CN117951606B - Power equipment fault diagnosis method, system, equipment and storage medium - Google Patents
Power equipment fault diagnosis method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN117951606B CN117951606B CN202410353503.0A CN202410353503A CN117951606B CN 117951606 B CN117951606 B CN 117951606B CN 202410353503 A CN202410353503 A CN 202410353503A CN 117951606 B CN117951606 B CN 117951606B
- Authority
- CN
- China
- Prior art keywords
- power equipment
- temperature
- target power
- current moment
- spectrogram
- 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.)
- Active
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012545 processing Methods 0.000 claims abstract description 28
- 238000007637 random forest analysis Methods 0.000 claims abstract description 17
- 238000012546 transfer Methods 0.000 claims description 35
- 230000005855 radiation Effects 0.000 claims description 31
- 230000006870 function Effects 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 13
- 238000001228 spectrum Methods 0.000 claims description 10
- 238000003066 decision tree Methods 0.000 claims description 7
- 230000007613 environmental effect Effects 0.000 claims description 5
- 230000017525 heat dissipation Effects 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000005236 sound signal Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
-
- 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
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/56—Testing of electric apparatus
-
- 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
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Power Engineering (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Probability & Statistics with Applications (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a power equipment fault diagnosis method, a system, equipment and a storage medium, and belongs to the technical field of operation and maintenance of power equipment. Comprising the following steps: acquiring historical operation data of target power equipment, inputting a trained random forest model for processing, and acquiring a temperature predicted value at the next moment; performing temperature compensation on the temperature predicted value according to the running temperature of the target power equipment at the current moment, the environment temperature and the running temperature of the adjacent power equipment to obtain the running predicted temperature of the target power equipment at the next moment; judging whether a fault risk exists or not according to the operation prediction temperature and a preset fault risk early warning threshold value; if yes, acquiring a voiceprint signal of the target power equipment; acquiring a spectrogram according to the voiceprint signal; and carrying out reconstruction processing on the spectrogram, generating a reconstructed spectrogram, carrying out fault identification, and obtaining a fault identification result. The power equipment can be subjected to accurate fault diagnosis, and the efficiency is improved; the problem of current fault diagnosis real-time performance, accuracy are relatively poor is solved.
Description
Technical Field
The present invention relates to the field of operation and maintenance technologies of electrical equipment, and in particular, to a method, a system, an apparatus, and a storage medium for diagnosing a fault of an electrical equipment.
Background
The statements in this section merely relate to the background of the present disclosure and may not necessarily constitute prior art.
The power system is a basic system for supporting daily electricity, consists of power equipment with different running functions, and can be subdivided into primary equipment and secondary equipment; in the use process of the power system, equipment abnormality inevitably occurs, so that the normal operation of the power system is affected. Therefore, it is important to diagnose the failure of the power equipment.
The operation temperature of the power equipment is an visual representation of the operation state of the power equipment, such as a transformer, a generator, a power cable and the like, and extra heat is easy to generate when the power equipment fails, so that the operation temperature of the power equipment is abnormally increased, and therefore, the monitoring and the prediction of the operation temperature of the power equipment are effective means for judging whether the failure risk exists.
The number of the power equipment in the power system is numerous, the types of the power equipment are complex, the temperatures of the adjacent power equipment and the surrounding environment in the same space can also be mutually influenced, the conventional power equipment temperature prediction usually only focuses on the historical data of the power equipment to carry out fitting prediction, the accuracy of the running temperature prediction is poor, and the fault diagnosis accuracy is lowered.
In the prior art, the temperature information of the power equipment is obtained by processing image information such as infrared images or visible light images, so that a large amount of image data is generated in the daily inspection process of the power equipment, the processing flow of the image data is complicated, and the real-time performance is not strong; and the accuracy is limited by the image quality, and once the image texture is unclear, the accuracy of temperature information acquisition is affected, so that the reliability of fault diagnosis results is reduced.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides a power equipment fault diagnosis method, a system, electronic equipment and a computer readable storage medium, wherein fault diagnosis is divided into fault risk early warning and fault diagnosis, and fault diagnosis is carried out only when fault risk exists, so that data processing capacity is reduced; meanwhile, the accuracy of fault risk judgment and fault diagnosis is improved by means of temperature data and voiceprint signals.
In a first aspect, the present invention provides a method for diagnosing a fault of an electrical device;
A power equipment fault diagnosis method, comprising:
Acquiring historical operation data of the target power equipment, inputting the historical operation data into a trained random forest model for processing, and acquiring a temperature predicted value of the target power equipment at the next moment;
Acquiring the running temperature of the target power equipment at the current moment, the environment temperature at the current moment and the running temperature of the adjacent power equipment at the current moment; performing temperature compensation on a temperature predicted value of the next time of the target power equipment according to the running temperature of the target power equipment at the current time, the environment temperature at the current time and the running temperature of the adjacent power equipment at the current time to acquire the running predicted temperature of the next time of the target power equipment;
Judging whether the target power equipment has fault risks or not according to the operation prediction temperature and a preset fault risk early warning threshold value; if yes, acquiring a voiceprint signal of the target power equipment at the current moment;
acquiring a spectrogram according to the voiceprint signal; and carrying out reconstruction processing on the spectrogram, generating a reconstructed spectrogram, carrying out fault diagnosis, and obtaining a fault diagnosis result of the target power equipment.
Further, before the historical operation data is input into the trained random forest model for processing, the method further comprises the following steps:
Acquiring historical operating voltage, historical operating current, historical operating power, equipment state and corresponding historical temperature of target power equipment, and constructing a training sample set;
and training the random forest model by adopting the training sample set to obtain the random forest model comprising a plurality of decision trees.
Further, performing temperature compensation on a temperature predicted value of the target power equipment at a next time according to the operation temperature of the target power equipment at the current time, the environment temperature at the current time and the operation temperature of the adjacent power equipment at the current time, and obtaining the operation predicted temperature of the target power equipment at the next time includes:
According to the ambient temperature at the current moment and the running temperature of the target power equipment at the current moment, combining the convection heat exchange between the target power equipment and the environment to obtain a first temperature compensation value; according to the running temperature of the target power equipment at the current moment and the running temperature of the adjacent power equipment at the current moment, combining radiation heat transfer between the target power equipment and the adjacent power equipment to obtain a second temperature compensation value;
And according to the first temperature compensation value and the second temperature compensation value, combining the temperature predicted value of the next moment of the target power equipment to obtain the operation predicted temperature of the next moment of the target power equipment.
Preferably, the obtaining the first temperature compensation value according to the ambient temperature at the current time and the running temperature of the target power equipment at the current time and combining the convective heat exchange between the target power equipment and the environment specifically includes:
According to the environmental temperature at the current moment and the running temperature of the target power equipment at the current moment, the convection heat exchange quantity between the target power equipment and the environment is obtained;
according to the heat transfer area between the target power equipment and the environment, acquiring the convection heat transfer resistance between the target power equipment and the environment;
and obtaining a first temperature compensation value according to the convection heat transfer resistance and the convection heat transfer quantity.
Preferably, the obtaining the second temperature compensation value according to the operation temperature of the target power device at the current time and the operation temperature of the adjacent power device at the current time by combining radiation heat transfer between the target power device and the adjacent power device specifically includes:
According to the current running temperature of the adjacent power equipment, acquiring the radiation heat between the target power equipment and the adjacent power equipment through a heat conduction equation;
Determining radiation heat dissipation thermal resistance according to the radiation heat and the current running temperature of adjacent power equipment; and obtaining a second temperature compensation value according to the radiation heat quantity and the radiation heat radiation thermal resistance.
Further, the obtaining the spectrogram according to the voiceprint signal specifically includes:
Acquiring a short-term amplitude spectrum estimated value of the voiceprint signal according to the voiceprint signal and the window function;
based on the short-term amplitude spectrum estimation value, a spectrogram is obtained through a spectrum energy density function.
Further, the reconstructing the spectrogram, generating the reconstructed spectrogram includes:
inputting the spectrogram into a preset coding network for processing to obtain an initial code, and comparing the initial code with a stored normal operation characteristic code to obtain a similar code;
and calculating a weighted average between the initial code and the similar code, and inputting the weighted average into a decoding network to obtain a reconstructed spectrogram.
In a second aspect, the present invention provides a power equipment fault diagnosis system;
a power equipment fault diagnosis system, comprising:
A temperature prediction module configured to: acquiring historical operation data of the target power equipment, inputting the historical operation data into a trained random forest model for processing, and acquiring a temperature predicted value of the target power equipment at the next moment;
A fault early warning module configured to: acquiring the running temperature of the target power equipment at the current moment, the environment temperature at the current moment and the running temperature of the adjacent power equipment at the current moment; performing temperature compensation on a temperature predicted value of the next time of the target power equipment according to the running temperature of the target power equipment at the current time, the environment temperature at the current time and the running temperature of the adjacent power equipment at the current time to acquire the running predicted temperature of the next time of the target power equipment; acquiring a fault early warning result according to the operation prediction temperature and a preset fault risk early warning threshold value, and judging whether the power equipment has fault risk or not;
A fault diagnosis module configured to: if yes, acquiring a voiceprint signal of the target power equipment at the current moment; acquiring a spectrogram according to the voiceprint signal; and carrying out reconstruction processing on the spectrogram, generating a reconstructed spectrogram, carrying out fault diagnosis, and obtaining a fault diagnosis result.
In a third aspect, the present invention provides an electronic device;
An electronic device comprising a memory and a processor and computer instructions stored on the memory and running on the processor, which when executed by the processor, perform the steps of the above-described power device fault diagnosis method.
In a fourth aspect, the present invention provides a computer-readable storage medium;
A computer readable storage medium storing computer instructions which, when executed by a processor, perform the steps of the above-described power equipment fault diagnosis method.
Compared with the prior art, the invention has the beneficial effects that:
1. According to the technical scheme provided by the invention, the environment temperature at the current moment, the running temperature at the current moment of the adjacent power equipment, the running temperature at the current moment of the target power equipment and the historical running data of the target power equipment are combined to accurately predict the running temperature of the target power equipment at the next moment, and the accurate fault risk judgment is carried out on the target power equipment based on the accurate temperature prediction data so as to realize accurate pre-fault risk early warning.
2. According to the technical scheme provided by the invention, the information contained in the voiceprint signal is comprehensively presented through the spectrogram; meanwhile, fault diagnosis is carried out by means of the difference between the sound characteristics of the target power equipment running at the current moment and the characteristics of the equipment in normal running, fault diagnosis caused by few fault samples according to judgment basis is avoided, and the accuracy of fault diagnosis is improved.
3. According to the technical scheme provided by the invention, after the potential fault risk of the target power equipment is determined, the fault diagnosis of the target power equipment is performed, so that a large amount of data is prevented from being directly processed, and the real-time performance of the fault diagnosis is prevented from being influenced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a schematic flow chart provided in an embodiment of the present invention;
fig. 2 is a system frame diagram provided in an embodiment of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular forms also are intended to include the plural forms, and furthermore, it is to be understood that the terms "comprises" and "comprising" and any variations thereof are intended to cover non-exclusive inclusions, such as, for example, processes, methods, systems, products or devices that comprise a series of steps or units, are not necessarily limited to those steps or units that are expressly listed, but may include other steps or units that are not expressly listed or inherent to such processes, methods, products or devices.
Embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Example 1
The existing power equipment fault diagnosis method has large data processing capacity, and the accuracy and the real-time performance can not meet the operation monitoring requirement of the power equipment; therefore, the invention provides a power equipment fault diagnosis method, which is used for designing a diagnosis flow based on temperature information and sound physical signals, so that unnecessary data processing is reduced; meanwhile, the influence of the environment and the adjacent power equipment on the temperature of the target power equipment is comprehensively considered, the accurate prediction of the running temperature of the target power equipment at the next moment is carried out, and the accuracy and the instantaneity of fault diagnosis are improved.
Next, a power equipment fault diagnosis method disclosed in the present embodiment will be described in detail with reference to fig. 1. The power equipment fault diagnosis method comprises the following steps:
S1, acquiring historical operation data of the target power equipment, inputting the historical operation data into a trained random forest model for processing, and acquiring a temperature predicted value of the target power equipment at the next moment.
As one embodiment, before the historical operation data is input into the trained random forest model for processing, the method further comprises: taking the historical operating voltage, the historical operating current, the historical operating power and the equipment state of the target power equipment and the corresponding historical temperature to construct a training sample set; training a random forest model by adopting a training sample set, and obtaining a plurality of decision trees through repeated iteration and splitting, wherein each decision tree is trained through a training sample selected randomly until the training is completed.
The random forest model is an algorithm comprising a plurality of decision trees, the generalization capability of the model is improved by synthesizing output results of the plurality of decision trees, and the random forest model can be constructed through a machine learning library and model parameters such as the number of the decision trees, the maximum feature number and the like are initialized.
In this embodiment, the target power device is a generator, and the historical operating data is time series data including the historical operating parameters of the target power device, which may be expressed asThe system comprises an operation voltage, an operation current, an operation power and an equipment state of a week before the current moment, wherein the equipment state refers to the equipment aging degree and the working state of a cooling system, and is obtained through an operation and maintenance information sheet filled by operation and maintenance personnel.
Will beAnd inputting the trained random forest model, and outputting a temperature predicted value of the target power equipment at the next moment.
S2, acquiring the running temperature of the target power equipment at the current moment, the environment temperature at the current moment and the running temperature of the adjacent power equipment at the current moment; the operating temperature of the target power equipment is acquired by a temperature sensor arranged on the target power equipment, and the ambient temperature is acquired by averaging the temperatures acquired by the temperature sensors arranged at a plurality of monitoring points in an installation space.
In this embodiment, the target power device is a generator, and the adjacent power devices are devices, such as a transformer, a control cabinet, and the like, arranged around the generator. Considering that the volume of the inspection data of the power equipment is huge, and the operation temperature of the power equipment is the most visual representation of the operation state of the power equipment, in the embodiment, the fault risk of the target power equipment is judged and early-warned by means of the temperature.
And S3, performing temperature compensation on a temperature predicted value of the next time of the target power equipment according to the running temperature of the target power equipment at the current time, the environment temperature at the current time and the running temperature of the adjacent power equipment at the current time, and obtaining the running predicted temperature of the next time of the target power equipment.
In consideration of the fact that the ambient temperature and the diffusion of the running temperatures of the adjacent power equipment also affect the running temperatures of the power equipment, in the embodiment, the running temperature of the target power equipment at the current moment, the ambient temperature at the current moment and the running temperature of the adjacent power equipment at the current moment are utilized to correct the temperature predicted value of the target power equipment at the next moment, so that the accuracy of temperature prediction is improved, and the efficiency of fault risk early warning is further guaranteed.
As one embodiment, S3 specifically includes:
S301, according to the ambient temperature at the current moment and the running temperature of the target power equipment at the current moment, combining the convection heat exchange between the target power equipment and the environment to obtain a first temperature compensation value.
Specifically, firstly, according to the ambient temperature at the current moment and the running temperature of the target power equipment at the current moment, the convection heat exchange amount between the target power equipment and the surrounding environment is obtained; then, according to the heat transfer area between the target power equipment and the surrounding environment, acquiring the convection heat transfer resistance between the target power equipment and the surrounding environment; and finally, acquiring a first temperature compensation value according to the convection heat transfer resistance and the convection heat transfer quantity.
Illustratively, the amount of convective heat transfer is expressed as:
，
Wherein, Indicating the amount of convective heat transfer between the target power device and the environment,Representing a convective heat transfer coefficient between the target power device and the environment; s is the heat transfer area; For the current time of operation temperature of the target power device, Is the ambient temperature at the current moment, p isE is the subscript ofIs a corner mark of (2).
The convective heat transfer resistance is expressed as:
，
the first temperature compensation value is expressed as:
。
S302, acquiring radiation heat between the target power equipment and the adjacent power equipment through a heat conduction equation according to the current running temperature of the adjacent power equipment; determining radiation heat dissipation thermal resistance according to the radiation heat, the running temperature of the target power equipment at the current moment and the running temperature of the adjacent power equipment at the current moment; and obtaining a second temperature compensation value according to the radiation heat and the radiation heat radiation thermal resistance.
Illustratively, radiant heat is expressed as:
，
Wherein, For surface emissivity, σ is the Stefan-Boltzmann constant, B is the radiating surface area, T o is the operating temperature of the adjacent power equipment, and o is the subscript of T o.
The radiation heat dissipation resistance is expressed as:
。
The second temperature compensation value is expressed as:
。
S303, acquiring an operation prediction temperature of the target power equipment at the next moment according to the first temperature compensation value and the second temperature compensation value; wherein, the operation prediction temperature is expressed as follows:
，
In the method, in the process of the invention, And the predicted value is the temperature of the target power equipment at the next moment.
In this embodiment, considering the actual application scenario, the first temperature compensation value and the second temperature compensation value may be positive values or negative values.
S4, if the operation prediction temperature of the target power equipment at the next moment is greater than a preset fault risk early warning threshold value, executing S5; and if the operation prediction temperature of the target power equipment at the next moment is smaller than the preset fault early warning threshold value, executing S1.
In the embodiment, the fault diagnosis is performed only after the fault risk early warning of the target power equipment occurs, so that the data processing volume in the fault diagnosis is reduced, and the influence of normal operation data on the fault diagnosis is avoided.
S5, acquiring a voiceprint signal of the target power equipment at the current moment, and acquiring a spectrogram according to the voiceprint signal. The horizontal coordinate of the spectrogram represents time, the vertical axis represents frequency, the color represents the mildness of sound under a certain frequency and time, and the frequency composition and the sound energy information of the sound in the time dimension can be comprehensively displayed.
As one embodiment, a short-term amplitude spectrum estimation value of the voiceprint signal is obtained according to the voiceprint signal and a window function; based on the short-term amplitude spectrum estimate, a spectrogram can be drawn by a spectral energy density function.
Illustratively, the voiceprint signal is assumed to beThe calculation formula of the spectrogram is expressed as follows:
，
，
，1≤k≤P，
，
Wherein, To that obtained after windowingA frame sound signal is provided which is a frame sound signal,For the window function, P is the number of points of the fourier transform,Is angular frequency; Is that Short-term amplitude spectrum estimates of (a); The spectral energy density function is time, is a non-negative real matrix, n is the abscissa of the spectrogram, represents time, k is the ordinate of the spectrogram, and represents frequency, and each pixel position (n, k) color on the spectrogram reflects the signal energy density at the moment of time n and the frequency k.
S6, reconstructing the spectrogram, generating a reconstructed spectrogram, performing fault diagnosis, and obtaining a fault diagnosis result.
Since the volume of the sound signal data is small when the power equipment fails, the network model cannot learn the characteristics thereof sufficiently, and therefore, in the embodiment, the failure recognition is performed based on the acoustic characteristics in the normal operation state of the power equipment.
As one embodiment, S6 specifically includes:
S601, inputting the spectrogram into a preset coding network for processing, obtaining an initial code, comparing the initial code with a stored normal operation characteristic code, screening similar codes from the normal operation characteristic code, and calculating a weighted average between the initial code and the similar codes to be used as the spectrogram code.
In this embodiment, the preset encoding network is a convolutional neural network, after the spectrogram is input into the convolutional neural network, the convolutional neural network gradually compresses the dimension of the spectrogram through multi-layer convolution processing and extracts key features, and an implicit vector is output, namely the initial encoding.
The normal operation feature codes are pre-stored spectrogram coding data of the power equipment when the power equipment is normal in operation during training of the automatic encoder; in this embodiment, in order to highlight the information of normal operation of the device contained in the spectrogram, similar codes are screened out by comparison in the normal operation feature codes and weighted average is performed with the initial codes.
The method for screening similar codes by comparison in the normal feature codes comprises the following steps: and calculating cosine similarity between the initial code and all stored normal operation feature codes, and taking the normal operation feature code with the maximum cosine similarity with the initial code as a similar code.
Illustratively, cosine similarity is expressed as:
，
The spectrogram code is expressed as:
,
In the method, in the process of the invention, For the initial encoding purposes,For a similar code to be used,As a first weight parameter,As a second weight parameter, the first weight parameter,And is also provided withAnd further, the normal operation characteristics of the equipment contained in the prominent spectrogram are ensured, and the real characteristics of the equipment are not lost.
S602, inputting the spectrogram codes into a decoding network to obtain a reconstructed spectrogram.
In this embodiment, the decoding network is a decoder, and the reconstructed spectrogram is obtained by recovering the spectrogram from the weighted average between the initial encoding and the similar encoding by the decoder.
S603, calculating an operation deviation value between the spectrogram and the reconstructed spectrogram through a mean square error function, and judging whether faults occur or not according to the operation deviation value and an alarm threshold value. And when the running deviation value is larger than the alarm threshold value, judging that the fault occurs, wherein the alarm threshold value is set by an operation and maintenance person according to the maximum running deviation value obtained by the model training experiment.
Because the original spectrogram and the nearest information of the normal operation feature codes are contained in the reconstructed spectrogram, the information of the original spectrogram deviating from the normal operation state can be obtained by calculating the mean square error function between the spectrogram and the reconstructed spectrogram, and whether the operation of the target power equipment is abnormal or not can be judged.
Wherein the running deviation value is expressed as:
,
Wherein, Is a graph of the speech spectrum,And reconstructing the spectrogram.
Example two
In connection with fig. 2, the present embodiment discloses a power equipment fault diagnosis system, including:
A temperature prediction module configured to: acquiring the running temperature of the target power equipment at the current moment, the environment temperature at the current moment and the running temperature of the adjacent power equipment at the current moment;
a fault early warning module configured to: performing temperature compensation on the running temperature of the current moment of the target power equipment according to the running temperature of the current moment of the target power equipment, the environment temperature of the current moment and the running temperature of the current moment of the adjacent power equipment, and obtaining the running predicted temperature of the next moment of the target power equipment; acquiring a fault early warning result according to the operation prediction temperature and a preset fault risk early warning threshold value, and judging whether the target power equipment has fault risk or not;
A fault diagnosis module configured to: if yes, acquiring a voiceprint signal of the target power equipment at the current moment; acquiring a spectrogram according to the voiceprint signal; and carrying out reconstruction processing on the spectrogram, generating a reconstructed spectrogram, carrying out fault identification, and obtaining a fault diagnosis result of the target power equipment.
It should be noted that, the temperature prediction module, the fault early warning module, and the fault diagnosis module correspond to the steps in the first embodiment, and the modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure in the first embodiment. It should be noted that the modules described above may be implemented as part of a system in a computer system, such as a set of computer-executable instructions.
Example III
An electronic device according to a third embodiment of the present invention includes a memory, a processor, and computer instructions stored in the memory and running on the processor, where the steps of the above-described power device fault diagnosis method are completed when the computer instructions are run by the processor.
Example IV
A fourth embodiment of the present invention provides a computer readable storage medium storing computer instructions that, when executed by a processor, complete the steps of the above-described power equipment fault diagnosis method.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing embodiments are directed to various embodiments, and details of one embodiment may be found in the related description of another embodiment.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. A power equipment fault diagnosis method, characterized by comprising:
Acquiring historical operation data of the target power equipment, inputting the historical operation data into a trained random forest model for processing, and acquiring a temperature predicted value of the target power equipment at the next moment;
Acquiring the running temperature of the target power equipment at the current moment, the environment temperature at the current moment and the running temperature of the adjacent power equipment at the current moment; performing temperature compensation on a temperature predicted value of the next time of the target power equipment according to the running temperature of the target power equipment at the current time, the environment temperature at the current time and the running temperature of the adjacent power equipment at the current time to acquire the running predicted temperature of the next time of the target power equipment; the method specifically comprises the following steps: according to the ambient temperature at the current moment and the running temperature of the target power equipment at the current moment, combining the convection heat exchange between the target power equipment and the environment to obtain a first temperature compensation value;
according to the running temperature of the target power equipment at the current moment and the running temperature of the adjacent power equipment at the current moment, combining radiation heat transfer between the target power equipment and the adjacent power equipment to obtain a second temperature compensation value;
According to the first temperature compensation value and the second temperature compensation value, combining a temperature predicted value of the next moment of the target power equipment to obtain an operation predicted temperature of the next moment of the target power equipment;
the method for obtaining the first temperature compensation value by combining the convection heat exchange between the target power equipment and the environment according to the environmental temperature at the current moment and the running temperature of the target power equipment at the current moment specifically comprises the following steps:
according to the environmental temperature at the current moment and the running temperature of the target power equipment at the current moment, the convection heat exchange quantity between the target power equipment and the environment is obtained; the convective heat transfer is expressed as:
，
Wherein, Indicating the amount of convective heat transfer between the target power device and the environment,Representing a convective heat transfer coefficient between the target power device and the environment; s is the heat transfer area; For the current time of operation temperature of the target power device, Is the ambient temperature at the current moment, p isE is the subscript ofIs a corner mark of (2);
According to the heat transfer area between the target power equipment and the environment, acquiring the convection heat transfer resistance between the target power equipment and the environment; expressed as:
；
acquiring a first temperature compensation value according to the convection heat transfer resistance and the convection heat transfer quantity; expressed as:
；
According to the operation temperature of the target power equipment at the current moment and the operation temperature of the adjacent power equipment at the current moment, combining the radiation heat transfer between the target power equipment and the adjacent power equipment to obtain a second temperature compensation value specifically comprises:
According to the current running temperature of the adjacent power equipment, acquiring the radiation heat between the target power equipment and the adjacent power equipment through a heat conduction equation; expressed as:
，
Wherein, For surface emissivity, σ is the Stefan-Boltzmann constant, B is the radiating surface area, T o is the operating temperature of the adjacent power equipment, o is the subscript of T o;
determining radiation heat dissipation thermal resistance according to the radiation heat and the current running temperature of adjacent power equipment; expressed as:
；
Acquiring a second temperature compensation value according to the radiation heat and the radiation heat radiation thermal resistance; expressed as:
；
Judging whether the target power equipment has fault risks or not according to the operation prediction temperature and a preset fault risk early warning threshold value; if yes, acquiring a voiceprint signal of the target power equipment at the current moment;
acquiring a spectrogram according to the voiceprint signal; reconstructing the spectrogram to generate a reconstructed spectrogram, and performing fault identification to obtain a fault diagnosis result of the target power equipment; the reconstructing the spectrogram to generate a reconstructed spectrogram specifically comprises:
inputting the spectrogram into a preset coding network for processing to obtain an initial code, and comparing the initial code with a stored normal operation characteristic code to obtain a similar code;
Calculating a weighted average between the initial code and the similar code, and inputting the weighted average into a decoding network to obtain a reconstructed spectrogram;
And calculating an operation deviation value between the spectrogram and the reconstructed spectrogram through a mean square error function, and judging whether a fault occurs according to the operation deviation value and an alarm threshold value.
2. The power equipment fault diagnosis method as claimed in claim 1, further comprising, before inputting the historical operation data into the trained random forest model for processing:
Acquiring historical operating voltage, historical operating current, historical operating power, equipment state and corresponding historical temperature of target power equipment, and constructing a training sample set;
And training the random forest model by adopting the training sample set to obtain a trained random forest model comprising a plurality of decision trees.
3. The method for diagnosing a fault in an electrical device according to claim 1, wherein the obtaining a spectrogram from the voiceprint signal comprises:
Acquiring a short-term amplitude spectrum estimated value of the voiceprint signal according to the voiceprint signal and the window function;
based on the short-term amplitude spectrum estimation value, a spectrogram is obtained through a spectrum energy density function.
4. A power equipment fault diagnosis system, characterized by comprising:
A temperature prediction module configured to: acquiring historical operation data of the target power equipment, inputting the historical operation data into a trained random forest model for processing, and acquiring a temperature predicted value of the target power equipment at the next moment;
A fault early warning module configured to: acquiring the running temperature of the target power equipment at the current moment, the environment temperature at the current moment and the running temperature of the adjacent power equipment at the current moment; performing temperature compensation on a temperature predicted value of the next time of the target power equipment according to the running temperature of the target power equipment at the current time, the environment temperature at the current time and the running temperature of the adjacent power equipment at the current time to acquire the running predicted temperature of the next time of the target power equipment; judging whether the target power equipment has fault risks or not according to the operation prediction temperature and a preset fault risk early warning threshold value;
The method specifically comprises the following steps: according to the ambient temperature at the current moment and the running temperature of the target power equipment at the current moment, combining the convection heat exchange between the target power equipment and the environment to obtain a first temperature compensation value;
according to the running temperature of the target power equipment at the current moment and the running temperature of the adjacent power equipment at the current moment, combining radiation heat transfer between the target power equipment and the adjacent power equipment to obtain a second temperature compensation value;
According to the first temperature compensation value and the second temperature compensation value, combining a temperature predicted value of the next moment of the target power equipment to obtain an operation predicted temperature of the next moment of the target power equipment;
the method for obtaining the first temperature compensation value by combining the convection heat exchange between the target power equipment and the environment according to the environmental temperature at the current moment and the running temperature of the target power equipment at the current moment specifically comprises the following steps:
according to the environmental temperature at the current moment and the running temperature of the target power equipment at the current moment, the convection heat exchange quantity between the target power equipment and the environment is obtained; the convective heat transfer is expressed as:
，
Wherein, Indicating the amount of convective heat transfer between the target power device and the environment,Representing a convective heat transfer coefficient between the target power device and the environment; s is the heat transfer area; For the current time of operation temperature of the target power device, Is the ambient temperature at the current moment, p isE is the subscript ofIs a corner mark of (2);
According to the heat transfer area between the target power equipment and the environment, acquiring the convection heat transfer resistance between the target power equipment and the environment; expressed as:
；
acquiring a first temperature compensation value according to the convection heat transfer resistance and the convection heat transfer quantity; expressed as:
；
According to the operation temperature of the target power equipment at the current moment and the operation temperature of the adjacent power equipment at the current moment, combining the radiation heat transfer between the target power equipment and the adjacent power equipment to obtain a second temperature compensation value specifically comprises:
According to the current running temperature of the adjacent power equipment, acquiring the radiation heat between the target power equipment and the adjacent power equipment through a heat conduction equation; expressed as:
，
Wherein, For surface emissivity, σ is the Stefan-Boltzmann constant, B is the radiating surface area, T o is the operating temperature of the adjacent power equipment, o is the subscript of T o;
determining radiation heat dissipation thermal resistance according to the radiation heat and the current running temperature of adjacent power equipment; expressed as:
；
Acquiring a second temperature compensation value according to the radiation heat and the radiation heat radiation thermal resistance; expressed as:
；
A fault diagnosis module configured to: if yes, acquiring a voiceprint signal of the target power equipment at the current moment; acquiring a spectrogram according to the voiceprint signal; reconstructing the spectrogram, generating a reconstructed spectrogram, performing fault identification, and obtaining a fault identification result; the reconstructing the spectrogram to generate a reconstructed spectrogram specifically comprises:
inputting the spectrogram into a preset coding network for processing to obtain an initial code, and comparing the initial code with a stored normal operation characteristic code to obtain a similar code;
Calculating a weighted average between the initial code and the similar code, and inputting the weighted average into a decoding network to obtain a reconstructed spectrogram;
And calculating an operation deviation value between the spectrogram and the reconstructed spectrogram through a mean square error function, and judging whether a fault occurs according to the operation deviation value and an alarm threshold value.
5. An electronic device comprising a memory and a processor, and computer instructions stored on the memory and running on the processor, which when executed by the processor, perform the power device fault diagnosis method of any one of claims 1-3.
6. A computer readable storage medium storing computer instructions which, when executed by a processor, perform the power equipment fault diagnosis method of any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410353503.0A CN117951606B (en) | 2024-03-27 | 2024-03-27 | Power equipment fault diagnosis method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410353503.0A CN117951606B (en) | 2024-03-27 | 2024-03-27 | Power equipment fault diagnosis method, system, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117951606A CN117951606A (en) | 2024-04-30 |
| CN117951606B true CN117951606B (en) | 2024-07-19 |
Family
ID=90792460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410353503.0A Active CN117951606B (en) | 2024-03-27 | 2024-03-27 | Power equipment fault diagnosis method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117951606B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118518397A (en) * | 2024-07-22 | 2024-08-20 | 国网江西省电力有限公司电力科学研究院 | Intelligent diagnosis method and system for copper alloy material continuous casting production line |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114400019A (en) * | 2021-12-31 | 2022-04-26 | 深圳市声扬科技有限公司 | Model generation method, abnormality detection device, and electronic apparatus |
| CN116415931A (en) * | 2023-03-14 | 2023-07-11 | 成都电通能源有限公司 | Big data-based power equipment operation state monitoring method and system |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100236506B1 (en) * | 1990-11-29 | 2000-01-15 | 퍼킨-엘머시터스인스트루먼츠 | Apparatus for polymerase chain reaction |
| JP4389744B2 (en) * | 2004-10-05 | 2009-12-24 | 株式会社明電舎 | Temperature compensation method for communication control equipment |
| CN105045966A (en) * | 2015-06-29 | 2015-11-11 | 上海电机学院 | Hybrid calculation method for inner temperature field of transformer |
| US10684634B1 (en) * | 2019-01-30 | 2020-06-16 | Quanta Computer Inc. | Method and system for compensating for temperature rise effects |
| CN112183647B (en) * | 2020-09-30 | 2024-07-26 | 国网山西省电力公司大同供电公司 | Method for detecting and positioning sound faults of substation equipment based on deep learning |
| CN117705121A (en) * | 2023-12-15 | 2024-03-15 | 大唐武定新能源有限责任公司 | Multi-dimensional inspection system for power plant |
-
2024
- 2024-03-27 CN CN202410353503.0A patent/CN117951606B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114400019A (en) * | 2021-12-31 | 2022-04-26 | 深圳市声扬科技有限公司 | Model generation method, abnormality detection device, and electronic apparatus |
| CN116415931A (en) * | 2023-03-14 | 2023-07-11 | 成都电通能源有限公司 | Big data-based power equipment operation state monitoring method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117951606A (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117951606B (en) | Power equipment fault diagnosis method, system, equipment and storage medium | |
| US10729382B2 (en) | Methods and systems to predict a state of the machine using time series data of the machine | |
| CN110426415A (en) | Based on thermal fault detection method inside depth convolutional neural networks and the oil-immersed transformer of image segmentation | |
| CN110017901B (en) | Infrared spectrum diagnosis method for operating state of electrical equipment in power system | |
| CN106504122B (en) | Fault monitoring method and system of ring main unit based on neighborhood preserving embedding algorithm | |
| CN113033011B (en) | Ship mechanical health state assessment method and system | |
| JP6543028B2 (en) | Apparatus and method for diagnosing abnormality | |
| CN117407679B (en) | Data acquisition method and system of intelligent end screen sensor | |
| CN109886337B (en) | Depth measurement learning method and system based on self-adaptive sampling | |
| CN115908407B (en) | Power equipment defect detection method and device based on infrared image temperature value | |
| CN117783769B (en) | Power distribution network fault positioning method, system, equipment and storage medium based on visual platform | |
| CN116341272A (en) | Construction safety risk management and control system for digital distribution network engineering | |
| CN117056814B (en) | Transformer voiceprint vibration fault diagnosis method | |
| CN115329986A (en) | Wind turbine generator anomaly detection and positioning method based on interpretable graph neural network | |
| CN114155212B (en) | Method and device for detecting abnormal insulators of transformer substation based on infrared images | |
| CN117371207A (en) | Extra-high voltage converter valve state evaluation method, medium and system | |
| CN116363075A (en) | Photovoltaic module hot spot detection method and system and electronic equipment | |
| CN117576724A (en) | Unmanned plane bird detection method, system, equipment and medium | |
| CN118224552A (en) | Outdoor pipeline heat preservation effect monitoring system in job site | |
| CN114157023A (en) | Distribution transformer early warning information acquisition method | |
| JP2020016527A (en) | Method of investigating stationary gas detection device installation site | |
| CN117456637A (en) | Vehicle data detection method, vehicle data detection device, vehicle, and storage medium | |
| CN115100592B (en) | Method and device for identifying hidden danger of external damage of power transmission channel and storage medium | |
| CN116559713A (en) | Intelligent monitoring method and device for power supply of communication base station | |
| CN114050650B (en) | Intelligent pole tower based on power transmission line area autonomous system architecture |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |