CN114580474A - Transformer sound vibration fault diagnosis method, system, equipment and storage medium - Google Patents

Transformer sound vibration fault diagnosis method, system, equipment and storage medium Download PDF

Info

Publication number
CN114580474A
CN114580474A CN202210192886.9A CN202210192886A CN114580474A CN 114580474 A CN114580474 A CN 114580474A CN 202210192886 A CN202210192886 A CN 202210192886A CN 114580474 A CN114580474 A CN 114580474A
Authority
CN
China
Prior art keywords
sound vibration
transformer
fault diagnosis
fault
intelligent agent
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
Application number
CN202210192886.9A
Other languages
Chinese (zh)
Inventor
徐建南
焦飞
雷龙武
张中浩
谈元鹏
刘冰倩
黄建业
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
China Electric Power Research Institute Co Ltd CEPRI
Electric Power Research Institute of State Grid Fujian Electric Power Co Ltd
State Grid Fujian Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
China Electric Power Research Institute Co Ltd CEPRI
Electric Power Research Institute of State Grid Fujian Electric Power Co Ltd
State Grid Fujian Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, China Electric Power Research Institute Co Ltd CEPRI, Electric Power Research Institute of State Grid Fujian Electric Power Co Ltd, State Grid Fujian Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202210192886.9A priority Critical patent/CN114580474A/en
Publication of CN114580474A publication Critical patent/CN114580474A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/02—Preprocessing
    • G06F2218/04—Denoising
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • 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
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
    • Y04S10/52—Outage or fault management, e.g. fault detection or location

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Molecular Biology (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Signal Processing (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)

Abstract

The invention discloses a method, a system, equipment and a storage medium for diagnosing sound vibration faults of a transformer, wherein the method comprises the following steps: acquiring a sound vibration signal of the transformer to be diagnosed; and inputting the sound vibration signal of the transformer to be diagnosed into a sound vibration fault diagnosis intelligent agent, and carrying out sound vibration fault identification through the sound vibration fault diagnosis intelligent agent according to the sound vibration signal to obtain a sound vibration fault diagnosis result of the transformer to be diagnosed.

Description

Transformer sound vibration fault diagnosis method, system, equipment and storage medium
Technical Field
The invention belongs to the technical field of fault diagnosis, and relates to a transformer sound vibration fault diagnosis method, a transformer sound vibration fault diagnosis system, transformer sound vibration fault diagnosis equipment and a storage medium.
Background
The transformer is used as a key core device of a power system, and the stable operation of the transformer is closely related to the safety and reliability of a power grid, so that the analysis of the operation state of the transformer in time and the fault diagnosis are very important, and the transformer is significant in guaranteeing the stability of power supply and avoiding national economic loss. Because the transformer is in a state of load operation for a long time, the probability of the fault is higher than that of other power equipment, the trans-regional dispatching of the power grid is more and more popular at present, once the fault of the transformer cannot be timely and accurately diagnosed and repaired, a series of adverse reactions occur on the local part of the power grid, and the loss which cannot be estimated is easily caused to the operation of the power grid.
At present, the traditional fault diagnosis research method for the transformer still has some problems. The expert system method has the problems of excessive dependence on prior knowledge and expert experience and lack of expert knowledge, and the stability and accuracy of a fault diagnosis result are difficult to ensure; for the method of extracting the time-frequency domain characteristics of the fault signals firstly and then realizing fault diagnosis classification by combining the classifier, the problems that the manual extraction of the characteristics is complicated and the fault diagnosis precision is influenced by the effectiveness of the extracted characteristics exist, and if the effectiveness of the extracted characteristics is poor, the fault diagnosis precision is possibly low.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a transformer sound vibration fault diagnosis method, a transformer sound vibration fault diagnosis system, transformer sound vibration fault diagnosis equipment and a storage medium, wherein the transformer sound vibration fault diagnosis method, the transformer sound vibration fault diagnosis system, the transformer sound vibration fault diagnosis equipment and the storage medium can accurately perform online fault diagnosis on a transformer.
In order to achieve the purpose, the invention adopts the following technical scheme:
in one aspect, the present invention provides a method for diagnosing a sound vibration fault of a transformer, including:
acquiring a sound vibration signal of the transformer to be diagnosed;
inputting the sound vibration signal of the transformer to be diagnosed into a sound vibration fault diagnosis intelligent agent, and carrying out sound vibration fault identification through the sound vibration fault diagnosis intelligent agent according to the sound vibration signal to obtain a sound vibration fault diagnosis result of the transformer to be diagnosed; the intelligent body for diagnosing the sound vibration fault is obtained by training a sound vibration signal sample in a deep reinforcement learning mode.
The transformer sound vibration fault diagnosis method is further improved as follows:
before the input of the sound vibration signal of the transformer to be diagnosed into the sound vibration fault diagnosis agent, the method further comprises:
collecting sound vibration signals of a transformer in various fault states, and dividing the collected sound vibration signals of the transformer in various fault states into a training sample set and a test sample set;
constructing an intelligent agent;
and training the intelligent agent through the training sample set, and testing the trained intelligent agent through the test sample set to obtain the sound vibration fault diagnosis intelligent agent.
The specific process for constructing the intelligent agent comprises the following steps: and establishing an agent based on the deep Q dual-network model structure.
The deep Q dual-network model comprises an estimation network Eval-Net and a Target network Target-Net, wherein the estimation network Eval-Net and the Target network Target-Net are both multilayer perceptrons and have consistent network structures.
The intelligent agent is trained through the training sample set, the trained intelligent agent is tested through the testing sample set, and the specific process of obtaining the intelligent agent for diagnosing the sound vibration fault is as follows: :
marking a fault label for each sample in the training sample set, wherein the fault labels of the samples of the same fault type are the same;
determining a reward return function of the agent based on the sample proportion of each fault label;
and training the intelligent agent through the training sample set based on the reward return function of the intelligent agent, and testing the trained intelligent agent through the test sample set to obtain the sound vibration fault diagnosis intelligent agent.
The reward return function is:
Figure BDA0003524980190000031
wherein,
Figure BDA0003524980190000032
the number of samples of the i-th type fault label,
Figure BDA0003524980190000033
to be in a fault environment state stAction a by greedy policytNumber of samples of the corresponding trouble ticket, ltIs an environmental state stFault labels corresponding to the samples, K being the number of fault types of the transformer, each fault type corresponding to an action ai。
The training the agent through the training sample set includes: and calculating the current Q value by using the estimation network Eval-Net, calculating the Target Q value by using the Target network Target-Net according to the action selected by the estimation network Eval-Net in the state at the next moment, and training the parameters in the intelligent body by using the Target Q value and the current Q value to obtain the sound vibration fault diagnosis intelligent body.
In a second aspect of the present invention, the present invention provides a transformer acoustic vibration fault diagnosis system, including:
the acquisition module is used for acquiring a sound vibration signal of the transformer to be diagnosed;
and the diagnosis module is used for inputting the sound vibration signal of the transformer to be diagnosed into the sound vibration fault diagnosis intelligent agent, and performing sound vibration fault identification according to the sound vibration signal through the sound vibration fault diagnosis intelligent agent to obtain a sound vibration fault diagnosis result of the transformer to be diagnosed.
In three aspects, the invention provides a computer device, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the transformer sound vibration fault diagnosis method when executing the computer program.
In a fourth aspect of the present invention, the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of the transformer sound vibration fault diagnosis method.
The invention has the following beneficial effects:
when the transformer sound vibration fault diagnosis method, the system, the equipment and the storage medium are specifically operated, the sound vibration signal of the transformer to be diagnosed is input into the sound vibration fault diagnosis intelligent agent, the output result of the sound vibration fault diagnosis intelligent agent is used as the sound vibration fault diagnosis result of the transformer, so that the online diagnosis of the transformer fault is realized, the diagnosis efficiency is improved, and the sound vibration fault diagnosis intelligent agent is a diagnosis model obtained by training a sound vibration signal sample in a deep reinforcement learning mode.
Furthermore, the reward return function is designed by utilizing the sample proportion rate of each fault label, the problem that the fault samples of the sound vibration signal of the transformer are unbalanced is solved, and the diagnosis accuracy rate of few-sample faults is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of a transformer sound vibration fault diagnosis method according to the present invention;
FIG. 2 is a flow chart of the transformer sound vibration fault diagnosis method of the present invention;
fig. 3 is a structural diagram of the sound vibration fault diagnosis system of the transformer of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or 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.
The invention is described in further detail below with reference to the accompanying drawings:
example one
Referring to fig. 1 and 2, the method for diagnosing the sound vibration fault of the transformer according to the present invention includes the following steps:
1) obtaining a fault sample;
the specific process of the step 1) is as follows:
collecting the sound vibration signals of the transformer in various fault states, denoising the sound vibration signals, and taking the denoised sound vibration signals as fault samples; in addition, the audio signal of the sound vibration signal is converted into a time series signal, then the time series signal and the vibration signal are respectively subjected to normalization processing, then the two signals are combined into a vector, and the vector is used as the fault environment state.
2) Constructing an environment state space;
specifically, the environment state space S is composed of all fault environment states, each environment state S corresponds to one fault environment state, K fault types of the transformer are represented as an action space a ═ 0, 1., K-1}, and each fault type corresponds to one action aiMapping the environment state space to the action space A to obtain the environment state space set of the fault type
Figure BDA0003524980190000063
Comprises the following steps:
Figure BDA0003524980190000061
wherein s isnFor the nth state in the failure environment state space set, the relationship between the action space a and the environment state space S is:
Figure BDA0003524980190000062
partitioning the environmental state space S into trainingSet environment state space StrainAnd test set environmental State space Stest。
3) Establishing an intelligent agent;
the specific process of the step 3) is as follows:
establishing an intelligent agent based on a deep Q double-network model structure, wherein the deep Q double-network model comprises an estimation network Eval-Net and a Target network Target-Net, and the estimation network Eval-Net and the Target network Target-Net are both multilayer perceptrons and have consistent network structures. Wherein the estimated network Eval-Net is used for calculating the current Q value Q(s)t,at(ii) a Theta), the Target network Target-Net is used for calculating a Target Q value, and the calculation process is shown as the formula (3) and the formula (4);
Figure BDA0003524980190000071
Target Q＝r+γQ(st+1,a*；θ-) (4)
wherein, theta and theta-Network parameters of an estimated network Eval-Net and a Target network Target-Net are respectively, r is an instant reward return value, gamma is a discount factor, and gamma belongs to [0,1 ]]。
4) Utilizing a training set environmental state space StrainTraining the agent:
the specific process of the step 4) is as follows:
41) adopting greedy strategy at current fault environment state s according to formula (5)tLower selection action atWherein the greedy policy is an epsilon-greedy policy of 0<ε<1, the method is used for balancing the utilization and exploration degree of the intelligent agent on the environment in the learning and training process. When the random number is smaller than epsilon, the random number indicates that one action is randomly selected from the action space, otherwise, the output Q(s) of the network Eval-Net is estimatedt,at(ii) a θ) selects the action corresponding to the maximum Q value.
Figure BDA0003524980190000072
42) Labels are marked on all samples in a training set, wherein the labels of the samples of the same fault type are the same, a reward return function of the intelligent agent is determined based on the sample occupation ratio of each label, and the specific reward return function is shown as a formula (6).
Figure BDA0003524980190000081
Wherein,
Figure BDA0003524980190000082
the number of samples of the i-th type fault label,
Figure BDA0003524980190000083
to be in a fault environment state stAction a by greedy policytNumber of samples of the corresponding trouble ticket, ltIs an environmental state stFault labels corresponding to the samples, K being the number of fault types of the transformer, each fault type corresponding to an action aiAnd when the current diagnosis result is correct, returning a positive reward value, otherwise, returning a negative penalty value.
43) From the training set environmental state space StrainRandomly selecting a fault environment state as a next time state st+1And apply the empirical data et＝(st,at,rt,st+1) Save to experience pool D (D ═ { e }1,e2,…enH), wherein the state transition probability P(s)t+1|st,at) Determined and uniformly distributed.
44) In each round of T fault diagnosis processes, the state s at the next moment is obtainedt+1As the current environmental state stAnd repeating the steps 41) to 43), and calculating the accuracy of fault judgment of each round.
45) Training network model parameters, specifically, sampling and extracting k empirical data in an empirical pool D at random, calculating the mean square loss L (theta) of the current Q value and the Target Q value and the gradient of the mean square loss L (theta) and the gradient of the Target Q value according to the formula (7) and the formula (8), updating the parameters of the estimated network Eval-Net by using a gradient descent method, and copying the parameters of the estimated network Eval-Net into a Target network Target-Net every C training rounds.
L(θ)＝Ε[(TargetQ-Q(st,at；θ))2] (7)
Figure BDA0003524980190000084
Where u (D) represents random uniform sampling in the experience pool D.
46) And repeating the steps 41) to 45) until a preset training turn is reached, wherein in the training process, parameters of the estimation network Eval-Net with the highest accuracy are stored by comparing the accuracy of fault judgment of each turn, so as to complete the training of the intelligent agent, and thus the sound vibration fault diagnosis intelligent agent is obtained.
5) Utilizing test set environmental state space StestTesting the sound vibration fault diagnosis intelligent agent;
the specific process of the step 5) is as follows:
test set environment state space StestThe fault environment state in the sound vibration fault diagnosis intelligent agent is input into the sound vibration fault diagnosis intelligent agent, and the accuracy of the fault diagnosis result is further compared to verify the effectiveness of the sound vibration fault diagnosis intelligent agent.
6) Acquiring a sound vibration signal of the transformer to be diagnosed;
7) and inputting the sound vibration signal of the transformer to be diagnosed into a sound vibration fault diagnosis intelligent agent, and carrying out sound vibration fault identification through the sound vibration fault diagnosis intelligent agent according to the sound vibration signal to obtain a sound vibration fault diagnosis result of the transformer to be diagnosed.
It should be noted that the invention constructs the sound vibration fault diagnosis intelligent agent based on the deep reinforcement learning technology, and avoids the problems of complex artificial feature extraction and poor fault diagnosis precision, so as to improve the fault diagnosis precision.
Meanwhile, the intelligent agent is constructed based on a deep Q double-network model structure, the nonlinear mapping relation between the sound vibration signal and the fault type is established by utilizing the estimation network and the target network in the multilayer sensing mechanism model construction structure, and the action of state selection of the estimation network at the next moment is adopted when the target Q value for updating the network parameters is calculated, so that the problem of over-high estimation of the Q value is avoided.
In addition, aiming at the problem that fewer-sample fault diagnosis accuracy is low due to unbalance of sound vibration signal fault samples collected on site, the reward return function of the intelligent agent is determined based on the sample occupation ratio of each label, so that fewer-sample faults obtain high return values, and the diagnosis accuracy is improved.
Example two
Referring to fig. 3, the sound vibration fault diagnosis system of the transformer according to the present invention includes:
the acquisition module 1 is used for acquiring a sound vibration signal of the transformer to be diagnosed;
the diagnosis module 2 is used for inputting the sound vibration signal of the transformer to be diagnosed into a sound vibration fault diagnosis intelligent agent, and performing sound vibration fault identification according to the sound vibration signal through the sound vibration fault diagnosis intelligent agent to obtain a sound vibration fault diagnosis result of the transformer to be diagnosed; the intelligent body for diagnosing the sound vibration fault is obtained by training a sound vibration signal sample in a deep reinforcement learning mode.
Further, the sound vibration fault diagnosis system of the transformer further comprises:
the acquisition module 3 is used for acquiring sound vibration signals of the transformer in various fault states and dividing the acquired sound vibration signals of the transformer in various fault states into a training sample set and a test sample set;
the building module 4 is used for building an agent;
and the training test module 5 is used for training the intelligent agent through the training sample set and testing the trained intelligent agent through the test sample set to obtain the sound vibration fault diagnosis intelligent agent.
Further, the training test module includes:
the design module 51 is configured to label a fault label for each sample in the training sample set, where the fault labels of the samples of the same fault type are the same; determining a reward return function of the agent based on the sample proportion of each fault label;
and the calculating module 52 is configured to train the agent through the training sample set based on the reward return function of the agent, and test the trained agent through the test sample set to obtain the sound vibration fault diagnosis agent.
All relevant contents of each step related to the embodiment of the transformer sound vibration fault diagnosis method may be cited to the functional description of the functional module corresponding to the transformer sound vibration fault diagnosis system in the embodiment of the present application, and are not described herein again.
The division of the modules in the embodiments of the present application is schematic, and is only a logical function division, and in actual implementation, there may be another division manner, and in addition, each functional module in each embodiment of the present application may be integrated in one processor, or may exist alone physically, or two or more modules are integrated in one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
EXAMPLE III
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the transformer sound vibration fault diagnosis method when executing the computer program, wherein the memory may comprise a memory, such as a high speed random access memory, or may further comprise a non-volatile memory, such as at least one disk memory, etc.; the processor, the network interface and the memory are connected with each other through an internal bus, wherein the internal bus can be an industrial standard system structure bus, a peripheral component interconnection standard bus, an extended industrial standard structure bus and the like, and the bus can be divided into an address bus, a data bus, a control bus and the like. The memory is used for storing programs, and particularly, the programs can comprise program codes which comprise computer operation instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
Example four
A computer readable storage medium storing a computer program which when executed by a processor implements the steps of the transformer vibro-acoustic fault diagnosis method, in particular the computer readable storage medium comprises but is not limited to e.g. volatile and/or non-volatile memory. The volatile memory may include Random Access Memory (RAM) and/or cache memory (cache), among others. The non-volatile memory may include a Read Only Memory (ROM), hard disk, flash memory, optical disk, magnetic disk, and the like.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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 application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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 solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.

Claims (10)

1. A transformer sound vibration fault diagnosis method is characterized by comprising the following steps:
acquiring a sound vibration signal of the transformer to be diagnosed;
inputting the sound vibration signal of the transformer to be diagnosed into a sound vibration fault diagnosis intelligent agent, and carrying out sound vibration fault identification through the sound vibration fault diagnosis intelligent agent according to the sound vibration signal to obtain a sound vibration fault diagnosis result of the transformer to be diagnosed; the intelligent body for diagnosing the sound vibration fault is obtained by training a sound vibration signal sample in a deep reinforcement learning mode.
2. The method for diagnosing the sound vibration fault of the transformer according to claim 1, wherein before the step of inputting the sound vibration signal of the transformer to be diagnosed into the intelligent agent for diagnosing the sound vibration fault, the method further comprises the following steps:
collecting sound vibration signals of a transformer in various fault states, and dividing the collected sound vibration signals of the transformer in various fault states into a training sample set and a test sample set;
constructing an intelligent agent;
and training the intelligent agent through the training sample set, and testing the trained intelligent agent through the test sample set to obtain the sound vibration fault diagnosis intelligent agent.
3. The sound-vibration fault diagnosis method for the transformer according to claim 2, wherein the specific process of constructing the intelligent agent is as follows: and establishing an agent based on the deep Q dual-network model structure.
4. The transformer sound vibration fault diagnosis method according to claim 3, wherein the deep Q dual-network model comprises an estimation network Eval-Net and a Target network Target-Net, and the estimation network Eval-Net and the Target network Target-Net are both multilayer perceptrons and have consistent network structures.
5. The method according to claim 4, wherein the training of the agent is performed through the training sample set, and the testing of the agent after training is performed through the testing sample set, and the specific process of obtaining the agent for diagnosing the acoustic vibration fault is as follows:
marking a fault label for each sample in the training sample set, wherein the fault labels of the samples of the same fault type are the same;
determining a reward return function of the agent based on the sample proportion of each fault label;
and training the intelligent agent through the training sample set based on the reward return function of the intelligent agent, and testing the trained intelligent agent through the test sample set to obtain the sound vibration fault diagnosis intelligent agent.
6. The transformer sound vibration fault diagnosis method according to claim 5, wherein the reward return function is:
Figure FDA0003524980180000021
wherein,
Figure FDA0003524980180000022
the number of samples of the i-th type fault label,
Figure FDA0003524980180000023
to be in a fault environment state stAction a by greedy policytNumber of samples of the corresponding trouble ticket, ltIs an environmental state stFault labels corresponding to the samples, K being the number of fault types of the transformer, each fault type corresponding to an action ai。
7. The transformer sound vibration fault diagnosis method according to claim 5, wherein the training of the agent through the training sample set comprises: and calculating the current Q value by using the estimation network Eval-Net, calculating the Target Q value by using the Target network Target-Net according to the action selected by the estimation network Eval-Net in the state at the next moment, and training the parameters in the intelligent body by using the Target Q value and the current Q value to obtain the sound vibration fault diagnosis intelligent body.
8. A transformer sound vibration fault diagnosis system is characterized by comprising:
the acquisition module is used for acquiring a sound vibration signal of the transformer to be diagnosed;
the diagnosis module is used for inputting the sound vibration signal of the transformer to be diagnosed into a sound vibration fault diagnosis intelligent agent, and performing sound vibration fault identification according to the sound vibration signal through the sound vibration fault diagnosis intelligent agent to obtain a sound vibration fault diagnosis result of the transformer to be diagnosed; the sound vibration fault diagnosis intelligent agent is obtained by training sound vibration signal samples in a deep reinforcement learning mode.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the transformer vibro-acoustic fault diagnosis method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the steps of the transformer sound vibration fault diagnosis method according to any one of claims 1 to 7.
CN202210192886.9A 2022-02-28 2022-02-28 Transformer sound vibration fault diagnosis method, system, equipment and storage medium Pending CN114580474A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210192886.9A CN114580474A (en) 2022-02-28 2022-02-28 Transformer sound vibration fault diagnosis method, system, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210192886.9A CN114580474A (en) 2022-02-28 2022-02-28 Transformer sound vibration fault diagnosis method, system, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114580474A true CN114580474A (en) 2022-06-03

Family

ID=81776383

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210192886.9A Pending CN114580474A (en) 2022-02-28 2022-02-28 Transformer sound vibration fault diagnosis method, system, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114580474A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115392293A (en) * 2022-08-01 2022-11-25 中国南方电网有限责任公司超高压输电公司昆明局 Transformer fault monitoring method and device, computer equipment and storage medium

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115392293A (en) * 2022-08-01 2022-11-25 中国南方电网有限责任公司超高压输电公司昆明局 Transformer fault monitoring method and device, computer equipment and storage medium

Similar Documents

Publication Publication Date Title
CN109976998B (en) Software defect prediction method and device and electronic equipment
CN111813657B (en) Software system quality assessment method and device
CN111174370A (en) Fault detection method and device, storage medium and electronic device
CN113743661A (en) Method, system, equipment and storage medium for predicting online capacity of lithium ion battery
CN114662386A (en) Bearing fault diagnosis method and system
CN111191696A (en) Deep learning algorithm-based steel bar layering method and system
CN116089870A (en) Industrial equipment fault prediction method and device based on meta-learning under small sample condition
CN114580474A (en) Transformer sound vibration fault diagnosis method, system, equipment and storage medium
Qamruzzaman et al. Revisiting the nexus between financial development, foreign direct investment and economic growth of Bangladesh: Evidence from symmetric and asymmetric investigation
CN117034143A (en) Distributed system fault diagnosis method and device based on machine learning
CN104077524B (en) Training method and viruses indentification method and device for viruses indentification
CN108595312A (en) A kind of automatic performance method and device of modelling customer behavior
CN111783242A (en) RVM-KF-based rolling bearing residual life prediction method and device
CN109359803B (en) Reliability evaluation method and device
CN117574238A (en) High-frequency electric appliance identification model construction method and system based on multi-gate expert network
CN114841553A (en) Fault diagnosis method, system, equipment and storage medium for generator rotating rectifier
CN113671386B (en) Method and device for analyzing durability of hydrogen fuel cell
CN113627553B (en) Image recognition method and system for recognizing abnormal label of electric energy meter
CN113033845B (en) Construction method and device for power transmission resource co-construction and sharing
CN109581194A (en) A kind of electronic system malfunction Test Strategy dynamic creation method
CN113779391A (en) Intelligent lock unlocking recommendation method, system and device based on modeling and storage medium
CN113066580A (en) Medical score determining method and device, electronic equipment and storage medium
CN112395167A (en) Operation fault prediction method and device and electronic equipment
CN117094863B (en) Intelligent learning behavior analysis system based on intelligent learning
CN118114920B (en) Training system and method for scheduling model in fire scene

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