence is realized, so that the accurate fault classification diagnosis of the power equipment is realized. The method can timely find out the abnormal condition of the power system equipment and provide reference for on-line fault diagnosis. And triggering a corresponding alarm mechanism according to the results of abnormality detection and fault diagnosis, and sending alarm information to maintenance personnel. And maintenance personnel timely process the fault problem of the power equipment according to the alarm information, and ensure the safe and stable operation of the power system.
The embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to the described embodiments. It will be apparent to those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, and yet fall within the scope of the invention.
The above system and method provided in this embodiment may be stored in a computer readable storage medium in a coded form, implemented in a computer program, and input basic parameter information required for calculation through computer hardware, and output a calculation result.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
The patent is not limited to the best mode, any person can obtain other various types of abnormal detection methods of the power system equipment model based on artificial intelligence under the teaching of the patent, and all equivalent changes and modifications made according to the scope of the patent application are covered by the patent.
Claims (7)
1. The method for detecting the abnormality of the power system equipment model based on the artificial intelligence is characterized by comprising the following steps of:
step S1: acquiring historical data and real-time data of an electric power system equipment model, and taking the historical data and the real-time data as input data for constructing the electric power system equipment model; and cleaning and preprocessing the data to improve the quality and accuracy of the data;
step S2: training and feature learning are carried out on the power system equipment model data by using an unsupervised learning method, relevant features in the data are extracted, and a basic feature space of the model is established; grouping the data based on an unsupervised learning method, thereby finding abnormal samples in the data;
step S3: constructing a neural network model based on decision scores, and accurately identifying abnormal samples in the power equipment model; the neural network model outputs decision scores by inputting sample data and training by using a training set, and the abnormality degree of the sample data is estimated;
step S4: adopting a supervised learning method to construct a fault classification model based on a narrow neural network; training by using known power equipment fault samples, so that the model can accurately classify the power equipment fault samples into different fault types, thereby providing support for online fault diagnosis;
step S5: combining unsupervised learning and neural network classification results to realize fault detection based on artificial intelligence; inputting sample data in the power equipment model into a neural network model, judging whether the sample data is abnormal or not through decision scores and results of a fault classification model, and performing fault classification diagnosis;
step S6: and triggering a corresponding alarm mechanism according to the results of abnormality detection and fault diagnosis.
2. The method for detecting the abnormality of the equipment model of the electric power system based on the artificial intelligence according to claim 1, wherein the method comprises the following steps: in step S1, the normalization processing is performed on the model data of the power system equipment, so as to ensure that different types of data have the same dimension, and improve the training and prediction effects of the model.
3. The method for detecting the abnormality of the equipment model of the electric power system based on the artificial intelligence according to claim 1, wherein the method comprises the following steps: in step S2, the unsupervised learning method includes evaluation of model training and selection of an optimal model to ensure that the selected model is capable of high accuracy and robustness in anomaly detection and fault diagnosis tasks.
4. The method for detecting the abnormality of the equipment model of the electric power system based on the artificial intelligence according to claim 1, wherein the method comprises the following steps: in step S3, the constructed neural network model includes an input layer, a hidden layer, and an output layer; the hidden layer includes a plurality of neurons and uses an activation function to non-linearly transform the output of each neuron.
5. The method for detecting the abnormality of the equipment model of the electric power system based on the artificial intelligence according to claim 1, wherein the method comprises the following steps: in step S5, the sample data is classified into a normal state, a potential fault state and a known fault state according to the abnormal score and classification result of the power equipment model data, thereby providing maintenance personnel with more specific and accurate fault information.
6. The method for detecting the abnormality of the equipment model of the electric power system based on the artificial intelligence according to claim 1, wherein the method comprises the following steps:
the constructed neural network framework is shown as follows:
wherein β represents a weighted model from an initial layer to a next layer of the neural network, α represents a matrix deviation, γ represents an output matrix of the optimization method, M represents the number of source data samples, and X m Representing a sequence of source data samples;
by changing the objective function of the specific nerve model, the beta enhancement of the gamma sum is realized based on an optimization method while the alpha of the gamma sum is enhanced independently:
similarly, enhancement of α is achieved by:
7. the method for detecting the abnormality of the equipment model of the power system based on the artificial intelligence according to claim 6, wherein the method comprises the following steps:
the goals of the neural network are as follows:
wherein the method comprises the steps ofIs the node in layer i for activation, +.>A j-th layer weighting matrix from i-th layer to i+1-th layer, y i Is used in each stageIs included in the bias matrix; the initial sample is identified as a at the initial stage j And the score for output and hidden layer i-1 is identified as a j The method comprises the steps of carrying out a first treatment on the surface of the The weighting matrix h and the bias matrix y are enhanced with a neural network system based on an sigmoid start-up function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410011534.8A CN117874612A (en) | 2024-01-03 | 2024-01-03 | Power system equipment model anomaly detection method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410011534.8A CN117874612A (en) | 2024-01-03 | 2024-01-03 | Power system equipment model anomaly detection method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117874612A true CN117874612A (en) | 2024-04-12 |
Family
ID=90586033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410011534.8A Pending CN117874612A (en) | 2024-01-03 | 2024-01-03 | Power system equipment model anomaly detection method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117874612A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118312734A (en) * | 2024-06-11 | 2024-07-09 | 北京前景无忧电子科技股份有限公司 | Power system equipment state monitoring and fault diagnosis method |
-
2024
- 2024-01-03 CN CN202410011534.8A patent/CN117874612A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118312734A (en) * | 2024-06-11 | 2024-07-09 | 北京前景无忧电子科技股份有限公司 | Power system equipment state monitoring and fault diagnosis method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Remaining useful life prediction based on a double-convolutional neural network architecture | |
| JP6740247B2 (en) | Anomaly detection system, anomaly detection method, anomaly detection program and learned model generation method | |
| CN111914873B (en) | Two-stage cloud server unsupervised anomaly prediction method | |
| Ren et al. | Multi-bearing remaining useful life collaborative prediction: A deep learning approach | |
| CN111902781B (en) | Apparatus and method for controlling a system | |
| CN113642754B (en) | Complex industrial process fault prediction method based on RF noise reduction self-coding information reconstruction and time convolution network | |
| CN104471542B (en) | The hidden Kalman filter of differentiation for the classification of the sensing data flowed in Stateful Inspection | |
| CN117273440B (en) | Engineering construction Internet of things monitoring and managing system and method based on deep learning | |
| CN117542169B (en) | Automatic equipment temperature abnormality early warning method based on big data analysis | |
| CN110705812A (en) | Industrial fault analysis system based on fuzzy neural network | |
| CN117874612A (en) | Power system equipment model anomaly detection method based on artificial intelligence | |
| CN110757510B (en) | Method and system for predicting remaining life of robot | |
| CN111340110B (en) | Fault early warning method based on industrial process running state trend analysis | |
| Mishra et al. | Fault detection of elevator systems using multilayer perceptron neural network | |
| US20230221684A1 (en) | Explaining Machine Learning Output in Industrial Applications | |
| CN115496384A (en) | Monitoring management method and device for industrial equipment and computer equipment | |
| Maniak et al. | Hierarchical spatial-temporal state machine for vehicle instrument cluster manufacturing | |
| WO2019066718A1 (en) | Self-assessing deep representational units | |
| CN115481726A (en) | Industrial robot complete machine health assessment method and system | |
| CN116204825A (en) | Production line equipment fault detection method based on data driving | |
| CN113283546A (en) | Furnace condition abnormity alarm method and system of heating furnace integrity management centralized control device | |
| Minhas et al. | Defect Detection using Deep Learning from Minimal Annotations. | |
| CN112016597A (en) | Depth sampling method based on Bayesian imbalance measurement in machine learning | |
| CN115047313B (en) | ZPW-2000R orbit circuit fault diagnosis method and device based on OC-SVM and DNN | |
| Zhu et al. | Generic process visualization using parametric t-SNE |
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 |