CN112115636B - Advanced prediction method and system for insulation aging life of power cable - Google Patents
Advanced prediction method and system for insulation aging life of power cable Download PDFInfo
- Publication number
- CN112115636B CN112115636B CN202010830377.5A CN202010830377A CN112115636B CN 112115636 B CN112115636 B CN 112115636B CN 202010830377 A CN202010830377 A CN 202010830377A CN 112115636 B CN112115636 B CN 112115636B
- Authority
- CN
- China
- Prior art keywords
- index
- cable
- prediction
- data
- life
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000032683 aging Effects 0.000 title claims abstract description 46
- 238000009413 insulation Methods 0.000 title claims abstract description 33
- 238000013528 artificial neural network Methods 0.000 claims abstract description 39
- 125000004122 cyclic group Chemical group 0.000 claims abstract description 18
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 230000008569 process Effects 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 10
- 210000002569 neuron Anatomy 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000012797 qualification Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 4
- 230000006386 memory function Effects 0.000 abstract description 3
- 230000008901 benefit Effects 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 230000018109 developmental process Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001808 coupling effect Effects 0.000 description 1
- 229920003020 cross-linked polyethylene Polymers 0.000 description 1
- 239000004703 cross-linked polyethylene Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
- G01R31/1263—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation
- G01R31/1272—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation of cable, line or wire insulation, e.g. using partial discharge measurements
-
- 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
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/16—Cables, cable trees or wire harnesses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Biophysics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- Manufacturing & Machinery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention provides a power cable insulation aging life advanced prediction method and a system, wherein index historical data are selected, index prediction is carried out by adopting a cyclic neural network method, the cyclic neural network can generate a memory function for the state at the last moment and is used for calculating an output vector at the current moment, the method has unique superiority in predicting time sequence data, can accurately evaluate the operation reliability of the cable, calculates the residual insulation aging life of the cable, and has higher prediction precision compared with the traditional BP neural network method under the same data scale and calculation environment.
Description
Technical Field
The invention relates to the technical field of power system equipment management, in particular to a power cable insulation aging life advanced prediction method and system.
Background
Compared with an overhead line, the cable has the advantages of small occupied area, high reliability, large distributed capacitance, small maintenance workload, small electric shock probability and the like. In addition, with the development of the power system, the cable has more favorable conditions for ultra-high voltage, large capacity and long-distance development, so that the proportion of the cable to the total number of transmission lines is gradually increased in the development process of the power system.
However, the above factors also aggravate the problems of serious repeated production, repeated construction, surplus productivity, uneven process and quality in the cable production industry, and bring great challenges to the safe, efficient and economic operation of the power system. Therefore, the power cable is subjected to the whole life cycle management, various costs can be comprehensively considered, the total cost is reduced, the reliability of equipment and systems is improved, and benefits are improved.
However, the existing work is mainly developed aiming at a specific index, and for the power cable in the actual operation of engineering, the life and state of the power cable cannot be predicted and comprehensively estimated in real time, or the prediction and estimation result is difficult to reflect the coupling property with time. In addition, most of the current methods for predicting the service life and evaluating the state of the cable are to carry out evaluation calculation in a laboratory through experiments after the cable is returned, so that the practical value is not high. Along with the continuous increase of the current online monitoring data volume and the development of cloud computing technology, the advantages of the artificial intelligence method are gradually highlighted, and the application of the artificial intelligence method to the whole life cycle management of the power cable has good development and application prospects, and is an important research direction in the field.
Disclosure of Invention
The invention aims to provide a power cable insulation aging life advanced prediction method and system, which aim to solve the problem that the service life of a cable cannot be predicted and comprehensively estimated in real time in the prior art, realize accurate evaluation of the operation reliability of the cable and improve the prediction precision.
In order to achieve the technical purpose, the invention provides a power cable insulation aging life advance prediction method, which comprises the following steps:
S1, acquiring cable online state evaluation index historical data, and converting the index historical data into time sequence data with the same time interval;
S2, training and learning index historical data by adopting a cyclic neural network method, and carrying out online advanced prediction on future index data;
And S3, constructing and calculating a cable reliability index by using a fuzzy analytic hierarchy process according to the index prediction result, and calculating the residual insulation aging life of the cable according to the operation time and the reliability index.
Preferably, the index history data includes a dielectric loss tangent tan δ, a direct current leakage current I, and a ground capacitance current I c.
Preferably, the specific process of performing online advanced prediction on the future index data is as follows:
S201, determining the number of neuron nodes of each layer of the circulating neural network;
S202, setting the input vector cut-off length of a neural network;
S203, training and learning index historical data;
s204, conducting advanced prediction on future index data.
Preferably, the specific process of constructing and calculating the reliability index of the cable by using the fuzzy analytic hierarchy process is as follows:
S301, layering a final decision target and each influence factor according to a mutual relation to obtain a hierarchical structure diagram;
s302, constructing a fuzzy judgment matrix;
s303, performing transformation adjustment on the fuzzy judgment matrix to obtain a consistency matrix;
s304, calculating the weight of the evaluation index;
and S305, carrying out normalization processing on all the index data obtained through prediction to obtain the relative aging degree of the cable represented by various indexes, and calculating the reliability index of the final cable according to the relative aging degree and the weight of the cable.
Preferably, the calculation formula of the relative aging degree of the cable is as follows:
Where U i denotes a cable relative aging degree normalization index value, U if denotes a qualification threshold value of the index i, U io denotes an initial value of the index i, and U i denotes a measurement value of the index i.
Preferably, the reliability index is calculated as follows:
Preferably, the remaining insulation aging life of the cable is calculated as follows:
Where T S represents the remaining life of the cable and T R represents the time the cable has been put into operation.
The invention also provides a power cable insulation aging life advance prediction system, which comprises:
The cable historical data processing module is used for acquiring cable online state evaluation index historical data and converting the index historical data into time sequence data with the same time interval;
The future data prediction module is used for training and learning index historical data by adopting a cyclic neural network method and carrying out online advanced prediction on the future index data;
And the cable life calculation module is used for constructing and calculating a cable reliability index by using a fuzzy analytic hierarchy process according to the index prediction result and calculating the residual insulation aging life of the cable according to the operation time and the reliability index.
Preferably, the index history data includes a dielectric loss tangent tan δ, a direct current leakage current I, and a ground capacitance current I c.
Preferably, the remaining insulation aging life of the cable is calculated as follows:
Wherein T S represents the residual life of the cable, T R represents the put-into-service time of the cable, y is a reliability index, U i represents a normalized index value of the relative aging degree of the cable, k i is the weight of the index i, U if represents the qualification threshold of the index i, U io represents the initial value of the index i, and U i represents the measured value of the index i.
The effects provided in the summary of the invention are merely effects of embodiments, not all effects of the invention, and one of the above technical solutions has the following advantages or beneficial effects:
Compared with the prior art, the method has the advantages that index historical data are selected, the index prediction is carried out by adopting the cyclic neural network method, the cyclic neural network can generate a memory function for the state at the last moment and is used for calculating the output vector at the current moment, the method has unique superiority in the aspect of predicting time sequence data, the operation reliability of the cable can be accurately evaluated, the residual insulation aging life of the cable is calculated, and under the same data scale and computing environment, the prediction precision is higher than that of the traditional BP neural network method.
Drawings
FIG. 1 is a flowchart of a method for predicting the advanced life of insulation aging of a power cable according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an overall framework of a method for predicting the advanced life of insulation aging of a power cable according to an embodiment of the present invention;
FIG. 3 is a schematic view of a dielectric loss tangent lead prediction curve provided in an embodiment of the present invention;
FIG. 4 is a schematic diagram of a DC leakage current advanced prediction curve according to an embodiment of the present invention;
Fig. 5 is a schematic diagram of a ground capacitor current lead prediction curve according to an embodiment of the present invention.
Detailed Description
In order to clearly illustrate the technical features of the present solution, the present invention will be described in detail below with reference to the following detailed description and the accompanying drawings. The following disclosure provides many different embodiments, or examples, for implementing different structures of the invention. In order to simplify the present disclosure, components and arrangements of specific examples are described below. Furthermore, the present invention may repeat reference numerals and/or letters in the various examples. This repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed. It should be noted that the components illustrated in the figures are not necessarily drawn to scale. Descriptions of well-known components and processing techniques and processes are omitted so as to not unnecessarily obscure the present invention.
The following describes a method and a system for predicting the advanced service life of insulation aging of a power cable according to an embodiment of the present invention in detail.
As shown in fig. 1 and 2, an embodiment of the invention discloses a power cable insulation aging life advance prediction method, which comprises the following operations:
S1, acquiring cable online state evaluation index historical data, and converting the index historical data into time sequence data with the same time interval;
The index history data includes a dielectric loss tangent tan delta, a direct current leakage current I, and a ground capacitance current I c. To ensure the effectiveness of training, learning, and prediction, the data must be of a certain scale. For these data that continuously change over time, it is impossible to completely predict the continuous change in one day, and it is necessary to process the historical data of the above three indexes into discrete time series, where a certain time interval Δt is taken between two adjacent moments in the time series.
S2, training and learning index historical data by adopting a cyclic neural network method, and carrying out online advanced prediction on future index data;
In a conventional neural network structure, neurons between layers are generally fully connected, and neurons in each layer are not connected in pairs, namely, an output vector at the current moment is only related to an input vector at the current moment, but when time series data are processed, the structure cannot reflect the relation and change rule of the data and time, so that the calculation and prediction effects are often poor.
For the structure of the cyclic neural network, the connection exists between the neurons of the hidden layers of the cyclic neural network, namely, the output at the current moment not only depends on the input at the current moment, but also depends on the system state at the last moment, namely, the cyclic neural network can memorize the past system state and use the past system state to calculate the output vector at the current moment, so that the problem of time series can be better processed.
The calculation process is as follows:
st＝f(Ugit+Wgst-1+b)
ot＝softmax(Vst+c)
In the formula, s t is the state of an implicit layer at the time t, f is an activation function of the neural network, b is a bias vector, W is the weight of the input, and U is the weight of the sample input at the moment. When t=0, s -1＝0.ot is the output at time t by default, V represents the sample weight of the output, and c is the bias vector.
From the above equation, the output of the recurrent neural network is related to all the previous inputs, but in the actual calculation, the relationship between two times with too long interval is considered to be reduced, so the neural network is truncated to have a maximum length, that is, the output of a certain time is related to all the previous inputs in a specific time.
The specific process of adopting the cyclic neural network to conduct advanced prediction is as follows:
S201, determining the number of neuron nodes of each layer of the circulating neural network; the circulating neural network is composed of a plurality of neuron nodes and is divided into an input layer, an hidden layer and an output layer, the neuron nodes among the layers are generally fully connected, in addition, the nodes among the hidden layers in the circulating neural network are also connected, and before training, learning and prediction are carried out by using the neural network, the scale of the circulating neural network, namely the quantity and the connection relation of the neurons of each layer, must be determined;
S202, when training the cyclic neural network, setting the input vector cut-off length of the neural network as l, namely, indicating that an index predicted value at a certain moment is related to index data and change trend in the previous l multiplied by delta t time;
S203, training and learning index historical data, and reserving a certain proportion of verification data sets for preventing overfitting;
S204, carrying out advanced prediction on future index data;
s205, calculating the root mean square error between the predicted result and the true value, wherein the calculation formula is as follows:
Wherein X is a set of predicted values of each time of a certain index, N is a predicted time number, X (t) is a predicted value of a t-th time index X, Is the true value of the time index X at the t-th moment.
And S3, constructing and calculating a cable reliability index by using a fuzzy analytic hierarchy process according to the index prediction result, and calculating the residual insulation aging life of the cable according to the operation time and the reliability index.
The specific process of constructing and calculating the cable reliability index by using the fuzzy analytic hierarchy process is as follows:
S301, layering a final decision target and each influence factor according to a mutual relation to obtain a hierarchical structure diagram;
S302, a fuzzy judgment matrix a= (a ij)n×n, wherein an element a ij in the matrix represents the importance of the index i relative to the index j, the importance of the index is evaluated according to a scale of 0.1-0.9, and a ij+aji =1 (i, j=1, 2, …, n) is satisfied, and the scale rule is shown in table 1:
TABLE 1
S303, performing transformation adjustment on the fuzzy judgment matrix to obtain a consistency matrix B, wherein a transformation formula is as follows:
bij＝(bi-bj)/[2(n-1)]+0.5
s304, calculating the weight k i of the evaluation index i, wherein the calculation formula is as follows:
s305, carrying out normalization processing on all index data obtained through prediction to obtain the relative aging degree of the cable represented by various indexes, wherein the formula is as follows:
Where U i denotes a cable relative aging degree normalization index value, U if denotes a qualification threshold value of the index i, U io denotes an initial value of the index i, and U i denotes a measurement value of the index i. The greater the value of u i, the less aged the cable.
And calculating the reliability index y of the final cable according to the relative aging degree and the weight of the cable, wherein the calculation formula is as follows:
where a larger value of y indicates a longer remaining life of the cable.
And calculating the residual insulation aging life of the cable through the operation time and the reliability index, wherein the calculation formula is as follows:
Where T S represents the remaining life of the cable and T R represents the time the cable has been put into operation.
The embodiment of the invention selects a 110kV voltage class crosslinked polyethylene cable which is put into operation in 9 months and 16 days in 2007 as an example, and further describes the specific implementation process of the invention.
And selecting index real-time monitoring data between 1 month and 1 day in 2010 and 31 days in 2017 and 12 months in 2010 to train and learn the neural network, wherein the sampling time interval is 1 hour, and the total data is 70128 groups. Setting the cut-off length of the circulating neural network to 48, namely, the index value at a certain moment is related to the index value in the previous 48 hours, so that the index data between 1 month 1 day in 2018 and 31 days 12 months 31 in 2019 are predicted online. And compares the predicted result with a conventional BP neural network (BPNN) predicted result. The on-line predictions of the various indices are shown in fig. 3-5, and the root mean square error between the predictions and the true values of the indices are shown in table 2:
TABLE 2
Therefore, the prediction based on the cyclic neural network provided by the embodiment of the invention can accurately predict the insulation aging index of various power cables on line, and compared with the traditional BP neural network, the accuracy is higher, and the effectiveness and the superiority of the method are proved.
And combining the prediction results of all indexes to obtain the cable with the residual insulation aging life of about 4 months in 11 years by the year bottom of 2019.
According to the embodiment of the invention, the index prediction is carried out by adopting a cyclic neural network method, the cyclic neural network can generate a memory function for the state at the last moment and is used for calculating the output vector at the current moment, the method has unique advantages in the aspect of predicting time sequence data, the operation reliability of the cable can be accurately evaluated, the residual insulation aging life of the cable is calculated, and under the same data scale and calculation environment, the prediction precision is higher than that of the traditional BP neural network method.
The embodiment of the invention also discloses a power cable insulation aging life advance prediction system, which comprises:
The cable historical data processing module is used for acquiring cable online state evaluation index historical data and converting the index historical data into time sequence data with the same time interval;
The future data prediction module is used for training and learning index historical data by adopting a cyclic neural network method and carrying out online advanced prediction on the future index data;
And the cable life calculation module is used for constructing and calculating a cable reliability index by using a fuzzy analytic hierarchy process according to the index prediction result and calculating the residual insulation aging life of the cable according to the operation time and the reliability index.
The advanced prediction method for the insulation aging life of the power cable is realized by the system.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (4)
1. A method for advanced prediction of insulation aging life of a power cable, the method comprising the steps of:
S1, acquiring cable online state evaluation index historical data, and converting the index historical data into time sequence data with the same time interval;
S2, training and learning index historical data by adopting a cyclic neural network method, and carrying out online advanced prediction on future index data;
S3, constructing and calculating a cable reliability index by using a fuzzy analytic hierarchy process according to the index prediction result, and calculating the residual insulation aging life of the cable according to the operation time and the reliability index;
The index historical data comprise a dielectric loss tangent tan delta, a direct current leakage current I and a grounding capacitance current I c;
the calculation formula of the relative aging degree of the cable is as follows:
Wherein U i represents a normalized index value of relative aging degree of the cable, U if represents a qualification threshold value of the index i, U io represents an initial value of the index i, and U i represents a measured value of the index i;
the calculation formula of the reliability index is as follows:
The residual insulation aging life of the cable is calculated as follows:
Where T S represents the remaining life of the cable and T R represents the time the cable has been put into operation.
2. The power cable insulation aging life advance prediction method according to claim 1, wherein the specific process of performing online advance prediction on future index data is as follows:
S201, determining the number of neuron nodes of each layer of the circulating neural network;
S202, setting the input vector cut-off length of a neural network;
S203, training and learning index historical data;
s204, conducting advanced prediction on future index data.
3. The method for predicting the insulation aging life of the power cable according to claim 1, wherein the specific process of constructing and calculating the reliability index of the cable by using the fuzzy analytic hierarchy process is as follows:
S301, layering a final decision target and each influence factor according to a mutual relation to obtain a hierarchical structure diagram;
s302, constructing a fuzzy judgment matrix;
s303, performing transformation adjustment on the fuzzy judgment matrix to obtain a consistency matrix;
s304, calculating the weight of the evaluation index;
and S305, carrying out normalization processing on all the index data obtained through prediction to obtain the relative aging degree of the cable represented by various indexes, and calculating the reliability index of the final cable according to the relative aging degree and the weight of the cable.
4. A power cable insulation aging life advance prediction system, the system comprising:
The cable historical data processing module is used for acquiring cable online state evaluation index historical data and converting the index historical data into time sequence data with the same time interval;
The future data prediction module is used for training and learning index historical data by adopting a cyclic neural network method and carrying out online advanced prediction on the future index data;
the cable life calculation module is used for constructing and calculating a cable reliability index by using a fuzzy analytic hierarchy process according to the index prediction result, and calculating the residual insulation aging life of the cable according to the operation time and the reliability index;
The index historical data comprise a dielectric loss tangent tan delta, a direct current leakage current I and a grounding capacitance current I c;
The residual insulation aging life of the cable is calculated as follows:
Wherein T S represents the residual life of the cable, T R represents the put-into-service time of the cable, y is a reliability index, U i represents a normalized index value of the relative aging degree of the cable, k i is the weight of the index i, U if represents the qualification threshold of the index i, U io represents the initial value of the index i, and U i represents the measured value of the index i.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010830377.5A CN112115636B (en) | 2020-08-18 | 2020-08-18 | Advanced prediction method and system for insulation aging life of power cable |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010830377.5A CN112115636B (en) | 2020-08-18 | 2020-08-18 | Advanced prediction method and system for insulation aging life of power cable |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112115636A CN112115636A (en) | 2020-12-22 |
| CN112115636B true CN112115636B (en) | 2024-06-14 |
Family
ID=73803768
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010830377.5A Active CN112115636B (en) | 2020-08-18 | 2020-08-18 | Advanced prediction method and system for insulation aging life of power cable |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112115636B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113204857A (en) * | 2021-03-15 | 2021-08-03 | 北京锐达芯集成电路设计有限责任公司 | Method for predicting residual life of electronic device based on extreme gradient lifting tree algorithm |
| CN113128111A (en) * | 2021-04-12 | 2021-07-16 | 中国南方电网有限责任公司超高压输电公司昆明局 | Diagnostic method and diagnostic device for operating parameters in ultra-high voltage circuit |
| CN115600478B (en) * | 2021-06-28 | 2023-08-15 | 中企网络通信技术有限公司 | Software defined wide area network analysis system and method of operation thereof |
| CN113763205A (en) * | 2021-09-07 | 2021-12-07 | 南方电网电力科技股份有限公司 | Cable insulation state detection method and related device |
| CN114323337B (en) * | 2021-11-30 | 2024-09-17 | 上海海能信息科技股份有限公司 | Cable conductor temperature prediction method and system considering historical data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102735970A (en) * | 2012-06-15 | 2012-10-17 | 安徽中兴继远信息技术股份有限公司 | Insulation monitoring and life prediction method of cross linked polyethylene cable |
| CN104166788A (en) * | 2014-07-22 | 2014-11-26 | 国家电网公司 | Overhead transmission line optimal economic life range assessment method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107516015A (en) * | 2017-08-29 | 2017-12-26 | 武汉大学 | Composite insulator ageing state comprehensive estimation method based on multi-characteristicquantity quantity |
| CN109031014B (en) * | 2017-12-28 | 2020-08-14 | 国网湖北省电力公司宜昌供电公司 | Transformer comprehensive reliability assessment and prediction method based on operation data |
| CN109902336A (en) * | 2019-01-15 | 2019-06-18 | 国网浙江省电力有限公司 | Cable insulation lifetime estimation method based on Fuzzy AHP |
| CN110321601B (en) * | 2019-06-14 | 2021-03-26 | 山东大学 | Advanced prediction method and system for dynamic current carrying capacity of overhead line |
| CN110378052B (en) * | 2019-07-25 | 2020-11-06 | 北京航空航天大学 | Equipment residual life prediction method considering future working conditions based on cyclic neural network |
-
2020
- 2020-08-18 CN CN202010830377.5A patent/CN112115636B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102735970A (en) * | 2012-06-15 | 2012-10-17 | 安徽中兴继远信息技术股份有限公司 | Insulation monitoring and life prediction method of cross linked polyethylene cable |
| CN104166788A (en) * | 2014-07-22 | 2014-11-26 | 国家电网公司 | Overhead transmission line optimal economic life range assessment method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112115636A (en) | 2020-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112115636B (en) | Advanced prediction method and system for insulation aging life of power cable | |
| CN110263866B (en) | Power consumer load interval prediction method based on deep learning | |
| CN111736084B (en) | Valve-regulated lead-acid storage battery health state prediction method based on improved LSTM neural network | |
| CN113156917A (en) | Power grid equipment fault diagnosis method and system based on artificial intelligence | |
| CN111539515A (en) | Complex equipment maintenance decision method based on fault prediction | |
| CN107274067B (en) | Distribution transformer overload risk assessment method | |
| CN113723010A (en) | Bridge damage early warning method based on LSTM temperature-displacement correlation model | |
| CN116167527B (en) | Pure data-driven power system static safety operation risk online assessment method | |
| CN110210670A (en) | A kind of prediction technique based on power-system short-term load | |
| CN113516271A (en) | Wind power cluster power day-ahead prediction method based on space-time neural network | |
| CN111680712B (en) | Method, device and system for predicting oil temperature of transformer based on similar time in day | |
| CN113758652B (en) | Oil leakage detection method and device for converter transformer, computer equipment and storage medium | |
| CN106408016A (en) | Distribution network power outage time automatic identification model construction method | |
| CN112541634B (en) | Method and device for predicting top-layer oil temperature and discriminating false alarm and storage medium | |
| Zhang et al. | Remaining useful life prediction of lithium-ion batteries based on TCN-DCN fusion model combined with IRRS filtering | |
| CN117407675A (en) | Lightning arrester leakage current prediction method based on multi-variable reconstruction combined dynamic weight | |
| CN112363012A (en) | Power grid fault early warning device and method | |
| CN116452070A (en) | Large-scale equipment health assessment method and device under multi-identification framework | |
| CN116401610A (en) | Inverter parameter fault diagnosis method based on depth residual error network and joint distribution | |
| Gan | Discrete Hopfield neural network approach for crane safety evaluation | |
| Yang et al. | Prediction of top oil Temperature for oil-immersed transformers Based on PSO-LSTM | |
| Liu et al. | Long-Term Prediction of Multistress Accelerated Aging of Capacitors by Long Short-Term Memory Network | |
| CN115221731A (en) | Transformer life evaluation method based on data fusion and Wiener model | |
| CN114741952A (en) | Short-term load prediction method based on long-term and short-term memory network | |
| Moradzadeh et al. | Image processing-based data integrity attack detection in dynamic line rating forecasting applications |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |