CN116842837A - Transformer fault diagnosis method and device, electronic equipment and storage medium - Google Patents
Transformer fault diagnosis method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116842837A CN116842837A CN202310788435.6A CN202310788435A CN116842837A CN 116842837 A CN116842837 A CN 116842837A CN 202310788435 A CN202310788435 A CN 202310788435A CN 116842837 A CN116842837 A CN 116842837A
- Authority
- CN
- China
- Prior art keywords
- transformer
- performance data
- fault diagnosis
- historical
- transformer fault
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 133
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000003860 storage Methods 0.000 title claims abstract description 21
- 239000013598 vector Substances 0.000 claims abstract description 23
- 238000012544 monitoring process Methods 0.000 claims abstract description 12
- 230000000306 recurrent effect Effects 0.000 claims abstract description 12
- 230000006870 function Effects 0.000 claims description 86
- 238000012549 training Methods 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 23
- 238000012360 testing method Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 18
- 238000005457 optimization Methods 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 230000002068 genetic effect Effects 0.000 claims description 9
- 230000001537 neural effect Effects 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 230000009286 beneficial effect Effects 0.000 abstract description 5
- 238000011156 evaluation Methods 0.000 abstract description 5
- 238000003062 neural network model Methods 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 8
- 230000002159 abnormal effect Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000287196 Asthenes Species 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Operations Research (AREA)
- Medical Informatics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a transformer fault diagnosis method, a transformer fault diagnosis device, electronic equipment and a storage medium. Acquiring transformer state performance data corresponding to a transformer to be subjected to fault diagnosis in real time; inputting the transformer state performance data into a pre-trained transformer fault classifier model to obtain a transformer fault diagnosis result; the transformer fault classifier model is based on an optimized integrated support vector recurrent neural network model algorithm; and feeding back the fault diagnosis result of the transformer to a user so as to realize real-time monitoring of the state of the transformer. The invention solves the problem that the state of the transformer cannot be diagnosed in real time, realizes the timely evaluation of the running condition of the transformer, and is beneficial to ensuring the safe and stable running of the power system.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method and an apparatus for diagnosing a transformer fault, an electronic device, and a storage medium.
Background
Transformers play an important role in power systems, being responsible for the critical tasks of transmission and distribution. The safe and stable operation of the electric power system is crucial to production and life, and once the electric power system fails, the electric power system is negatively affected. Therefore, timely evaluation of the operation condition of the transformer is helpful to ensure safe and stable operation of the power system.
The inventors have found that the following drawbacks exist in the prior art in the process of implementing the present invention: at present, the transformer diagnosis technology mainly comprises a three-ratio method and an artificial intelligence method. However, the three-ratio method has the problem of coding deficiency, which can reduce the diagnosis accuracy of the transformer; however, some current artificial intelligence technologies such as bayesian classifiers and neural networks have the problems of poor generalization capability, difficult convergence and the like. .
Disclosure of Invention
The invention provides a transformer fault diagnosis method, a device, electronic equipment and a storage medium, which are used for timely evaluating the running condition of a transformer and helping to ensure the safe and stable running of a power system.
According to an aspect of the present invention, there is provided a transformer fault diagnosis method, including:
acquiring transformer state performance data corresponding to a transformer to be subjected to fault diagnosis in real time;
inputting the transformer state performance data into a pre-trained transformer fault classifier model to obtain a transformer fault diagnosis result;
wherein the transformer fault classifier model is based on an optimized ESVRNN (Ensemble Support Vector Recurrent Neural Network, integrated support vector recurrent neural network) model algorithm;
And feeding back the fault diagnosis result of the transformer to a user so as to realize real-time monitoring of the state of the transformer.
According to another aspect of the present invention, there is provided a transformer fault diagnosis apparatus, including:
the transformer state performance data acquisition module is used for acquiring transformer state performance data corresponding to the transformer to be subjected to fault diagnosis in real time;
the transformer fault diagnosis result determining module is used for inputting the transformer state performance data into a pre-trained transformer fault classifier model to obtain a transformer fault diagnosis result;
wherein, the transformer fault classifier model is based on an optimized ESVRNN model algorithm;
and the transformer fault diagnosis result feedback module is used for feeding back the transformer fault diagnosis result to a user so as to realize real-time monitoring of the state of the transformer.
According to another aspect of the present invention, there is provided an electronic device including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for diagnosing a transformer fault according to any of the embodiments of the present invention when executing the computer program.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the transformer fault diagnosis method according to any one of the embodiments of the present invention when executed.
According to the technical scheme, the transformer state performance data corresponding to the transformer to be subjected to fault diagnosis are obtained in real time; inputting the transformer state performance data into a pre-trained transformer fault classifier model to obtain a transformer fault diagnosis result; the transformer fault classifier model is based on an optimized integrated support vector recurrent neural network model algorithm; and feeding back the fault diagnosis result of the transformer to a user so as to realize real-time monitoring of the state of the transformer. The invention solves the problem that the state of the transformer cannot be diagnosed in real time, realizes the timely evaluation of the running condition of the transformer, and is beneficial to ensuring the safe and stable running of the power system.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a transformer fault diagnosis method according to a first embodiment of the present invention;
fig. 2 is a schematic structural diagram of a transformer fault diagnosis device according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "target," "current," and the like in the description and claims of the present invention and the above-described drawings are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a transformer fault diagnosis method according to an embodiment of the present invention, where the method may be implemented by a transformer fault diagnosis device, and the transformer fault diagnosis device may be implemented in hardware and/or software.
Accordingly, as shown in fig. 1, the method includes:
s110, acquiring transformer state performance data corresponding to the transformer to be subjected to fault diagnosis in real time.
The transformer state performance data may be data describing performance of the transformer state. In general, an acquisition time point corresponds to a set of transformer state performance data, and the state performance of the transformer is described by the set of transformer state performance data.
In this embodiment, the transformer state performance data of the target transformer may be obtained in real time, and when the transformer state performance data is collected, it needs to be analyzed and processed to obtain a corresponding data analysis result.
S120, inputting the transformer state performance data into a pre-trained transformer fault classifier model to obtain a transformer fault diagnosis result.
The transformer fault classifier model is based on an optimized ESVRNN model algorithm.
The transformer fault classifier model can be a classifier capable of processing according to transformer state performance data to obtain a transformer fault type.
In addition, the transformer fault diagnosis result may include a transformer fault diagnosis normal result and a transformer fault diagnosis abnormal result.
In this embodiment, the ESVRNN model algorithm is an integrated support vector recurrent neural network algorithm model. In particular, recurrent neural networks in the ESVRNN model algorithm may encode a tree or graph structure information as a vector, i.e., map the information into a semantic vector space. In particular, a recurrent neural network is a representation learning that maps words, sentences, segments, or words into the same vector space according to their semantics, i.e. represents combinable information as meaningful vectors, i.e. representing a tree or graph structure as a vector.
It can be understood that the transformer state performance data is input into a pre-trained transformer fault classifier model, and the transformer fault classifier model can perform data analysis and processing to further obtain a transformer fault diagnosis result, where the transformer fault diagnosis result may include that the current state of the transformer is in a normal state or an abnormal state.
And S130, feeding back the fault diagnosis result of the transformer to a user so as to realize real-time monitoring of the state of the transformer.
In this embodiment, when a normal result of the transformer fault diagnosis or an abnormal result of the transformer fault diagnosis is determined, feedback is performed. Specifically, the visual processing can be performed through remote message transmission, or a corresponding alarm device is installed, and when the transformer fault diagnosis result is determined to be the abnormal transformer fault diagnosis result, alarm operation is performed. Therefore, real-time state detection processing of the transformer can be realized, and a user can be timely informed of corresponding operation, so that the safety of a power system where the target transformer is located can be better ensured.
Optionally, before the acquiring, in real time, the transformer state performance data corresponding to the transformer to be diagnosed, the method further includes: acquiring a plurality of historical transformer state performance data and historical transformer fault diagnosis types respectively corresponding to the historical transformer state performance data; and the state performance data of each historical transformer and the fault diagnosis type of the historical transformer are jointly input into a pre-constructed initial transformer fault classifier model for training, and when the fault judgment accuracy corresponding to the initial transformer fault classifier model reaches a preset accuracy threshold, the training is determined to be completed on the transformer fault classifier model.
The historical transformer state performance data is collected to describe historical data of transformer state performance. The historical transformer fault diagnosis type corresponds to the historical transformer state performance data. The fault judging accuracy rate can be the accuracy rate corresponding to the transformer fault classifier model after training, and the higher the accuracy rate is, the better the model judging accuracy rate is. The accuracy threshold may be a magnitude condition of a threshold of accuracy of a pre-set transformer fault classifier model.
In this embodiment, it is necessary to acquire historical transformer state performance data and a historical transformer fault diagnosis type, and further train an initial transformer fault classifier model, so as to obtain a transformer fault classifier model. The obtained transformer fault classifier model can be processed according to the transformer state performance data of the transformer obtained in real time, so that the function of monitoring and controlling the transformer in real time is realized.
Optionally, the acquiring a plurality of historical transformer state performance data and the historical transformer fault diagnosis types respectively corresponding to the historical transformer state performance data includes: according to the formula Carrying out maximum and minimum normalization processing on the state performance data of each historical transformer to obtain state performance normalized data x' of each historical transformer; wherein x represents a vector matrix composed of historical transformer state performance data, and x ε R n×1 The method comprises the steps of carrying out a first treatment on the surface of the And respectively acquiring data type labels corresponding to the state performance normalized data of each historical transformer, and respectively determining the fault diagnosis type of the historical transformer corresponding to the state performance normalized data of the historical transformer according to each data type label.
The historical transformer state performance normalization data may be data obtained by performing normalization processing on the historical transformer state performance data. The data type label can be a data label obtained by labeling the historical transformer state performance normalized data.
In this embodiment, the maximum and minimum normalization processing is performed on the state performance data of each historical transformer by the formulaTo calculate the result.
Accordingly, assume that one of the historical transformer state performance data is x i ＝[a 1 ,a 2 ,a 3 ,…,a n ]Wherein i is a positive integer from 1 to n, and x i A vector matrix of n columns and one row. Further, x is i Inputting into the above formula for processing to obtain historical transformer state performance normalized data x' 1 。
In addition, the expert can label the historical transformer state performance data in advance, the corresponding data label can be assumed to be 1 when the historical transformer state performance data is the normal operation data of the transformer, and the corresponding data label can be assumed to be-1 when the historical transformer state performance data is the abnormal operation data of the transformer.
Therefore, it is necessary to acquire data type labels corresponding to the state performance normalization data of each of the historical transformers, so that the type of the fault diagnosis of the historical transformers, that is, the normal fault diagnosis result and the abnormal fault diagnosis result of the transformer, can be further determined according to the data type labels.
Optionally, the decision function corresponding to the transformer fault classifier model is f (x) =w T x+b; wherein w represents a weight vector matrix and w ε R n×1 The method comprises the steps of carrying out a first treatment on the surface of the b represents bias; f (x) represents a decision function.
In this embodiment, a decision function may be further constructed according to a performance data matrix constructed according to a plurality of sets of historical transformer state performance data and historical transformer fault diagnosis types. Specifically, the decision function can further judge the normal or abnormal state of the transformer through the positive and negative of f (x).
In addition, w is a weight vector matrix, each historical transformer state performance data corresponds to one weight, and w is a vector matrix of n columns and one row.
Optionally, the method further comprises: performing standard quadratic programming processing on the decision function, and optimizing kernel function parameters and penalty functions in the acquired ESVRNN model algorithm according to a genetic algorithmDetermining a thermodynamic equation corresponding to the transformer fault classifier model asWherein γ represents a scalar parameter, and γ > 0; gamma e t Representing error function adjustment parameters; epsilon (t) represents the error function.
In the present embodiment, first, for f (x) =w T And x+b is subjected to standard quadratic programming, so that the accuracy of classification can be ensured, the classification interval can be maximized, and the decision function can be equivalently converted into the problem of standard quadratic programming.
For example, f (x) =w T Conversion of x+b toAnd optimizing the kernel function parameters and the penalty function in the acquired ESVRNN model algorithm according to the genetic algorithm, wherein the kernel function parameters can be set as K, and the penalty function can be set as P. Specifically, the fault diagnosis type of the historical transformer is y, and each historical transformer state performance data x i Respectively correspond to y i 。
Further, it can be determined that the thermodynamic equation corresponding to the transformer fault classifier model is
Specifically, γ represents a scalar parameter, and γ > 0; gamma e t Representing error function adjustment parameters; epsilon (t) represents the error function.
Optionally, the performing standard quadratic programming processing on the decision function, and optimizing kernel function parameters and penalty functions in the obtained ESVRNN model algorithm according to a genetic algorithm to determine a thermodynamic equation corresponding to the transformer fault classifier model, where the determining step includes: performing standard quadratic programming treatment on the decision function, and obtaining a maximum and minimum decision function through a Lagrange multiplier conversion method; obtaining kernel function parameters and penalty functions in an ESVRNN model algorithm, and optimizing the kernel function parameters and penalty functions according to a genetic algorithm to obtain kernel function optimization parameters and penalty optimization functions; and determining a neural dynamics equation corresponding to the transformer fault classifier model according to the maximum and minimum decision function, the kernel function optimization parameter and the penalty optimization function.
The maximum and minimum decision function can be a decision function obtained by carrying out standard quadratic programming processing on the decision function and carrying out equivalent conversion through the maximum and minimum processing.
In determining the standard quadratic programming problem asThen, the Lagrangian multiplier conversion method is needed, namely, lagrangian multiplier alpha is introduced i The quadratic programming problem can be equivalently converted into a minimum maximum problem, and a maximum and minimum decision function L is obtained P The method comprises the following steps:
further, the maximum and minimum decision functions can be equivalently treated as a convex optimization problem, i.e., forThe partial derivatives of w and b of (c) can be calculated:and +.>
Further, kernel function parameters K and penalty functions P in the ESVRNN model algorithm are obtained. Wherein, the kernel function parameters are:j is a positive integer from 1 to n; the optimization problem can be further obtained as +.>
Further, by further simplification, the above-described planning problem can be further equivalent to the following form:in addition, the penalty function obtained is: />
Wherein N is i ＝d i -J i α，And sigma, p>0. The penalty function is substituted into the quadratic programming problem, and the equivalent result can be obtained: />
In order to determine the weight w of the separation line, i.e. the parameter α in the above equation, a method according to the lagrangian multiplier is now introduced, in which the lagrangian function is first constructed as:
according to the general practice of the Lagrangian multiplier method, the partial derivatives of the Lagrangian function L (α, λ) for α and λ, respectively, are obtained as follows, and let 0:
Further simplified into the following matrix form: az=g.
Now solving the matrix equation above gives α, i.e. the weight w mentioned above. Further, it can be determined that
In addition, assuming that both matrices z and g change with time t, the error function ε (t) may be further defined as: epsilon (t) =az (t) -g (t).
According to the variable parameter recurrent neural network method in the ESVRNN model algorithm, the following neural dynamics equation is constructed:
optionally, the step of jointly inputting the state performance data of each historical transformer and the fault diagnosis type of the historical transformer to a pre-constructed initial transformer fault classifier model for training, and determining that training is completed when the fault judgment accuracy corresponding to the initial transformer fault classifier model reaches a preset accuracy threshold value comprises the following steps: dividing each of the historical transformer state performance data and the historical transformer fault diagnosis type into a test performance data set and a training performance data set; wherein, in the test performance data set and the training performance data set, each of the historical transformer state performance data corresponds to one of the historical transformer fault diagnosis types; the historical transformer state performance data and the historical transformer fault diagnosis types in the training performance data set are input into an initial transformer fault classifier model which is built in advance to train, and when the training performance data set is traversed, the transformer fault classifier model to be tested is obtained; inputting each historical transformer state performance data in the test performance data set to the to-be-tested transformer fault classifier model to obtain a test transformer fault diagnosis result; calculating to obtain the fault judgment accuracy according to the transformer fault diagnosis result and the historical transformer fault diagnosis type; and if the fault judging accuracy rate reaches the accuracy rate threshold value, determining the fault diagnosis result of the test transformer as the transformer fault classifier model.
In this embodiment, the acquired historical transformer state performance data and the historical transformer fault diagnosis type need to be divided into a test performance data set and a training performance data set. For example, assume that 1000 sets of historical transformer state performance data and historical transformer fault diagnosis types exist, each corresponding to one of the historical transformer fault diagnosis types, the historical transformer state performance data and the historical transformer fault diagnosis types occurring in pairs.
Assuming that the test performance data set and the training performance data set are divided according to a 3:7 ratio, it may be determined that 300 sets of data exist for the test performance data set; and the training performance dataset is 700 sets of data.
Further, the transformer fault classifier model is initialized through 700 groups of data respectively until the 700 groups of data are traversed, and the transformer fault classifier model to be tested is obtained.
Correspondingly, each historical transformer state performance data in the 300 groups of test performance data sets is input into a transformer fault classifier model to be tested, and 300 test transformer fault diagnosis results are obtained. Furthermore, the fault determination accuracy can be calculated according to the fault diagnosis result of the transformer and the fault diagnosis type of the historical transformer, and the fault determination accuracy can be assumed to be 98%.
Further, assuming that the accuracy threshold is 97.5%, determining that the fault diagnosis result of the test transformer is the transformer fault classifier model because the fault judgment accuracy 98% reaches the accuracy threshold of 97.5%.
In addition, if the failure judgment accuracy rate does not reach the accuracy rate threshold value, retraining the transformer failure classifier model to be tested is needed until the requirement of the accuracy rate threshold value is met.
It can be understood that the transformer state performance data obtained in real time and the transformer fault diagnosis type corresponding to the transformer fault diagnosis result can also be input into the transformer fault classifier model for retraining, so that the model optimization of the transformer fault classifier model is realized.
According to the technical scheme, the transformer state performance data corresponding to the transformer to be subjected to fault diagnosis are obtained in real time; inputting the transformer state performance data into a pre-trained transformer fault classifier model to obtain a transformer fault diagnosis result; the transformer fault classifier model is based on an optimized integrated support vector recurrent neural network model algorithm; and feeding back the fault diagnosis result of the transformer to a user so as to realize real-time monitoring of the state of the transformer. The invention solves the problem that the state of the transformer cannot be diagnosed in real time, realizes the timely evaluation of the running condition of the transformer, and is beneficial to ensuring the safe and stable running of the power system.
Example two
Fig. 2 is a schematic structural diagram of a transformer fault diagnosis device according to a second embodiment of the present invention. The transformer fault diagnosis device provided by the embodiment of the invention can be realized through software and/or hardware, and can be configured in terminal equipment or a server to realize the transformer fault diagnosis method in the embodiment of the invention. As shown in fig. 2, the apparatus includes: the system comprises a transformer state performance data acquisition module 210, a transformer fault diagnosis result determination module 220 and a transformer fault diagnosis result feedback module 230.
The transformer state performance data acquisition module 210 is configured to acquire, in real time, transformer state performance data corresponding to a transformer to be diagnosed;
the transformer fault diagnosis result determining module 220 is configured to input the transformer state performance data into a pre-trained transformer fault classifier model, so as to obtain a transformer fault diagnosis result;
wherein, the transformer fault classifier model is based on an optimized ESVRNN model algorithm;
the transformer fault diagnosis result feedback module 230 is configured to feed back the transformer fault diagnosis result to a user, so as to monitor the state of the transformer in real time.
According to the technical scheme, the transformer state performance data corresponding to the transformer to be subjected to fault diagnosis are obtained in real time; inputting the transformer state performance data into a pre-trained transformer fault classifier model to obtain a transformer fault diagnosis result; the transformer fault classifier model is based on an optimized integrated support vector recurrent neural network model algorithm; and feeding back the fault diagnosis result of the transformer to a user so as to realize real-time monitoring of the state of the transformer. The invention solves the problem that the state of the transformer cannot be diagnosed in real time, realizes the timely evaluation of the running condition of the transformer, and is beneficial to ensuring the safe and stable running of the power system.
Optionally, the transformer fault classifier model training module may be specifically configured to: acquiring a plurality of historical transformer state performance data and historical transformer fault diagnosis types respectively corresponding to the historical transformer state performance data; and the state performance data of each historical transformer and the fault diagnosis type of the historical transformer are jointly input into a pre-constructed initial transformer fault classifier model for training, and when the fault judgment accuracy corresponding to the initial transformer fault classifier model reaches a preset accuracy threshold, the training is determined to be completed on the transformer fault classifier model.
Optionally, the transformer fault classifier model training module may be further specifically configured to: according to the formulaCarrying out maximum and minimum normalization processing on the state performance data of each historical transformer to obtain state performance normalized data x' of each historical transformer; wherein x represents a vector matrix composed of historical transformer state performance data, and x ε R n×1 The method comprises the steps of carrying out a first treatment on the surface of the And respectively acquiring data type labels corresponding to the state performance normalized data of each historical transformer, and respectively determining the fault diagnosis type of the historical transformer corresponding to the state performance normalized data of the historical transformer according to each data type label.
Optionally, the transformer fault classifier model training module may further haveThe body is used for: the decision function corresponding to the transformer fault classifier model is f (x) =w T x+b; wherein w represents a weight vector matrix and w ε R n×1 The method comprises the steps of carrying out a first treatment on the surface of the b represents bias; f (x) represents a decision function.
Optionally, the transformer fault classifier model training module may be further specifically configured to: performing standard quadratic programming processing on the decision function, and optimizing kernel function parameters and penalty functions in the acquired ESVRNN model algorithm according to a genetic algorithm to determine that a neural dynamics equation corresponding to the transformer fault classifier model is Wherein γ represents a scalar parameter, and γ > 0; gamma e t Representing error function adjustment parameters; epsilon (t) represents the error function.
Optionally, the transformer fault classifier model training module may be further specifically configured to: performing standard quadratic programming treatment on the decision function, and obtaining a maximum and minimum decision function through a Lagrange multiplier conversion method; obtaining kernel function parameters and penalty functions in an ESVRNN model algorithm, and optimizing the kernel function parameters and penalty functions according to a genetic algorithm to obtain kernel function optimization parameters and penalty optimization functions; and determining a neural dynamics equation corresponding to the transformer fault classifier model according to the maximum and minimum decision function, the kernel function optimization parameter and the penalty optimization function.
Optionally, the transformer fault classifier model training module may be further specifically configured to: dividing each of the historical transformer state performance data and the historical transformer fault diagnosis type into a test performance data set and a training performance data set; wherein, in the test performance data set and the training performance data set, each of the historical transformer state performance data corresponds to one of the historical transformer fault diagnosis types; the historical transformer state performance data and the historical transformer fault diagnosis types in the training performance data set are input into an initial transformer fault classifier model which is built in advance to train, and when the training performance data set is traversed, the transformer fault classifier model to be tested is obtained; inputting each historical transformer state performance data in the test performance data set to the to-be-tested transformer fault classifier model to obtain a test transformer fault diagnosis result; calculating to obtain the fault judgment accuracy according to the transformer fault diagnosis result and the historical transformer fault diagnosis type; and if the fault judging accuracy rate reaches the accuracy rate threshold value, determining the fault diagnosis result of the test transformer as the transformer fault classifier model.
The transformer fault diagnosis device provided by the embodiment of the invention can execute the transformer fault diagnosis method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example III
Fig. 3 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement a third embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 3, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the respective methods and processes described above, such as a transformer fault diagnosis method.
In some embodiments, the transformer fault diagnosis method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the transformer fault diagnosis method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the transformer fault diagnosis method by any other suitable means (e.g. by means of firmware).
The method comprises the following steps: acquiring transformer state performance data corresponding to a transformer to be subjected to fault diagnosis in real time; inputting the transformer state performance data into a pre-trained transformer fault classifier model to obtain a transformer fault diagnosis result; wherein, the transformer fault classifier model is based on an optimized ESVRNN model algorithm; and feeding back the fault diagnosis result of the transformer to a user so as to realize real-time monitoring of the state of the transformer.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Example IV
A fourth embodiment of the present invention also provides a computer-readable storage medium containing computer-readable instructions, which when executed by a computer processor, are for performing a transformer fault diagnosis method, the method comprising: acquiring transformer state performance data corresponding to a transformer to be subjected to fault diagnosis in real time; inputting the transformer state performance data into a pre-trained transformer fault classifier model to obtain a transformer fault diagnosis result; wherein, the transformer fault classifier model is based on an optimized ESVRNN model algorithm; and feeding back the fault diagnosis result of the transformer to a user so as to realize real-time monitoring of the state of the transformer.
Of course, the computer-readable storage medium provided by the embodiments of the present invention has computer-executable instructions not limited to the above-described method operations, but also can perform related operations in the transformer fault diagnosis method provided by any of the embodiments of the present invention.
From the above description of embodiments, it will be clear to a person skilled in the art that the present invention may be implemented by means of software and necessary general purpose hardware, but of course also by means of hardware, although in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, etc., and include several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments of the present invention.
It should be noted that, in the embodiment of the transformer fault diagnosis apparatus described above, each unit and module included are only divided according to the functional logic, but not limited to the above-described division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for diagnosing a transformer fault, comprising:
acquiring transformer state performance data corresponding to a transformer to be subjected to fault diagnosis in real time;
inputting the transformer state performance data into a pre-trained transformer fault classifier model to obtain a transformer fault diagnosis result;
the transformer fault classifier model is based on an optimized integrated support vector recurrent neural network ESVRNN model algorithm;
And feeding back the fault diagnosis result of the transformer to a user so as to realize real-time monitoring of the state of the transformer.
2. The method of claim 1, further comprising, prior to the acquiring, in real time, the transformer state performance data corresponding to the transformer to be fault diagnosed:
acquiring a plurality of historical transformer state performance data and historical transformer fault diagnosis types respectively corresponding to the historical transformer state performance data;
and the state performance data of each historical transformer and the fault diagnosis type of the historical transformer are jointly input into a pre-constructed initial transformer fault classifier model for training, and when the fault judgment accuracy corresponding to the initial transformer fault classifier model reaches a preset accuracy threshold, the training is determined to be completed on the transformer fault classifier model.
3. The method of claim 2, wherein the obtaining a plurality of historical transformer state performance data and a historical transformer fault diagnosis type respectively corresponding to each of the historical transformer state performance data comprises:
according to the formulaCarrying out maximum and minimum normalization processing on the state performance data of each historical transformer to obtain state performance normalized data x' of each historical transformer;
Wherein x represents a vector matrix composed of historical transformer state performance data, and x ε R n×1 ；
And respectively acquiring data type labels corresponding to the state performance normalized data of each historical transformer, and respectively determining the fault diagnosis type of the historical transformer corresponding to the state performance normalized data of the historical transformer according to each data type label.
4. A method according to claim 3, wherein the transformer fault classifier model corresponds to a decision function of f (x) =w T x+b；
Wherein w represents a weight vector matrix and w ε R n×1 The method comprises the steps of carrying out a first treatment on the surface of the b represents bias; f (x) represents a decision function.
5. The method as recited in claim 4, further comprising:
performing standard quadratic programming processing on the decision function, and optimizing kernel function parameters and penalty functions in the acquired ESVRNN model algorithm according to a genetic algorithm to determine that a neural dynamics equation corresponding to the transformer fault classifier model is
Wherein γ represents a scalar parameter, and γ > 0; gamma e t Representing error function adjustment parameters; epsilon (t) represents the error function.
6. The method of claim 5, wherein the performing the standard quadratic programming process on the decision function and optimizing the kernel function parameters and the penalty function in the obtained ESVRNN model algorithm according to the genetic algorithm to determine the neural dynamics equation corresponding to the transformer fault classifier model comprises:
Performing standard quadratic programming treatment on the decision function, and obtaining a maximum and minimum decision function through a Lagrange multiplier conversion method;
obtaining kernel function parameters and penalty functions in an ESVRNN model algorithm, and optimizing the kernel function parameters and penalty functions according to a genetic algorithm to obtain kernel function optimization parameters and penalty optimization functions;
and determining a neural dynamics equation corresponding to the transformer fault classifier model according to the maximum and minimum decision function, the kernel function optimization parameter and the penalty optimization function.
7. The method according to claim 6, wherein the step of inputting each of the historical transformer state performance data and the historical transformer fault diagnosis type in combination to a pre-constructed initial transformer fault classifier model for training, and determining that training is completed when the fault determination accuracy corresponding to the initial transformer fault classifier model reaches a preset accuracy threshold value, comprises:
dividing each of the historical transformer state performance data and the historical transformer fault diagnosis type into a test performance data set and a training performance data set; wherein, in the test performance data set and the training performance data set, each of the historical transformer state performance data corresponds to one of the historical transformer fault diagnosis types;
The historical transformer state performance data and the historical transformer fault diagnosis types in the training performance data set are input into an initial transformer fault classifier model which is built in advance to train, and when the training performance data set is traversed, the transformer fault classifier model to be tested is obtained;
inputting each historical transformer state performance data in the test performance data set to the to-be-tested transformer fault classifier model to obtain a test transformer fault diagnosis result;
calculating to obtain the fault judgment accuracy according to the transformer fault diagnosis result and the historical transformer fault diagnosis type;
and if the fault judging accuracy rate reaches the accuracy rate threshold value, determining the fault diagnosis result of the test transformer as the transformer fault classifier model.
8. A transformer fault diagnosis apparatus, comprising:
the transformer state performance data acquisition module is used for acquiring transformer state performance data corresponding to the transformer to be subjected to fault diagnosis in real time;
the transformer fault diagnosis result determining module is used for inputting the transformer state performance data into a pre-trained transformer fault classifier model to obtain a transformer fault diagnosis result;
The transformer fault classifier model is based on an optimized integrated support vector recurrent neural network ESVRNN model algorithm;
and the transformer fault diagnosis result feedback module is used for feeding back the transformer fault diagnosis result to a user so as to realize real-time monitoring of the state of the transformer.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the transformer fault diagnosis method of any one of claims 1-7 when the computer program is executed by the processor.
10. A computer readable storage medium storing computer instructions for causing a processor to implement the transformer fault diagnosis method of any one of claims 1-7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310788435.6A CN116842837A (en) | 2023-06-29 | 2023-06-29 | Transformer fault diagnosis method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310788435.6A CN116842837A (en) | 2023-06-29 | 2023-06-29 | Transformer fault diagnosis method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116842837A true CN116842837A (en) | 2023-10-03 |
Family
ID=88161085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310788435.6A Pending CN116842837A (en) | 2023-06-29 | 2023-06-29 | Transformer fault diagnosis method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116842837A (en) |
-
2023
- 2023-06-29 CN CN202310788435.6A patent/CN116842837A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020259421A1 (en) | Method and apparatus for monitoring service system | |
| CN109447461B (en) | User credit evaluation method and device, electronic equipment and storage medium | |
| CN113379059B (en) | Model training method for quantum data classification and quantum data classification method | |
| CN114841619A (en) | State evaluation method and device for isolating switch, electronic equipment and medium | |
| CN116021981A (en) | Method, device, equipment and storage medium for predicting ice coating faults of power distribution network line | |
| CN117556238A (en) | Power equipment inspection method and system based on fault prediction | |
| CN113449778A (en) | Model training method for quantum data classification and quantum data classification method | |
| CN117370857A (en) | Water turbine governor management method, device, equipment and storage medium | |
| CN117674119A (en) | Power grid operation risk assessment method, device, computer equipment and storage medium | |
| CN116359738A (en) | Method, device, equipment and storage medium for monitoring health state of battery | |
| CN116842837A (en) | Transformer fault diagnosis method and device, electronic equipment and storage medium | |
| CN115392715A (en) | Power utilization data risk assessment method, device, equipment and storage medium | |
| CN115794578A (en) | Data management method, device, equipment and medium for power system | |
| CN115809818A (en) | Multidimensional diagnosis and evaluation method and device for auxiliary equipment of pumped storage power station | |
| CN115481767A (en) | Operation data processing method and device for power distribution network maintenance and computer equipment | |
| CN110413482B (en) | Detection method and device | |
| CN114938385B (en) | Electric power physical network security situation awareness method, device, equipment and medium | |
| CN114926447B (en) | Method for training a model, method and device for detecting a target | |
| CN116703109A (en) | Method, device, equipment and storage medium for selecting power distribution network project | |
| CN117251809A (en) | Power grid time sequence data anomaly detection method, device, equipment and storage medium | |
| CN115795913A (en) | Analysis and diagnosis method, device, equipment and medium for weak link of power distribution network voltage | |
| CN116128296A (en) | Risk prediction method, risk prediction device, electronic equipment and storage medium | |
| CN117763091A (en) | Equipment fault detection method based on weight correction and related components | |
| CN117591876A (en) | Breaker fault diagnosis method, device, equipment and storage medium | |
| CN116975719A (en) | Fault diagnosis model training method, device, equipment and medium |
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 |