CN110119713A - Mechanical Failure of HV Circuit Breaker diagnostic method based on D-S evidence theory - Google Patents
Mechanical Failure of HV Circuit Breaker diagnostic method based on D-S evidence theory Download PDFInfo
- Publication number
- CN110119713A CN110119713A CN201910397845.1A CN201910397845A CN110119713A CN 110119713 A CN110119713 A CN 110119713A CN 201910397845 A CN201910397845 A CN 201910397845A CN 110119713 A CN110119713 A CN 110119713A
- Authority
- CN
- China
- Prior art keywords
- evidence
- conflict
- basic probability
- rule
- fuzzy
- 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
- 238000002405 diagnostic procedure Methods 0.000 title abstract 3
- 238000003745 diagnosis Methods 0.000 claims abstract description 22
- 230000003044 adaptive effect Effects 0.000 claims abstract description 13
- 238000000034 method Methods 0.000 claims description 35
- 238000005315 distribution function Methods 0.000 claims description 33
- 230000001537 neural effect Effects 0.000 claims description 17
- 230000005284 excitation Effects 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 14
- 238000010606 normalization Methods 0.000 claims description 14
- 230000005236 sound signal Effects 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 9
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 3
- 239000011541 reaction mixture Substances 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 2
- 230000004927 fusion Effects 0.000 abstract description 10
- 238000010338 mechanical breakdown Methods 0.000 abstract 1
- 238000012937 correction Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008094 contradictory effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/043—Architecture, e.g. interconnection topology based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Automation & Control Theory (AREA)
- Bioinformatics & Computational Biology (AREA)
- Fuzzy Systems (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
This application discloses a kind of Mechanical Failure of HV Circuit Breaker diagnostic method based on D-S evidence theory, which comprises establish Adaptive Neuro-fuzzy Inference model；Obtain the voice signal and vibration signal of high-voltage circuitbreaker；Extract the characteristic quantity of the voice signal and vibration signal；By the Adaptive Neuro-fuzzy Inference model classification pretreatment is carried out to the characteristic quantity respectively, obtains Basic probability assignment function；The Basic probability assignment function is merged by high conflicting evidence modified D-S evidence theory, obtains mechanical fault diagnosis result.Diagnostic method provided by the present application combines sound with vibration signal, carries out information fusion using D-S evidence theory, the mechanical breakdown of comprehensive diagnos high-voltage circuitbreaker improves the reliability and accuracy of status assessment.
Description
Technical Field
The application relates to the technical field of high-voltage circuit breaker mechanical fault diagnosis, in particular to a high-voltage circuit breaker mechanical fault diagnosis method based on a D-S evidence theory.
Background
Due to the rapid development of industrial automation, the automation production line puts higher requirements on power supply reliability and power quality. As one of the most important devices in the entire power system, a high voltage circuit breaker whose stable operation is a necessary condition for improving the reliability of power supply and the quality of electric power. Among various faults of the high-voltage circuit breaker, the main factor influencing the operation reliability of the high-voltage circuit breaker when the high-voltage circuit breaker is in a mechanical fault accounts for 70% -80% of the total fault, so that the mechanical characteristics of the high-voltage circuit breaker need to be monitored on line.
At present, the mechanical characteristics of the circuit breaker are mainly monitored by a signal comparison method, and when a certain characterization signal is changed from a normal condition, a fault is possibly generated. However, since the diagnostic object has a complex operating state and numerous influencing factors, the same fault is often presented differently, the same symptom may be multiple faults, and the fault characteristic quantity obtained by single signal detection generally cannot effectively complete fault diagnosis, so that the accuracy of fault diagnosis is difficult to guarantee.
Disclosure of Invention
The application provides a high-voltage circuit breaker mechanical fault diagnosis method based on a D-S evidence theory, and aims to solve the problem that the accuracy of the existing high-voltage circuit breaker mechanical fault diagnosis method is low.
In order to solve the technical problem, the embodiment of the application discloses the following technical scheme:
the embodiment of the application discloses a high-voltage circuit breaker mechanical fault diagnosis method based on a D-S evidence theory, which comprises the following steps:
establishing a self-adaptive neural fuzzy inference system model;
acquiring a sound signal and a vibration signal of the high-voltage circuit breaker;
extracting characteristic quantities of the sound signal and the vibration signal;
classifying and preprocessing the characteristic quantities respectively through the self-adaptive neural fuzzy inference system model to obtain a basic probability distribution function;
and fusing the basic probability distribution functions through a D-S evidence theory corrected by the high-conflict evidence to obtain a mechanical fault diagnosis result.
Optionally, the establishing of the adaptive neural fuzzy inference system model includes:
acquiring historical data of sound and vibration signals of the high-voltage circuit breaker;
extracting characteristic quantities of historical data of the sound and vibration signals;
and respectively carrying out self-adaptive neural fuzzy control training on the characteristic quantities and establishing a self-adaptive neural fuzzy inference system model.
Optionally, the network structure of the adaptive neuro-fuzzy inference system model includes a fuzzy layer, a regular inference layer, a normalization layer, an inverse fuzzy layer and an output layer, wherein,
the fuzzification layer fuzzifies the input characteristic quantity, and the output function of the node i is as follows:
in the formula (1), x is the input of the node i, AiAnd Bi-2As a fuzzy set, O1,iMembership function values of a fuzzy set represent that x belongs to AiSize of degree of (D), μ AiAnd μ Bi-2Membership functions that are fuzzy sets;
in the formulae (2) and (3), ci，σiIs a parameter of the membership function;
the rule reasoning layer calculates the excitation degree of each rule, and the output expression is as follows:
in the formula (4), wiThe excitation strength of the corresponding rule, namely the weight of each fuzzy rule;
the normalization layer calculates the ratio of the excitation intensity of the ith rule to the sum of the excitation intensities of all the rules, and the output expression is as follows:
in the formula (5), the reaction mixture is,the normalized excitation intensity of the ith rule represents the contribution of the ith rule to the final result;
the inverse fuzzy layer calculates the output of each rule, and the output expression is as follows:
in the formula (6), the parameter pi、qi、riThe back-piece parameters of each node are obtained;
the output layer calculates the sum of all the defuzzified node outputs and outputs,
in the formula (7), Y is the total output of the system, YiIs the output of the ith rule.
Optionally, the fusing the basic probability distribution function through a high-conflict evidence modified D-S evidence theory to obtain a mechanical fault diagnosis result, including:
calculating an evidence distance d and a normalization constant k between the evidences;
averaging the evidence distance d and the normalization constant k to obtain a collision coefficient sigma;
judging whether a conflict evidence exists according to the conflict coefficient sigma;
if conflict evidence exists, correcting the basic probability distribution function, and fusing the corrected basic probability distribution function through a D-S evidence theory;
and if no conflict evidence exists, fusing the basic probability distribution functions directly through a D-S evidence theory.
Optionally, calculating the evidence distance d and the normalization constant k between the evidences includes:
evidence m1、m2The witness distance d between is:
in the formulae (8) and (9), Ai，Bj∈U,m1(Ai)、m2(Bj) Respectively, the basic probability assignment of the element A, B, and | A | is the number of the included elements;
the normalized constant k is calculated as:
in the formula (10), k reflects the conflict degree of the evidence, and the value range is [0,1 ].
Optionally, if there is a collision evidence, modifying the basic probability distribution function, including:
calculate confidence for each evidence:
in formula (11), sim (m)i,mj) As evidence mi、mjSimilarity between them, sim (m)i,mj)＝1-d(mi,mj)；
Under a unified recognition framework, conflicts among multiple evidence sources are computed:
the conflict of the remaining evidence after removing the jth evidence source from the evidence source is:
according to the conflict k0And conflict kjCalculating the false degree of the obtained evidence:
calculating according to the trust degree and the false degree to obtain the weight distributed by the evidence focal element as follows:
τi＝CrdPmi-γ*Falmi+1 (15)
in the formula (15), if the coefficient of collision σ is greater than 0.5, γ is 1 or 2; if the coefficient of conflict sigma is greater than 0.9, then gamma is taken
Normalizing the weight to obtain the weight T of the conflict evidencei：
According to the weight TiAnd correcting the basic probability distribution function.
Optionally, the rule for fusing the basic probability distribution function through the D-S evidence theory is as follows:
wherein,
the D-S evidence theory-based high-voltage circuit breaker mechanical fault diagnosis method has the following beneficial effects:
(1) the method combines sound and vibration signals, comprehensively diagnoses the mechanical fault of the high-voltage circuit breaker, and is more reliable and accurate;
(2) the method has the advantages that the repeated extraction training of historical data is not needed after the Adaptive Neural Fuzzy Inference System (ANFIS) is constructed, and the diagnosis speed can be improved under the real-time monitoring condition;
(3) the method adopts the D-S evidence theory to carry out information fusion, provides high-conflict evidence correction aiming at the problem that a fusion result is contradictory to a fact when high-conflict evidence exists, only corrects the conflict evidence on the basis of not changing the original evidence trust, does not damage the credibility of a source evidence, can improve the convergence speed and precision to a certain extent, and does not generate the contradictory condition to the fact in the fusion result.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a method for diagnosing a mechanical fault of a high-voltage circuit breaker based on a D-S evidence theory according to an embodiment of the present application;
fig. 2 is a detailed flowchart of S500 in the method for diagnosing a mechanical fault of a high-voltage circuit breaker based on the D-S evidence theory according to the embodiment of the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The sound and vibration signals of the high-voltage circuit breaker belong to non-stable and non-deterministic signals, and can reflect the complex mechanical action process of the circuit breaker. The fault diagnosis of the single signal has various defects, the defects are solved to a certain extent by adopting a multi-signal fusion technology of a D-S evidence theory, and the method has great advantages in identifying the fault type of the circuit breaker. Referring to fig. 1, a flowchart of a method for diagnosing a mechanical fault of a high-voltage circuit breaker based on a D-S evidence theory is provided in an embodiment of the present application.
As shown in fig. 1, the method for diagnosing a mechanical fault of a high-voltage circuit breaker based on a D-S evidence theory provided by the embodiment of the present application includes:
s100: and establishing a self-adaptive neural fuzzy inference system model.
The method comprises the steps of firstly sorting collected sound and vibration historical data collected by a high-voltage circuit breaker, selecting four states of normal state, rotating shaft jamming, base looseness and brake opening rejection, carrying out diagnosis and classification, respectively selecting 20 groups, carrying out bispectrum analysis on sound signals to inhibit Gaussian noise, then carrying out Hilbert-Huang transformation to obtain IMF energy entropy as characteristic quantity for training by using ANFIS (adaptive network-based Fuzzy Inference System), carrying out wavelet packet multiresolution analysis on vibration signals, then carrying out wavelet packet reconstruction on each layer of decomposition node coefficients on the basis, and finally reconstructing a phase space state matrix and calculating the singular spectrum entropy of the characteristic matrix as the characteristic quantity for training by using ANFIS.
And selecting the characteristic quantity of each 20 groups of the processed samples as input training times to be 200 times, training the adaptive neural fuzzy inference system, observing an error curve after the training is finished, and obtaining the adaptive neural fuzzy inference system model of the sound and vibration signals respectively, wherein the error is reduced to be within 0.05 to indicate that a fuzzy control rule is available.
The network structure of the adaptive neuro-fuzzy inference system model (taking two inputs and single output as an example) is as follows:
layer 1: the fuzzy layer is used for carrying out fuzzy processing on input data, and the output function of the node i is as follows:
in the formula (1), x is the input of the node i, AiAnd Bi-2As a fuzzy set, O1,iMembership function values of a fuzzy set represent that x belongs to AiSize of degree of (D), μ AiAnd μ Bi-2Gaussian is selected as membership function of fuzzy setA function.
In the formulae (2) and (3), ci，σiIs a parameter of the membership function, also called a precursor parameter.
Layer 2: the rule reasoning layer calculates the excitation degree of each rule, and the output expression is as follows:
O2,i＝wi＝μAi(x1)μBi(x2),I＝1,2 (4)
in the formula (4), wiThe excitation strength of the corresponding rule, i.e. the weight of each fuzzy rule.
Layer 3: and a normalization layer, which normalizes the excitation intensity of each rule, i.e. calculates the ratio of the excitation intensity of the ith rule to the sum of the excitation intensities of all rules, and the output expression is as follows:
in the formula (5), the reaction mixture is,the normalized excitation strength for the ith rule represents the contribution of the ith rule to the final result.
Layer 4: and the inverse fuzzy layer calculates the output of each rule, and the output expression of the inverse fuzzy layer is as follows:
in the formula (6), the parameter pi、qi、riAnd obtaining the back-piece parameters of each node of the layer by ANFIS.
Layer 5: an output layer that sums the outputs of all the defuzzified nodes and produces the final ANFIS output:
in the formula (7), Y is the total output of the system, YiIs the output of the ith rule.
And identifying the front part parameters and the back part parameters of the system by a mixed algorithm of a homoregression gradient descent method and a least square method, thereby realizing the establishment of the fuzzy model. For a hybrid algorithm, the learning process of each period comprises a forward transmission part and a backward propagation part 2, in the forward learning process, front part parameters are fixed, and back part parameters are identified by applying a least square method; in the process of reverse learning, error calculation is carried out on the back piece parameters obtained through calculation, the BP algorithm in the feedforward neural network is adopted, errors are reversely transmitted to the input end from the output end, and finally the gradient descent method is used for updating the front piece parameters.
S200: and acquiring a sound signal and a vibration signal of the high-voltage circuit breaker.
S300: and extracting the characteristic quantities of the sound signal and the vibration signal.
S400: and respectively carrying out classification pretreatment on the characteristic quantities through a self-adaptive neural fuzzy inference system model to obtain a basic probability distribution function.
S500: and fusing the basic probability distribution functions through a D-S evidence theory corrected by the high-conflict evidence to obtain a mechanical fault diagnosis result.
The method comprises the steps of collecting sound signals and vibration signals of the high-voltage circuit breaker, carrying out noise reduction on the sound signals, and then respectively extracting characteristic quantities of the sound signals and the vibration signals by adopting a proper method so as to represent mechanical characteristic information contained in the signals.
The method comprises the steps of taking characteristic quantities of sound signals and vibration signals as input, carrying out classification pretreatment on the characteristic quantities through an established self-adaptive neural fuzzy inference system model to obtain a Basic probability distribution function (BPA), fusing the obtained Basic probability distribution function by using a D-S evidence theory corrected by high-conflict evidence, and finally obtaining mechanical fault diagnosis of the high-voltage circuit breaker based on the sound signals and the vibration signals.
The steps of multi-information fusion based on the D-S evidence theory of high-conflict evidence correction are shown in FIG. 2:
s501: calculating an evidence distance d and a normalization constant k between the evidences:
under the recognition framework U, if the function m: 2u-＞[0,1]Satisfies the conditionsAnd isThen m (A) is called the elemental probability assignment for element A and also represents the confidence in evidence A, where A is such that m (A) > 0 is called the focal element. Evidence m1、m2The witness distance d between is:
in the formulae (8) and (9), Ai，BjE.g. U, | A | represents the number of the contained elements, evidence m1、m2Similarity between them sim (m)1,m2)＝1-d(m1,m2) Extensible to multiple certificatesThe similarity matrix is used for representing the data, and the larger the value of the similarity matrix is, the larger the similarity between the evidences is, the smaller the conflict is.
The normalized constant k is calculated as:
in the formula (10), k reflects the conflict degree of the evidence, and the value range is [0,1 ].
S502: and averaging the certificate distance d and the normalization constant k to obtain a collision coefficient sigma.
S503: and judging whether a conflict evidence exists according to the conflict coefficient sigma.
And judging whether a conflict evidence exists according to whether the conflict coefficient sigma is greater than 0.5, judging the conflict degree of the evidence, and correcting the conflict evidence.
S504: and if the conflict evidence exists, correcting the basic probability distribution function, and fusing the corrected basic probability distribution function through a D-S evidence theory.
If the conflict evidence exists, calculating the weight T of the conflict evidenceiAnd carrying out weighted average correction on the basic probability distribution function. The method for performing weighted correction on the basic probability distribution function specifically comprises the following steps:
the trust degree of an evidence is used for describing the trust degree of other evidence to a certain evidence, and is the degree of the evidence supported in the whole evidence. Suppose there are n evidence bodies m1,m2…mnThen, the confidence calculation formula of each evidence is:
and the falseness degree is used for describing the falseness degree of the evidence in the whole body, the falseness degree of the evidence is opposite to the confidence degree, and the falseness degree is larger when the confidence degree is smaller. Under the unified recognition framework Θ, their conflicts among multiple evidence sources are:
the conflict of the remaining evidence after removing the jth evidence source from the evidence source is:
then the degree of falseness of the evidence is:
the weights assigned by the evidence focal elements available from the confidence level and the false level are as follows:
τi＝CrdPmi-γ*Falmi+1 (15)
in the formula (15), if the coefficient of collision σ is greater than 0.5, γ is 1 or 2; if the coefficient of conflict sigma is greater than 0.9, then gamma is taken
Weight T of conflict evidence after weight normalization processing assigned to evidence focal elementiComprises the following steps:
weight T based on evidence of conflictiThe basic probability distribution function is modified.
And after the basic probability distribution function is corrected, the corrected basic probability distribution function is subjected to information fusion by using a D-S combination rule, and the mechanical fault of the circuit breaker is comprehensively diagnosed.
S505: and if the collision coefficient does not exist, directly fusing the basic probability distribution function through a D-S evidence theory.
Fusing the basic probability distribution functions by using the D-S evidence theoryTwo functions m on U1,m2The Dempster synthesis rule is:
according to the high-voltage circuit breaker mechanical fault diagnosis method based on the D-S evidence theory, after feature quantity extraction is carried out on normal and fault samples of sound signals and vibration signals, adaptive neural fuzzy control training is respectively carried out, an Adaptive Neural Fuzzy Inference System (ANFIS) model is established, classification pretreatment is respectively carried out on monitoring data after the feature quantity extraction, a basic probability distribution function (BPA) is obtained, information fusion is carried out through the D-S evidence theory, and circuit breaker mechanical faults are comprehensively diagnosed. Aiming at the conflict problem existing in the fusion process, the D-S evidence fusion is carried out after the basic probability distribution function (BPA) is subjected to weighting correction through the conflict coefficient, so that the credibility of the source evidence is not damaged, the convergence speed and precision can be improved to a certain extent, and the situation that the fusion result is contrary to the fact does not occur. The high-voltage circuit breaker mechanical fault diagnosis method based on the D-S evidence theory combines sound and vibration signals, comprehensively diagnoses the mechanical fault of the high-voltage circuit breaker, and improves reliability and accuracy of state evaluation.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
The above-described embodiments of the present application do not limit the scope of the present application.
Claims (7)
1. A high-voltage circuit breaker mechanical fault diagnosis method based on a D-S evidence theory is characterized by comprising the following steps:
establishing a self-adaptive neural fuzzy inference system model;
acquiring a sound signal and a vibration signal of the high-voltage circuit breaker;
extracting characteristic quantities of the sound signal and the vibration signal;
classifying and preprocessing the characteristic quantities respectively through the self-adaptive neural fuzzy inference system model to obtain a basic probability distribution function;
and fusing the basic probability distribution functions through a D-S evidence theory corrected by the high-conflict evidence to obtain a mechanical fault diagnosis result.
2. The method of claim 1, wherein building an adaptive neuro-fuzzy inference system model comprises:
acquiring historical data of sound and vibration signals of the high-voltage circuit breaker;
extracting characteristic quantities of historical data of the sound and vibration signals;
and respectively carrying out self-adaptive neural fuzzy control training on the characteristic quantities and establishing a self-adaptive neural fuzzy inference system model.
3. The method of claim 2, wherein the network structure of the adaptive neuro-fuzzy inference system model comprises a fuzzy layer, a regular inference layer, a normalization layer, an inverse fuzzy layer, and an output layer, wherein,
the fuzzification layer fuzzifies the input characteristic quantity, and the output function of the node i is as follows:
in the formula (1), x is the input of the node i, AiAnd Bi-2As a fuzzy set, O1,iMembership function values of a fuzzy set represent that x belongs to AiSize of degree of (D), μ AiAnd μ Bi-2Membership functions that are fuzzy sets;
in the formulae (2) and (3), ci，σiIs a membership functionThe parameters of (1);
the rule reasoning layer calculates the excitation degree of each rule, and the output expression is as follows:
in the formula (4), wiThe excitation strength of the corresponding rule, namely the weight of each fuzzy rule;
the normalization layer calculates the ratio of the excitation intensity of the ith rule to the sum of the excitation intensities of all the rules, and the output expression is as follows:
in the formula (5), the reaction mixture is,the normalized excitation intensity of the ith rule represents the contribution of the ith rule to the final result;
the inverse fuzzy layer calculates the output of each rule, and the output expression is as follows:
in the formula (6), the parameter pi、qi、riThe back-piece parameters of each node are obtained;
the output layer calculates the sum of all the defuzzified node outputs and outputs,
in the formula (7), Y is the total output of the system, YiIs the output of the ith rule.
4. The method according to claim 1, wherein fusing the basic probability distribution functions through a high-collision evidence modified D-S evidence theory to obtain a mechanical fault diagnosis result comprises:
calculating an evidence distance d and a normalization constant k between the evidences;
averaging the evidence distance d and the normalization constant k to obtain a collision coefficient sigma;
judging whether a conflict evidence exists according to the conflict coefficient sigma;
if conflict evidence exists, correcting the basic probability distribution function, and fusing the corrected basic probability distribution function through a D-S evidence theory;
and if no conflict evidence exists, fusing the basic probability distribution functions directly through a D-S evidence theory.
5. The method of claim 4, wherein computing the evidence distance d and the normalization constant k between the evidences comprises:
evidence m1、m2The witness distance d between is:
in the formulae (8) and (9), Ai，Bj∈U,m1(Ai)、m2(Bj) Respectively, the basic probability assignment of the element A, B, and | A | is the number of the included elements;
the normalized constant k is calculated as:
in the formula (10), k reflects the conflict degree of the evidence, and the value range is [0,1 ].
6. The method of claim 4, wherein revising the basic probability distribution function if conflicting evidence exists comprises:
calculate confidence for each evidence:
in formula (11), sim (m)i,mj) As evidence mi、mjSimilarity between them, sim (m)i,mj)＝1-d(mi,mj)；
Under a unified recognition framework, conflicts among multiple evidence sources are computed:
the conflict of the remaining evidence after removing the jth evidence source from the evidence source is:
according to the conflict k0And conflict kjCalculating the false degree of the obtained evidence:
calculating according to the trust degree and the false degree to obtain the weight distributed by the evidence focal element as follows:
τi＝CrdPmi-γ*Falmi+1 (15)
in the formula (15), if the coefficient of collision σ is greater than 0.5, γ is 1 or 2; if the conflict coefficient sigma is larger than 0.9, taking gamma as 2;
normalizing the weight to obtain the weight T of the conflict evidencei：
According to the weight TiAnd correcting the basic probability distribution function.
7. The method according to claim 4, wherein the rule for fusing the basic probability distribution functions by D-S evidence theory is:
wherein,
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910397845.1A CN110119713A (en) | 2019-05-14 | 2019-05-14 | Mechanical Failure of HV Circuit Breaker diagnostic method based on D-S evidence theory |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910397845.1A CN110119713A (en) | 2019-05-14 | 2019-05-14 | Mechanical Failure of HV Circuit Breaker diagnostic method based on D-S evidence theory |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110119713A true CN110119713A (en) | 2019-08-13 |
Family
ID=67522272
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910397845.1A Pending CN110119713A (en) | 2019-05-14 | 2019-05-14 | Mechanical Failure of HV Circuit Breaker diagnostic method based on D-S evidence theory |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110119713A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110530631A (en) * | 2019-08-21 | 2019-12-03 | 贵州大学 | A kind of gear list type fault detection method based on hybrid classifer |
| CN111260502A (en) * | 2020-01-10 | 2020-06-09 | 河南大学 | Conflict evidence fusion method based on similarity and false degree |
| CN111523394A (en) * | 2020-03-27 | 2020-08-11 | 国网宁夏电力有限公司电力科学研究院 | Method and system for detecting foreign matter defects inside GIS equipment |
| CN111667193A (en) * | 2020-06-12 | 2020-09-15 | 中国矿业大学(北京) | Coal mine gas safety evaluation method based on D-S evidence theory |
| CN111814890A (en) * | 2020-07-15 | 2020-10-23 | 辽宁大学 | Network live broadcast illegal behavior determination method based on D-S evidence theory |
| CN111832730A (en) * | 2020-07-09 | 2020-10-27 | 西安交通大学 | Reliability characterization and state identification method for uncertain oil state |
| CN111832731A (en) * | 2020-07-09 | 2020-10-27 | 西安交通大学 | Multi-index monitoring method for representing uncertain state of oil and diagnosing faults |
| CN112255538A (en) * | 2020-10-14 | 2021-01-22 | 国网青海省电力公司海西供电公司 | Multi-feature optimization fusion high-voltage circuit breaker fault diagnosis method |
| CN112580425A (en) * | 2020-10-13 | 2021-03-30 | 浙江工业大学 | Water pump fault classification method based on neural network and D-S evidence theory |
| CN112733951A (en) * | 2021-01-19 | 2021-04-30 | 中国矿业大学(北京) | Multi-information decision weight distribution and fusion method for mechanical defect diagnosis of circuit breaker |
| CN112748331A (en) * | 2020-12-24 | 2021-05-04 | 国网江苏省电力有限公司电力科学研究院 | Circuit breaker mechanical fault identification method and device based on DS evidence fusion |
| CN113240121A (en) * | 2021-05-08 | 2021-08-10 | 云南中烟工业有限责任公司 | Method for predicting nondestructive bead blasting breaking sound |
| CN113671363A (en) * | 2021-08-13 | 2021-11-19 | 华北电力大学（保定） | High-voltage circuit breaker state identification system and method |
| CN114792112A (en) * | 2022-04-22 | 2022-07-26 | 河南大学 | Time domain evidence fusion method based on self-adaptive processing strategy |
| CN115758120A (en) * | 2022-11-21 | 2023-03-07 | 南京航空航天大学 | Vehicle door system diagnosis method based on uncertain information fusion |
| CN117572229A (en) * | 2023-11-16 | 2024-02-20 | 广东电网有限责任公司 | Maintenance strategy formulation method, device, equipment and medium for gas circuit breaker group |
| CN118539376A (en) * | 2024-07-26 | 2024-08-23 | 浙江亿腾电气科技有限公司 | Control system and method for direct current breaker |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512761A (en) * | 2015-12-04 | 2016-04-20 | 华北电力科学研究院有限责任公司 | Economic life determination method and device for power transformer |
| CN106932712A (en) * | 2016-12-30 | 2017-07-07 | 江苏南瑞泰事达电气有限公司 | A kind of circuit breaker failure diagnostic method based on improvement Fuzzy Petri Net |
-
2019
- 2019-05-14 CN CN201910397845.1A patent/CN110119713A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512761A (en) * | 2015-12-04 | 2016-04-20 | 华北电力科学研究院有限责任公司 | Economic life determination method and device for power transformer |
| CN106932712A (en) * | 2016-12-30 | 2017-07-07 | 江苏南瑞泰事达电气有限公司 | A kind of circuit breaker failure diagnostic method based on improvement Fuzzy Petri Net |
Non-Patent Citations (11)
| Title |
|---|
| 孟媛媛: "基于高冲突证据修正的D-S证据理论及其应用研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 01, 15 January 2019 (2019-01-15), pages 1 - 4 * |
| 孟媛媛: "基于高冲突证据修正的D-S证据理论及其应用研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, pages 140 - 840 * |
| 李建鹏等: "基于双谱和希尔伯特-黄变换的断路器声波信号处理", 《电力自动化设备》, pages 0 * |
| 王升杰: "高压断路器故障诊断方法的研究", 《中国优秀硕士学位论文全文数据库工程科技II辑》, pages 3 * |
| 胡秀洁等: "D-S证据理论和多模型结合的模拟电路故障诊断", 《软件导刊》, no. 9, 31 October 2014 (2014-10-31), pages 1 * |
| 胡秀洁等: "D-S证据理论和多模型结合的模拟电路故障诊断", 《软件导刊》, pages 1 * |
| 赵庆海;赵玮;石玉霞;: "现代故障诊断技术研究现状与趋势", 包装工程, no. 15, pages 169 - 175 * |
| 赵莉华等: "基于自适应神经模糊推理系统的高压断路器操作机构状态评估", 《高电压技术》, pages 3 * |
| 赵莉华等: "基于自适应神经模糊推理系统的高压断路器操作机构状态评估", 《高电压技术》, vol. 43, no. 06, 30 June 2017 (2017-06-30), pages 3 * |
| 高振兴等: "基于多源信息融合的电网故障诊断方法研究", 《电力系统保护与控制》 * |
| 高振兴等: "基于多源信息融合的电网故障诊断方法研究", 《电力系统保护与控制》, no. 06, 16 March 2011 (2011-03-16), pages 28 - 34 * |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110530631A (en) * | 2019-08-21 | 2019-12-03 | 贵州大学 | A kind of gear list type fault detection method based on hybrid classifer |
| CN111260502A (en) * | 2020-01-10 | 2020-06-09 | 河南大学 | Conflict evidence fusion method based on similarity and false degree |
| CN111523394A (en) * | 2020-03-27 | 2020-08-11 | 国网宁夏电力有限公司电力科学研究院 | Method and system for detecting foreign matter defects inside GIS equipment |
| CN111523394B (en) * | 2020-03-27 | 2023-06-27 | 国网宁夏电力有限公司电力科学研究院 | Method and system for detecting foreign matter defects in GIS (gas insulated switchgear) |
| CN111667193A (en) * | 2020-06-12 | 2020-09-15 | 中国矿业大学(北京) | Coal mine gas safety evaluation method based on D-S evidence theory |
| CN111667193B (en) * | 2020-06-12 | 2024-01-02 | 中国矿业大学(北京) | Coal mine gas safety evaluation method based on D-S evidence theory |
| CN111832731A (en) * | 2020-07-09 | 2020-10-27 | 西安交通大学 | Multi-index monitoring method for representing uncertain state of oil and diagnosing faults |
| CN111832730A (en) * | 2020-07-09 | 2020-10-27 | 西安交通大学 | Reliability characterization and state identification method for uncertain oil state |
| CN111832730B (en) * | 2020-07-09 | 2022-07-26 | 西安交通大学 | Reliability characterization and state identification method for uncertain oil state |
| CN111814890A (en) * | 2020-07-15 | 2020-10-23 | 辽宁大学 | Network live broadcast illegal behavior determination method based on D-S evidence theory |
| CN112580425A (en) * | 2020-10-13 | 2021-03-30 | 浙江工业大学 | Water pump fault classification method based on neural network and D-S evidence theory |
| CN112255538A (en) * | 2020-10-14 | 2021-01-22 | 国网青海省电力公司海西供电公司 | Multi-feature optimization fusion high-voltage circuit breaker fault diagnosis method |
| CN112255538B (en) * | 2020-10-14 | 2024-04-23 | 国网青海省电力公司海西供电公司 | Multi-feature optimization fusion fault diagnosis method for high-voltage circuit breaker |
| CN112748331A (en) * | 2020-12-24 | 2021-05-04 | 国网江苏省电力有限公司电力科学研究院 | Circuit breaker mechanical fault identification method and device based on DS evidence fusion |
| CN112733951A (en) * | 2021-01-19 | 2021-04-30 | 中国矿业大学(北京) | Multi-information decision weight distribution and fusion method for mechanical defect diagnosis of circuit breaker |
| CN112733951B (en) * | 2021-01-19 | 2021-09-28 | 中国矿业大学(北京) | Multi-information decision weight distribution and fusion method for mechanical defect diagnosis of circuit breaker |
| CN113240121A (en) * | 2021-05-08 | 2021-08-10 | 云南中烟工业有限责任公司 | Method for predicting nondestructive bead blasting breaking sound |
| CN113240121B (en) * | 2021-05-08 | 2022-10-25 | 云南中烟工业有限责任公司 | Method for predicting nondestructive bead blasting breaking sound |
| CN113671363A (en) * | 2021-08-13 | 2021-11-19 | 华北电力大学（保定） | High-voltage circuit breaker state identification system and method |
| CN114792112A (en) * | 2022-04-22 | 2022-07-26 | 河南大学 | Time domain evidence fusion method based on self-adaptive processing strategy |
| CN114792112B (en) * | 2022-04-22 | 2024-02-20 | 河南大学 | Time domain evidence fusion method based on self-adaptive processing strategy |
| CN115758120A (en) * | 2022-11-21 | 2023-03-07 | 南京航空航天大学 | Vehicle door system diagnosis method based on uncertain information fusion |
| CN117572229A (en) * | 2023-11-16 | 2024-02-20 | 广东电网有限责任公司 | Maintenance strategy formulation method, device, equipment and medium for gas circuit breaker group |
| CN118539376A (en) * | 2024-07-26 | 2024-08-23 | 浙江亿腾电气科技有限公司 | Control system and method for direct current breaker |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110119713A (en) | Mechanical Failure of HV Circuit Breaker diagnostic method based on D-S evidence theory | |
| CN110502636B (en) | Joint modeling and mining method and system for subjective and objective test questions | |
| CN106323636A (en) | Adaptive extraction and diagnosis method for degree features of mechanical fault through stack-type sparse automatic coding depth neural network | |
| Di et al. | Ensemble deep transfer learning driven by multisensor signals for the fault diagnosis of bevel-gear cross-operation conditions | |
| Zhou et al. | Harnessing fuzzy neural network for gear fault diagnosis with limited data labels | |
| CN114500335B (en) | SDN network flow control method based on fuzzy C-means and mixed kernel least square support vector machine | |
| CN112684012A (en) | Equipment key force-bearing structural part fault diagnosis method based on multi-parameter information fusion | |
| Mou et al. | Knowledge representation and acquisition using R‐numbers Petri nets considering conflict opinions | |
| Cornelius et al. | Estimating and leveraging uncertainties in deep learning for remaining useful life prediction in mechanical systems | |
| CN114580934A (en) | Early warning method for food detection data risk based on unsupervised anomaly detection | |
| CN111414943B (en) | Anomaly detection method based on mixed hidden naive Bayes model | |
| Castro et al. | An interpretation of neural networks as inference engines with application to transformer failure diagnosis | |
| CN116822652A (en) | Subway fault prediction method, subway fault prediction device, electronic equipment, subway fault prediction system and storage medium | |
| Mohsin | Investigating the use of an adaptive neuro-fuzzy inference system in software development effort estimation | |
| Rocha et al. | A fuzzy type-2 fault detection methodology to minimize false alarm rate in induction motor monitoring applications | |
| CN111260024A (en) | Fault detection method and system based on combination of long-term and short-term memory and typical correlation | |
| Katyara et al. | Signal parameter estimation and classification using mixed supervised and unsupervised machine learning approaches | |
| CN114383846B (en) | Bearing composite fault diagnosis method based on fault label information vector | |
| CN114202110B (en) | Service fault prediction method and device based on RF-XGBOOST | |
| CN116451121A (en) | Switch fault diagnosis method, system, equipment and medium | |
| Khoshgoftaar et al. | Detecting noisy instances with the ensemble filter: A study in software quality estimation | |
| CN115174421A (en) | Network fault prediction method and device based on self-supervision unwrapping hypergraph attention | |
| Marwala et al. | Neuro-rough models for modelling HIV | |
| CN110826690A (en) | Equipment state identification method and system and computer readable storage medium | |
| Mukherjee et al. | A statistical approach to dynamic synchrony analysis of neuronal ensemble spiking |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190813 |