CN111126489A - Power transmission equipment state evaluation method based on ensemble learning - Google Patents
Power transmission equipment state evaluation method based on ensemble learning Download PDFInfo
- Publication number
- CN111126489A CN111126489A CN201911351082.3A CN201911351082A CN111126489A CN 111126489 A CN111126489 A CN 111126489A CN 201911351082 A CN201911351082 A CN 201911351082A CN 111126489 A CN111126489 A CN 111126489A
- Authority
- CN
- China
- Prior art keywords
- power transmission
- equipment
- samples
- transmission equipment
- state
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 63
- 238000011156 evaluation Methods 0.000 title claims abstract description 35
- 238000012549 training Methods 0.000 claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000013210 evaluation model Methods 0.000 claims abstract description 14
- 238000005070 sampling Methods 0.000 claims abstract description 12
- 238000000513 principal component analysis Methods 0.000 claims abstract description 6
- 230000010354 integration Effects 0.000 claims abstract description 4
- 230000007547 defect Effects 0.000 claims description 27
- 238000007689 inspection Methods 0.000 claims description 13
- 238000012423 maintenance Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 9
- 230000003449 preventive effect Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 230000000306 recurrent effect Effects 0.000 description 4
- 238000013145 classification model Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 239000012212 insulator Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Economics (AREA)
- Water Supply & Treatment (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Bioinformatics & Computational Biology (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power transmission equipment state evaluation method based on ensemble learning, which comprises the following steps: acquiring a historical sample containing data related to the operation of the power transmission equipment; selecting characteristic quantities and labels corresponding to the historical samples by a method of principal component analysis and expert experience judgment; sampling normal samples in the historical samples by adopting a bootstrap sampling method, establishing N normal sample sets, and combining the normal sample sets and the fault samples to obtain N balanced sample training sets; respectively carrying out network training on the N balanced sample training sets by adopting N LSTM-based learners to obtain N classification results; and carrying out Bagging integration on the N classification results to obtain a power transmission equipment state evaluation model, and carrying out real-time comprehensive evaluation on the state of the power transmission equipment. According to the invention, by providing the network model suitable for the intelligent state evaluation of the power transmission equipment, the quasi-real-time comprehensive evaluation of the running state of the power transmission equipment is realized, the running state of the power transmission line can be reflected, and the reliability of a power system is improved.
Description
Technical Field
The invention relates to the technical field of power transmission line state evaluation, in particular to a power transmission equipment state evaluation method based on ensemble learning.
Background
At present, the maintenance plan of a power transmission system aiming at power transmission equipment is gradually changed from traditional regular maintenance into maintenance based on the running state of the equipment, so that the pertinence of maintenance tasks is improved, and the waste of manpower and material resources is avoided. The key point of arranging the maintenance plan based on the running state of the equipment lies in timely and accurately grasping the state of the equipment, and along with the continuous development of related detection technologies, various state detection means such as online monitoring, offline experiments, manual inspection, unmanned aerial vehicle inspection and the like are widely applied to state detection of power transmission equipment at present, and a large amount of historical data are accumulated. However, the current state evaluation method still has the following problems: most of the analysis and judgment are carried out based on a small number or single state quantity, the influence of external factors on the equipment state is not considered, the analysis result is extensive and one-sided, and the latent fault is difficult to be timely detected; most of the judgment is carried out by operation and maintenance experts according to manual experience and relevant state evaluation guide rules, and subjective errors caused by human factors exist; the equipment state information data are distributed in each part of the power system, the data parameters are uneven, the difficulty of effective data extraction and fusion analysis is high, and the equipment abnormality detection and state evaluation efficiency is low; the single state evaluation model has difficulty in guaranteeing the applicability to different environmental devices.
The large-data equipment state evaluation is focused on fusion analysis and deep mining by utilizing a large amount of equipment state information, power grid operation information and environmental meteorological information collected by an increasingly perfect electric power information platform, valuable information is mined from the perspective of internal rule analysis of data, and personalized state evaluation and rapid detection of equipment abnormity are realized. The big data analysis algorithm is adopted for research, so that valuable information for evaluating the state of the power transmission equipment can be obtained from a large amount of data without establishing a complex mathematical physical model, and a brand-new solution idea and technical means are provided for the refined state and prediction of the state of the equipment; in addition, the big data analysis can be combined with a physical model to realize diversified and complicated comprehensive analysis of the power transmission equipment, and the accuracy of state evaluation and diagnosis of the power transmission equipment is improved.
Disclosure of Invention
The invention provides a power transmission equipment state evaluation method based on ensemble learning, and aims to overcome the defects in the prior art.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a power transmission apparatus state evaluation method based on ensemble learning, the method comprising:
acquiring a historical sample containing data related to the operation of the power transmission equipment from a historical record of the power system;
selecting characteristic quantities and labels corresponding to the historical samples by a method of principal component analysis and expert experience judgment;
sampling normal samples in the historical samples by adopting a bootstrap sampling method, establishing N normal sample sets, and combining the normal sample sets and fault samples to obtain N balanced sample training sets;
respectively carrying out network training on the N balanced sample training sets by adopting N LSTM-based learners to obtain N classification results;
carrying out Bagging integration on the N classification results to obtain a power transmission equipment state evaluation model;
and performing real-time comprehensive evaluation on the state of the power transmission equipment by adopting the power transmission equipment state evaluation model.
Further, in the method for evaluating the state of the power transmission equipment based on ensemble learning, the power system historical records comprise power system line patrol records, preventive test records, operation records, defect records, a power company defect library and emergency major defect statistics.
Further, in the method for evaluating the state of the power transmission equipment based on ensemble learning, the operation related data of the power transmission equipment comprise equipment account information, equipment nameplate information, technical parameters of a detection instrument, equipment operation data and meteorological information.
Further, in the method for evaluating the state of the power transmission equipment based on ensemble learning, the historical samples include normal samples and fault samples;
the normal samples are samples which are detected by inspection and found that the equipment is in a defect state, but the equipment does not have a fault in the next inspection cycle after the defect is eliminated according to the established maintenance plan;
the fault sample is a sample which is used for finding that the equipment is in a defect state and the equipment has faults in the next line patrol period.
Further, in the method for evaluating a state of a power transmitting apparatus based on ensemble learning, the method further includes:
n LSTM-based learners based on the LSTM network are established.
According to the power transmission equipment state evaluation method based on ensemble learning, provided by the embodiment of the invention, the quasi-real-time comprehensive evaluation of the operation state of the power transmission equipment is realized by providing the network model suitable for the intelligent state evaluation of the power transmission equipment, the operation state of the power transmission equipment can be better reflected, and the reliability of a power system is improved as much as possible.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a schematic flowchart of a power transmission equipment state evaluation method based on ensemble learning according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a power transmission equipment state evaluation method based on ensemble learning according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a network structure using an LSTM-based learner according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Referring to fig. 1 to 2, a schematic flow chart of a power transmission equipment state evaluation method based on ensemble learning according to an embodiment of the present invention is shown. The method specifically comprises the following steps:
s101, acquiring a history sample containing operation related data of the power transmission equipment from a history record of the power system;
the power system historical record comprises power system line patrol records, preventive test records, operation records, defect records, a power company defect library and emergency major defect statistics.
The power transmission equipment operation related data comprises equipment account information, equipment nameplate information, technical parameters of detection instruments, equipment operation data and meteorological information.
The historical samples comprise normal samples and fault samples;
the normal samples are samples which are detected by inspection and found that the equipment is in a defect state, but the equipment does not have a fault in the next inspection cycle after the defect is eliminated according to the established maintenance plan;
the fault sample is a sample which is used for finding that the equipment is in a defect state and the equipment has faults in the next line patrol period.
S102, selecting characteristic quantities and labels corresponding to the historical samples by a method of principal component analysis and expert experience judgment;
the device operation related data of the history samples acquired by the invention comprise characteristic input quantities closely related to the state information of the power transmission device. Considering that the types of data covered by the equipment operation related data are more, the association degree of each type of data and the state of the power transmission equipment is different. According to the method, characteristic quantities closely related to the state information of the power transmission equipment are selected from the power transmission equipment operation related data through a principal component analysis and expert experience judgment method.
When the power transmission equipment is in a defect state, the maintenance department can eliminate the defect according to a preset maintenance plan, so that actual faults do not necessarily occur in the next line patrol period. The method comprises the following steps of defining a defect sample related to equipment operation as a normal sample and a fault sample, wherein the normal sample refers to a sample which is detected by inspection to be in a defect state, but does not have a fault in the next inspection cycle after the defect is eliminated according to a set inspection plan; the fault sample refers to a sample which is detected by inspection to find that the equipment is in a defect state and the equipment has faults in the next line inspection period. The data that each data sample should have established by the invention comprises: the running characteristic quantity of the sample for 3 months continuously, the detection record and the running label corresponding to the sample.
S103, sampling normal samples in the historical samples by adopting a bootstrap sampling method, establishing N normal sample sets, and combining the normal sample sets and fault samples to obtain N balanced sample training sets;
considering that the number of normal samples in a power system is far larger than that of fault samples, the classification of the states of power transmission equipment belongs to the classification of a pair of unbalanced sample sets, and the training effect of using a traditional neural network is poor, the invention provides a classification model based on an LSTM network. The invention establishes N LSTM networks as a base learner for state classification of power transmission equipment, and correspondingly establishes N balanced sample training sets as the training networks of the LSTM. The construction method of the balanced sample training set comprises the following steps: sampling the normal samples by adopting a bootstrap sampling method, establishing N normal sample sets, and combining the normal sample sets and the fault samples to obtain N more balanced sample training sets.
S104, respectively carrying out network training on the N balanced sample training sets by adopting N LSTM-based learners to obtain N classification results;
and for each independent LSTM-based learner, performing model training by using the data in the corresponding training set of the balanced samples. And taking the characteristic quantity of the training sample in the training set as model input, and taking the label of the training sample as model output. And obtaining the relevant weight of the network by solving the least square solution of the classification result error to obtain N independent LSTM-based line state classification models and N classification results.
Preferably, the method further comprises:
n LSTM-based learners based on the LSTM network are established.
S105, carrying out Bagging integration on the N classification results to obtain a power transmission equipment state evaluation model;
processing the unbalanced samples by using a Bagging ensemble learning idea, combining the N base learners by using a voting method to obtain a final prediction result, and testing through corresponding test data to obtain a power transmission equipment state evaluation model.
And S106, carrying out real-time comprehensive evaluation on the state of the power transmission equipment by adopting the power transmission equipment state evaluation model.
The invention provides a semantic type classification mode different from the semantic type classification modes of normal, abnormal, serious and critical of the traditional guide rule, and defines the severity of the running state of the equipment as the probability of the fault of the equipment to be evaluated in a next line patrol period. The evaluation method can enable operation and maintenance personnel to better know the condition of the equipment to be overhauled and whether the line patrol period needs to be adjusted correspondingly.
According to the method, a non-fault sample subset is obtained through bootstrap random sampling, and the sample is placed back to the original data set, so that certain disturbance can be brought to the original data, more diversity is brought to the determination of the non-fault sample set, certain diversity is created to the learning of an LSTM-based learner, and the generalization performance of the model can be improved to a certain extent.
The invention adopts an LSTM network as a base learner of a Bagging integrated learning model, the LSTM network is a network model which is added with a gate control unit on the basis of a recurrent neural network, and the gate control unit can be used for determining the influence degree of historical information on instant information, thereby being an implementation mode for solving the problem of difficult long-time span sequence modeling. The long-time and short-time memory network can solve the problem that the traditional recurrent neural network is insensitive to time sequence information to a great extent.
Fig. 3 shows a schematic diagram of a network structure using an LSTM-based learner according to an embodiment of the present invention:
the LSTM network is a network model which is added with a gate control unit on the basis of a recurrent neural network, the gate control unit can be used for determining the influence degree of historical information on instant information, and the LSTM network is an implementation mode for solving the problem of long-time span sequence modeling. The long-time and short-time memory network can solve the problem that the traditional recurrent neural network is insensitive to time sequence information to a great extent.
The current time is represented by time t, and the specific expression of the LSTM is as follows:
the LSTM comprises an input gate, an output gate and a forgetting gate. The input includes: sequence input x at time ttLSTM output h at time t-1t-1, and cell state c at time t-1t-1. The output includes: LSTM output h at time ttAnd cell state c at time tt. The LSTM protects and controls information through three gates. Wherein f ist，it，otThe outputs of the forgetting gate, the input gate and the output gate are respectively; wf，Wi，WoThe weight matrixes are respectively a forgetting gate, an input gate and an output gate; bf，bi，boRespectively, the offset items of the forgetting gate, the input gate and the output gate. The final output of the LSTM is determined by the output gate and cell state. WcIs a weight matrix of the input unit; bcIs a deviation term of the input unit; tanh is the activation function; o denotes matrix dot multiplication.
When the LSTM-based learner is adopted for state classification application of power transmission equipment, a balanced sample training set obtained through bootstrap sampling preprocessing is used as a training set, the proportion of normal samples and fault samples in the balanced sample training set is balanced, and the problem of high misclassification probability caused by the fact that the number of the normal samples is far more than that of the fault samples is solved.
Meanwhile, LSTMs can be overlapped to form a multilayer LSTM, and the method has the advantages of extracting deeper data characteristics, improving the evaluation accuracy and reducing the training time. After multiple LSTM layers, a softmax layer is accessed, mapping the LSTM outputs to a probability distribution with a value at (0, 1).
The input quantity of the LSTM network training model consists of characteristic quantities recorded by three continuous line patrols, wherein the characteristic quantities are selected from power transmission equipment operation related data through a method of principal component analysis and expert experience judgment. And forming a time sequence by the characteristic quantities recorded by three successive line patrols, cascading a plurality of LSTM networks to form a deep LSTM network, extracting deep characteristics of the time sequence data, and finally outputting an evaluation result by taking a full-connection layer of Softmax as an output layer.
The invention utilizes the established training data set and the back propagation algorithm to carry out parameter training on the network model, and stops training when the specified cycle number or accuracy is not improved any more. Under the two-classification problem, the labels of the training data are fault and normal, the output of the network model is the probability that the result is the fault, and the probability is the quantitative index for evaluating the severity of the operation state of the power transmission equipment.
The algorithm is realized through python, and a model is built based on TensorFlow and a Keras library. Considering that there are 6000 normal samples and more than 100 fault samples in the training samples, in order to realize the positive and negative sample balance of the training samples, the invention sets 50 LSTM learners as the base learners. Each LSTM-based learner includes an input layer, 20 hidden layers, and an output layer. And constructing a power transmission equipment state evaluation model based on Bagging-LSTM ensemble learning.
The invention examines the equipment running state classification accuracy of the evaluation model established by the invention by taking the test set as an example.
Case 2 is a broken strand defect case detected by a certain 220kV overhead transmission line conductor, but the broken strand defect case does not have a fault. And inputting the characteristic parameters of the test case for three months continuously into a corresponding state evaluation model obtained by training, calculating to obtain a result of 12% of the severity of the fault of the lead, and classifying the result to be a normal sample.
Case 3 is a case of a wire breakage fault detected by a certain 220kV overhead transmission line wire. And inputting the characteristic parameters of the test case for three consecutive months into a corresponding state evaluation model obtained by training, calculating to obtain a lead fault severity result of 84%, and classifying the result into a fault sample.
According to the power transmission equipment state evaluation method based on ensemble learning, provided by the embodiment of the invention, the quasi-real-time comprehensive evaluation of the operation state of the power transmission equipment is realized by providing the network model suitable for the intelligent state evaluation of the power transmission equipment, the operation state of the power transmission equipment can be better reflected, and the reliability of a power system is improved as much as possible.
The foregoing description of the embodiments has been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the disclosure. Individual elements or features of a particular embodiment are generally not limited to that particular embodiment, but, where applicable, are interchangeable and can be used in a selected embodiment, even if not specifically shown or described. The same elements or features may also vary in many respects. Such variations are not to be regarded as a departure from the disclosure, and all such modifications are intended to be included within the scope of the disclosure.
Example embodiments are provided so that this disclosure will be thorough and will fully convey the scope to those skilled in the art. Numerous details are set forth, such as examples of specific parts, devices, and methods, in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent to those skilled in the art that specific details need not be employed, that example embodiments may be embodied in many different forms and that neither should be construed to limit the scope of the disclosure. In certain example embodiments, well-known processes, well-known device structures, and well-known technologies are not described in detail.
The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises" and "comprising" are intended to be inclusive and therefore specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The method steps, processes, and operations described herein are not to be construed as necessarily requiring their performance in the particular order discussed and illustrated, unless explicitly indicated as an order of performance. It should also be understood that additional or alternative steps may be employed.
When an element or layer is referred to as being "on" … … "," engaged with "… …", "connected to" or "coupled to" another element or layer, it can be directly on, engaged with, connected to or coupled to the other element or layer, or intervening elements or layers may also be present. In contrast, when an element or layer is referred to as being "directly on … …," "directly engaged with … …," "directly connected to" or "directly coupled to" another element or layer, there may be no intervening elements or layers present. Other words used to describe the relationship of elements should be interpreted in a similar manner (e.g., "between … …" and "directly between … …", "adjacent" and "directly adjacent", etc.). As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items. Although the terms first, second, third, etc. may be used herein to describe various elements, components, regions, layers and/or sections, these elements, components, regions, layers and/or sections should not be limited by these terms. These terms may be only used to distinguish one element, component, region or section from another element, component, region or section. Unless clearly indicated by the context, use of terms such as the terms "first," "second," and other numerical values herein does not imply a sequence or order. Thus, a first element, component, region, layer or section discussed below could be termed a second element, component, region, layer or section without departing from the teachings of the example embodiments.
Spatially relative terms, such as "inner," "outer," "below," "… …," "lower," "above," "upper," and the like, may be used herein for ease of description to describe a relationship between one element or feature and one or more other elements or features as illustrated in the figures. Spatially relative terms may be intended to encompass different orientations of the device in addition to the orientation depicted in the figures. For example, if the device in the figures is turned over, elements described as "below" or "beneath" other elements or features would then be oriented "above" the other elements or features. Thus, the example term "below … …" can encompass both an orientation of facing upward and downward. The device may be otherwise oriented (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted.
Claims (5)
1. A power transmission apparatus state evaluation method based on ensemble learning, characterized by comprising:
acquiring a historical sample containing data related to the operation of the power transmission equipment from a historical record of the power system;
selecting characteristic quantities and labels corresponding to the historical samples by a method of principal component analysis and expert experience judgment;
sampling normal samples in the historical samples by adopting a bootstrap sampling method, establishing N normal sample sets, and combining the normal sample sets and fault samples to obtain N balanced sample training sets;
respectively carrying out network training on the N balanced sample training sets by adopting N LSTM-based learners to obtain N classification results;
carrying out Bagging integration on the N classification results to obtain a power transmission equipment state evaluation model;
and performing real-time comprehensive evaluation on the state of the power transmission equipment by adopting the power transmission equipment state evaluation model.
2. The ensemble learning-based power transmitting apparatus state evaluating method according to claim 1, wherein the power system history record includes a power system line patrol record, a preventive test record, an operation record, a defect record, a power company defect library, and an urgent significant defect statistic.
3. The ensemble learning-based power transmitting equipment state evaluation method according to claim 1, wherein the power transmitting equipment operation-related data includes equipment ledger information, equipment nameplate information, instrumentation technical parameters, equipment operation data, and weather information.
4. The integrated learning-based power transmitting apparatus state evaluation method according to claim 1, characterized in that the history samples include normal samples and failure samples;
the normal samples are samples which are detected by inspection and found that the equipment is in a defect state, but the equipment does not have a fault in the next inspection cycle after the defect is eliminated according to the established maintenance plan;
the fault sample is a sample which is used for finding that the equipment is in a defect state and the equipment has faults in the next line patrol period.
5. The integrated learning-based power transmitting apparatus state evaluation method according to claim 1, characterized by further comprising:
n LSTM-based learners based on the LSTM network are established.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911351082.3A CN111126489A (en) | 2019-12-24 | 2019-12-24 | Power transmission equipment state evaluation method based on ensemble learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911351082.3A CN111126489A (en) | 2019-12-24 | 2019-12-24 | Power transmission equipment state evaluation method based on ensemble learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111126489A true CN111126489A (en) | 2020-05-08 |
Family
ID=70502087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911351082.3A Pending CN111126489A (en) | 2019-12-24 | 2019-12-24 | Power transmission equipment state evaluation method based on ensemble learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111126489A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112036496A (en) * | 2020-09-02 | 2020-12-04 | 哈尔滨工程大学 | Nuclear power device fault diagnosis method and system |
| CN112329346A (en) * | 2020-11-06 | 2021-02-05 | 国网四川省电力公司泸州供电公司 | Analysis and optimization method for lightning ground flashover data of power transmission line |
| CN112990776A (en) * | 2021-04-26 | 2021-06-18 | 广东电网有限责任公司东莞供电局 | Distribution network equipment health degree evaluation method |
| CN113591728A (en) * | 2021-08-03 | 2021-11-02 | 天津大学 | Electric energy quality disturbance classification method based on integrated deep learning |
| CN113780401A (en) * | 2021-09-06 | 2021-12-10 | 国网山东省电力公司电力科学研究院 | Composite insulator fault detection method and system based on principal component analysis method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108037378A (en) * | 2017-10-26 | 2018-05-15 | 上海交通大学 | Running state of transformer Forecasting Methodology and system based on long memory network in short-term |
| CN109829543A (en) * | 2019-01-31 | 2019-05-31 | 中国科学院空间应用工程与技术中心 | A kind of online method for detecting abnormality of data flow based on integrated study |
| CN109886288A (en) * | 2019-01-07 | 2019-06-14 | 中国电力科学研究院有限公司 | A kind of method for evaluating state and device for power transformer |
| CN110045209A (en) * | 2019-05-10 | 2019-07-23 | 广东电网有限责任公司 | Detection method, device, equipment and the readable storage medium storing program for executing of electricity consumption data exception |
| CN110188826A (en) * | 2019-05-31 | 2019-08-30 | 湖南科技大学 | Household electrical appliance operating status non-invasive inspection methods based on intelligent electric meter data |
| CN110263846A (en) * | 2019-06-18 | 2019-09-20 | 华北电力大学 | The method for diagnosing faults for being excavated and being learnt based on fault data depth |
| CN110598907A (en) * | 2019-08-13 | 2019-12-20 | 中国电力科学研究院有限公司 | Intelligent diagnosis method and system for health state of power distribution network |
-
2019
- 2019-12-24 CN CN201911351082.3A patent/CN111126489A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108037378A (en) * | 2017-10-26 | 2018-05-15 | 上海交通大学 | Running state of transformer Forecasting Methodology and system based on long memory network in short-term |
| CN109886288A (en) * | 2019-01-07 | 2019-06-14 | 中国电力科学研究院有限公司 | A kind of method for evaluating state and device for power transformer |
| CN109829543A (en) * | 2019-01-31 | 2019-05-31 | 中国科学院空间应用工程与技术中心 | A kind of online method for detecting abnormality of data flow based on integrated study |
| CN110045209A (en) * | 2019-05-10 | 2019-07-23 | 广东电网有限责任公司 | Detection method, device, equipment and the readable storage medium storing program for executing of electricity consumption data exception |
| CN110188826A (en) * | 2019-05-31 | 2019-08-30 | 湖南科技大学 | Household electrical appliance operating status non-invasive inspection methods based on intelligent electric meter data |
| CN110263846A (en) * | 2019-06-18 | 2019-09-20 | 华北电力大学 | The method for diagnosing faults for being excavated and being learnt based on fault data depth |
| CN110598907A (en) * | 2019-08-13 | 2019-12-20 | 中国电力科学研究院有限公司 | Intelligent diagnosis method and system for health state of power distribution network |
Non-Patent Citations (2)
| Title |
|---|
| 代杰杰 等: "采用LSTM网络的电力变压器运行状态预测方法研究", 《高电压技术》 * |
| 罗建军 等: "融合多源数据的架空输电线路运行状态评估方法", 《电子测量技术》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112036496A (en) * | 2020-09-02 | 2020-12-04 | 哈尔滨工程大学 | Nuclear power device fault diagnosis method and system |
| CN112329346A (en) * | 2020-11-06 | 2021-02-05 | 国网四川省电力公司泸州供电公司 | Analysis and optimization method for lightning ground flashover data of power transmission line |
| CN112329346B (en) * | 2020-11-06 | 2022-06-14 | 国网四川省电力公司泸州供电公司 | Analysis and optimization method for lightning ground flashover data of power transmission line |
| CN112990776A (en) * | 2021-04-26 | 2021-06-18 | 广东电网有限责任公司东莞供电局 | Distribution network equipment health degree evaluation method |
| CN113591728A (en) * | 2021-08-03 | 2021-11-02 | 天津大学 | Electric energy quality disturbance classification method based on integrated deep learning |
| CN113780401A (en) * | 2021-09-06 | 2021-12-10 | 国网山东省电力公司电力科学研究院 | Composite insulator fault detection method and system based on principal component analysis method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111126489A (en) | Power transmission equipment state evaluation method based on ensemble learning | |
| CN111985561B (en) | Fault diagnosis method and system for intelligent electric meter and electronic device | |
| CN105512474B (en) | A kind of method for detecting abnormality of Transformer's Condition Monitoring data | |
| CN113156917B (en) | Power grid equipment fault diagnosis method and system based on artificial intelligence | |
| CN106651169A (en) | Fuzzy comprehensive evaluation-based distribution automation terminal state evaluation method and system | |
| CN104732276B (en) | One kind metering production facility on-line fault diagnosis method | |
| CN110320892A (en) | The sewage disposal device fault diagnosis system and method returned based on Lasso | |
| CN106154209A (en) | Electrical energy meter fault Forecasting Methodology based on decision Tree algorithms | |
| CN108320043A (en) | A kind of distribution network equipment state diagnosis prediction method based on electric power big data | |
| CN109597396B (en) | A kind of distribution transforming on-line fault diagnosis method based on high amount of traffic and transfer learning | |
| CN105467971B (en) | A kind of second power equipment monitoring system and method | |
| CN104218570A (en) | Method and system for online evaluating overall measuring errors of electric energy measuring device | |
| CN110533007B (en) | Intelligent identification and extraction method for bridge vehicle-mounted strain influence line features | |
| CN105425768A (en) | Electric power secondary equipment monitoring device and method | |
| CN107944571A (en) | A kind of power transformer remaining life Forecasting Methodology | |
| CN106650959A (en) | Power distribution network repair ability assessment method based on improved grey clustering | |
| CN117708669A (en) | Multi-source data-based adaptive probability neural network high-voltage cable state evaluation method | |
| CN104317778A (en) | Massive monitoring data based substation equipment fault diagnosis method | |
| CN116467950A (en) | Unmanned aerial vehicle flight data anomaly detection method based on uncertain characterization | |
| CN207992717U (en) | A kind of gate of hydropower station on-line condition monitoring system | |
| Dang et al. | seq2graph: Discovering dynamic non-linear dependencies from multivariate time series | |
| CN105741184A (en) | Transformer state evaluation method and apparatus | |
| CN112418662A (en) | Power distribution network operation reliability analysis method using artificial neural network | |
| CN116433018A (en) | Digital twinning-based power distribution network risk situation sensing method and device | |
| CN103235206A (en) | Transformer fault diagnosis method |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200508 |
|
| RJ01 | Rejection of invention patent application after publication |