CN117131419A - Intelligent distribution network equipment fault type identification method and system based on data analysis - Google Patents
Intelligent distribution network equipment fault type identification method and system based on data analysis Download PDFInfo
- Publication number
- CN117131419A CN117131419A CN202311089712.0A CN202311089712A CN117131419A CN 117131419 A CN117131419 A CN 117131419A CN 202311089712 A CN202311089712 A CN 202311089712A CN 117131419 A CN117131419 A CN 117131419A
- Authority
- CN
- China
- Prior art keywords
- machine learning
- learning model
- sample library
- data
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000007405 data analysis Methods 0.000 title claims abstract description 31
- 238000010801 machine learning Methods 0.000 claims abstract description 184
- 238000012549 training Methods 0.000 claims abstract description 79
- 238000012360 testing method Methods 0.000 claims abstract description 38
- 238000013135 deep learning Methods 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims description 53
- 210000002569 neuron Anatomy 0.000 claims description 28
- 238000006243 chemical reaction Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 14
- 210000002364 input neuron Anatomy 0.000 claims description 12
- 230000001537 neural effect Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 102100025142 Beta-microseminoprotein Human genes 0.000 claims description 8
- 101000576812 Homo sapiens Beta-microseminoprotein Proteins 0.000 claims description 8
- 210000004218 nerve net Anatomy 0.000 claims description 8
- 210000004205 output neuron Anatomy 0.000 claims description 8
- 238000001228 spectrum Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 210000005036 nerve Anatomy 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000000593 degrading effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000007 visual 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
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Neurology (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Debugging And Monitoring (AREA)
Abstract
The application discloses a fault type identification method and system for intelligent distribution network equipment based on data analysis, belonging to the field of intelligent distribution network equipment, wherein the method comprises the following steps: collecting fault data of different types of intelligent distribution network equipment; extracting features from the fault data; constructing a first equipment failure sample library and a second equipment failure sample library, preprocessing the characteristics in the first equipment failure sample library and the second equipment failure sample library, and dividing the preprocessed characteristics into a training set and a testing set; constructing a first machine learning model and a second machine learning model based on deep learning, and obtaining corresponding classification labels through training a training set and predicting a testing set; judging whether the machine learning model needs to be retrained according to the classification label output by the first machine learning model and the classification label output by the second machine learning model, outputting the fault type of the intelligent distribution network equipment when the machine learning model does not need to be retrained, and otherwise retrained the machine learning model.
Description
Technical Field
The application relates to the field of intelligent distribution network equipment, in particular to a fault type identification method and system for intelligent distribution network equipment based on data analysis.
Background
At present, a plurality of fault identification methods of intelligent distribution network equipment exist, most of the fault identification methods are used for identifying faults of the intelligent distribution network equipment through self-checking of the equipment (such as equipment short circuit, abnormal power consumption of the equipment and the like), and more visual monitoring is used for degrading one or more functions of the equipment which can be discovered by a user when the equipment is used. These fault monitoring methods of devices have their advantages, but cannot be used at certain moments, and the accuracy of such methods is low, and periodic detection of intelligent distribution network devices cannot be achieved. How to realize the identification of the fault type based on the data of the equipment is a calculation problem to be solved in the prior art.
Therefore, there is a need for a method and a system for identifying fault types of intelligent distribution network equipment based on data analysis.
Disclosure of Invention
The application mainly aims to provide a fault type identification method and system for intelligent distribution network equipment based on data analysis, which at least solve the problem of how to realize fault type identification based on data of the intelligent distribution network equipment in the prior art.
In order to achieve the above object, according to one aspect of the present application, there is provided a method for identifying a fault type of an intelligent distribution network device based on data analysis, including:
collecting fault data of different types of intelligent distribution network equipment, wherein the fault data comprise ultrahigh frequency signal data and ultrasonic signal data;
extracting features from the fault data;
constructing a first equipment fault sample library and a second equipment fault sample library, wherein the first equipment fault sample library is used for storing ultrahigh frequency signal data and corresponding features, and the second equipment fault sample library is used for storing ultrasonic signal data and corresponding features; preprocessing the characteristics in the first equipment failure sample library and the second equipment failure sample library;
dividing the preprocessed features in the first equipment failure sample library and the second equipment failure sample library into a training set and a testing set according to a preset proportion, and respectively constructing the training set and the testing set;
constructing a first machine learning model and a second machine learning model based on deep learning; training a first machine learning model through a training set of a first equipment failure sample library, and training a second machine learning model through a training set of a second equipment failure sample library;
after training is completed, inputting a test set of a first equipment failure sample library into a first machine learning model, outputting a corresponding classification label by the first machine learning model, inputting a test set of a second equipment failure sample library into a second machine learning model, and outputting a corresponding classification label by the second machine learning model;
judging whether the machine learning model needs to be retrained according to the classification label output by the first machine learning model and the classification label output by the second machine learning model, outputting the fault type of the intelligent distribution network equipment when the machine learning model does not need to be retrained, and otherwise retrained the machine learning model.
Optionally, extracting features from the fault data includes: PRPS spectrum features are extracted from the ultrahigh frequency signal data, and Mel spectrum features are extracted from the ultrasonic signal data.
Optionally, the PRPS profile features include at least: skewness, kurtosis, peak count, and cross-correlation factor.
Optionally, preprocessing the features in the obtained first equipment failure sample library and the second equipment failure sample library, including:
deleting invalid data, repeated data, processing missing values and abnormal values of the first equipment failure sample library and the second equipment failure sample library;
and adding labels to fault data of the first equipment fault sample library and the second equipment fault sample library, wherein the labels are set target fault categories.
Optionally, collecting the uhf signal data includes: and collecting the partial discharge ultrahigh frequency signal image of the intelligent distribution network equipment, and preprocessing the partial discharge ultrahigh frequency signal image to obtain ultrahigh frequency signal data.
Optionally, the method for constructing the first machine learning model and the second machine learning model based on deep learning is the same, and constructing the first machine learning model based on deep learning includes:
constructing a plurality of input neurons for receiving an input, one of said input neurons for receiving an input;
constructing a plurality of task generating neurons for generating data processing tasks, wherein each input neuron is connected with all task generating neurons, each task generating neuron independently works, and one task generating neuron generates one data processing task;
a conversion neural layer for converting data processing tasks is constructed, each task generating neuron is connected with the conversion neural layer, and the conversion neural layer is used for receiving more than one data processing task at the same time and converting the received data processing tasks into a plurality of internal subtasks according to a preset rule;
constructing a subtask processing layer communicated with the conversion nerve layer, wherein the subtask processing layer comprises more than one subtask processing nerve net, and each subtask processing nerve net only processes one subtask;
and constructing an output neuron, wherein the output neuron is connected with each subtask processing neuron, and is used for acquiring the data output of each subtask processing neuron in real time and converting the data output into final output according to a preset rule.
Optionally, the condition for determining whether the machine learning model needs to be retrained is: judging whether the classification labels output by the first machine learning model and the second machine learning model are consistent, and when the classification labels are consistent, retraining the machine learning model is not needed; and otherwise, retraining the machine learning model.
According to still another aspect of the present application, there is also provided an intelligent distribution network equipment fault type identification system based on data analysis, including:
the data acquisition module is used for acquiring fault data of different types of intelligent distribution network equipment, wherein the fault data comprises ultrahigh frequency signal data and ultrasonic signal data;
the feature extraction module is used for extracting features from the fault data;
the equipment fault sample library module is used for constructing a first equipment fault sample library and a second equipment fault sample library, wherein the first equipment fault sample library is used for storing ultrahigh frequency signal data and corresponding characteristics, and the second equipment fault sample library is used for storing ultrasonic signal data and corresponding characteristics; preprocessing the characteristics in the first equipment failure sample library and the second equipment failure sample library;
the data classification module is used for dividing the preprocessed features in the first equipment fault sample library and the second equipment fault sample library into a training set and a testing set according to a preset proportion, and respectively constructing the training set and the testing set;
a machine learning model module for constructing a first machine learning model and a second machine learning model based on deep learning; training a first machine learning model through a training set of a first equipment failure sample library, and training a second machine learning model through a training set of a second equipment failure sample library; after training is completed, inputting a test set of a first equipment failure sample library into a first machine learning model, outputting a corresponding classification label by the first machine learning model, inputting a test set of a second equipment failure sample library into a second machine learning model, and outputting a corresponding classification label by the second machine learning model;
the fault type identification module is used for judging whether the machine learning model needs to be retrained according to the classification label output by the first machine learning model and the classification label output by the second machine learning model, outputting the fault type of the intelligent distribution network equipment when the machine learning model does not need to be retrained, and otherwise retrained the machine learning model.
According to an aspect of the present application, there is provided a computer readable storage medium, wherein the computer readable storage medium includes a stored program, and when the program runs, the device in which the computer readable storage medium is controlled to execute any one of the method for identifying a failure type of an intelligent distribution network device based on data analysis.
According to yet another aspect of the present application, an electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute any one of the intelligent distribution network equipment fault type identification methods based on data analysis by using the computer program.
Compared with the prior art, the application has the following beneficial effects:
1. according to the method provided by the application, the fault type is identified by collecting the parameters of the equipment and fully mining the characteristics in the parameter data to construct the learning model, so that compared with the prior art, the accuracy and reliability of identification are obviously improved, and the periodic detection of the equipment can be realized.
2. The learning model is utilized to have the attribute of self-learning capability, and when the number of collected samples reaches a certain degree or the detection period reaches a certain stage, the parameters of the learning model can be better perfected, so that the detection accuracy is ensured.
Drawings
In order to more clearly illustrate the technical solutions of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawing in the description below is only one embodiment of the present application, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for identifying fault types of intelligent distribution network equipment based on data analysis according to an embodiment of the application;
fig. 2 is a schematic diagram of an intelligent distribution network equipment fault type identification system based on data analysis according to an embodiment of the present application.
Detailed Description
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus, article, or device that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or device.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.
Fig. 1 is a flowchart of a fault type identification method of an intelligent distribution network device based on data analysis according to an embodiment of the present application, as shown in fig. 1, the method includes the following steps:
step S1, collecting fault data of different types of intelligent distribution network equipment, wherein the fault data comprise ultrahigh frequency signal data and ultrasonic signal data;
s2, extracting features from the fault data;
s3, constructing a first equipment fault sample library and a second equipment fault sample library, wherein the first equipment fault sample library is used for storing ultrahigh frequency signal data and corresponding features, and the second equipment fault sample library is used for storing ultrasonic signal data and corresponding features; preprocessing the characteristics in the first equipment failure sample library and the second equipment failure sample library;
s4, dividing the preprocessed features in the first equipment fault sample library and the second equipment fault sample library into a training set and a testing set according to a preset proportion, and respectively constructing the training set and the testing set;
s5, constructing a first machine learning model and a second machine learning model based on deep learning; training a first machine learning model through a training set of a first equipment failure sample library, and training a second machine learning model through a training set of a second equipment failure sample library;
s6, after training is completed, inputting a test set of a first equipment failure sample library into a first machine learning model, outputting a corresponding classification label by the first machine learning model, inputting a test set of a second equipment failure sample library into a second machine learning model, and outputting a corresponding classification label by the second machine learning model;
and S7, judging whether the machine learning model needs to be retrained according to the classification label output by the first machine learning model and the classification label output by the second machine learning model, outputting the fault type of the intelligent distribution network equipment when the machine learning model does not need to be retrained, and otherwise retrained the machine learning model.
In the embodiment, the step S1 of collecting the uhf signal data includes: and collecting the partial discharge ultrahigh frequency signal image of the intelligent distribution network equipment, and preprocessing the partial discharge ultrahigh frequency signal image to obtain ultrahigh frequency signal data.
In the illustrated embodiment, step S2 of extracting features from fault data includes: PRPS spectrum features are extracted from the ultrahigh frequency signal data, and Mel spectrum features are extracted from the ultrasonic signal data.
Wherein the PRPS profile features include at least: skewness Sk, ku, peak count Pe, and cross-correlation factor Cc.
In the embodiment, the method for constructing the first machine learning model and the second machine learning model based on deep learning in step S3 is the same, and the constructing the first machine learning model based on deep learning includes:
constructing a plurality of input neurons for receiving an input, one of said input neurons for receiving an input;
constructing a plurality of task generating neurons for generating data processing tasks, wherein each input neuron is connected with all task generating neurons, each task generating neuron independently works, and one task generating neuron generates one data processing task;
a conversion neural layer for converting data processing tasks is constructed, each task generating neuron is connected with the conversion neural layer, and the conversion neural layer is used for receiving more than one data processing task at the same time and converting the received data processing tasks into a plurality of internal subtasks according to a preset rule;
constructing a subtask processing layer communicated with the conversion nerve layer, wherein the subtask processing layer comprises more than one subtask processing nerve net, and each subtask processing nerve net only processes one subtask;
and constructing an output neuron, wherein the output neuron is connected with each subtask processing neuron, and is used for acquiring the data output of each subtask processing neuron in real time and converting the data output into final output according to a preset rule.
In the described embodiment, preprocessing the features in the obtained first equipment failure sample library and the second equipment failure sample library in step S3 includes:
deleting invalid data, repeated data, processing missing values and abnormal values of the first equipment failure sample library and the second equipment failure sample library;
and adding labels to fault data of the first equipment fault sample library and the second equipment fault sample library, wherein the labels are set target fault categories.
In the embodiment, the training methods of the first machine learning model and the second machine learning model are consistent, and the step S5 is specifically described by the training steps of the machine learning model:
step S51, training data of a training set and attribute indexes of a machine learning model are received;
step S52, determining a machine learning model by utilizing a model database according to at least one part of attribute indexes, wherein the model database comprises the machine learning model and attribute data thereof, and the attribute indexes are indexes expected by users of the attribute data;
step S53, training the machine learning model by utilizing training data to obtain a trained machine learning model and attribute data thereof;
step S54, determining whether the trained machine learning model meets the attribute indexes according to the attribute data of the trained machine learning model, and repeatedly executing the steps S52-S53 until the machine learning model meeting the attribute indexes is obtained when the trained machine learning model does not meet the attribute indexes;
wherein the attribute data includes at least one of: attributes of the input data of the model; the number of parameters of the model; the model aims at the input data and the calculation speed of the operation platform; and the model is aimed at the input data and the calculation accuracy of the operation platform.
In the illustrated embodiment, the condition for determining whether the machine learning model needs to be retrained in step S7 is: judging whether the classification labels output by the first machine learning model and the second machine learning model are consistent, and when the classification labels are consistent, retraining the machine learning model is not needed; and otherwise, retraining the machine learning model.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
The embodiment of the application also provides an intelligent distribution network equipment fault type identification system based on data analysis, and the intelligent distribution network equipment fault type identification system based on data analysis can be used for executing the intelligent distribution network equipment fault type identification method based on data analysis. The system is used to implement the embodiments and the preferred embodiments, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the system described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
The following describes a generation system of an extended random tree based on constraint sampling provided by an embodiment of the present application.
Fig. 2 is a schematic diagram of an intelligent distribution network equipment fault type identification system based on data analysis according to an embodiment of the present application. As shown in fig. 2, the intelligent distribution network equipment fault type identification system based on data analysis includes:
the data acquisition module is used for acquiring fault data of different types of intelligent distribution network equipment, wherein the fault data comprises ultrahigh frequency signal data and ultrasonic signal data;
the feature extraction module is used for extracting features from the fault data;
the equipment fault sample library module is used for constructing a first equipment fault sample library and a second equipment fault sample library, wherein the first equipment fault sample library is used for storing ultrahigh frequency signal data and corresponding characteristics, and the second equipment fault sample library is used for storing ultrasonic signal data and corresponding characteristics; preprocessing the characteristics in the first equipment failure sample library and the second equipment failure sample library;
the data classification module is used for dividing the preprocessed features in the first equipment fault sample library and the second equipment fault sample library into a training set and a testing set according to a preset proportion, and respectively constructing the training set and the testing set;
a machine learning model module for constructing a first machine learning model and a second machine learning model based on deep learning; training a first machine learning model through a training set of a first equipment failure sample library, and training a second machine learning model through a training set of a second equipment failure sample library; after training is completed, inputting a test set of a first equipment failure sample library into a first machine learning model, outputting a corresponding classification label by the first machine learning model, inputting a test set of a second equipment failure sample library into a second machine learning model, and outputting a corresponding classification label by the second machine learning model;
the fault type identification module is used for judging whether the machine learning model needs to be retrained according to the classification label output by the first machine learning model and the classification label output by the second machine learning model, outputting the fault type of the intelligent distribution network equipment when the machine learning model does not need to be retrained, and otherwise retrained the machine learning model.
In the described embodiment, the data acquisition module acquires uhf signal data comprising: and collecting the partial discharge ultrahigh frequency signal image of the intelligent distribution network equipment, and preprocessing the partial discharge ultrahigh frequency signal image to obtain ultrahigh frequency signal data.
In the described embodiment, the data collection module extracting features from the fault data includes: PRPS spectrum features are extracted from the ultrahigh frequency signal data, and Mel spectrum features are extracted from the ultrasonic signal data.
Wherein the PRPS profile features include at least: skewness Sk, ku, peak count Pe, and cross-correlation factor Cc.
In the described embodiment, the method for constructing the first machine learning model and the second machine learning model based on deep learning by the equipment failure sample library module is the same, and the constructing the first machine learning model based on deep learning includes:
constructing a plurality of input neurons for receiving an input, one of said input neurons for receiving an input;
constructing a plurality of task generating neurons for generating data processing tasks, wherein each input neuron is connected with all task generating neurons, each task generating neuron independently works, and one task generating neuron generates one data processing task;
a conversion neural layer for converting data processing tasks is constructed, each task generating neuron is connected with the conversion neural layer, and the conversion neural layer is used for receiving more than one data processing task at the same time and converting the received data processing tasks into a plurality of internal subtasks according to a preset rule;
constructing a subtask processing layer communicated with the conversion nerve layer, wherein the subtask processing layer comprises more than one subtask processing nerve net, and each subtask processing nerve net only processes one subtask;
and constructing an output neuron, wherein the output neuron is connected with each subtask processing neuron, and is used for acquiring the data output of each subtask processing neuron in real time and converting the data output into final output according to a preset rule.
In the described embodiment, the device fault sample library module pre-processes the features in the obtained first device fault sample library and the second device fault sample library, including:
deleting invalid data, repeated data, processing missing values and abnormal values of the first equipment failure sample library and the second equipment failure sample library;
and adding labels to fault data of the first equipment fault sample library and the second equipment fault sample library, wherein the labels are set target fault categories.
In the described embodiment, the training methods of the first machine learning model and the second machine learning model are consistent, and the training of the machine learning model module is specifically described through the training steps of the machine learning model:
step S51, training data of a training set and attribute indexes of a machine learning model are received;
step S52, determining a machine learning model by utilizing a model database according to at least one part of attribute indexes, wherein the model database comprises the machine learning model and attribute data thereof, and the attribute indexes are indexes expected by users of the attribute data;
step S53, training the machine learning model by utilizing training data to obtain a trained machine learning model and attribute data thereof;
step S54, determining whether the trained machine learning model meets the attribute indexes according to the attribute data of the trained machine learning model, and repeatedly executing the steps S52-S53 until the machine learning model meeting the attribute indexes is obtained when the trained machine learning model does not meet the attribute indexes;
wherein the attribute data includes at least one of: attributes of the input data of the model; the number of parameters of the model; the model aims at the input data and the calculation speed of the operation platform; and the model is aimed at the input data and the calculation accuracy of the operation platform.
In the described embodiment, the condition for the fault type recognition module to determine whether the machine learning model needs to be retrained is: judging whether the classification labels output by the first machine learning model and the second machine learning model are consistent, and when the classification labels are consistent, retraining the machine learning model is not needed; and otherwise, retraining the machine learning model.
The present application is not limited to the above embodiments, but is to be accorded the widest scope consistent with the principles and other features of the present application.
The embodiment of the application provides an electronic device, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor is used for executing the intelligent distribution network equipment fault type identification method based on data analysis through the computer program.
Specifically, the intelligent distribution network equipment fault type identification method based on data analysis comprises the following steps: collecting fault data of different types of intelligent distribution network equipment, wherein the fault data comprise ultrahigh frequency signal data and ultrasonic signal data; extracting features from the fault data; constructing a first equipment fault sample library and a second equipment fault sample library, wherein the first equipment fault sample library is used for storing ultrahigh frequency signal data and corresponding features, and the second equipment fault sample library is used for storing ultrasonic signal data and corresponding features; preprocessing the characteristics in the first equipment failure sample library and the second equipment failure sample library; dividing the preprocessed features in the first equipment failure sample library and the second equipment failure sample library into a training set and a testing set according to a preset proportion, and respectively constructing the training set and the testing set; constructing a first machine learning model and a second machine learning model based on deep learning; training a first machine learning model through a training set of a first equipment failure sample library, and training a second machine learning model through a training set of a second equipment failure sample library; after training is completed, inputting a test set of a first equipment failure sample library into a first machine learning model, outputting a corresponding classification label by the first machine learning model, inputting a test set of a second equipment failure sample library into a second machine learning model, and outputting a corresponding classification label by the second machine learning model; judging whether the machine learning model needs to be retrained according to the classification label output by the first machine learning model and the classification label output by the second machine learning model, outputting the fault type of the intelligent distribution network equipment when the machine learning model does not need to be retrained, and otherwise retrained the machine learning model.
The embodiment of the application provides equipment, which comprises a processor, a memory and a program stored in the memory and capable of running on the processor, wherein the processor realizes at least the following steps when executing the program:
collecting fault data of different types of intelligent distribution network equipment, wherein the fault data comprise ultrahigh frequency signal data and ultrasonic signal data;
extracting features from the fault data;
constructing a first equipment fault sample library and a second equipment fault sample library, wherein the first equipment fault sample library is used for storing ultrahigh frequency signal data and corresponding features, and the second equipment fault sample library is used for storing ultrasonic signal data and corresponding features; preprocessing the characteristics in the first equipment failure sample library and the second equipment failure sample library;
dividing the preprocessed features in the first equipment failure sample library and the second equipment failure sample library into a training set and a testing set according to a preset proportion, and respectively constructing the training set and the testing set;
constructing a first machine learning model and a second machine learning model based on deep learning; training a first machine learning model through a training set of a first equipment failure sample library, and training a second machine learning model through a training set of a second equipment failure sample library;
after training is completed, inputting a test set of a first equipment failure sample library into a first machine learning model, outputting a corresponding classification label by the first machine learning model, inputting a test set of a second equipment failure sample library into a second machine learning model, and outputting a corresponding classification label by the second machine learning model;
judging whether the machine learning model needs to be retrained according to the classification label output by the first machine learning model and the classification label output by the second machine learning model, outputting the fault type of the intelligent distribution network equipment when the machine learning model does not need to be retrained, and otherwise retrained the machine learning model.
The device herein may be a server, PC, PAD, cell phone, etc.
The application also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with at least the following method steps: specifically, the intelligent distribution network equipment fault type identification method based on data analysis comprises the following steps:
collecting fault data of different types of intelligent distribution network equipment, wherein the fault data comprise ultrahigh frequency signal data and ultrasonic signal data;
extracting features from the fault data;
constructing a first equipment fault sample library and a second equipment fault sample library, wherein the first equipment fault sample library is used for storing ultrahigh frequency signal data and corresponding features, and the second equipment fault sample library is used for storing ultrasonic signal data and corresponding features; preprocessing the characteristics in the first equipment failure sample library and the second equipment failure sample library;
dividing the preprocessed features in the first equipment failure sample library and the second equipment failure sample library into a training set and a testing set according to a preset proportion, and respectively constructing the training set and the testing set;
constructing a first machine learning model and a second machine learning model based on deep learning; training a first machine learning model through a training set of a first equipment failure sample library, and training a second machine learning model through a training set of a second equipment failure sample library;
after training is completed, inputting a test set of a first equipment failure sample library into a first machine learning model, outputting a corresponding classification label by the first machine learning model, inputting a test set of a second equipment failure sample library into a second machine learning model, and outputting a corresponding classification label by the second machine learning model;
judging whether the machine learning model needs to be retrained according to the classification label output by the first machine learning model and the classification label output by the second machine learning model, outputting the fault type of the intelligent distribution network equipment when the machine learning model does not need to be retrained, and otherwise retrained the machine learning model.
It will be appreciated by those skilled in the art that the modules or steps of the application described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps of them may be fabricated into a single integrated circuit module. Thus, the present application is not limited to any specific combination of hardware and software.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the 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.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of non-volatile memory, random Access Memory (RAM), and/or nonvolatile memory in a computer-readable medium, such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. Examples of storage media that can be used for storing information that can be accessed by a computing device include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disc read-only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. The intelligent distribution network equipment fault type identification method based on data analysis is characterized by comprising the following steps of:
collecting fault data of different types of intelligent distribution network equipment, wherein the fault data comprise ultrahigh frequency signal data and ultrasonic signal data;
extracting features from the fault data;
constructing a first equipment fault sample library and a second equipment fault sample library, wherein the first equipment fault sample library is used for storing ultrahigh frequency signal data and corresponding features, and the second equipment fault sample library is used for storing ultrasonic signal data and corresponding features; preprocessing the characteristics in the first equipment failure sample library and the second equipment failure sample library;
dividing the preprocessed features in the first equipment failure sample library and the second equipment failure sample library into a training set and a testing set according to a preset proportion, and respectively constructing the training set and the testing set;
constructing a first machine learning model and a second machine learning model based on deep learning; training a first machine learning model through a training set of a first equipment failure sample library, and training a second machine learning model through a training set of a second equipment failure sample library;
after training is completed, inputting a test set of a first equipment failure sample library into a first machine learning model, outputting a corresponding classification label by the first machine learning model, inputting a test set of a second equipment failure sample library into a second machine learning model, and outputting a corresponding classification label by the second machine learning model;
judging whether the machine learning model needs to be retrained according to the classification label output by the first machine learning model and the classification label output by the second machine learning model, outputting the fault type of the intelligent distribution network equipment when the machine learning model does not need to be retrained, and otherwise retrained the machine learning model.
2. The intelligent distribution network equipment fault type identification method based on data analysis according to claim 1, wherein extracting features from fault data comprises: PRPS spectrum features are extracted from the ultrahigh frequency signal data, and Mel spectrum features are extracted from the ultrasonic signal data.
3. The intelligent distribution network equipment fault type identification method based on data analysis according to claim 2, wherein the PRPS map features at least comprise: skewness, kurtosis, peak count, and cross-correlation factor.
4. The method for identifying the fault type of the intelligent distribution network equipment based on the data analysis according to claim 1, wherein preprocessing the characteristics in the obtained first equipment fault sample library and the second equipment fault sample library comprises the following steps:
deleting invalid data, repeated data, processing missing values and abnormal values of the first equipment failure sample library and the second equipment failure sample library;
and adding labels to fault data of the first equipment fault sample library and the second equipment fault sample library, wherein the labels are set target fault categories.
5. The method for identifying the fault type of the intelligent distribution network equipment based on data analysis according to claim 1, wherein the step of collecting the ultrahigh frequency signal data comprises the following steps: and collecting the partial discharge ultrahigh frequency signal image of the intelligent distribution network equipment, and preprocessing the partial discharge ultrahigh frequency signal image to obtain ultrahigh frequency signal data.
6. The method for identifying a fault type of intelligent distribution network equipment based on data analysis according to claim 1, wherein the method for constructing a first machine learning model based on deep learning and a second machine learning model is the same, and the method for constructing the first machine learning model based on deep learning includes:
constructing a plurality of input neurons for receiving an input, one of said input neurons for receiving an input;
constructing a plurality of task generating neurons for generating data processing tasks, wherein each input neuron is connected with all task generating neurons, each task generating neuron independently works, and one task generating neuron generates one data processing task;
a conversion neural layer for converting data processing tasks is constructed, each task generating neuron is connected with the conversion neural layer, and the conversion neural layer is used for receiving more than one data processing task at the same time and converting the received data processing tasks into a plurality of internal subtasks according to a preset rule;
constructing a subtask processing layer communicated with the conversion nerve layer, wherein the subtask processing layer comprises more than one subtask processing nerve net, and each subtask processing nerve net only processes one subtask;
and constructing an output neuron, wherein the output neuron is connected with each subtask processing neuron, and is used for acquiring the data output of each subtask processing neuron in real time and converting the data output into final output according to a preset rule.
7. The method for identifying a fault type of intelligent distribution network equipment based on data analysis according to claim 1, wherein the condition for judging whether the machine learning model needs to be retrained is: judging whether the classification labels output by the first machine learning model and the second machine learning model are consistent, and when the classification labels are consistent, retraining the machine learning model is not needed; and otherwise, retraining the machine learning model.
8. An intelligent distribution network equipment fault type identification system based on data analysis is characterized by comprising:
the data acquisition module is used for acquiring fault data of different types of intelligent distribution network equipment, wherein the fault data comprises ultrahigh frequency signal data and ultrasonic signal data;
the feature extraction module is used for extracting features from the fault data;
the equipment fault sample library module is used for constructing a first equipment fault sample library and a second equipment fault sample library, wherein the first equipment fault sample library is used for storing ultrahigh frequency signal data and corresponding characteristics, and the second equipment fault sample library is used for storing ultrasonic signal data and corresponding characteristics; preprocessing the characteristics in the first equipment failure sample library and the second equipment failure sample library;
the data classification module is used for dividing the preprocessed features in the first equipment fault sample library and the second equipment fault sample library into a training set and a testing set according to a preset proportion, and respectively constructing the training set and the testing set;
a machine learning model module for constructing a first machine learning model and a second machine learning model based on deep learning; training a first machine learning model through a training set of a first equipment failure sample library, and training a second machine learning model through a training set of a second equipment failure sample library; after training is completed, inputting a test set of a first equipment failure sample library into a first machine learning model, outputting a corresponding classification label by the first machine learning model, inputting a test set of a second equipment failure sample library into a second machine learning model, and outputting a corresponding classification label by the second machine learning model;
the fault type identification module is used for judging whether the machine learning model needs to be retrained according to the classification label output by the first machine learning model and the classification label output by the second machine learning model, outputting the fault type of the intelligent distribution network equipment when the machine learning model does not need to be retrained, and otherwise retrained the machine learning model.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored program, wherein the program, when run, controls a device in which the computer-readable storage medium is located to execute the intelligent distribution network device fault type identification method based on data analysis as claimed in any one of claims 1 to 7.
10. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to perform the intelligent distribution network equipment fault type identification method based on data analysis according to any of claims 1 to 7 by means of the computer program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311089712.0A CN117131419A (en) | 2023-08-28 | 2023-08-28 | Intelligent distribution network equipment fault type identification method and system based on data analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311089712.0A CN117131419A (en) | 2023-08-28 | 2023-08-28 | Intelligent distribution network equipment fault type identification method and system based on data analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117131419A true CN117131419A (en) | 2023-11-28 |
Family
ID=88850413
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311089712.0A Pending CN117131419A (en) | 2023-08-28 | 2023-08-28 | Intelligent distribution network equipment fault type identification method and system based on data analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117131419A (en) |
-
2023
- 2023-08-28 CN CN202311089712.0A patent/CN117131419A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110348580B (en) | Method and device for constructing GBDT model, and prediction method and device | |
CN113792825B (en) | Fault classification model training method and device for electricity information acquisition equipment | |
CN111079658B (en) | Multi-target continuous behavior analysis method, system and device based on video | |
CN112393931B (en) | Detection method, detection device, electronic equipment and computer readable medium | |
Sindhwani et al. | Performance analysis of deep neural networks using computer vision | |
CN111134664B (en) | Epileptic discharge identification method and system based on capsule network and storage medium | |
US10810508B1 (en) | Methods and apparatus for classifying and discovering historical and future operational states based on Boolean and numerical sensor data | |
CN111767957B (en) | Log abnormality detection method and device, storage medium and electronic equipment | |
CN112288021A (en) | Medical wastewater monitoring data quality control method, device and system | |
CN111143578A (en) | Method, device and processor for extracting event relation based on neural network | |
CN109918296A (en) | Automatic software test method and device | |
Aburasain et al. | Drone-based cattle detection using deep neural networks | |
CN110909826A (en) | Diagnosis monitoring method and device for energy equipment and electronic equipment | |
CN115456107A (en) | Time series abnormity detection system and method | |
CN113704389A (en) | Data evaluation method and device, computer equipment and storage medium | |
CN113077821A (en) | Audio quality detection method and device, electronic equipment and storage medium | |
CN116306806A (en) | Fault diagnosis model determining method and device and nonvolatile storage medium | |
CN116361147A (en) | Method for positioning root cause of test case, device, equipment, medium and product thereof | |
Huangfu et al. | System failure detection using deep learning models integrating timestamps with nonuniform intervals | |
CN117608889A (en) | Log semantic based anomaly detection method and related equipment | |
Dutta et al. | Big data architecture for environmental analytics | |
CN117131419A (en) | Intelligent distribution network equipment fault type identification method and system based on data analysis | |
CN112433952B (en) | Method, system, device and medium for testing fairness of deep neural network model | |
CN114334062A (en) | Disease abnormity early warning method, equipment and medium based on medical history | |
Jallepalli et al. | Data-driven fault classification using support vector machines |
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 |