CN111610407A - Cable aging state evaluation method and device based on naive Bayes - Google Patents

Cable aging state evaluation method and device based on naive Bayes Download PDF

Info

Publication number
CN111610407A
CN111610407A CN202010417893.5A CN202010417893A CN111610407A CN 111610407 A CN111610407 A CN 111610407A CN 202010417893 A CN202010417893 A CN 202010417893A CN 111610407 A CN111610407 A CN 111610407A
Authority
CN
China
Prior art keywords
cable
aging state
naive bayes
variables
relevant parameters
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.)
Granted
Application number
CN202010417893.5A
Other languages
Chinese (zh)
Other versions
CN111610407B (en
Inventor
谭笑
陈杰
刘洋
王永强
柏仓
李陈莹
胡丽斌
曹京荥
张伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
State Grid Jiangsu Electric Power Co Ltd
Electric Power Research Institute of State Grid Jiangsu Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
State Grid Jiangsu Electric Power Co Ltd
Electric Power Research Institute of State Grid Jiangsu Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, State Grid Jiangsu Electric Power Co Ltd, Electric Power Research Institute of State Grid Jiangsu Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202010417893.5A priority Critical patent/CN111610407B/en
Publication of CN111610407A publication Critical patent/CN111610407A/en
Application granted granted Critical
Publication of CN111610407B publication Critical patent/CN111610407B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G01R31/08—Locating faults in cables, transmission lines, or networks
    • G01R31/088—Aspects of digital computing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks

Abstract

The invention discloses a cable aging state evaluation method and device based on naive Bayes, wherein the method comprises the following steps: collecting relevant parameters of a cable to be evaluated; inputting relevant parameters of the cable into a pre-constructed naive Bayes classifier, and evaluating the aging state of the cable; the pre-constructed naive Bayes classifier is constructed by the following method: acquiring relevant parameters and cable aging states of the existing cable as training data; and calculating prior probability of each attribute variable based on a training data set by taking the relevant parameters of the cable in the training data as the attribute variables of the naive Bayes classification model and the aging state of the cable as class variables, and establishing a naive Bayes classifier. The method can accurately evaluate the aging state of the cable at lower calculation cost based on a small amount of samples, and provides targeted guidance for the operation and maintenance of the cable.

Description

Cable aging state evaluation method and device based on naive Bayes
Technical Field
The invention belongs to the technical field of power equipment maintenance, and particularly relates to a cable aging state evaluation method and device.
Background
Cables are very important electrical devices that fail to cause a power outage to the consumer. If the aging state of the cable can be evaluated before the cable breaks down, the cable can be overhauled and replaced in time, the fault loss can be reduced, and the power supply reliability is improved.
The cable aging state evaluation method mainly comprises two categories: 1) the slicing method comprises the steps of manufacturing a cable sample slice, and detecting the cable sample slice, wherein the physical and chemical properties are detected as follows: the cable aging degree is judged according to physicochemical detection results, such as a Fourier transform infrared spectrometer, differential calorimetric scanning analysis, X-ray diffraction analysis, scanning electron microscope analysis and the like. For example, in a method for judging the aging state of the insulating water tree of the XLPE cable disclosed in the publication No. CN 102778638A, the aging degree of the insulating water tree of the cable is comprehensively evaluated and diagnosed by carrying out the physicochemical test and then according to data such as dielectric loss peak, low-frequency conductance, thickness change of lamella, radical disappearance and the like; after the cable sample is sliced, the test results are visual, but the requirements of actual cable operation and maintenance are difficult to meet; 2) and the mathematical method is used for establishing a mathematical model by analyzing various influence factors of cable aging and evaluating the cable aging state. For example, in a cable state evaluation method based on a probabilistic neural network algorithm disclosed in publication number CN 106251059 a, a multi-source information database is constructed according to multiple categories of information sources such as basic information, operation inspection information, family defects and the like of cable equipment; and preprocessing a database under incomplete information by using a factor analysis method, providing a multi-source information fusion algorithm based on a probabilistic neural network, and comprehensively evaluating the overall state of the cable under the condition of the incomplete information. For example, in a power cable state evaluation method based on the momentum BP neural network of publication No. CN 109272190A, a momentum BP neural network into which momentum factors are introduced is established to evaluate an operation state of a power cable. However, the neural network needs a large amount of data to train, and practical operation experience shows that the relevant sample data of cable aging is less. How to establish an accurate evaluation model by analyzing less sample data is a problem worthy of study.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the defects of the prior art, the invention provides a cable aging state evaluation method and device based on naive Bayes, which can evaluate the cable aging state according to cable aging influence factors and provide guidance for operation and maintenance of cables.
The technical scheme is as follows: in order to achieve the above purpose, the invention adopts the following technical scheme:
in a first aspect, a cable aging state evaluation method based on naive Bayes is provided, which comprises the following steps:
collecting relevant parameters of a cable to be evaluated;
inputting relevant parameters of the cable to be evaluated into a pre-constructed naive Bayes classifier, and evaluating the aging state of the cable; the pre-constructed naive Bayes classifier is constructed by the following method:
acquiring relevant parameters and cable aging states of the existing cable as training data;
and (3) taking the relevant parameters of the cable in the training data as attribute variables of a naive Bayes classification model, taking the cable aging state as a class variable, calculating the prior probability of each attribute variable, and establishing a naive Bayes classifier.
Wherein, the related parameters of the cable comprise: cable running time, whether the cable has an earth fault, cable partial discharge and cable dielectric loss.
Further, when the prior probability of each attribute variable is calculated, the prior probability is calculated by using the frequency of laplace correction for the discrete variable, and the prior probability is calculated by using gaussian distribution for the continuous variable.
The prior probability is calculated by using the frequency of the laplace correction on the discrete variable, and the specific formula is as follows:
Figure BDA0002495756780000021
Figure BDA0002495756780000022
wherein the variable X is discretetA total of m values, i.e. { xt1,xt2,…,xtmP (c) is the probability value of the cable status class c, P (x)tiI c) is a discrete variable X when the cable status category is ctHas a value of xtiI is more than or equal to 1 and less than or equal to m, DcIndicates the number of cable status categories c, D indicates the total number,
Figure BDA0002495756780000023
discrete variable X representing cable state as class ctHas a value of xtiN denotes the number of possible cable state classes, NtRepresents variable XtThe number of possible categories.
The calculating the prior probability by adopting the Gaussian distribution on the continuous variable comprises the following steps:
for continuous variable XjCalculating the continuous variable X when the class is c by using Gaussian distributionjHas a value of xjkThe specific formula of the probability value of (2) is as follows:
Figure BDA0002495756780000024
wherein P (x)jk| c) is when the class is c, the continuous variable XjHas a value of xjkThe probability value mu is an average value and is a standard deviation, both are obtained by variables in the training data, and the calculation formula is as follows:
Figure BDA0002495756780000031
Figure BDA0002495756780000032
wherein xj1,xj2,…,xjnRepresenting continuous variables X in training datajOf (2), i.e. Xj＝{xj1,xj2,…,xjn}。
The expression of the naive bayes classifier is as follows:
Figure BDA0002495756780000033
wherein c represents the cable aging state category, y is the value set of c, argmax is a function, if there is a result x0Argmax (f (x)) means when the function f (x) takes x ═ x0When f (x) is obtained, the maximum value of the value range of f (x) is obtained, and the argmax function returns x which enables f (x) to be maximum in value, so that hnb(x) Is shown to make
Figure BDA0002495756780000034
The category c with the largest value.
Preferably, the method further comprises: and preprocessing the cable data, wherein the preprocessing comprises deleting missing data and abnormal data, the abnormal data are detected by using description statistics in the SPSS, and the data with the Z score larger than 3 or smaller than-3 are regarded as the abnormal data.
In a second aspect, a naive bayes-based cable aging state evaluation apparatus is provided, which includes:
the system comprises a parameter acquisition module, a parameter evaluation module and a parameter analysis module, wherein the parameter acquisition module is used for collecting relevant parameters of a cable to be evaluated and acquiring relevant parameters and a cable aging state of an existing cable, and the relevant parameters and the cable aging state of the existing cable form training data;
the model building module is used for building a cable aging state evaluation model based on a naive Bayesian classification model according to relevant parameters and an aging state of a cable in training data, wherein the cable aging state evaluation model takes the relevant parameters of the cable in the training data as attribute variables of the naive Bayesian classification model, takes the cable aging state as class variables, and calculates prior probabilities of the attribute variables;
and the state evaluation module is used for evaluating the aging state of the cable according to the relevant parameters of the cable to be evaluated and the cable aging state evaluation model.
Wherein the relevant parameters of the cable include: cable running time, whether the cable has an earth fault, cable partial discharge and cable dielectric loss.
Further, when the model building module calculates the prior probability of each attribute variable, the prior probability is calculated by using the frequency of laplacian correction on the discrete variable, and the prior probability is calculated by using gaussian distribution on the continuous variable.
Has the advantages that: the invention evaluates the aging state of the cable by analyzing possible influence factors of the cable aging fault by using a naive Bayes classification method. Naive Bayes is a typical sample machine learning method, a posterior probability is deduced through a prior probability, evaluation and judgment are made according to the posterior probability, compared with the prior art, the method does not need to slice a cable sample, the required sample size is small, the method is quick and simple, and the aging state of the cable is evaluated in a grading way by analyzing the cable detection state quantity, the operation time, whether the cable has a ground fault or not, and the like, so that more targeted guidance can be provided for the operation and maintenance of the cable.
Drawings
Fig. 1 is a general flowchart of a cable aging state evaluation method based on naive bayes according to the present invention.
Detailed Description
The technical scheme of the invention is further clarified by the following specific embodiments in combination with the attached drawings.
Referring to fig. 1, the cable aging state evaluation method based on naive bayes of the invention comprises the following steps:
and step A, collecting related data of the cable. Including cable run time, whether the cable has an earth fault, partial discharge of the cable, dielectric loss of the cable, aging state of the cable, etc.
As shown in Table 1, which is an example of data obtained in one embodiment, the total number of data collected is 50, 33 of which are slightly aged, 8 of which are moderately aged, and 9 of which are severely aged, and there are 4 variables in the table that may be related to cable aging, X respectively1，X2，X3，X4. X for cable aging degree5And (4) showing.
TABLE 1 Cable related data
Figure BDA0002495756780000041
Figure BDA0002495756780000051
Figure BDA0002495756780000061
And B, preprocessing the data based on the cable related data acquired in the step A, mainly deleting missing data and abnormal data, wherein the abnormal data is detected by description statistics in SPSS, and regarding the data with the Z score larger than 3 or smaller than-3 as abnormal data.
And C: and B, establishing a naive Bayes classifier based on the data preprocessed in the step B.
From the data shown in table 1, a total of 4 variables can be seen, wherein the operation time, the partial discharge and the dielectric loss are continuous variables, and whether the ground fault occurs is a discrete variable.
Firstly, calculating the probability of cable aging state categories, wherein the number of cable aging states is 3, and the possible values of c are 1, 2 and 3. According to the frequency of Laplace correction, calculating the prior probability of the cable aging state to obtain:
Figure BDA0002495756780000062
Figure BDA0002495756780000063
Figure BDA0002495756780000064
for discrete variable, calculating prior probability by using frequency of Laplace correction, and for variable X2(whether or not a ground fault occurs), the variable X is calculated based on the frequency of the Laplace correction2The prior conditional probability of (a) can be obtained:
Figure BDA0002495756780000065
Figure BDA0002495756780000066
Figure BDA0002495756780000071
Figure BDA0002495756780000072
Figure BDA0002495756780000073
Figure BDA0002495756780000074
for the continuous type variables, the gaussian distribution parameters for each variable were found as follows:
TABLE 2 Gaussian distribution parameters of continuous variables
Figure BDA0002495756780000075
The conditional probabilities of the values of the variables when the cable states are of different classes (e.g., c-1, c-2, or c-3) can be determined by a gaussian distribution function. For example for variable X1When the cable status category is c ═ 1, then the variable X is added1Has a value of x1kThe conditional probability at this time:
Figure BDA0002495756780000076
for other cases of variables, a similar method can be used to determine the conditional probability.
Based on the cable aging state category probability and the conditional probability of each variable value, a naive Bayes classifier can be constructed, and the expression is as follows:
Figure BDA0002495756780000077
step D: inputting a cable state parameter (for example, the related parameter data of a certain cable is X) according to the naive Bayes classifier established in the step C1＝235，X2＝1，X3＝14，X40.08), each when the cable state c is 1, c is 2 and c is 3 is calculated according to a bayesian classifier
Figure BDA0002495756780000078
A value of (A), as a resultThe following:
when c is equal to 1, the reaction is carried out,
Figure BDA0002495756780000081
when c is equal to 2, the process is carried out,
Figure BDA0002495756780000082
when c is 3, the process is repeated,
Figure BDA0002495756780000083
comparing the above calculation results, it is known that the probability value is 151.6 (relative probability) at the maximum when c is 3, and thus it is possible to determine that the state of the cable is c 3, that is, a severely aged state.
According to another embodiment of the present invention, there is provided a naive bayes-based cable aging state evaluation apparatus, including:
the parameter acquisition module is used for collecting related parameters of the cable; the cable related parameters include: cable running time, whether the cable has an earth fault, cable partial discharge and cable dielectric loss.
The model building module is used for building a cable aging state evaluation model based on a naive Bayesian classification model according to relevant parameters and an aging state of a cable in training data, wherein the cable aging state evaluation model takes the relevant parameters of the cable as attribute variables of the naive Bayesian classification model, the cable aging state as class variables, the prior probability of each attribute variable is calculated, the prior probability is calculated by adopting the frequency of Laplace correction on discrete variables, and the prior probability is calculated by adopting Gaussian distribution on continuous variables. Specifically, the calculating the prior probability by using the frequency of the laplace correction on the discrete variable includes:
let discrete variable XtA total of m values, i.e. { xt1,xt2,…,xtmCalculating category probability and discrete variable X by using frequency corrected by LaplacetValue of xtiThe concrete formula of the prior probability is as follows:
Figure BDA0002495756780000084
Figure BDA0002495756780000091
wherein P (c) is a class probability value, P (x)tiI c) is the discrete variable X when the cable status category is ctHas a value of xtiI is more than or equal to 1 and less than or equal to m, DcIndicates the number of cable status categories c, D indicates the total number,
Figure BDA0002495756780000092
discrete variable X representing cable state as class ctHas a value of xtiN denotes the number of possible cable state classes, NtRepresents variable XtThe number of possible categories.
Calculating the prior probability using a gaussian distribution for the continuous variables includes:
for continuous variable XjOf variable XjObeying Gaussian distribution, calculating continuous variable X when the category is c by adopting Gaussian distributionjHas a value of xjkThe specific formula of the probability value of (2) is as follows:
Figure BDA0002495756780000093
wherein P (x)jk| c) is when the class is c, the continuous variable XjHas a value of xjkThe probability value of (a) is the mean value and the standard deviation, both are obtained by the variable in the training data, assuming the continuous variable X in the training dataj＝{xj1,xj2,…,xjnAnd then:
Figure BDA0002495756780000094
Figure BDA0002495756780000095
the cable aging state evaluation model expression based on the naive Bayes classification model is as follows:
Figure BDA0002495756780000096
wherein c represents the cable aging state category, y is the value set of c, argmax is a function, if there is a result x0Argmax (f (x)) means when the function f (x) takes x ═ x0When f (x) is obtained, the maximum value of the value range of f (x) is obtained, and the argmax function returns x which enables f (x) to be maximum in value, so that hnb(x) Is shown to make
Figure BDA0002495756780000097
The category c with the largest value.
And the state evaluation module is used for evaluating the aging state of the cable according to the relevant parameters of the cable to be evaluated and the cable aging state evaluation model. Specifically, a cable state parameter X to be evaluated is input into a cable aging state evaluation model, and each category c of the cable aging states different from each other is calculated
Figure BDA0002495756780000101
And taking the category c corresponding to the maximum probability value as the finally estimated cable aging state.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.

Claims (10)

1. A cable aging state evaluation method based on naive Bayes is characterized by comprising the following steps:
collecting relevant parameters of a cable to be evaluated;
inputting relevant parameters of the cable to be evaluated into a pre-constructed naive Bayes classifier, and evaluating the aging state of the cable; the pre-constructed naive Bayes classifier is constructed by the following method:
acquiring relevant parameters and cable aging states of the existing cable as training data;
and calculating prior probability of each attribute variable based on a training data set by taking the relevant parameters of the cable in the training data as the attribute variables of the naive Bayes classification model and the aging state of the cable as class variables, and establishing a naive Bayes classifier.
2. The naive bayes-based cable aging state assessment method according to claim 1, wherein the cable related parameters comprise: cable running time, whether the cable has an earth fault, cable partial discharge and cable dielectric loss.
3. The naive bayes-based cable aging state evaluation method according to claim 1, wherein, when calculating the prior probabilities of the attribute variables, the prior probabilities are calculated by using laplace correction frequency for discrete variables and the prior probabilities are calculated by using gaussian distribution for continuous variables.
4. The naive bayes-based cable aging state evaluation method according to claim 3, wherein the prior probability is calculated by using the frequency of laplace correction on the discrete variables, and the specific formula is as follows:
Figure FDA0002495756770000011
Figure FDA0002495756770000012
therein, get awayVariance XtA total of m values, denoted as { x }t1,xt2,…,xtmP (c) is the probability value of the cable status class c, P (x)tiI c) is a discrete variable X when the cable status category is ctHas a value of xtiI is more than or equal to 1 and less than or equal to m, DcIndicates the number of cable status categories c, D indicates the total number,
Figure FDA0002495756770000013
discrete variable X representing cable state as class ctHas a value of xtiN denotes the number of possible cable state classes, NtRepresents variable XtThe number of possible categories.
5. The naive bayes-based cable aging state assessment method of claim 3, wherein said computing a prior probability using a gaussian distribution for continuous variables comprises:
for continuous variable XjCalculating the continuous variable X when the class is c by using Gaussian distributionjHas a value of xjkThe specific formula of the probability value of (2) is as follows:
Figure FDA0002495756770000021
wherein P (x)jkI c) is a continuous variable X when the cable status category is cjHas a value of xjkThe probability value mu is an average value and is a standard deviation, both are obtained by variables in the training data, and the calculation formula is as follows:
Figure FDA0002495756770000022
Figure FDA0002495756770000023
wherein xj1,xj2,…,xjnRepresenting continuous variables X in training datajOf (1).
6. The naive bayes-based cable aging state assessment method of claim 1, wherein the expression of the naive bayes classifier is as follows:
Figure FDA0002495756770000024
wherein c represents the cable aging state category, y is the value set of c, argmax is a function, if there is a result x0Argmax (f (x)) means when the function f (x) takes x ═ x0When f (x) is obtained, the maximum value of the value range of f (x) is obtained, and the argmax function returns x which enables f (x) to be maximum in value, so that hnb(x) Is shown to make
Figure FDA0002495756770000025
The category c with the largest value.
7. The naive bayes-based cable aging state assessment method of claim 1, further comprising: and preprocessing the cable data, wherein the preprocessing comprises deleting missing data and abnormal data, the abnormal data are detected by using description statistics in the SPSS, and the data with the Z score larger than 3 or smaller than-3 are regarded as the abnormal data.
8. A cable aging state evaluation device based on naive Bayes, comprising:
the system comprises a parameter acquisition module, a parameter evaluation module and a parameter analysis module, wherein the parameter acquisition module is used for collecting relevant parameters of a cable to be evaluated and acquiring relevant parameters and a cable aging state of an existing cable, and the relevant parameters and the cable aging state of the existing cable form training data;
the model building module is used for building a cable aging state evaluation model based on a naive Bayesian classification model according to relevant parameters of cables in the training data and the cable aging state, wherein the cable aging state evaluation model takes the relevant parameters of the cables in the training data as attribute variables of the naive Bayesian classification model, takes the cable aging state as class variables, and calculates the prior probability of each attribute variable;
and the state evaluation module is used for evaluating the aging state of the cable according to the relevant parameters of the cable to be evaluated and the cable aging state evaluation model.
9. The naive bayes-based cable aging state assessment apparatus according to claim 8, wherein the cable's relevant parameters include: cable running time, whether the cable has an earth fault, cable partial discharge and cable dielectric loss.
10. The naive bayes-based cable aging state evaluation device according to claim 8, wherein when the model construction module calculates the prior probability of each attribute variable, the prior probability is calculated by using the frequency of laplace correction for discrete variables and the prior probability is calculated by using gaussian distribution for continuous variables.
CN202010417893.5A 2020-05-18 2020-05-18 Cable aging state evaluation method and device based on naive Bayes Active CN111610407B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010417893.5A CN111610407B (en) 2020-05-18 2020-05-18 Cable aging state evaluation method and device based on naive Bayes

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010417893.5A CN111610407B (en) 2020-05-18 2020-05-18 Cable aging state evaluation method and device based on naive Bayes

Publications (2)

Publication Number Publication Date
CN111610407A true CN111610407A (en) 2020-09-01
CN111610407B CN111610407B (en) 2022-10-18

Family

ID=72198878

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010417893.5A Active CN111610407B (en) 2020-05-18 2020-05-18 Cable aging state evaluation method and device based on naive Bayes

Country Status (1)

Country Link
CN (1) CN111610407B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112132811A (en) * 2020-09-24 2020-12-25 安徽德尔电气集团有限公司 Cable service condition comprehensive evaluation system
CN112529067A (en) * 2020-12-04 2021-03-19 国网电力科学研究院武汉南瑞有限责任公司 Power transmission line ice wind disaster fault type evaluation method based on naive Bayes
CN112669190A (en) * 2021-03-17 2021-04-16 北京英视睿达科技有限公司 Detection method and device for abnormal emission behavior of pollution source and computer equipment
CN113569315A (en) * 2021-07-27 2021-10-29 中铁大桥局集团有限公司 Bridge cluster dynamic evaluation method, device, equipment and readable storage medium
CN114062833A (en) * 2021-09-17 2022-02-18 国网山东省电力公司德州供电公司 Single-phase earth fault insulation degradation identification method based on fuzzy inference system
CN115222741A (en) * 2022-09-20 2022-10-21 江苏昱恒电气有限公司 Cable surface defect detection method

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103440493A (en) * 2013-02-27 2013-12-11 中国人民解放军空军装备研究院侦察情报装备研究所 Hyperspectral image blur classification method and device based on related vector machine
CN103454516A (en) * 2013-05-06 2013-12-18 国家电网公司 Intelligent transformer substation secondary equipment health state diagnosis method
CN103839239A (en) * 2014-02-28 2014-06-04 华南理工大学 Self-adaption denoising method for cable porcelain shell terminal infrared images
CN104535905A (en) * 2014-12-11 2015-04-22 国家电网公司 Partial discharge diagnosis method based on naive bayesian classification
US20180092568A1 (en) * 2015-03-31 2018-04-05 Koninklijke Philips N.V. Automatic detection/classification of ecg cable interchange for different ecg lead systems
CN108597603A (en) * 2018-05-04 2018-09-28 吉林大学 Cancer return forecasting system based on Multi-dimensional Gaussian distribution Bayes's classification
CN109060021A (en) * 2018-08-03 2018-12-21 河海大学 A kind of reactor health state evaluation method based on bayesian theory
CN110222744A (en) * 2019-05-23 2019-09-10 成都信息工程大学 A kind of Naive Bayes Classification Model improved method based on attribute weight
CN110390396A (en) * 2018-04-16 2019-10-29 日本电气株式会社 For estimating the causal methods, devices and systems between observational variable
CN110766264A (en) * 2019-07-31 2020-02-07 贵州电网有限责任公司 Transmission cable health state monitoring and evaluating method
CN110955963A (en) * 2019-11-20 2020-04-03 南京航空航天大学 Aviation cable residual life prediction method

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103440493A (en) * 2013-02-27 2013-12-11 中国人民解放军空军装备研究院侦察情报装备研究所 Hyperspectral image blur classification method and device based on related vector machine
CN103454516A (en) * 2013-05-06 2013-12-18 国家电网公司 Intelligent transformer substation secondary equipment health state diagnosis method
CN103839239A (en) * 2014-02-28 2014-06-04 华南理工大学 Self-adaption denoising method for cable porcelain shell terminal infrared images
CN104535905A (en) * 2014-12-11 2015-04-22 国家电网公司 Partial discharge diagnosis method based on naive bayesian classification
US20180092568A1 (en) * 2015-03-31 2018-04-05 Koninklijke Philips N.V. Automatic detection/classification of ecg cable interchange for different ecg lead systems
CN110390396A (en) * 2018-04-16 2019-10-29 日本电气株式会社 For estimating the causal methods, devices and systems between observational variable
CN108597603A (en) * 2018-05-04 2018-09-28 吉林大学 Cancer return forecasting system based on Multi-dimensional Gaussian distribution Bayes's classification
CN109060021A (en) * 2018-08-03 2018-12-21 河海大学 A kind of reactor health state evaluation method based on bayesian theory
CN110222744A (en) * 2019-05-23 2019-09-10 成都信息工程大学 A kind of Naive Bayes Classification Model improved method based on attribute weight
CN110766264A (en) * 2019-07-31 2020-02-07 贵州电网有限责任公司 Transmission cable health state monitoring and evaluating method
CN110955963A (en) * 2019-11-20 2020-04-03 南京航空航天大学 Aviation cable residual life prediction method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
柏晗: "基于加权引文的贝叶斯分类研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
陈新美，等: "基于朴素贝叶斯的局部放电诊断模型", 《计算机应用与软件》 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112132811A (en) * 2020-09-24 2020-12-25 安徽德尔电气集团有限公司 Cable service condition comprehensive evaluation system
CN112529067A (en) * 2020-12-04 2021-03-19 国网电力科学研究院武汉南瑞有限责任公司 Power transmission line ice wind disaster fault type evaluation method based on naive Bayes
CN112669190A (en) * 2021-03-17 2021-04-16 北京英视睿达科技有限公司 Detection method and device for abnormal emission behavior of pollution source and computer equipment
CN113569315A (en) * 2021-07-27 2021-10-29 中铁大桥局集团有限公司 Bridge cluster dynamic evaluation method, device, equipment and readable storage medium
CN113569315B (en) * 2021-07-27 2023-11-28 中铁大桥局集团有限公司 Bridge cluster dynamic evaluation method, device, equipment and readable storage medium
CN114062833A (en) * 2021-09-17 2022-02-18 国网山东省电力公司德州供电公司 Single-phase earth fault insulation degradation identification method based on fuzzy inference system
CN114062833B (en) * 2021-09-17 2024-02-27 国网山东省电力公司德州供电公司 Single-phase earth fault insulation degradation identification method based on fuzzy inference system
CN115222741A (en) * 2022-09-20 2022-10-21 江苏昱恒电气有限公司 Cable surface defect detection method

Also Published As

Publication number Publication date
CN111610407B (en) 2022-10-18

Similar Documents

Publication Publication Date Title
CN111610407B (en) Cable aging state evaluation method and device based on naive Bayes
CN111222290B (en) Multi-parameter feature fusion-based method for predicting residual service life of large-scale equipment
CN106092625A (en) The industrial process fault detection method merged based on correction type independent component analysis and Bayesian probability
CN111611545B (en) Cable aging state assessment method and device based on principal component analysis and logistic regression
CN101738998B (en) System and method for monitoring industrial process based on local discriminatory analysis
CN112904810B (en) Process industry nonlinear process monitoring method based on effective feature selection
CN115409131B (en) Production line abnormity detection method based on SPC process control system
CN113420061B (en) Steady state working condition analysis method, optimization debugging method and system of oil refining and chemical production device
CN114185760A (en) System risk assessment method and device and charging equipment operation and maintenance detection method
CN111931334A (en) Method and system for evaluating operation reliability of cable equipment
CN111612149A (en) Main network line state detection method, system and medium based on decision tree
CN114430361B (en) Abnormal bandwidth detection method and device, electronic equipment and storage medium
CN113721182B (en) Method and system for evaluating reliability of online performance monitoring result of power transformer
CN110084301B (en) Hidden Markov model-based multi-working-condition process working condition identification method
CN113283673A (en) Model performance attenuation evaluation method, model training method and device
CN116401532B (en) Method and system for recognizing frequency instability of power system after disturbance
CN113484817A (en) Intelligent electric energy meter automatic verification system abnormity detection method based on TSVM model
CN112949735A (en) Liquid hazardous chemical substance volatile concentration abnormity discovery method based on outlier data mining
CN110837953A (en) Automatic abnormal entity positioning analysis method
KR101983603B1 (en) Apparatus For Making A Predictive Diagnosis Of Nuclear Power Plant By Machine Learning And Augmented Reality
KR101991296B1 (en) Apparatus For Making A Predictive Diagnosis Of Nuclear Power Plant By Machine Learning
CN111507374A (en) Power grid mass data anomaly detection method based on random matrix theory
Zhang et al. Determining statistical process control baseline periods in long historical data streams
CN111680572B (en) Dynamic judgment method and system for power grid operation scene
CN114565051A (en) Test method of product classification model based on neuron influence degree

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