CN114239932A - Transformer life prediction method and device, computer equipment and storage medium - Google Patents

Transformer life prediction method and device, computer equipment and storage medium Download PDF

Info

Publication number
CN114239932A
CN114239932A CN202111458661.5A CN202111458661A CN114239932A CN 114239932 A CN114239932 A CN 114239932A CN 202111458661 A CN202111458661 A CN 202111458661A CN 114239932 A CN114239932 A CN 114239932A
Authority
CN
China
Prior art keywords
transformer
parameter information
dynamic parameter
predicted
operating data
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
CN202111458661.5A
Other languages
Chinese (zh)
Inventor
李鹏
姚钪
胡冉
伍炜卫
黄湛华
陈仁泽
樊小鹏
田兵
王志明
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.)
Southern Power Grid Digital Grid Research Institute Co Ltd
Original Assignee
Shenzhen Power Supply Co ltd
Southern Power Grid Digital Grid Research Institute 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 Shenzhen Power Supply Co ltd, Southern Power Grid Digital Grid Research Institute Co Ltd filed Critical Shenzhen Power Supply Co ltd
Priority to CN202111458661.5A priority Critical patent/CN114239932A/en
Publication of CN114239932A publication Critical patent/CN114239932A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/21Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • G06F18/241Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/044Recurrent networks, e.g. Hopfield networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • G06N3/084Backpropagation, e.g. using gradient descent
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067Enterprise or organisation modelling
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/20Administration of product repair or maintenance
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06Energy or water supply

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Development Economics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Educational Administration (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

The method inputs dynamic parameter information of a transformer to be predicted into a feature recognition model to be recognized to obtain dynamic parameter features of the transformer to be predicted, fuses the dynamic parameter features and static parameter information of the transformer to be predicted and inputs the fused dynamic parameter features and the static parameter information into a life prediction model to obtain a life prediction result of the transformer to be predicted. According to the transformer life prediction method, the transformer life prediction device, the computer equipment, the storage medium and the computer program product, the current life state and the residual life length of the transformer to be predicted can be estimated and obtained through the dynamic parameter information and the static parameter information of the transformer to be predicted, which influence the transformer life, and the pre-trained feature recognition model and the life prediction model, so that reliable and accurate technical support is provided for the state overhaul of the transformer.

Description

Transformer life prediction method and device, computer equipment and storage medium
Technical Field
The present application relates to the field of transformer technologies, and in particular, to a method, an apparatus, a computer device, a storage medium, and a computer program product for predicting a life of a transformer.
Background
In recent years, with the rapid development of economy in China, the electricity demand of society is on the trend of increasing year by year, and when a transformer is taken as an important voltage conversion device in a power system and fails, huge economic loss can be brought, so that the transformer needs to be effectively maintained to improve the stability and the economy of the operation of the power system. At present, the normal service life of an oil-immersed transformer is about 20 to 25 years, and in order to prolong the service life of the transformer to about 40 years, the operational reliability and the residual service life of the transformer need to be researched, so that the operational reliability of the transformer is improved, and the service life of the transformer is effectively prolonged.
Conventional oil-immersed transformer maintenance methods include post-repair and periodic repair methods. The after-event maintenance method is to inspect and maintain the equipment after the electric power equipment has an accident, and the maintenance mode belongs to the after-event compensation property, and can not meet the operation requirement gradually along with the improvement of the operation requirement of the electric power equipment. The regular maintenance method comprises the steps of making a fixed maintenance period based on the running condition of the equipment, and then stopping running and maintaining the power equipment according to the period, wherein the regular maintenance method can effectively prevent the occurrence of accidents of the power equipment, but the actual running condition of the power equipment cannot be effectively considered when the machine executes the preset maintenance period, and the preset maintenance period tends to be conservative in order to ensure the safe running of the power equipment as much as possible; as a result, there may be situations of inefficient shutdown or excessive maintenance, and even more serious, frequent maintenance of the electrical equipment may result in a greatly shortened life span.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a computer device, a computer readable storage medium, and a computer program product for predicting the remaining life of a transformer, which can accurately and reliably predict the remaining life of the transformer.
In a first aspect, the present application provides a method for predicting a life of a transformer, the method including:
acquiring dynamic parameter information of a transformer to be predicted, wherein the dynamic parameter information is data of real-time operation parameters influencing the service life of the transformer;
inputting the dynamic parameter information into a feature recognition model, recognizing to obtain the dynamic parameter features of the transformer to be predicted, and training the feature recognition model by using historical operating data of the transformer;
and fusing the dynamic parameter characteristics and the static parameter information of the transformer to be predicted, and inputting the fused dynamic parameter characteristics and the static parameter information into a life prediction model to obtain a life prediction result of the transformer to be predicted, wherein the static parameter information is data of transformer attribute parameters influencing the life of the transformer, and the life prediction model is obtained by utilizing historical operation data of the transformer for training.
In one embodiment, the method comprises the steps of acquiring dynamic parameter information of a transformer to be predicted, wherein the dynamic parameter information comprises the steps of acquiring original operation parameters influencing the service life of the transformer in the real-time operation process of the transformer to be predicted; and carrying out data cleaning on the acquired original operation parameters by using a noise reduction network to obtain dynamic parameter information, wherein the noise reduction network is obtained by using historical operation data of the transformer based on noise reduction self-encoder training.
In one embodiment, inputting the dynamic parameter information into the feature recognition model to recognize and obtain the dynamic parameter features of the transformer to be predicted, includes: performing discrete Fourier transform processing on the dynamic parameter information to obtain corresponding two-dimensional frequency spectrum image information; inputting the two-dimensional frequency spectrum image information corresponding to each piece of dynamic parameter information into a feature recognition model; and performing inverse Fourier transform processing on the output result of the feature identification model to obtain the dynamic parameter features.
In one embodiment, the method further comprises: training by using historical operating data, corresponding to a health factor 1 and a health factor 0, of historical operating data of the transformer in different life states to obtain a support vector machine neural network, wherein the historical operating data corresponding to the health factor 1 is historical operating data of the transformer in a health state, the historical operating data corresponding to the health factor 0 is historical operating data of the transformer in a failure state, and each set of historical operating data comprises dynamic parameter information and static parameter information of the transformer in operation in a corresponding life state; inputting the rest historical operating data into a trained support vector machine neural network to obtain health factors corresponding to the historical operating data within the range of 0-1; and training by utilizing all historical operating data and the corresponding health factors to obtain a life prediction model, wherein the output result of the life prediction model is the health factor, and the larger the health factor is, the longer the residual life of the transformer indicated by the corresponding life prediction result is.
In one embodiment, the life prediction model is obtained by training all historical operating data and the corresponding health factors, and the method includes: inputting the dynamic parameter information in each group of historical operating data into a trained feature recognition model, and outputting corresponding dynamic parameter features; and taking the static parameter information in each group of historical operating data and the dynamic parameter characteristics identified by the dynamic parameter information as input, taking the health factors of the historical operating data as output, and training based on a BP neural network to obtain a life prediction model.
In one embodiment, the dynamic parameter information includes at least one of transformer insulation winding hot spot temperature, transformer load voltage, transformer load current and transformer magnetic flux, and the static parameter information includes at least one of transformer insulation paper moisture content, transformer oil water-soluble acid content and transformer oil acidity value.
In a second aspect, the present application further provides a device for predicting a life of a transformer, the device including:
the parameter acquisition module is used for acquiring dynamic parameter information of the transformer to be predicted, wherein the dynamic parameter information is a real-time operation parameter influencing the service life of the transformer;
the fault feature extraction module is used for inputting the dynamic parameter information into the feature recognition model to be recognized to obtain the dynamic parameter features of the transformer to be predicted, and the feature recognition model is obtained by training the historical operation data of the transformer;
and the service life prediction module is used for fusing the dynamic parameter characteristics and the static parameter information of the transformer to be predicted and inputting the fused dynamic parameter characteristics and the static parameter information into the service life prediction model to obtain a service life prediction result of the transformer to be predicted, the static parameter information is a transformer attribute parameter influencing the service life of the transformer, and the service life prediction model is obtained by training the historical operation data of the transformer.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the transformer life prediction method provided by the first aspect when executing the computer program.
In a fourth aspect, the present application further provides a computer-readable storage medium. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the transformer life prediction method provided by the first aspect.
In a fifth aspect, the present application further provides a computer program product. A computer program product comprising a computer program which, when executed by a processor, carries out the steps of the transformer life prediction method provided by the first aspect.
According to the transformer life prediction method, the transformer life prediction device, the computer equipment, the storage medium and the computer program product, the current life state and the residual life length of the transformer to be predicted can be estimated and obtained through the dynamic parameter information and the static parameter information of the transformer to be predicted, which influence the transformer life, and the pre-trained feature recognition model and the life prediction model, so that reliable and accurate technical support is provided for the state overhaul of the transformer.
The method fully considers various parameters influencing the service life of the transformer to carry out model training and detection, has accurate and comprehensive prediction results, and overcomes the limitation caused by only using partial parameters.
Drawings
Fig. 1 is a schematic flowchart of a transformer life prediction method according to an embodiment.
FIG. 2 is a flow diagram illustrating step 102 in one embodiment.
FIG. 3 is a flowchart illustrating step 104 according to an embodiment.
FIG. 4 is a schematic flow chart of another embodiment.
Fig. 5 is a block diagram of a transformer life prediction apparatus according to an embodiment.
Fig. 6 is a block diagram of a transformer life prediction device in another embodiment.
FIG. 7 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In an embodiment, as shown in fig. 1, a transformer life prediction method is provided, and this embodiment is exemplified by applying the method to a terminal, and it is to be understood that the method may also be applied to a server, and may also be applied to a system including the terminal and the server, and is implemented by interaction between the terminal and the server. The method comprises the following steps:
and 102, acquiring dynamic parameter information of the transformer to be predicted.
The dynamic parameter information is data of real-time operation parameters influencing the service life of the transformer, is data which can change continuously in the real-time operation process of the transformer, and can be acquired through various sensors or detection circuits. Optionally, the dynamic parameter information includes at least one of a transformer insulation winding hot spot temperature, a transformer load voltage, a transformer load current, and a transformer magnetic flux, and for prediction accuracy and comprehensiveness, all of these types of data are included.
And 104, inputting the dynamic parameter information into the feature recognition model to recognize to obtain the dynamic parameter features of the transformer to be predicted.
The characteristic recognition model is obtained by training the historical operation data of the transformer.
And 106, fusing the dynamic parameter characteristics and the static parameter information of the transformer to be predicted, and inputting the fused dynamic parameter characteristics and the static parameter information into the service life prediction model to obtain a service life prediction result of the transformer to be predicted. And the service life prediction result is used for indicating the residual service life of the transformer to be predicted, and the service life prediction model is obtained by training the historical operation data of the transformer.
The static parameter information is data of transformer attribute parameters influencing the service life of the transformer, is data which is basically stable and unchangeable in the real-time operation process of the transformer, or is data which is basically stable and unchangeable within a preset time span, and can be acquired in the daily regular maintenance process. Optionally, the static parameter information includes at least one of a water content of the transformer insulation paper, a water-soluble acid component in the transformer oil, and an oil value of the transformer, and generally all of these types of data are included for prediction accuracy and comprehensiveness.
According to the transformer life prediction method, the life state of the transformer to be predicted can be estimated and obtained by the aid of the pre-trained feature recognition model and the life prediction model through dynamic parameter information and static parameter information of the transformer to be predicted, and reliable and accurate technical support is provided for state maintenance of the transformer.
Considering that noise is easily introduced by the external environment or the error of the sensor itself when acquiring the parameter information of the transformer to be predicted, in order to reduce the noise effect, in one embodiment, as shown in fig. 2, the step 102 includes:
step 202, collecting original operation parameters affecting the service life of the transformer in the real-time operation process of the transformer to be predicted, wherein the original operation data are data of the same information type of the dynamic parameter information in the step 102, and are data which are originally collected by the dynamic parameter information and possibly contain noise.
And 204, utilizing a noise reduction network to perform data cleaning on the acquired original operation parameters to obtain the dynamic parameter information of the step 102. The noise reduction network is obtained by utilizing historical operation data of the transformer based on noise reduction self-encoder training.
Similarly, optionally, the static parameter information of the transformer to be predicted in step 106 is also information obtained after data cleaning is performed by using the noise reduction network.
In one embodiment, before using the noise reduction network, step 203 is further included to train the noise reduction network using the historical operating data of the transformer. In one embodiment, when data cleaning needs to be performed on original data of dynamic parameter information and static parameter information of a transformer to be predicted, each set of historical operation data of the transformer for training the noise reduction network includes the dynamic parameter information and the static parameter information in the historical operation process of the transformer, where the historical operation data is generally statistical data of the transformer of the same model as the transformer to be predicted. In other embodiments, because the static parameter information of the transformer to be predicted is relatively stable and has small noise, and the dynamic parameter information has large fluctuation and large noise, only the original operation data of the dynamic parameter information can be subjected to data cleaning, and each group of historical operation data used for training the noise reduction network includes the dynamic parameter information of the transformer operating in the corresponding life state, and does not need to include the static parameter information.
The noise reduction network is obtained based on the training of the noise reduction self-encoder, the network learning rate epsilon is set, and the network parameters of the noise reduction self-encoder are initialized randomly, wherein the network parameters comprise a connection weight W and an offset b. Setting batch training number, iteration number and the like in a forward propagation algorithm, executing the forward propagation algorithm, and calculating the average activation amount rho of any hidden layer neuron jjThe cost function is calculated using the output of the noise reduction autoencoder as:
Figure BDA0003387355960000071
wherein x (i) is the input historical operating data, y (i) is the data from x (i) to the hidden layer via the input layer, hW,b(x (i)) is y (i) is a signal which is decoded by the hidden layer and output to the output layer, i is a parameter and represents a group of historical operating data, and n is the total number of groups of input historical operating data. β is a weight coefficient controlling the penalty term, s2 is the number of neurons of the hidden layer, j is a parameter and represents one neuron, ρ represents a sparsity parameter, and KL () is a relative entropy function.
And executing a back propagation algorithm, and updating the network parameters W and b of the noise reduction self-encoder by using a cost function according to the following formula:
Figure BDA0003387355960000072
Figure BDA0003387355960000073
in one embodiment, the feature recognition model is obtained based on convolutional neural network training, and in order to be suitable for the data type of the feature recognition model, in one embodiment, as shown in fig. 3, the step 104 includes the following steps:
and 302, performing discrete Fourier transform processing on the dynamic parameter information to obtain corresponding two-dimensional frequency spectrum image information. The obtained dynamic parameter information is one-dimensional data information containing a plurality of data points, and any dynamic parameter information containing N data points can be represented as
Figure BDA0003387355960000081
xnRepresenting any nth data point, the discrete Fourier transform processing is carried out on the dynamic parameter information to represent that
Figure BDA0003387355960000082
And step 304, inputting the two-dimensional frequency spectrum image information corresponding to each piece of dynamic parameter information into the trained feature recognition model.
And step 306, performing inverse Fourier transform processing on the output result of the feature identification model to obtain the dynamic parameter features. For any output result Y [ k ]]The inverse Fourier transform processing is expressed as
Figure BDA0003387355960000083
The dynamic parameter characteristic which can obtain a one-dimensional data information form and comprises M data points is expressed as
Figure BDA0003387355960000084
In one embodiment, before using the feature recognition model, step 303 is further included, the feature recognition model is obtained by training with historical operating data of the transformer. The historical operation data of the transformer used for training the feature recognition model comprises dynamic parameter information in the historical operation process of the transformer. The characteristic recognition model is obtained based on convolutional neural network training, the convolutional neural network comprises an input layer and a hidden layer, the hidden layer comprises a convolutional layer, an excitation function and a pooling layer, and the processing process is similar to the processing process of the dynamic parameter information of the transformer to be predicted. Because the convolutional neural network learns by using a gradient descent algorithm, and the input of the convolutional neural network needs to be standardized, after the historical operation data of the transformer is processed into two-dimensional frequency spectrum image information, normalization processing is firstly carried out, the original pixel values distributed in [0, 255] are normalized to the [0, 1] interval, and then the normalized pixel values are input into the convolutional neural network for training, and the standardization of the input data is beneficial to improving the learning efficiency and performance of the convolutional neural network. Optionally, as described in step 102 above, if the dynamic parameter information includes a plurality of different types of data, a multi-channel convolutional neural network is constructed and used for training to obtain the feature recognition model.
In one embodiment, before using the life prediction model in step 106, the method further includes the step of training the life prediction model, as shown in fig. 4:
and step 402, training by using historical operation data corresponding to the health factor 1 and the health factor 0 in the historical operation data of the transformer in different life states to obtain a support vector machine neural network.
The life states of the transformer include a healthy state, a failed state, and various intermediate states between the healthy state and the failed state. The historical operation data corresponding to the health factor 1 is historical operation data of the transformer in a healthy state, and the historical operation data corresponding to the health factor 0 is historical operation data of the transformer in a failure state.
The insulation paper of the oil-immersed transformer is one of the weakest components in the transformer, the operation life of the transformer is usually mainly determined by the chemical life of the insulation paper, and the most direct characteristic parameter of the insulation paper aging is the polymerization degree, so that optionally, the polymerization degree of the insulation paper is used for measuring the life state of the transformer, the state of the transformer when the polymerization degree of the insulation paper reaches a first preset threshold is determined as a healthy state, and the state corresponds to a health factor 1, for example, the value of the first preset threshold is within the range of 1000-1200. And determining the state of the transformer when the polymerization degree of the insulating paper is lower than a second preset threshold as a failure state, wherein the state corresponds to a health factor 0, and for example, the second preset threshold is a value in the range of 250-300.
Each group of historical operating data comprises dynamic parameter information and static parameter information when the transformer operates in a corresponding service life state, and the specific parameter meanings of the dynamic parameter information and the static parameter information are introduced as above.
Specifically, when the support vector machine neural network is obtained through training, historical operating data corresponding to the health factor 1 and the health factor 0 are proportionally divided into a training set and a testing set for training and testing, namely the historical operating data in various intermediate states are not used in the step. Specifically, the method comprises the following steps:
setting batch training number, iteration times and the like in a forward propagation algorithm, inputting training set data into a support vector machine neural network, executing the forward propagation algorithm, and calculating a cost function by using the output of the support vector machine neural network as follows:
Figure BDA0003387355960000101
where g (i) is the historical operating data input, HW,b(g (i)) is the output of g (i) after being input into the neural network of the support vector machine, q (i) is the health factor of g (i), and P is the total group number of the input historical operating data.
Adopting a stochastic gradient descent algorithm to execute back propagation calculation, and updating network parameters W and b of the support vector machine neural network by using a cost function according to the following formula:
Figure BDA0003387355960000102
Figure BDA0003387355960000103
and step 404, inputting the rest historical operating data into the trained support vector machine neural network to obtain health factors corresponding to the historical operating data within the range of 0-1, namely to obtain the health factors corresponding to the historical operating data when the transformer is in other various intermediate states.
And 406, training by using all historical operating data and the corresponding health factors to obtain a life prediction model, wherein the output result of the life prediction model is the health factor, and the larger the health factor is, the longer the residual life of the transformer indicated by the corresponding life prediction result is. The method comprises the following steps:
step 406a, inputting the dynamic parameter information in each group of historical operating data into the trained feature recognition model, and outputting the corresponding dynamic parameter features, which is specifically similar to the processing flow of step 302-306, and the second search is not performed any more in this embodiment.
And 406b, taking the static parameter information in each group of historical operating data and the dynamic parameter characteristics obtained by identifying the dynamic parameter information as input, taking the health factors of the historical operating data as output, and training on the basis of a BP neural network to obtain a life prediction model.
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the application also provides a transformer life prediction device for realizing the transformer life prediction method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so specific limitations in one or more embodiments of the transformer life prediction device provided below can be referred to the limitations on the transformer life prediction method in the foregoing, and details are not repeated herein.
In one embodiment, as shown in fig. 5, there is provided a transformer life prediction apparatus, including: a parameter acquisition module 510, a fault feature extraction module 520, and a life prediction module 530, wherein:
the parameter obtaining module 510 is configured to obtain dynamic parameter information of the transformer to be predicted, where the dynamic parameter information is a real-time operation parameter that affects the life of the transformer.
And the fault feature extraction module 520 is configured to input the dynamic parameter information into a feature recognition model, and recognize the dynamic parameter information to obtain a dynamic parameter feature of the transformer to be predicted, where the feature recognition model is obtained by training the historical operating data of the transformer.
And the service life prediction module 530 is used for fusing the dynamic parameter characteristics and the static parameter information of the transformer to be predicted and inputting the fused dynamic parameter characteristics and the static parameter information into the service life prediction model to obtain a service life prediction result of the transformer to be predicted, wherein the static parameter information is a transformer attribute parameter influencing the service life of the transformer, and the service life prediction model is obtained by training the historical operation data of the transformer.
In one embodiment, referring to fig. 6, the parameter obtaining module 510 includes a data collecting unit 511 and a data cleaning unit 512:
and the data acquisition unit 511 is used for acquiring original operation parameters influencing the service life of the transformer in the real-time operation process of the transformer to be predicted.
And the data cleaning unit 512 is configured to perform data cleaning on the acquired original operating parameters by using a noise reduction network to obtain dynamic parameter information, wherein the noise reduction network is obtained by using historical operating data of the transformer based on noise reduction self-encoder training.
In one embodiment, referring to fig. 6, the fault feature extraction module 520 includes a first transformation unit 521, an identification unit 522 and a second transformation unit 523.
First transforming section 521 is configured to perform discrete fourier transform processing on the dynamic parameter information into corresponding two-dimensional spectrum image information.
And an identifying unit 522, configured to input the two-dimensional spectrum image information corresponding to each piece of dynamic parameter information into the feature identification model.
The second transforming unit 523 is configured to perform inverse fourier transform processing on the output result of the feature identification model to obtain the dynamic parameter feature.
In one embodiment, the apparatus for predicting the life of a transformer further comprises a life prediction model training module 540, wherein the life prediction model training module 540 comprises:
and a first training unit 541, configured to train, by using historical operation data corresponding to the health factor 1 and the health factor 0 in historical operation data of the transformer in different life states, to obtain a support vector machine neural network. The historical operation data corresponding to the health factor 1 is historical operation data of the transformer in a healthy state, the historical operation data corresponding to the health factor 0 is historical operation data of the transformer in a failure state, and each set of historical operation data comprises dynamic parameter information and static parameter information of the transformer in operation in a corresponding service life state.
And the health factor acquisition unit 542 is configured to input the rest of the historical operating data into the trained support vector machine neural network, and obtain a health factor corresponding to each historical operating data within a range of 0 to 1.
The second training unit 543 is used for training all historical operating data and the corresponding health factors to obtain the life prediction model, the output result of the life prediction model is the health factor, and the larger the health factor is, the longer the remaining life of the transformer indicated by the corresponding life prediction result is.
In an embodiment, the second training unit 543 is further configured to input the dynamic parameter information in each set of historical operating data into the trained feature recognition model, and output a corresponding dynamic parameter feature. And taking the static parameter information in each group of historical operating data and the dynamic parameter characteristics identified by the dynamic parameter information as input, taking the health factors of the historical operating data as output, and training based on a BP neural network to obtain a life prediction model.
The modules in the transformer life prediction device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing the acquired dynamic parameter information of the transformer to be predicted, the acquired static parameter information of the transformer to be predicted, and a feature recognition model, a service life prediction model and a noise reduction network which are obtained by pre-training. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of predicting a life of a transformer.
Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring dynamic parameter information of a transformer to be predicted, wherein the dynamic parameter information is data of real-time operation parameters influencing the service life of the transformer;
inputting the dynamic parameter information into a feature recognition model, recognizing to obtain the dynamic parameter features of the transformer to be predicted, and training the feature recognition model by using historical operating data of the transformer;
and fusing the dynamic parameter characteristics and the static parameter information of the transformer to be predicted, and inputting the fused dynamic parameter characteristics and the static parameter information into a life prediction model to obtain a life prediction result of the transformer to be predicted, wherein the static parameter information is data of transformer attribute parameters influencing the life of the transformer, and the life prediction model is obtained by utilizing historical operation data of the transformer for training.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring original operation parameters influencing the service life of the transformer in the real-time operation process of the transformer to be predicted; and carrying out data cleaning on the acquired original operation parameters by using a noise reduction network to obtain dynamic parameter information, wherein the noise reduction network is obtained by using historical operation data of the transformer based on noise reduction self-encoder training.
In one embodiment, the processor, when executing the computer program, further performs the steps of: performing discrete Fourier transform processing on the dynamic parameter information to obtain corresponding two-dimensional frequency spectrum image information; inputting the two-dimensional frequency spectrum image information corresponding to each piece of dynamic parameter information into a feature recognition model; and performing inverse Fourier transform processing on the output result of the feature identification model to obtain the dynamic parameter features.
In one embodiment, the processor, when executing the computer program, further performs the steps of: training by using historical operating data, corresponding to a health factor 1 and a health factor 0, of historical operating data of the transformer in different life states to obtain a support vector machine neural network, wherein the historical operating data corresponding to the health factor 1 is historical operating data of the transformer in a health state, the historical operating data corresponding to the health factor 0 is historical operating data of the transformer in a failure state, and each set of historical operating data comprises dynamic parameter information and static parameter information of the transformer in operation in a corresponding life state; inputting the rest historical operating data into a trained support vector machine neural network to obtain health factors corresponding to the historical operating data within the range of 0-1; and training by utilizing all historical operating data and the corresponding health factors to obtain a life prediction model, wherein the output result of the life prediction model is the health factor, and the larger the health factor is, the longer the residual life of the transformer indicated by the corresponding life prediction result is.
In one embodiment, the processor, when executing the computer program, further performs the steps of: inputting the dynamic parameter information in each group of historical operating data into a trained feature recognition model, and outputting corresponding dynamic parameter features; and taking the static parameter information in each group of historical operating data and the dynamic parameter characteristics identified by the dynamic parameter information as input, taking the health factors of the historical operating data as output, and training based on a BP neural network to obtain a life prediction model.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring dynamic parameter information of a transformer to be predicted, wherein the dynamic parameter information is data of real-time operation parameters influencing the service life of the transformer;
inputting the dynamic parameter information into a feature recognition model, recognizing to obtain the dynamic parameter features of the transformer to be predicted, and training the feature recognition model by using historical operating data of the transformer;
and fusing the dynamic parameter characteristics and the static parameter information of the transformer to be predicted, and inputting the fused dynamic parameter characteristics and the static parameter information into a life prediction model to obtain a life prediction result of the transformer to be predicted, wherein the static parameter information is data of transformer attribute parameters influencing the life of the transformer, and the life prediction model is obtained by utilizing historical operation data of the transformer for training.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring original operation parameters influencing the service life of the transformer in the real-time operation process of the transformer to be predicted; and carrying out data cleaning on the acquired original operation parameters by using a noise reduction network to obtain dynamic parameter information, wherein the noise reduction network is obtained by using historical operation data of the transformer based on noise reduction self-encoder training.
In one embodiment, the computer program when executed by the processor further performs the steps of: performing discrete Fourier transform processing on the dynamic parameter information to obtain corresponding two-dimensional frequency spectrum image information; inputting the two-dimensional frequency spectrum image information corresponding to each piece of dynamic parameter information into a feature recognition model; and performing inverse Fourier transform processing on the output result of the feature identification model to obtain the dynamic parameter features.
In one embodiment, the computer program when executed by the processor further performs the steps of: training by using historical operating data, corresponding to a health factor 1 and a health factor 0, of historical operating data of the transformer in different life states to obtain a support vector machine neural network, wherein the historical operating data corresponding to the health factor 1 is historical operating data of the transformer in a health state, the historical operating data corresponding to the health factor 0 is historical operating data of the transformer in a failure state, and each set of historical operating data comprises dynamic parameter information and static parameter information of the transformer in operation in a corresponding life state; inputting the rest historical operating data into a trained support vector machine neural network to obtain health factors corresponding to the historical operating data within the range of 0-1; and training by utilizing all historical operating data and the corresponding health factors to obtain a life prediction model, wherein the output result of the life prediction model is the health factor, and the larger the health factor is, the longer the residual life of the transformer indicated by the corresponding life prediction result is.
In one embodiment, the computer program when executed by the processor further performs the steps of: inputting the dynamic parameter information in each group of historical operating data into a trained feature recognition model, and outputting corresponding dynamic parameter features; and taking the static parameter information in each group of historical operating data and the dynamic parameter characteristics identified by the dynamic parameter information as input, taking the health factors of the historical operating data as output, and training based on a BP neural network to obtain a life prediction model.
In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, performs the steps of:
acquiring dynamic parameter information of a transformer to be predicted, wherein the dynamic parameter information is data of real-time operation parameters influencing the service life of the transformer;
inputting the dynamic parameter information into a feature recognition model, recognizing to obtain the dynamic parameter features of the transformer to be predicted, and training the feature recognition model by using historical operating data of the transformer;
and fusing the dynamic parameter characteristics and the static parameter information of the transformer to be predicted, and inputting the fused dynamic parameter characteristics and the static parameter information into a life prediction model to obtain a life prediction result of the transformer to be predicted, wherein the static parameter information is data of transformer attribute parameters influencing the life of the transformer, and the life prediction model is obtained by utilizing historical operation data of the transformer for training.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring original operation parameters influencing the service life of the transformer in the real-time operation process of the transformer to be predicted; and carrying out data cleaning on the acquired original operation parameters by using a noise reduction network to obtain dynamic parameter information, wherein the noise reduction network is obtained by using historical operation data of the transformer based on noise reduction self-encoder training.
In one embodiment, the computer program when executed by the processor further performs the steps of: performing discrete Fourier transform processing on the dynamic parameter information to obtain corresponding two-dimensional frequency spectrum image information; inputting the two-dimensional frequency spectrum image information corresponding to each piece of dynamic parameter information into a feature recognition model; and performing inverse Fourier transform processing on the output result of the feature identification model to obtain the dynamic parameter features.
In one embodiment, the computer program when executed by the processor further performs the steps of: training by using historical operating data, corresponding to a health factor 1 and a health factor 0, of historical operating data of the transformer in different life states to obtain a support vector machine neural network, wherein the historical operating data corresponding to the health factor 1 is historical operating data of the transformer in a health state, the historical operating data corresponding to the health factor 0 is historical operating data of the transformer in a failure state, and each set of historical operating data comprises dynamic parameter information and static parameter information of the transformer in operation in a corresponding life state; inputting the rest historical operating data into a trained support vector machine neural network to obtain health factors corresponding to the historical operating data within the range of 0-1; and training by utilizing all historical operating data and the corresponding health factors to obtain a life prediction model, wherein the output result of the life prediction model is the health factor, and the larger the health factor is, the longer the residual life of the transformer indicated by the corresponding life prediction result is.
In one embodiment, the computer program when executed by the processor further performs the steps of: inputting the dynamic parameter information in each group of historical operating data into a trained feature recognition model, and outputting corresponding dynamic parameter features; and taking the static parameter information in each group of historical operating data and the dynamic parameter characteristics identified by the dynamic parameter information as input, taking the health factors of the historical operating data as output, and training based on a BP neural network to obtain a life prediction model.
It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims (10)

1. A method for predicting a life of a transformer, the method comprising:
acquiring dynamic parameter information of a transformer to be predicted, wherein the dynamic parameter information is data of real-time operation parameters influencing the service life of the transformer;
inputting the dynamic parameter information into a feature recognition model, and recognizing to obtain the dynamic parameter features of the transformer to be predicted, wherein the feature recognition model is obtained by training by using historical operating data of the transformer;
and fusing the dynamic parameter characteristics and the static parameter information of the transformer to be predicted, and inputting the fused dynamic parameter characteristics and the static parameter information into a service life prediction model to obtain a service life prediction result of the transformer to be predicted, wherein the static parameter information is data of transformer attribute parameters influencing the service life of the transformer, and the service life prediction model is obtained by training the historical operation data of the transformer.
2. The method according to claim 1, wherein the obtaining of the dynamic parameter information of the transformer to be predicted comprises:
acquiring original operation parameters influencing the service life of the transformer in the real-time operation process of the transformer to be predicted;
and carrying out data cleaning on the acquired original operation parameters by using a noise reduction network to obtain the dynamic parameter information, wherein the noise reduction network is obtained by using historical operation data of the transformer based on noise reduction self-encoder training.
3. The method according to claim 1, wherein the inputting the dynamic parameter information into a feature recognition model to recognize the dynamic parameter features of the transformer to be predicted comprises:
performing discrete Fourier transform processing on the dynamic parameter information to obtain corresponding two-dimensional frequency spectrum image information;
inputting two-dimensional frequency spectrum image information corresponding to each piece of dynamic parameter information into the feature identification model;
and performing inverse Fourier transform processing on the output result of the feature identification model to obtain the dynamic parameter features.
4. The method of claim 1, further comprising:
training by using historical operating data, corresponding to a health factor 1 and a health factor 0, of historical operating data of the transformer in different life states to obtain a support vector machine neural network, wherein the historical operating data corresponding to the health factor 1 is historical operating data of the transformer in a health state, the historical operating data corresponding to the health factor 0 is historical operating data of the transformer in a failure state, and each set of historical operating data comprises dynamic parameter information and static parameter information of the transformer in operation in a corresponding life state;
inputting the rest historical operating data into a trained support vector machine neural network to obtain health factors corresponding to the historical operating data within the range of 0-1;
and training by utilizing all historical operating data and the corresponding health factors to obtain the life prediction model, wherein the output result of the life prediction model is the health factor, and the larger the health factor is, the longer the residual life of the transformer indicated by the corresponding life prediction result is.
5. The method of claim 4, wherein the training with all historical operating data and their respective health factors to obtain the life prediction model comprises:
inputting the dynamic parameter information in each group of historical operating data into the trained feature recognition model, and outputting corresponding dynamic parameter features;
and taking the static parameter information in each group of historical operating data and the dynamic parameter characteristics obtained by identifying the dynamic parameter information as input, taking the health factors of the historical operating data as output, and training on the basis of a BP neural network to obtain the service life prediction model.
6. The method of claim 1,
the dynamic parameter information comprises at least one of the temperature of a hot spot of an insulating winding of the transformer, the load voltage of the transformer, the load current of the transformer and the magnetic flux of the transformer, and the static parameter information comprises at least one of the water content of insulating paper of the transformer, the water-soluble acid component in oil of the transformer and the oleic acid value of the transformer.
7. A transformer life prediction apparatus, characterized in that the apparatus comprises:
the parameter acquisition module is used for acquiring dynamic parameter information of the transformer to be predicted, wherein the dynamic parameter information is a real-time operation parameter influencing the service life of the transformer;
the fault feature extraction module is used for inputting the dynamic parameter information into a feature recognition model for recognition to obtain the dynamic parameter features of the transformer to be predicted, and the feature recognition model is obtained by training through historical operating data of the transformer;
and the service life prediction module is used for fusing the dynamic parameter characteristics and the static parameter information of the transformer to be predicted and inputting the fused dynamic parameter characteristics and the static parameter information into a service life prediction model to obtain a service life prediction result of the transformer to be predicted, wherein the static parameter information is a transformer attribute parameter influencing the service life of the transformer, and the service life prediction model is obtained by training the historical operation data of the transformer.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.
CN202111458661.5A 2021-12-01 2021-12-01 Transformer life prediction method and device, computer equipment and storage medium Pending CN114239932A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111458661.5A CN114239932A (en) 2021-12-01 2021-12-01 Transformer life prediction method and device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111458661.5A CN114239932A (en) 2021-12-01 2021-12-01 Transformer life prediction method and device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114239932A true CN114239932A (en) 2022-03-25

Family

ID=80752753

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111458661.5A Pending CN114239932A (en) 2021-12-01 2021-12-01 Transformer life prediction method and device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114239932A (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106199305A (en) * 2016-07-01 2016-12-07 太原理工大学 Underground coal mine electric power system dry-type transformer insulation health state evaluation method
TW201721479A (en) * 2015-12-07 2017-06-16 財團法人工業技術研究院 System and method for predicting remaining useful life of component of semiconductor equipment
CN110781592A (en) * 2019-10-25 2020-02-11 中国人民解放军火箭军工程大学 Method and system for predicting residual life of equipment
KR102178787B1 (en) * 2018-10-17 2020-11-13 고려대학교 산학협력단 Deep learning based analysis method and device for remaining useful lifetime of equipment or parts using vibration signals
CN112231975A (en) * 2020-10-13 2021-01-15 中国铁路上海局集团有限公司南京供电段 Data modeling method and system based on reliability analysis of railway power supply equipment
CN112232404A (en) * 2020-10-13 2021-01-15 中国铁路上海局集团有限公司南京供电段 Reliability calculation method and system based on historical abnormity and operation and maintenance information of railway power supply equipment
CN112257232A (en) * 2020-09-25 2021-01-22 广西大学 Life model establishing method based on ethanol in oil and transformer paper polymerization degree
CN113344295A (en) * 2021-06-29 2021-09-03 华南理工大学 Method, system and medium for predicting residual life of equipment based on industrial big data
CN113487083A (en) * 2021-07-06 2021-10-08 新智数字科技有限公司 Method and device for predicting residual service life of equipment, computer equipment and computer-readable storage medium

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW201721479A (en) * 2015-12-07 2017-06-16 財團法人工業技術研究院 System and method for predicting remaining useful life of component of semiconductor equipment
CN106199305A (en) * 2016-07-01 2016-12-07 太原理工大学 Underground coal mine electric power system dry-type transformer insulation health state evaluation method
KR102178787B1 (en) * 2018-10-17 2020-11-13 고려대학교 산학협력단 Deep learning based analysis method and device for remaining useful lifetime of equipment or parts using vibration signals
CN110781592A (en) * 2019-10-25 2020-02-11 中国人民解放军火箭军工程大学 Method and system for predicting residual life of equipment
CN112257232A (en) * 2020-09-25 2021-01-22 广西大学 Life model establishing method based on ethanol in oil and transformer paper polymerization degree
CN112231975A (en) * 2020-10-13 2021-01-15 中国铁路上海局集团有限公司南京供电段 Data modeling method and system based on reliability analysis of railway power supply equipment
CN112232404A (en) * 2020-10-13 2021-01-15 中国铁路上海局集团有限公司南京供电段 Reliability calculation method and system based on historical abnormity and operation and maintenance information of railway power supply equipment
CN113344295A (en) * 2021-06-29 2021-09-03 华南理工大学 Method, system and medium for predicting residual life of equipment based on industrial big data
CN113487083A (en) * 2021-07-06 2021-10-08 新智数字科技有限公司 Method and device for predicting residual service life of equipment, computer equipment and computer-readable storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
杜江;申畅;程法庆;王秀春;: "基于健康指数的电力变压器剩余寿命评估研究", 变压器, vol. 55, no. 10, 25 October 2018 (2018-10-25), pages 30 - 35 *
王浩州: "基于机器学习算法的变压器寿命损耗预测研究", 电气应用, vol. 40, no. 1, 15 January 2021 (2021-01-15), pages 72 - 78 *

Similar Documents

Publication Publication Date Title
JP7242101B2 (en) Engine surge failure prediction system and method based on fusion neural network model
CN111080072A (en) Distribution transformer health index evaluation method, device and system
CN112578891B (en) Uninterruptible power supply predictive maintenance method, device and storage medium
CN110334865B (en) Power equipment fault rate prediction method and system based on convolutional neural network
CN113093985B (en) Sensor data link abnormity detection method and device and computer equipment
CN113742993B (en) Method, device, equipment and storage medium for predicting life loss of dry-type transformer
CN115456306A (en) Bus load prediction method, system, equipment and storage medium
CN116663746A (en) Power load prediction method and device, computer equipment and storage medium
CN113110961B (en) Equipment abnormality detection method and device, computer equipment and readable storage medium
CN117175574A (en) Power system scheduling method, device, computer equipment and storage medium
CN113758652A (en) Converter transformer oil leakage detection method and device, computer equipment and storage medium
CN113255927A (en) Logistic regression model training method and device, computer equipment and storage medium
CN117407675A (en) Lightning arrester leakage current prediction method based on multi-variable reconstruction combined dynamic weight
CN112232570A (en) Forward active total electric quantity prediction method and device and readable storage medium
CN114239932A (en) Transformer life prediction method and device, computer equipment and storage medium
CN113887676B (en) Equipment fault early warning method, device, equipment and storage medium
CN114492636B (en) Transformer winding state signal acquisition system
CN110298490A (en) Time series Combination power load forecasting method and computer readable storage medium based on multiple regression
CN111382891B (en) Short-term load prediction method and short-term load prediction device
CN112256735A (en) Power utilization monitoring method and device, computer equipment and storage medium
CN115730506A (en) Transformer oil temperature abnormity early warning method based on information decision
CN113033414A (en) Power consumption data anomaly detection method and device, computer equipment and storage medium
CN113393102A (en) Distribution transformer operation state trend prediction method based on data driving
Kazemi et al. A multi-level artificial neural network for gasoline demand forecasting of Iran
Shi et al. Data augmentation to improve the performance of ensemble learning for system failure prediction with limited observations

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information

Country or region after: China

Address after: 518021 power dispatching communication building, 4020 Shennan East Road, Luohu District, Shenzhen City, Guangdong Province

Applicant after: Shenzhen Power Supply Co.,Ltd.

Applicant after: Southern Power Grid Digital Grid Research Institute Co.,Ltd.

Address before: 518021 power dispatching communication building, 4020 Shennan East Road, Luohu District, Shenzhen City, Guangdong Province

Applicant before: Shenzhen Power Supply Co.,Ltd.

Country or region before: China

Applicant before: Southern Power Grid Digital Grid Research Institute Co.,Ltd.

CB02 Change of applicant information
TA01 Transfer of patent application right

Effective date of registration: 20240312

Address after: Room 86, room 406, No.1, Yichuang street, Zhongxin Guangzhou Knowledge City, Huangpu District, Guangzhou City, Guangdong Province

Applicant after: Southern Power Grid Digital Grid Research Institute Co.,Ltd.

Country or region after: China

Address before: 518021 power dispatching communication building, 4020 Shennan East Road, Luohu District, Shenzhen City, Guangdong Province

Applicant before: Shenzhen Power Supply Co.,Ltd.

Country or region before: China

Applicant before: Southern Power Grid Digital Grid Research Institute Co.,Ltd.

TA01 Transfer of patent application right