CN107357275A - Non-gaussian industrial process fault detection method and system - Google Patents

Non-gaussian industrial process fault detection method and system Download PDF

Info

Publication number
CN107357275A
CN107357275A CN201710623082.9A CN201710623082A CN107357275A CN 107357275 A CN107357275 A CN 107357275A CN 201710623082 A CN201710623082 A CN 201710623082A CN 107357275 A CN107357275 A CN 107357275A
Authority
CN
China
Prior art keywords
mrow
msubsup
mover
msub
residual generation
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
CN201710623082.9A
Other languages
Chinese (zh)
Other versions
CN107357275B (en
Inventor
陈志文
彭涛
阳春华
袁小锋
杨超
杨笑悦
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.)
Central South University
Original Assignee
Central South University
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 Central South University filed Critical Central South University
Priority to CN201710623082.9A priority Critical patent/CN107357275B/en
Publication of CN107357275A publication Critical patent/CN107357275A/en
Application granted granted Critical
Publication of CN107357275B publication Critical patent/CN107357275B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
    • G05B19/41885—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by modeling, simulation of the manufacturing system
    • 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
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

The present invention relates to industrial process monitoring and fault diagnosis field, discloses a kind of non-gaussian industrial process fault detection method and system, with convenient and practical ground on-line checking non-gaussian industrial process.The inventive method includes：The first step, a number of normal history data set is chosen, average is carried out to data set and pre-processed, residual generation is established using Canonical Correlation Analysis；Second step, sampling DSMC determine the respective threshold of corresponding residual generation；3rd step, corresponding residual generation threshold value and real-time online detection is carried out to industrial process data determined by.

Description

Non-gaussian industrial process fault detection method and system
Technical field
The present invention relates to industrial process monitoring and fault diagnosis field, more particularly to a kind of non-gaussian industrial process failure to examine Survey method and system.
Background technology
With the rapid development of information technology and data acquisition technology, factory and enterprise have quite abundant production number According to resource, the industrial big data epoch slowly arrive.In industrial processes, due to severe production environment and longtime running, Equipment can inevitably be lost, or even failure, and these abnormal conditions not only influence the quality of product, but also can influence The safe and stable operation of system, it some times happens that great production accident, the traditional detection method for fully relying on operative employee is insufficient To solve complicated process test problems.
It is Data Over Cable, nonlinear, Gauss, non-gaussian etc. in actual production process, for different lifes Feature possessed by production process, different fault detection methods should be selected, to ensure the maximization of fault diagnosis efficiency.
Found through patent consulting, due to production process variable it is more the characteristics of, the process based on multi-variate statistical analysis in recent years Detection method, such as Independent component analysis technology (Independent component analysis, ICA), pivot analysis (Principal component analysis's, PCA) and offset minimum binary (Partial least squares, PLS) changes Enter the on-line checking that technology etc. has been widely used in nongausian process.But ICA and PCA methods mainly consider individual data Collection, does not make full use of the correlation between variable, and PLS methods are primarily used to solve recurrence to ask although it is contemplated that correlation Topic.Canonical correlation analysis technology (Canonical correlation analysis, CCA) considers the correlation between variable, It can be considered a kind of extension of above-mentioned basic fundamental.Therefore, the present invention has been sampled based on the method for canonical correlation analysis more to handle The problem on line detection of variable production process.
On the other hand, for nongausian process, the existing nongausian process detection method master based on multi-variate statistical analysis It is divided into two classes, one kind is to be based on existing Multielement statistical analysis method combination Threshold, main threshold value determination side Method has based on gauss hybrid models (Gaussian mixture model, GMM), based on kernel function estimation (Kernel-based) With based on order quantile method (Sequential quantile estimation, SQE) etc., although these methods are answered With, but it is still limited by the problems such as kernel functional parameter is chosen；Another kind of is the method based on ICA, and such method to process without becoming Amount carries out Gaussian Profile it is assumed that by finding out independent pivot, builds corresponding statistic and carries out fault detect, but this kind of method is only examined Consider forms data collection, and the determination of threshold value is also based on GMM, kernel-based, SQE etc..Therefore, how data to be made full use of Correlation and more simple and practical Threshold are detected in real time to nongausian process, at present could not also be enough preferable Solution method.
The content of the invention
Present invention aims at a kind of non-gaussian industrial process fault detection method and system is disclosed, with convenient and practical exist Line detects non-gaussian industrial process.
To achieve the above object, the invention discloses a kind of non-gaussian industrial process fault detection method, including：
The first step, a number of normal history data set is chosen, average is carried out to data set and pre-processed, utilizes typical case Correlation analysis method establishes residual generation；Specifically include：
Step A1, the process data under accidental conditions is chosen using historical data base, used respectivelyTwo variable datas of expression process Collection, wherein, l is measurand number in vectorial u, and m is measurand number in vectorial y, and N counts for independent sample；Then u (i), i= 1 ..., N represent that l variable represents in vectorial y m in the measured value at ith sample moment, y (i), i=1 ..., N in vectorial u Measured value of the variable at the ith sample moment；
Step A2, average value processing is carried out to data set；Average value processing is carried out respectively to two datasets so that two The average of each variable in data set is 0, obtains new data setWith
Step A3, after data set being normalized, required covariance matrix is estimated：
Wherein, Σu, ΣyAnd ΣuyU covariance matrix, y covariance matrix and u and y cross covariance are represented respectively Matrix；
Step A4, the covariance matrix obtained estimated by, establishing correlation matrix Υ is：It is and right Correlation matrix Υ carries out singular value decomposition, Υ=Γ Σ RT, wherein, Γ is the left singular vector of the correlation matrix, and R is described The right singular vector of correlation matrix, Σ are diagonal matrix；Then the first residual generation is obtained using canonical correlation analysis technology raWith the second residual generation rb：
ra=LTy-ΣTJTu,rb=JTu-ΣLTy
Wherein,
Second step, sampling DSMC determine the first threshold and the second residual error of first residual generation respectively The Second Threshold of generator；Specifically include：
Step B1, the fully big normal history data set of number of samples is chosen, determines Monte-Carlo Simulation number K, and set Put initial thresholdCurrent iteration number s=0；
Step B2, according to Monte Carlo number, K data set is chosen in the s times iteration
Step B3, the statistic of corresponding residual generation is expressed as Js, counting function is expressed asCounting function value For：
Wherein,The statistics value of k-th of sample moment during iteration s is represented,Represent corresponding to statistic to work as during iteration s Preceding threshold value,Represent the count value of k-th of sample moment during iteration s；The statistic is calculated as：
Wherein, raAnd rbRespectively the first residual generation and the residual signals of the second residual generation output；WithRespectively the first residual generation and the corresponding statistic of the second residual generation；WithRespectively corresponding residual error letter Number covariance matrix inverse matrix；
Step B4, after for K Monte-Carlo Simulation, rate of false alarm value is estimated：
If step B5,Establishment then returns to present threshold valueFor required threshold value, and makeIf It is invalid, continue iteration, makeAnd return to step B3；Wherein, pFARFor specified maximum allowable rate of false alarm, ε ＞ 0 is a constant, and Δ is that iteration tolerance (is also known as：Iteration step length)；
3rd step, real-time online detection is carried out to industrial process data, specifically included：
The vectorial u gathered in real time and the vectorial y variable data are obtained, and according to first residual generation Obtain corresponding residual signals with second residual generation, and calculate respectively the statistic of corresponding residual signals and with it is corresponding The first threshold and the Second Threshold be compared, if the statistic of corresponding first residual generation of gained has exceeded institute The statistic for stating first threshold or corresponding second residual generation has exceeded the Second Threshold, then exports fault warning.
Above-mentioned first residual generation and the second residual generation of the present invention can realize good complementation, it is ensured that the present invention The precision of detection and the time delay of energy optimizing detection so that detection time delay reduces, and has more preferable detection performance.It is used as this hair A kind of bright realization deteriorated, the residual generation of dependence first or the second residual generation that can be simple in above-mentioned detection process Detected, on the premise of Correlation method for data processing amount is reduced, precision compares the inspection that the first and second residual generations are combined Survey method slightly reduces.
Corresponding with the above method, invention additionally discloses a kind of supporting non-gaussian industrial process event for performing the above method Hinder detecting system.
The invention has the advantages that：
1st, present invention firstly provides a kind of non-height being combined based on canonical correlation analysis and Monte Carlo threshold learning This process online test method, this method can be with on-line checking non-gaussian industrial process；
2nd, detection method proposed by the present invention is real-time that, when industrial process breaks down, can timely detect Come；
3rd, Kernel-based methods data of the present invention, it is convenient and practical independent of accurate process model.
Below with reference to accompanying drawings, the present invention is further detailed explanation.
Brief description of the drawings
The accompanying drawing for forming the part of the application is used for providing a further understanding of the present invention, schematic reality of the invention Apply example and its illustrate to be used to explain the present invention, do not form inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is non-gaussian industrial process fault detection method flow chart disclosed in the embodiment of the present invention.
Embodiment
Embodiments of the invention are described in detail below in conjunction with accompanying drawing, but the present invention can be defined by the claims Implement with the multitude of different ways of covering.
Embodiment 1
A kind of non-gaussian industrial process fault detection method, reference picture 1, including：
The first step, a number of normal history data set is chosen, average is carried out to data set and pre-processed, utilizes typical case Correlation analysis method establishes residual generation.The step can be carried out under off-line state, be specifically included：
Step A1, the process data under accidental conditions is chosen using historical data base, used respectivelyTwo variable datas of expression process Collection, wherein, l is measurand number in vectorial u, and m is measurand number in vectorial y, and N counts for independent sample；Then u (i), i= 1 ..., N represent that l variable represents in vectorial y m in the measured value at ith sample moment, y (i), i=1 ..., N in vectorial u Measured value of the variable at the ith sample moment.
Step A2, average value processing is carried out to data set；Average value processing is carried out respectively to two datasets so that two The average of each variable in data set is 0, obtains new data setWith
In step A2, that removes average value processing realizes that step includes：
1st, Estimation of Mean,
2nd, average value processing is carried out to each sample：
Step A3, after data set being normalized, required covariance matrix is estimated：
Wherein, Σu, ΣyAnd ΣuyU covariance matrix, y covariance matrix and u and y cross covariance are represented respectively Matrix.
Step A4, the covariance matrix obtained estimated by, establishing correlation matrix Υ is：It is and right Correlation matrix Υ carries out singular value decomposition, Υ=Γ Σ RT, wherein, Γ is the left singular vector of the correlation matrix, and R is described The right singular vector of correlation matrix, Σ are diagonal matrix；Then the first residual generation is obtained using canonical correlation analysis technology raWith the second residual generation rb：
ra=LTy-ΣTJTu,rb=JTu-ΣLTy
Wherein,
Second step, sampling DSMC determine the first threshold and the second residual error of first residual generation respectively The Second Threshold of generator；Specifically include：
Step B1, the fully big normal history data set of number of samples is chosen, determines Monte-Carlo Simulation number K, and set Put initial thresholdCurrent iteration number s=0；
Step B2, according to Monte Carlo number, K data set is chosen in the s times iteration
Step B3, the statistic of corresponding residual generation is expressed as Js, counting function is expressed asCounting function value For：
Wherein,The statistics value of k-th of sample moment during iteration s is represented,Represent during iteration s corresponding to statistic Present threshold value,Represent the count value of k-th of sample moment during iteration s；The statistic is calculated as：
Wherein, raAnd rbRespectively the first residual generation and the residual signals of the second residual generation output；WithRespectively the first residual generation and the corresponding statistic of the second residual generation；WithRespectively corresponding residual error letter Number covariance matrix inverse matrix；
Step B4, after for K Monte-Carlo Simulation, rate of false alarm value is estimated：
If step B5,Establishment then returns to present threshold valueFor required threshold value, and makeIf It is invalid, continue iteration, makeAnd return to step B3；Wherein, pFARFor specified maximum allowable rate of false alarm, ε ＞ 0 is a constant, and Δ is iteration tolerance；
3rd step, real-time online detection is carried out to industrial process data, specifically included：
The vectorial u gathered in real time and the vectorial y variable data are obtained, and according to first residual generation Obtain corresponding residual signals with second residual generation, and calculate respectively the statistic of corresponding residual signals and with it is corresponding The first threshold and the Second Threshold be compared, if the statistic of corresponding first residual generation of gained has exceeded institute The statistic for stating first threshold or corresponding second residual generation has exceeded the Second Threshold, then exports fault warning.
For above-mentioned 3rd step, by taking the 1st sampling instant as an example, on-line monitoring comprises the following steps that：
The sample data for going equalization processing to collect in real time；During the 1st sampling collected by data collecting system The measurement data at quarter is designated asAnd the average obtained using off-line training step carries out equalization Processing, obtains new dataWith
Obtain residual signals；Corresponding residual signals r is respectively obtained by the first and second residual generationsaAnd rbIt is as follows：
Counting statistics amount；According to obtained residual signals, corresponding statistic is established respectivelyWithIt is as follows：
Wherein,WithThe inverse matrix of the covariance matrix of respectively corresponding residual signals；
CompareWithWith the size of respective threshold, if statistic is all not more than respective threshold, u (1), y (1) It is normal sample；Otherwise u (1), y (1) is fault sample, shows the faulty generation of process.
【Concrete application example】
Illustrate effectiveness of the invention with reference to the example of continuous stirred tank heating process.The data of embodiment come from moral The TR682CSTH semi-physical emulation platforms of state hamburger G.U.N.T Geraetebau GmbH exploitations.
This example has non-Gaussian system by injecting zero-mean coloured noise come simulation process.6 variables of the process are chosen, According to procedural knowledge, by liquid level L1, temperature in the kettle T1With temperature T in heating compartment2Form u vectors；By infusion fluid temperature T3, store Tank liquid temperature T4With enter flow quantity F1Form y vectors.Data set is divided into three parts：Training dataset, threshold learning data set and Test data set.Sampling time is arranged to 1s, and Monte-Carlo Simulation number K=800, training dataset is by 1000 sample groups Into each is made up of threshold learning data set 5000 samples, and test data set is made up of 850 samples.
For the fault detect effect of testing algorithm, step and random two kinds of fault types are introduced respectively, as shown in table 1
Table 1, the description of CSTH procedure faults：
Sequence number Fault type Failure introduces the time
1 The stuck failure of flow valve 401s
2 Liquid level sensor precise decreasing 401s
The implementation steps of the present invention are explained in detail with reference to the example of CSTH processes：
Part I：Off-line training, establish residual generation.
1) training data and threshold learning data set are gathered.The mistake under accidental conditions is chosen using historical data base Number of passes evidence, is used respectivelyRepresent Two variable data collection of process.
2) average value processing is removed.Average value processing is carried out to data set respectively, obtains new data set：
Covariance matrix is built, after entering normalized to data set, required covariance matrix is estimated by formula (1), Σu, ΣyAnd Σuy。
Build residual generation；According to estimated obtained covariance matrix, obtained using formula needed for residual generation Parameter J, L and Σ, it is as follows then to obtain two residual generations：ra=LTy-ΣTJTu,rb=JTu-ΣLTy。
Threshold value；Respective threshold J is determined according to above-mentioned threshold learning methodth,aAnd Jth,b。
Part II：On-line monitoring, by taking the 1st sampling instant as an example, on-line monitoring specific implementation step is as follows：
The sample data for going equalization processing to collect in real time；During the 1st sampling collected by data collecting system The measurement data at quarter is designated asAnd the average obtained using off-line training step carries out equalization Processing, obtains new dataWithThen corresponding residual signals r is obtainedaAnd rb。
Afterwards, according to obtained residual signals, corresponding statistic is established respectivelyWithCompareWith Jth,a,And Jth,bIf statistic is not more than respective threshold, u (1), y (1) is normal sample；Otherwise u (1), y (1) are failure samples This, shows the faulty generation of process, detects remaining sample successively.The result of fault detect such as table 2.
Table 2：
The testing result of 2 kinds of failure situations is given in Table 2, and the calculating of verification and measurement ratio and detection delay is to use Multi simulation running The method averaged calculates.From fault detect rate and the detection delay of table 2 it can be seen that the inventive method on-line monitoring work The feasibility and validity of industry process, and compared with the CCA methods of traditional processing Gaussian process, the failure of the inventive method Verification and measurement ratio is higher and detection delay is relatively low, has more preferable detection performance.
Non-gaussian industrial process fault detection method disclosed in the present embodiment, above-mentioned first residual generation and the second residual error Generator can realize good complementation, it is ensured that the precision and the time delay of energy optimizing detection that the present invention detects so that detection delay Property reduce, there is more preferable detection performance.
Embodiment 2
As a kind of realization deteriorated of above-described embodiment 1, the residual error of dependence first that can be simple in above-mentioned detection process Generator or the second residual generation are detected, and on the premise of Correlation method for data processing amount is reduced, precision is compared to first and the The detection method that two residual generations are combined slightly reduces.
Non-gaussian industrial process fault detection method (can refer to above-described embodiment 1) disclosed in the present embodiment, including：
The first step, a number of normal history data set is chosen, average is carried out to data set and pre-processed, utilizes typical case Correlation analysis method establishes residual generation；Specifically include：
Step A1, the process data under accidental conditions is chosen using historical data base, used respectivelyTwo variable datas of expression process Collection, wherein, l is measurand number in vectorial u, and m is measurand number in vectorial y, and N counts for independent sample；Then u (i), i= 1 ..., N represent that l variable represents in vectorial y m in the measured value at ith sample moment, y (i), i=1 ..., N in vectorial u Measured value of the variable at the ith sample moment；
Step A2, average value processing is carried out to data set；Average value processing is carried out respectively to two datasets so that two The average of each variable in data set is 0, obtains new data setWith
Step A3, after data set being normalized, required covariance matrix is estimated：
Wherein, Σu, ΣyAnd ΣuyU covariance matrix, y covariance matrix and u and y cross covariance are represented respectively Matrix；
Step A4, the covariance matrix obtained estimated by, establishing correlation matrix Υ is：It is and right Correlation matrix Υ carries out singular value decomposition, Υ=Γ Σ RT, wherein, Γ is the left singular vector of the correlation matrix, and R is described The right singular vector of correlation matrix, Σ are diagonal matrix；Then the first residual generation is obtained using canonical correlation analysis technology ra：
ra=LTy-ΣTJTu
Wherein,
Second step, sampling DSMC determine the first threshold of first residual generation, specifically include：
Step B1, the fully big normal history data set of number of samples is chosen, determines Monte-Carlo Simulation number K, and set Put initial thresholdCurrent iteration number s=0；
Step B2, according to Monte Carlo number, K data set is chosen in the s times iteration
Step B3, the statistic of corresponding residual generation is expressed as Js, counting function is expressed asCounting function value For：
Wherein,The statistics value of k-th of sample moment during iteration s is represented,Represent during iteration s corresponding to statistic Present threshold value,Represent the count value of k-th of sample moment during iteration s；The statistic is calculated as：
Wherein, raFor the residual signals of first residual generation output；For first residual generation Statistic；For the inverse matrix of the covariance matrix of corresponding residual signals；
Step B4, after for K Monte-Carlo Simulation, rate of false alarm value is estimated：
If step B5,Establishment then returns to present threshold valueFor required threshold value, and makeIf It is invalid, continue iteration, makeAnd return to step B3；Wherein, pFARFor specified maximum allowable rate of false alarm, ε ＞ 0 is a constant, and Δ is iteration tolerance；
3rd step, real-time online detection is carried out to industrial process data, specifically included：
The vectorial u and the real-time variable datas of vectorial y are gathered, and phase is obtained according to first residual generation Residual signals answered, and calculate the statistic of corresponding residual signals and compared with the first threshold, if gained corresponding the The statistic of one residual generation has exceeded the first threshold, then exports fault warning.
Embodiment 3
The present embodiment is similar with above-described embodiment 2, discloses a kind of non-gaussian industrial process fault detection method and (can refer to State embodiment 1), including：
The first step, a number of normal history data set is chosen, average is carried out to data set and pre-processed, utilizes typical case Correlation analysis method establishes residual generation；Specifically include：
Step A1, the process data under accidental conditions is chosen using historical data base, used respectivelyTwo variable datas of expression process Collection, wherein, l is measurand number in vectorial u, and m is measurand number in vectorial y, and N counts for independent sample；Then u (i), i= 1 ..., N represent that l variable represents in vectorial y m in the measured value at ith sample moment, y (i), i=1 ..., N in vectorial u Measured value of the variable at the ith sample moment；
Step A2, average value processing is carried out to data set；Average value processing is carried out respectively to two datasets so that two The average of each variable in data set is 0, obtains new data setWith
Step A3, after data set being normalized, required covariance matrix is estimated：
Wherein, Σu, ΣyAnd ΣuyU covariance matrix, y covariance matrix and u and y cross covariance are represented respectively Matrix；
Step A4, the covariance matrix obtained estimated by, establishing correlation matrix Υ is：It is and right Correlation matrix Υ carries out singular value decomposition, Υ=Γ Σ RT, wherein, Γ is the left singular vector of the correlation matrix, and R is described The right singular vector of correlation matrix, Σ are diagonal matrix；Then the second residual generation is obtained using canonical correlation analysis technology rb：
rb=JTu-ΣLTy
Wherein,
Second step, sampling DSMC determine the Second Threshold of second residual generation；Specifically include：
Step B1, the fully big normal history data set of number of samples is chosen, determines Monte-Carlo Simulation number K, and set Put initial thresholdCurrent iteration number s=0；
Step B2, according to Monte Carlo number, K data set is chosen in the s times iteration
Step B3, the statistic of corresponding residual generation is expressed as Js, counting function is expressed asCounting function value For：
Wherein,The statistics value of k-th of sample moment during iteration s is represented,Represent corresponding to statistic to work as during iteration s Preceding threshold value,Represent the count value of k-th of sample moment during iteration s；The statistic is calculated as：
Wherein, rbFor the residual signals of second residual generation output；For second residual generation Statistic；For the inverse matrix of the covariance matrix of corresponding residual signals；
Step B4, after for K Monte-Carlo Simulation, rate of false alarm value is estimated：
If step B5,Establishment then returns to present threshold valueFor required threshold value, and makeIf It is invalid, continue iteration, makeAnd return to step B3；Wherein, pFARFor specified maximum allowable rate of false alarm, ε ＞ 0 is a constant, and Δ is iteration tolerance；
3rd step, real-time online detection is carried out to industrial process data, specifically included：
The vectorial u gathered in real time and the vectorial y variable data are obtained, and according to second residual generation Corresponding residual signals are obtained, and calculate the statistic of corresponding residual signals and compared with the Second Threshold, if gained The statistic of corresponding second residual generation has exceeded the Second Threshold, then exports fault warning.
To sum up, non-gaussian industrial process fault detection method disclosed in the present embodiment, has the advantages that：
1st, present invention firstly provides a kind of non-height being combined based on canonical correlation analysis and Monte Carlo threshold learning This process online test method, this method can be with on-line checking non-gaussian industrial process；
2nd, detection method proposed by the present invention is real-time that, when industrial process breaks down, can timely detect Come；
3rd, Kernel-based methods data of the present invention, convenient and practical independent of accurate process model and supporting system Letter is realized in (developing the known technology that corollary system is those skilled in the art according to the above method, will not be described here) exploitation List, system run all right are reliable.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies Change, equivalent substitution, improvement etc., should be included in the scope of the protection.

Claims (6)

  1. A kind of 1. non-gaussian industrial process fault detection method, it is characterised in that including：
    The first step, a number of normal history data set is chosen, average is carried out to data set and pre-processed, utilizes canonical correlation Analysis method establishes residual generation；Specifically include：
    Step A1, the process data under accidental conditions is chosen using historical data base, used respectivelyTwo variable datas of expression process Collection, wherein, l is measurand number in vectorial u, and m is measurand number in vectorial y, and N counts for independent sample；ThenRepresent that l variable represents vector in the measured value at ith sample moment, y (i), i=1 ..., N in vectorial u Measured value of the m variable at the ith sample moment in y；
    Step A2, average value processing is carried out to data set；Average value processing is carried out respectively to two datasets so that two data The average for each variable concentrated is 0, obtains new data setWith
    Step A3, after data set being normalized, required covariance matrix is estimated：
    <mrow> <msub> <mi>&amp;Sigma;</mi> <mi>u</mi> </msub> <mo>=</mo> <mfrac> <mrow> <mover> <mi>U</mi> <mo>&amp;OverBar;</mo> </mover> <msup> <mover> <mi>U</mi> <mo>&amp;OverBar;</mo> </mover> <mi>T</mi> </msup> </mrow> <mrow> <mi>N</mi> <mo>-</mo> <mn>1</mn> </mrow> </mfrac> <mo>,</mo> <msub> <mi>&amp;Sigma;</mi> <mi>y</mi> </msub> <mo>=</mo> <mfrac> <mrow> <mover> <mi>Y</mi> <mo>&amp;OverBar;</mo> </mover> <msup> <mover> <mi>Y</mi> <mo>&amp;OverBar;</mo> </mover> <mi>T</mi> </msup> </mrow> <mrow> <mi>N</mi> <mo>-</mo> <mn>1</mn> </mrow> </mfrac> <mo>,</mo> <msub> <mi>&amp;Sigma;</mi> <mrow> <mi>u</mi> <mi>y</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <mover> <mi>U</mi> <mo>&amp;OverBar;</mo> </mover> <msup> <mover> <mi>Y</mi> <mo>&amp;OverBar;</mo> </mover> <mi>T</mi> </msup> </mrow> <mrow> <mi>N</mi> <mo>-</mo> <mn>1</mn> </mrow> </mfrac> </mrow>
    Wherein, Σu, ΣyAnd ΣuyU covariance matrix, y covariance matrix and u and y Cross-covariance are represented respectively；
    Step A4, the covariance matrix obtained estimated by, establishing correlation matrix Υ is：And to correlation Matrix Υ carries out singular value decomposition, Υ=Γ Σ RT, wherein, Γ is the left singular vector of the correlation matrix, and R is the correlation The right singular vector of matrix, Σ are diagonal matrix；Then the first residual generation r is obtained using canonical correlation analysis technologyaWith Second residual generation rb：
    ra=LTy-ΣTJTu,rb=JTu-ΣLTy
    Wherein,
    Second step, sampling DSMC determine that the first threshold of first residual generation and the second residual error occur respectively The Second Threshold of device；Specifically include：
    Step B1, the fully big normal history data set of number of samples is chosen, determines Monte-Carlo Simulation number K, and set just Beginning threshold valueCurrent iteration number s=0；
    Step B2, according to Monte Carlo number, K data set is chosen in the s times iteration
    Step B3, the statistic of corresponding residual generation is expressed as Js, counting function is expressed asCounting function value is：
    <mrow> <msubsup> <mi>I</mi> <mi>J</mi> <mrow> <mi>s</mi> <mo>,</mo> <mi>k</mi> </mrow> </msubsup> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <mn>1</mn> <mo>,</mo> </mrow> </mtd> <mtd> <mrow> <msubsup> <mi>J</mi> <mi>k</mi> <mi>s</mi> </msubsup> <mo>&gt;</mo> <msubsup> <mi>J</mi> <mrow> <mi>t</mi> <mi>h</mi> </mrow> <mi>s</mi> </msubsup> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mn>0</mn> <mo>,</mo> </mrow> </mtd> <mtd> <mrow> <msubsup> <mi>J</mi> <mi>k</mi> <mi>s</mi> </msubsup> <mo>&amp;le;</mo> <msubsup> <mi>J</mi> <mrow> <mi>t</mi> <mi>h</mi> </mrow> <mi>s</mi> </msubsup> </mrow> </mtd> </mtr> </mtable> </mfenced> </mrow>
    Wherein,The statistics value of k-th of sample moment during iteration s is represented,Represent current threshold corresponding to statistic during iteration s Value,Represent the count value of k-th of sample moment during iteration s；The statistic is calculated as：
    <mrow> <msubsup> <mi>T</mi> <mi>a</mi> <mn>2</mn> </msubsup> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>=</mo> <msubsup> <mi>r</mi> <mi>a</mi> <mi>T</mi> </msubsup> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> <msubsup> <mi>&amp;Sigma;</mi> <mi>a</mi> <mrow> <mo>-</mo> <mn>1</mn> </mrow> </msubsup> <msub> <mi>r</mi> <mi>a</mi> </msub> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>;</mo> <msubsup> <mi>T</mi> <mi>b</mi> <mn>2</mn> </msubsup> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>=</mo> <msubsup> <mi>r</mi> <mi>b</mi> <mi>T</mi> </msubsup> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> <msubsup> <mi>&amp;Sigma;</mi> <mi>b</mi> <mrow> <mo>-</mo> <mn>1</mn> </mrow> </msubsup> <msub> <mi>r</mi> <mi>b</mi> </msub> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>;</mo> </mrow>
    Wherein, raAnd rbRespectively the first residual generation and the residual signals of the second residual generation output；WithPoint Wei not the first residual generation and the corresponding statistic of the second residual generation；WithThe association of respectively corresponding residual signals The inverse matrix of variance matrix；
    Step B4, after for K Monte-Carlo Simulation, rate of false alarm value is estimated：
    <mrow> <msubsup> <mover> <mi>p</mi> <mo>^</mo> </mover> <mrow> <mi>F</mi> <mi>A</mi> <mi>R</mi> </mrow> <mi>s</mi> </msubsup> <mo>=</mo> <mfrac> <mrow> <munderover> <mo>&amp;Sigma;</mo> <mi>i</mi> <mi>K</mi> </munderover> <munderover> <mo>&amp;Sigma;</mo> <mi>k</mi> <msub> <mi>N</mi> <mi>i</mi> </msub> </munderover> <msubsup> <mi>I</mi> <mi>J</mi> <mrow> <mi>s</mi> <mo>,</mo> <mi>k</mi> </mrow> </msubsup> </mrow> <mrow> <mi>K</mi> <mo>&amp;CenterDot;</mo> <msub> <mi>N</mi> <mi>i</mi> </msub> </mrow> </mfrac> </mrow>
    If step B5,Establishment then returns to present threshold valueFor required threshold value, and makeIf not into It is vertical then continue iteration, makeAnd return to step B3；Wherein, pFARFor specified maximum allowable rate of false alarm, ε ＞ 0 are One constant, Δ are iteration tolerance；
    3rd step, real-time online detection is carried out to industrial process data, specifically included：
    The vectorial u gathered in real time and the vectorial y variable data are obtained, and according to first residual generation and institute State the second residual generation and obtain corresponding residual signals, and calculate respectively the statistic of corresponding residual signals and with corresponding institute State first threshold and the Second Threshold is compared, if the statistic of corresponding first residual generation of gained has exceeded described the One threshold value or the statistic of corresponding second residual generation have exceeded the Second Threshold, then export fault warning.
  2. A kind of 2. non-gaussian industrial process fault detection system for being used to perform method as claimed in claim 1.
  3. A kind of 3. non-gaussian industrial process fault detection method, it is characterised in that including：
    The first step, a number of normal history data set is chosen, average is carried out to data set and pre-processed, utilizes canonical correlation Analysis method establishes residual generation；Specifically include：
    Step A1, the process data under accidental conditions is chosen using historical data base, used respectivelyTwo variable datas of expression process Collection, wherein, l is measurand number in vectorial u, and m is measurand number in vectorial y, and N counts for independent sample；ThenRepresent that l variable represents vector in the measured value at ith sample moment, y (i), i=1 ..., N in vectorial u Measured value of the m variable at the ith sample moment in y；
    Step A2, average value processing is carried out to data set；Average value processing is carried out respectively to two datasets so that two data The average for each variable concentrated is 0, obtains new data setWith
    Step A3, after data set being normalized, required covariance matrix is estimated：
    <mrow> <msub> <mi>&amp;Sigma;</mi> <mi>u</mi> </msub> <mo>=</mo> <mfrac> <mrow> <mover> <mi>U</mi> <mo>&amp;OverBar;</mo> </mover> <msup> <mover> <mi>U</mi> <mo>&amp;OverBar;</mo> </mover> <mi>T</mi> </msup> </mrow> <mrow> <mi>N</mi> <mo>-</mo> <mn>1</mn> </mrow> </mfrac> <mo>,</mo> <msub> <mi>&amp;Sigma;</mi> <mi>y</mi> </msub> <mo>=</mo> <mfrac> <mrow> <mover> <mi>Y</mi> <mo>&amp;OverBar;</mo> </mover> <msup> <mover> <mi>Y</mi> <mo>&amp;OverBar;</mo> </mover> <mi>T</mi> </msup> </mrow> <mrow> <mi>N</mi> <mo>-</mo> <mn>1</mn> </mrow> </mfrac> <mo>,</mo> <msub> <mi>&amp;Sigma;</mi> <mrow> <mi>u</mi> <mi>y</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <mover> <mi>U</mi> <mo>&amp;OverBar;</mo> </mover> <msup> <mover> <mi>Y</mi> <mo>&amp;OverBar;</mo> </mover> <mi>T</mi> </msup> </mrow> <mrow> <mi>N</mi> <mo>-</mo> <mn>1</mn> </mrow> </mfrac> </mrow>
    Wherein, Σu, ΣyAnd ΣuyU covariance matrix, y covariance matrix and u and y Cross-covariance are represented respectively；
    Step A4, the covariance matrix obtained estimated by, establishing correlation matrix Υ is：And to correlation Matrix Υ carries out singular value decomposition, Υ=Γ Σ RT, wherein, Γ is the left singular vector of the correlation matrix, and R is the correlation The right singular vector of matrix, Σ are diagonal matrix；Then the first residual generation r is obtained using canonical correlation analysis technologya：
    ra=LTy-ΣTJTu
    Wherein,
    Second step, sampling DSMC determine the first threshold of first residual generation, specifically include：
    Step B1, the fully big normal history data set of number of samples is chosen, determines Monte-Carlo Simulation number K, and set just Beginning threshold valueCurrent iteration number s=0；
    Step B2, according to Monte Carlo number, K data set is chosen in the s times iteration
    Step B3, the statistic of corresponding residual generation is expressed as Js, counting function is expressed asCounting function value is：
    <mrow> <msubsup> <mi>I</mi> <mi>J</mi> <mrow> <mi>s</mi> <mo>,</mo> <mi>k</mi> </mrow> </msubsup> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <mn>1</mn> <mo>,</mo> </mrow> </mtd> <mtd> <mrow> <msubsup> <mi>J</mi> <mi>k</mi> <mi>s</mi> </msubsup> <mo>&gt;</mo> <msubsup> <mi>J</mi> <mrow> <mi>t</mi> <mi>h</mi> </mrow> <mi>s</mi> </msubsup> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mn>0</mn> <mo>,</mo> </mrow> </mtd> <mtd> <mrow> <msubsup> <mi>J</mi> <mi>k</mi> <mi>s</mi> </msubsup> <mo>&amp;le;</mo> <msubsup> <mi>J</mi> <mrow> <mi>t</mi> <mi>h</mi> </mrow> <mi>s</mi> </msubsup> </mrow> </mtd> </mtr> </mtable> </mfenced> </mrow>
    Wherein,The statistics value of k-th of sample moment during iteration s is represented,Represent current threshold corresponding to statistic during iteration s Value,Represent the count value of k-th of sample moment during iteration s；The statistic is calculated as：
    <mrow> <msubsup> <mi>T</mi> <mi>a</mi> <mn>2</mn> </msubsup> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>=</mo> <msubsup> <mi>r</mi> <mi>a</mi> <mi>T</mi> </msubsup> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> <msubsup> <mi>&amp;Sigma;</mi> <mi>a</mi> <mrow> <mo>-</mo> <mn>1</mn> </mrow> </msubsup> <msub> <mi>r</mi> <mi>a</mi> </msub> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>;</mo> </mrow>
    Wherein, raFor the residual signals of first residual generation output；For the statistics of first residual generation Amount；For the inverse matrix of the covariance matrix of corresponding residual signals；
    Step B4, after for K Monte-Carlo Simulation, rate of false alarm value is estimated：
    <mrow> <msubsup> <mover> <mi>p</mi> <mo>^</mo> </mover> <mrow> <mi>F</mi> <mi>A</mi> <mi>R</mi> </mrow> <mi>s</mi> </msubsup> <mo>=</mo> <mfrac> <mrow> <munderover> <mo>&amp;Sigma;</mo> <mi>i</mi> <mi>K</mi> </munderover> <munderover> <mo>&amp;Sigma;</mo> <mi>k</mi> <msub> <mi>N</mi> <mi>i</mi> </msub> </munderover> <msubsup> <mi>I</mi> <mi>J</mi> <mrow> <mi>s</mi> <mo>,</mo> <mi>k</mi> </mrow> </msubsup> </mrow> <mrow> <mi>K</mi> <mo>&amp;CenterDot;</mo> <msub> <mi>N</mi> <mi>i</mi> </msub> </mrow> </mfrac> </mrow>
    If step B5,Establishment then returns to present threshold valueFor required threshold value, and makeIt is if invalid Then continue iteration, makeAnd return to step B3；Wherein, pFARFor specified maximum allowable rate of false alarm, ε ＞ 0 are one Constant, Δ are iteration tolerance；
    3rd step, real-time online detection is carried out to industrial process data, specifically included：
    The vectorial u and the real-time variable datas of vectorial y are gathered, and is obtained accordingly according to first residual generation Residual signals, and calculate the statistic of corresponding residual signals and compared with the first threshold, if gained corresponding first is residual The statistic of difference generator has exceeded the first threshold, then exports fault warning.
  4. A kind of 4. non-gaussian industrial process fault detection system for being used to perform method as claimed in claim 3.
  5. A kind of 5. non-gaussian industrial process fault detection method, it is characterised in that including：
    The first step, a number of normal history data set is chosen, average is carried out to data set and pre-processed, utilizes canonical correlation Analysis method establishes residual generation；Specifically include：
    Step A1, the process data under accidental conditions is chosen using historical data base, used respectivelyTwo variable datas of expression process Collection, wherein, l is measurand number in vectorial u, and m is measurand number in vectorial y, and N counts for independent sample；ThenRepresent that l variable represents vector in the measured value at ith sample moment, y (i), i=1 ..., N in vectorial u Measured value of the m variable at the ith sample moment in y；
    Step A2, average value processing is carried out to data set；Average value processing is carried out respectively to two datasets so that two data The average for each variable concentrated is 0, obtains new data setWith
    Step A3, after data set being normalized, required covariance matrix is estimated：
    <mrow> <msub> <mi>&amp;Sigma;</mi> <mi>u</mi> </msub> <mo>=</mo> <mfrac> <mrow> <mover> <mi>U</mi> <mo>&amp;OverBar;</mo> </mover> <msup> <mover> <mi>U</mi> <mo>&amp;OverBar;</mo> </mover> <mi>T</mi> </msup> </mrow> <mrow> <mi>N</mi> <mo>-</mo> <mn>1</mn> </mrow> </mfrac> <mo>,</mo> <msub> <mi>&amp;Sigma;</mi> <mi>y</mi> </msub> <mo>=</mo> <mfrac> <mrow> <mover> <mi>Y</mi> <mo>&amp;OverBar;</mo> </mover> <msup> <mover> <mi>Y</mi> <mo>&amp;OverBar;</mo> </mover> <mi>T</mi> </msup> </mrow> <mrow> <mi>N</mi> <mo>-</mo> <mn>1</mn> </mrow> </mfrac> <mo>,</mo> <msub> <mi>&amp;Sigma;</mi> <mrow> <mi>u</mi> <mi>y</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <mover> <mi>U</mi> <mo>&amp;OverBar;</mo> </mover> <msup> <mover> <mi>Y</mi> <mo>&amp;OverBar;</mo> </mover> <mi>T</mi> </msup> </mrow> <mrow> <mi>N</mi> <mo>-</mo> <mn>1</mn> </mrow> </mfrac> </mrow>
    Wherein, Σu, ΣyAnd ΣuyU covariance matrix, y covariance matrix and u and y Cross-covariance are represented respectively；
    Step A4, the covariance matrix obtained estimated by, establishing correlation matrix Υ is：And to correlation Matrix Υ carries out singular value decomposition, Υ=Γ Σ RT, wherein, Γ is the left singular vector of the correlation matrix, and R is the correlation The right singular vector of matrix, Σ are diagonal matrix；Then the second residual generation r is obtained using canonical correlation analysis technologyb：
    rb=JTu-ΣLTy
    Wherein,
    Second step, sampling DSMC determine the Second Threshold of second residual generation；Specifically include：
    Step B1, the fully big normal history data set of number of samples is chosen, determines Monte-Carlo Simulation number K, and set just Beginning threshold valueCurrent iteration number s=0；
    Step B2, according to Monte Carlo number, K data set is chosen in the s times iteration
    Step B3, the statistic of corresponding residual generation is expressed as Js, counting function is expressed asCounting function value is：
    <mrow> <msubsup> <mi>I</mi> <mi>J</mi> <mrow> <mi>s</mi> <mo>,</mo> <mi>k</mi> </mrow> </msubsup> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <mn>1</mn> <mo>,</mo> </mrow> </mtd> <mtd> <mrow> <msubsup> <mi>J</mi> <mi>k</mi> <mi>s</mi> </msubsup> <mo>&gt;</mo> <msubsup> <mi>J</mi> <mrow> <mi>t</mi> <mi>h</mi> </mrow> <mi>s</mi> </msubsup> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mn>0</mn> <mo>,</mo> </mrow> </mtd> <mtd> <mrow> <msubsup> <mi>J</mi> <mi>k</mi> <mi>s</mi> </msubsup> <mo>&amp;le;</mo> <msubsup> <mi>J</mi> <mrow> <mi>t</mi> <mi>h</mi> </mrow> <mi>s</mi> </msubsup> </mrow> </mtd> </mtr> </mtable> </mfenced> </mrow>
    Wherein,The statistics value of k-th of sample moment during iteration s is represented,Represent current threshold corresponding to statistic during iteration s Value,Represent the count value of k-th of sample moment during iteration s；The statistic is calculated as：
    <mrow> <msubsup> <mi>T</mi> <mi>a</mi> <mn>2</mn> </msubsup> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>=</mo> <msubsup> <mi>r</mi> <mi>a</mi> <mi>T</mi> </msubsup> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> <msubsup> <mi>&amp;Sigma;</mi> <mi>a</mi> <mrow> <mo>-</mo> <mn>1</mn> </mrow> </msubsup> <msub> <mi>r</mi> <mi>a</mi> </msub> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>;</mo> </mrow>
    Wherein, rbFor the residual signals of second residual generation output；For the statistics of second residual generation Amount；For the inverse matrix of the covariance matrix of corresponding residual signals；
    Step B4, after for K Monte-Carlo Simulation, rate of false alarm value is estimated：
    <mrow> <msubsup> <mover> <mi>p</mi> <mo>^</mo> </mover> <mrow> <mi>F</mi> <mi>A</mi> <mi>R</mi> </mrow> <mi>s</mi> </msubsup> <mo>=</mo> <mfrac> <mrow> <munderover> <mo>&amp;Sigma;</mo> <mi>i</mi> <mi>K</mi> </munderover> <munderover> <mo>&amp;Sigma;</mo> <mi>k</mi> <msub> <mi>N</mi> <mi>i</mi> </msub> </munderover> <msubsup> <mi>I</mi> <mi>J</mi> <mrow> <mi>s</mi> <mo>,</mo> <mi>k</mi> </mrow> </msubsup> </mrow> <mrow> <mi>K</mi> <mo>&amp;CenterDot;</mo> <msub> <mi>N</mi> <mi>i</mi> </msub> </mrow> </mfrac> </mrow>
    If step B5,Establishment then returns to present threshold valueFor required threshold value, and makeIt is if invalid Then continue iteration, makeAnd return to step B3；Wherein, pFARFor specified maximum allowable rate of false alarm, ε ＞ 0 are one Constant, Δ are iteration tolerance；
    3rd step, real-time online detection is carried out to industrial process data, specifically included：
    The vectorial u gathered in real time and the vectorial y variable data are obtained, and is obtained according to second residual generation Corresponding residual signals, and calculate the statistic of corresponding residual signals and compared with the Second Threshold, if gained is corresponding The statistic of second residual generation has exceeded the Second Threshold, then exports fault warning.
  6. A kind of 6. non-gaussian industrial process fault detection system for being used to perform method as claimed in claim 5.
CN201710623082.9A 2017-07-27 2017-07-27 Non-gaussian industrial process fault detection method and system Active CN107357275B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710623082.9A CN107357275B (en) 2017-07-27 2017-07-27 Non-gaussian industrial process fault detection method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710623082.9A CN107357275B (en) 2017-07-27 2017-07-27 Non-gaussian industrial process fault detection method and system

Publications (2)

Publication Number Publication Date
CN107357275A true CN107357275A (en) 2017-11-17
CN107357275B CN107357275B (en) 2019-08-27

Family

ID=60286354

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710623082.9A Active CN107357275B (en) 2017-07-27 2017-07-27 Non-gaussian industrial process fault detection method and system

Country Status (1)

Country Link
CN (1) CN107357275B (en)

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108170648A (en) * 2017-12-15 2018-06-15 宁波大学 A kind of nongausian process monitoring method returned based on given data
CN108646719A (en) * 2018-07-05 2018-10-12 中南大学 A kind of Weak fault detection method and system
CN109203995A (en) * 2018-07-10 2019-01-15 中南大学 A kind of trailer system major loop ground fault diagnosis method and system
CN109507972A (en) * 2018-12-19 2019-03-22 中国计量大学 Industrial processes fault monitoring method based on layer-stepping non-gaussian monitoring algorithm
CN109523195A (en) * 2018-12-19 2019-03-26 中国计量大学 The fault detection method of layer-stepping non-gaussian algorithm based on the multi-modal classification of sample
CN110046054A (en) * 2018-01-17 2019-07-23 中兴通讯股份有限公司 Virtual machine method for detecting abnormality, device, equipment and computer readable storage medium
CN108803465B (en) * 2018-06-19 2019-08-23 哈尔滨工业大学 A kind of distributed plug and play fault monitoring method based on closed-loop data driving
CN110187206A (en) * 2019-05-22 2019-08-30 中国人民解放军国防科技大学 Fault detection method for suspension system in non-Gaussian process under complex working condition
CN110209145A (en) * 2019-05-16 2019-09-06 浙江大学 One kind being based on the approximate carbon dioxide absorption tower method for diagnosing faults of nuclear matrix
CN110580488A (en) * 2018-06-08 2019-12-17 中南大学 Multi-working-condition industrial monitoring method, device, equipment and medium based on dictionary learning
CN110879372A (en) * 2019-12-03 2020-03-13 中南大学 Traction system main loop earth fault diagnosis method and system based on feature correlation
CN111209973A (en) * 2020-01-09 2020-05-29 浙江理工大学 Process monitoring method based on mixed kernel PCA-CCA and kernel density estimation
CN113189968A (en) * 2021-05-08 2021-07-30 哈尔滨工业大学 Distributed fault diagnosis method for interconnected industrial process
CN114545907A (en) * 2022-03-15 2022-05-27 中南大学 Fault detection method of flight control system based on filter

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105739489A (en) * 2016-05-12 2016-07-06 电子科技大学 Batch process fault detecting method based on ICA-KNN
CN106054859A (en) * 2016-05-30 2016-10-26 宁波大学 Double-layer integrated type industrial process fault detection method based on modified independent component analysis (MICA)
CN106092625A (en) * 2016-05-30 2016-11-09 宁波大学 The industrial process fault detection method merged based on correction type independent component analysis and Bayesian probability
CN106569487A (en) * 2016-11-16 2017-04-19 北京理工大学 Fault detection method for servo system based on observer

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105739489A (en) * 2016-05-12 2016-07-06 电子科技大学 Batch process fault detecting method based on ICA-KNN
CN106054859A (en) * 2016-05-30 2016-10-26 宁波大学 Double-layer integrated type industrial process fault detection method based on modified independent component analysis (MICA)
CN106092625A (en) * 2016-05-30 2016-11-09 宁波大学 The industrial process fault detection method merged based on correction type independent component analysis and Bayesian probability
CN106569487A (en) * 2016-11-16 2017-04-19 北京理工大学 Fault detection method for servo system based on observer

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
徐莹等: "基于ALSICA算法的多工况非高斯过程故障检测方法", 《计算机与应用化学》 *
徐莹等: "基于FRICA算法的非高斯过程故障检测方法", 《上海应用技术学院学报（自然科学版）》 *
蔡连芳等: "一种基于改进KICA的非高斯过程故障检测方法", 《化工学报》 *

Cited By (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108170648A (en) * 2017-12-15 2018-06-15 宁波大学 A kind of nongausian process monitoring method returned based on given data
CN108170648B (en) * 2017-12-15 2021-05-18 宁波大学 non-Gaussian process monitoring method based on known data regression
CN110046054A (en) * 2018-01-17 2019-07-23 中兴通讯股份有限公司 Virtual machine method for detecting abnormality, device, equipment and computer readable storage medium
CN110580488A (en) * 2018-06-08 2019-12-17 中南大学 Multi-working-condition industrial monitoring method, device, equipment and medium based on dictionary learning
CN110580488B (en) * 2018-06-08 2022-04-01 中南大学 Multi-working-condition industrial monitoring method, device, equipment and medium based on dictionary learning
CN108803465B (en) * 2018-06-19 2019-08-23 哈尔滨工业大学 A kind of distributed plug and play fault monitoring method based on closed-loop data driving
CN108646719B (en) * 2018-07-05 2021-04-06 中南大学 Weak fault detection method and system
CN108646719A (en) * 2018-07-05 2018-10-12 中南大学 A kind of Weak fault detection method and system
CN109203995A (en) * 2018-07-10 2019-01-15 中南大学 A kind of trailer system major loop ground fault diagnosis method and system
CN109523195A (en) * 2018-12-19 2019-03-26 中国计量大学 The fault detection method of layer-stepping non-gaussian algorithm based on the multi-modal classification of sample
CN109523195B (en) * 2018-12-19 2023-01-06 中国计量大学 Sample multi-modal classification-based fault detection method for hierarchical non-Gaussian algorithm
CN109507972A (en) * 2018-12-19 2019-03-22 中国计量大学 Industrial processes fault monitoring method based on layer-stepping non-gaussian monitoring algorithm
CN110209145A (en) * 2019-05-16 2019-09-06 浙江大学 One kind being based on the approximate carbon dioxide absorption tower method for diagnosing faults of nuclear matrix
CN110209145B (en) * 2019-05-16 2020-09-11 浙江大学 Carbon dioxide absorption tower fault diagnosis method based on nuclear matrix approximation
CN110187206A (en) * 2019-05-22 2019-08-30 中国人民解放军国防科技大学 Fault detection method for suspension system in non-Gaussian process under complex working condition
CN110879372B (en) * 2019-12-03 2021-04-23 中南大学 Traction system main loop earth fault diagnosis method and system based on feature correlation
CN110879372A (en) * 2019-12-03 2020-03-13 中南大学 Traction system main loop earth fault diagnosis method and system based on feature correlation
CN111209973A (en) * 2020-01-09 2020-05-29 浙江理工大学 Process monitoring method based on mixed kernel PCA-CCA and kernel density estimation
CN111209973B (en) * 2020-01-09 2023-04-07 浙江理工大学 Process monitoring method based on mixed kernel PCA-CCA and kernel density estimation
CN113189968A (en) * 2021-05-08 2021-07-30 哈尔滨工业大学 Distributed fault diagnosis method for interconnected industrial process
CN113189968B (en) * 2021-05-08 2022-08-26 哈尔滨工业大学 Distributed fault diagnosis method for interconnected industrial process
CN114545907A (en) * 2022-03-15 2022-05-27 中南大学 Fault detection method of flight control system based on filter
CN114545907B (en) * 2022-03-15 2023-12-19 中南大学 Fault detection method of flight control system based on filter

Also Published As

Publication number Publication date
CN107357275B (en) 2019-08-27

Similar Documents

Publication Publication Date Title
CN107357275A (en) Non-gaussian industrial process fault detection method and system
CN107016236B (en) Power grid false data injection attack detection method based on nonlinear measurement equation
CN110738274A (en) nuclear power device fault diagnosis method based on data driving
CN109613428A (en) It is a kind of can be as system and its application in motor device fault detection method
CN103776480B (en) Small fault detection method based on repeatedly rolling average and device
CN106092625B (en) The industrial process fault detection method merged based on amendment type independent component analysis and Bayesian probability
CN104483962B (en) The online fault detection method of batch process based on multidirectional orthogonal locality preserving projections
CN107153409B (en) A kind of nongausian process monitoring method based on missing variable modeling thinking
CN103713628B (en) Fault diagnosis method based on signed directed graph and data constitution
CN105955219A (en) Distributed dynamic process fault detection method based on mutual information
CN105629958B (en) A kind of batch process method for diagnosing faults based on sub-period MPCA SVM
CN103776654A (en) Method for diagnosing faults of multi-sensor information fusion
CN105846780A (en) Decision tree model-based photovoltaic assembly fault diagnosis method
CN101738998B (en) System and method for monitoring industrial process based on local discriminatory analysis
CN103631145B (en) Multiple operating modes process monitoring method and system based on monitor control index switching
CN111580506A (en) Industrial process fault diagnosis method based on information fusion
US20220155770A1 (en) Method of Fault Monitoring of Sewage Treatment Process Based on OICA and RNN Fusion Model
CN109409425A (en) A kind of fault type recognition method based on neighbour&#39;s constituent analysis
CN106647650A (en) Distributed industrial process monitoring method based variable weighting PCA (Principal Component Analysis) model
CN105182141A (en) Transformer fault detection method and system
CN108153267A (en) A kind of Industrial Process Monitoring method based on error Principal Component Analysis Model
CN103678938B (en) A kind of degradation model consistency check method of space-oriented shape and range of error
CN110244692A (en) Chemical process small fault detection method
CN108830006A (en) Linear-nonlinear industrial processes fault detection method based on the linear evaluation factor
CN103853144A (en) On-site sensor fault detection method based on oil-extraction production data

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