CN112180893B - Construction method of fault-related distributed orthogonal neighborhood preserving embedded model in CSTR process and fault monitoring method thereof - Google Patents
Construction method of fault-related distributed orthogonal neighborhood preserving embedded model in CSTR process and fault monitoring method thereof Download PDFInfo
- Publication number
- CN112180893B CN112180893B CN202010969145.8A CN202010969145A CN112180893B CN 112180893 B CN112180893 B CN 112180893B CN 202010969145 A CN202010969145 A CN 202010969145A CN 112180893 B CN112180893 B CN 112180893B
- Authority
- CN
- China
- Prior art keywords
- sub
- fault
- newi
- block
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Complex Calculations (AREA)
Abstract
The invention discloses a method for constructing a fault-related distributed orthogonal neighborhood preserving embedded model in a CSTR process, which comprises the following steps: n historical normal samples of the physical quantity monitored by m physical quantity monitoring points in the CSTR process are obtainedUsing SNR algorithm to pick out the variable related to each fault to form B +1 sub-blocks [ X ]1,…,XB+1]Calculating the historical normal sample of each sub-blockStatistic of (2)And statistics SPEb,i(i-1, …, n) and its control limitsSPEb,lim(ii) a Acquiring physical quantity data of m physical quantity monitoring points in the CSTR process on line, corresponding the data to B +1 sub-blocks, and calculating X sub-block of each sub-blockb,newX of the ith (i ═ 1,2, …, n1) measurement sample of (a)b,newiStatisticsStatistics SPEb,newi(ii) a Constructing statistics using Bayesian inferenceAndstatisticsExceeding its control limit indicates that a fault has occurred. The method considers local information of CSTR process data, establishes a distributed monitoring model and improves the detection rate of faults.
Description
Technical Field
The invention belongs to the technical field of fault monitoring in a chemical production process, and particularly relates to a construction method of a fault-related distributed orthogonal neighborhood preserving embedded model in a CSTR process and a fault monitoring method thereof, which are used for improving the fault monitoring accuracy in the chemical process.
Background
Continuous Stirred Tank Reactors (CSTRs) are important in the industrial chemical process facilities and are widely used in the chemical reactions. It is widely used in pharmaceutical and synthetic food industries, and in semiconductor manufacturing industries. Along with diversification of chemical industrial production equipment and raw materials and increasingly complicated process flow, various production safety accidents also enter a peak period of easy occurrence and multiple occurrence; therefore, fault monitoring in CSTR processes is also becoming increasingly important.
Multivariate Statistical Process Monitoring (MSPM) technology represented by principal component analysis has become a research hotspot for fault monitoring of chemical process due to the strong capability of extracting useful information. Modern increasingly complex chemical processes typically involve large numbers of production equipment and control systems whose measurement data have high-dimensional, strong correlations, especially strong non-linearities that are prevalent among variables. The MSPM technique does not effectively account for non-linear fluctuations in the data and therefore cannot be used to monitor non-linear chemical processes.
Due to the complex correlation between CSTR process variables, the existing fault monitoring model is usually a global model, it is difficult to fully adapt it as a global monitoring model for the whole process, since it ignores the local behavior of the physicochemical data, and the monitoring results are often difficult to interpret.
Disclosure of Invention
The invention aims to solve the technical problem of providing a CSTR process Fault monitoring method based on a Fault-dependent distributed orthogonal neighborhood preserving embedding (FDONPE) model, so as to solve the technical problem of low Fault detection rate caused by neglecting of physicochemical parameters or local behaviors of data in the existing global model.
In order to solve the technical problems, the inventor establishes an FDONPE model based on an ONPE method based on long-term practical research in the field, and applies the FDONPE model to CSTR process fault monitoring so as to maintain local characteristics of process physical parameters or data and better extract distribution characteristics and essential information of each physical parameter.
Among them, the Neighborhood Orthogonal Preserving Embedding (ONPE) algorithm (Liu X M, Yin J W, Feng Z L, et al. organic New born Embedding for Face Recognition [ C ]// Proceedings of 2007 IEEE International reference on Image, ICIP 2007.New York,2007: 133-.
The specific technical scheme adopted by the invention is as follows:
a construction method of a fault-related distributed orthogonal neighborhood preserving embedded model in a CSTR process is designed, and comprises the following steps:
(1) obtaining n historical normal samples of the physical quantity monitored by m physical quantity monitoring points in the CSTR process, and constructing a matrix X' belonging to the Rm×nSubtracting the mean value of all sample data in the row from each row of X', and dividing the mean value by the standard deviation of all sample data in the row to obtain a matrix X e Rm×n。
(2) Using SNR algorithm to pick out the variable related to each fault to form B sub-blocks [ X ]1,X2,…,XB]And the global variable X is considered as a new block, constituting in total B +1 sub-blocks [ X1,…,XB+1]Sub-blockSub-block samplesdb(B-1, 2, …, B +1) is the subblock Xb(B-1, 2, …, B +1), where B is the number of known failure types.
(3) Obtaining each sub-block X based on ONPE modelb(B-1, 2, …, B +1) projection matrixAnd calculating the historical normal sample of each sub-blockStatistic of (2)And statistics SPEb,i(i=1,…,n)。
Wherein, ab,i(i=1,…,gb) Is the projection vector, gbIs dimension reduction, Λb=YbYb T/(n-1),Yb=Ab TXb,yb,i=Ab Txb,i(i=1,2,…,n)。
(4) Computing each sub-block X using a kernel density estimation functionb(B-1, 2, …, B) control limitAnd control limit SPEb,lim。
Further, in the step (2), the history is normalizedData partitioning sub-block XbThe method of (B ═ 1,2, …, B) is:
consider a set of fault data setsXfThe data in (1) is collected in an operation mode in which a certain failure occurs in the system; wherein m isfIs the number of variables, nfIs the number of samples.
SNR is the ratio of signal s to noise e in a system, and each variable i (i ═ 1, …, m)f) SNR of (1)iThe calculation is as follows:
whereinXf(i, j) is XfValue in ith row and jth column, Xf(i,: means X)fThe vector of row i; SNRiIt is the signal-to-noise ratio of the ith variable in a certain failure operation mode, which reflects the change degree of the ith variable after failure, and is higher than each variable i (i is 1, …, m)f) SNR of (1)iThe magnitude of (c) indicates that it has changed significantly since the failure occurred, the selection and { SNR }i,i=1,…,mfAnd the variables corresponding to the first C maximum values in the sequence are taken as relevant variables of the fault.
Further, in the step (3), each sub-block X is calculated based on the ONPE modelb(B-1, 2, …, B +1) projection matrixComprises the following steps:
(3a) construction of neighborhood set Sb: for some normal history sample point xb,i(i ═ 1,2, …, n), calculating Euclidean distances to other sample points, and then selecting k with the minimum Euclidean distance to the sample pointbPoints constitute a neighborhood set
(3b) Determining a weight coefficient matrix Wb:
By a minimization functionObtaining a spatial neighborhood set SbIs given by the weight coefficient matrix Wb:
WhereinRepresents a sample xb,iThe j-th proximity point, WbijIs a matrix WbRow i and column j of (1), representing a sampleFor reconstructed sample xb,iThe weight coefficient of (a); the constraint condition isIf sampleIs not xb,iNeighborhood of (1), then Wbij=0。
(3c) Establishing an objective function J (y)b):
J(Ab)=minAb TXbMbXb TAb (6)
wherein M isb=(Ib-Wb)T(Ib-Wb)。
Adding constraint conditions on the basis of the formula (6): a. theb TXbXb TAb=Ib,The lagrange multiplier method is utilized to contain constraints to solve the optimization problem, and the formula (6) can be converted into the following generalized eigenvalue solving problem, namely:
XbMbXb TAb=λbXbXb TAb (7)
solving equation (7) yields:
1)ab,1is (X)bXb T)-1XbMbXb TThe feature vector corresponding to the minimum feature value of (1);
2)ab,i(i=2,…,gb) Is Qb (i)The feature vector corresponding to the minimum feature value of (1);
Qb (i)={Ib-(XbXb T)-1ab (i-1)[Gb (i-1)]T}(XbXb T)-1XbMbXb T (8)
in the formula, Gb (i-1)=[ab (i-1)]T(XbXb T)-1ab (i-1);ab (i-1)=[ab,1,ab,2,…ab,i-1]。
Determining all a from the formula (8)b,i(i=1,…,gb) To obtain a projection matrix Ab。
On the other hand, a CSTR process fault monitoring method based on FDONPE is designed, and comprises the following steps:
firstly, acquiring n1 measurement samples of physical quantities of m physical quantity monitoring points in the chemical production process on line, and constructing a measurement matrix X'new∈Rm×n1Will beSubtracting the average value of all sample data in the ith row of the matrix X' from each value in the ith (i-1, …, n1) row in (a), and dividing the average value by the standard deviation of all sample data in the ith row to obtain preprocessed Xnew. Handle XnewCorresponds to the sub-block of step (2) in claim 1, forming B +1 sub-blocksSub-blocksSub-block samples
② calculating each sub-block X by using fault monitoring method of ONPE modelb,newX of the ith (i ═ 1,2, …, n1) measurement sample of (a)b,newiStatisticsStatistics SPEb,newi:
SPEb,newi=xb,newi(Ib-Ab TAb)[xb,newi(Ib-Ab TAb)]T (10)
Wherein, Λb=(Ab TXb,new)(Ab TXb,new)T/(n1-1),yb,newi=Ab Txb,newi(i=1,2,…,n1)。
Constructing the ith measurement sample x based on Bayesian inferencenewi(i=1,...,n1)∈RmBayes statistic of (d):
n and F represent normal and fault conditions, statistics, respectivelyAnd statistics SPEb,newiThe probabilities under normal and fault conditions are respectively:
PSPE(xb,newi)=PSPE(xb,newi|N)PSPE(N)+PSPE(xb,newi|F)PSPE(F) (14)
Fourthly, the Bayes statisticAndcomparing with the control limit 1-alpha respectively, the part exceeding the control limit indicates the ith sample xnewiA fault occurs.
Compared with the prior art, the invention has the main beneficial technical effects that:
1. compared with the traditional CSTR process monitoring method based on the ONPE model, the CSTR process monitoring method based on the FDONPE model considers the local information of the process data, divides the process physical quantity into a plurality of sub-physical quantity modules through an SNR algorithm, then models each sub-physical quantity space by adopting the ONPE method, and finally constructs new statistic by adopting Bayesian inference to realize the monitoring of the CSTR process data; the method fully utilizes the intra-block local physicochemical data information and the overall global physicochemical data information, and improves the accuracy of fault monitoring.
2. According to the method, the fault information is utilized, the variable set strongly related to the fault is selected and used for model development, the monitoring model is established, and more meaningful directions can be extracted for monitoring, so that the accuracy of fault detection is improved.
The ONPE model has certain processing capacity on the nonlinear data, and the improved FDONPE model can effectively explain the nonlinear fluctuation in the physicochemical data; therefore, the process monitoring model established based on the nonlinear algorithm can also judge whether the online physicochemical data really deviate from the normal working condition.
Drawings
FIG. 1 is a flow chart of an off-line modeling process of a CSTR process monitoring method based on an FDONPE model according to the present invention.
FIG. 2 is a flow chart of the on-line monitoring process of the CSTR process monitoring method based on the FDONPE model of the present invention.
Fig. 3 is a monitoring result of the fault 10 in the CSTR monitoring process by using the ONPE method in the embodiment of the present invention, in which the abscissa is a sample and the ordinate is a statistic.
Fig. 4 is a monitoring result of the fault 10 in the CSTR monitoring process by using the fdonfe method in the embodiment of the present invention, in which the abscissa in the figure is a sample and the ordinate is a statistic.
Fig. 5 shows the 10 sub-block monitoring results of the CSTR fault 10 monitored by using the fdonne method in the embodiment of the present invention, where the abscissa in the figure is a sample and the ordinate is a statistic.
Detailed Description
The following examples are given to illustrate specific embodiments of the present invention, but are not intended to limit the scope of the present invention in any way.
The following embodiments are explained based on a CSTR system, data are generated through a CSTR model built by a Simulink module of matlab, the simulation system can set a plurality of physical measuring point positions corresponding to 10 basic faults and 7 physical quantities to be monitored, and each fault is obtained from the following stepsThe 201 st test sample was introduced. 1200 measurement data were collected, of which the first 200 were normal data and the last 1000 were failure data. Reactor solute concentration Q in example one at 10 failuresCThe description will be given with reference to variations as examples.
The first embodiment of the CSTR process monitoring method based on the FDONPE model is used for processing physical quantity data acquired at a plurality of physical quantity monitoring points in the CSTR process so as to monitor the physical quantity data which fails, and therefore production maintenance personnel can find problems in production as soon as possible and perform corresponding processing conveniently. The physical quantity monitoring points and the corresponding monitored physical quantities of the CSTR process are shown in Table 1.
The method mainly comprises the following steps:
step (I): establishing an offline FDONPE model
(1) Obtaining n historical normal samples of the physical quantity monitored by m physical quantity monitoring points in the CSTR process, and constructing a matrix X' belonging to the Rm×nSubtracting the mean value of all sample data in the row from each row of X' (the mean function of Matlab software can be used), and dividing the mean value by the standard deviation of all sample data in the row (the std function of Matlab software can be used) to obtain a matrix X epsilon Rm×nWhere m is 7 and n is 1200.
(2) The Signal-to-Noise Ratio (SNR) algorithm is applied to pick out the variables related to each fault to form 10 subblocks, namely [ X ]1,X2,…,X10]Sub-blockdb(b-1, 2, …,10) is the sub-block Xb(b is 1,2, …,10) the number of physical quantities, where d isb=2。
Partitioning sub-blocks [ X ] according to failure data1,X2,…,X10]The algorithm is as follows:
collecting a set of historical failure data setsXfThe data in (1) is collected in an operation mode in which a certain failure occurs in the system; wherein m isfIs 7 isNumber of variables, n f800 is the number of samples.
SNR refers to the ratio of signal s to noise e in a system, and the SNR of each variable iiThe following can be calculated:
wherein(the mean function of Matlab software can be used),(eiei Tobtained by var function of Matlab software), Xf(i, j) means XfThe value in the ith and jth columns, Xf(i,: means X)fThe vector of row i.
SNRiThe signal-to-noise ratio of the ith variable in a certain fault operation mode; it can reflect the change degree of the ith variable after the fault occurs; each variable i (i ═ 1, …, m)f) SNR of (1)iThe size of (d); selection and { SNRiAnd the variable corresponding to the first 2 maximum values in the i 1, …,7 is used as the related variable of the fault.
The variables corresponding to the first 2 maximum values of 10 faults in the CSTR process are found out as the related variables of the faults according to the method, and a sub-block is formed.
The global variable X is considered as a new block, taking into account the global nature of the data. The proposed algorithm therefore comprises 11 subblocks [ X ]1,…,X11]。
(3) Obtaining each sub-block X by applying fault monitoring method of ONPE modelb(b 1,2, …,11) projection matrixAnd calculating historical normal sample x of each sub-blockb,i(i=1,2,…,1200)∈R2Statistic of (2)And statistics SPEb,i(i=1,…,1200)。
Wherein, ai(i=1,…,gb) Is the projection vector, gbIs the dimension of dimension reduction, here gbIs generally equal to pair sub-block Xb(b is 1,2, …,11) the contribution rate of PCA (principal component analysis) decomposition is 85% (PCA function of Matlab software can be used). Lambdab=YbYb T/(1200-1),Yb=Ab TXb,yb,i=Ab Txb,i(i=1,2,…,1200)。
Calculating each sub-block X by applying ONPE modelb(b 1,2, …,11) projection matrix abMainly comprises the following steps:
(3a) construction of neighborhood set Sb:
For some normal history sample point xb,i(i ═ 1,2, …,1200), the Euclidean distances to other sample points are calculated (using matlab function EuDist2), and then k is chosen that is the minimum Euclidean distance from this sample pointbPoints constitute a neighborhood setWhere k isb=Kb+1,KbIs sub-block Xb(b is 1,2, …,11) the contribution rate of PCA (principal component analysis) decomposition is 85% (PCA function of Matlab software can be used).
(3b) Determining a weight coefficient matrix Wb:
First, by minimizing a functionObtaining a spatial neighborhood set SbIs given by the weight coefficient matrix Wb:
WhereinRepresents a sample xb,iThe j-th proximity point, WbijIs a matrix WbRow i and column j of (1), representing a sampleFor reconstructed sample xb,iThe weight coefficient of (a); the constraint condition isIf the sampleIs not xb,iNeighborhood of (1), then Wbij=0。
(3c) Establishing an objective function J (y)b):
(3d) Computing a projection matrix AbThis can be obtained by solving equation (19):
J(Ab)=minAb TXbMbXb TAb (20)
wherein M isb=(Ib-Wb)T(Ib-Wb)。
Adding a constraint condition on the basis of the formula (20): a. theb TXbXb TAb=Ib,By solving the above optimization problem using lagrange multiplier method including constraints, equation (20) can be converted into the following generalized eigenvalue solution problem, namely:
XbMbXb TAb=λbXbXb TAb (21)
solving equation (21) yields:
1)ab,1is (X)bXb T)-1XbMbXb TThe minimum eigenvalue of (matlab function eigs).
2)ab,i(i=2,…,gb) Is Qb (i)The minimum eigenvalue of (matlab function eigs).
Qb (i)={Ib-(XbXb T)-1ab (i-1)[Gb (i-1)]T}(XbXb T)-1XbMbXb T (22)
In the formula: gb (i-1)=[ab (i-1)]T(XbXb T)-1ab (i-1);ab (i-1)=[ab,1,ab,2,…ab,i-1]。
Through (22) formulaWe can find out all ab,i(i=1,…,gb) To obtain a projection matrix Ab。
(4) Computing each sub-block X using Kernel Density Estimation (KDE)bControl limit of (B ═ 1,2, …, B)And control limit SPEb,lim(using the fitsist and icdf functions of matlab software).
Step (II): online process monitoring
(5) 1200 measurement samples of the physical quantity of 7 physical quantity monitoring points in the CSTR process are acquired on line, and a measurement matrix X 'is constructed'new∈R7×1200To measurement matrix X'newPretreatment is carried out, namely X'newSubtracting the average value of all sample data in ith row of the matrix X' from each value in ith (i-1, 2, …,7) row in (a), and dividing by the standard deviation of all sample data in ith row to obtain preprocessed Xnew(ii) a Handle XnewCorresponding the data in step (2) to the sub-blocks to form 11 sub-blocks [ X ]1,new,…,X11,new]。
(6) Each sub-block X is calculated according to equations (3) to (4)b,newX of the ith (i ═ 1,2, …,1200) measurement sample of (a)b,newiStatisticsStatistics SPEb,newi。
(7) Constructing the ith measurement sample x according to equations (5) - (8) and Bayesian inferencenewi(i=1,...,n1)∈RmBayesian statistics ofAnd
(8) bayesian statisticsAndthe part exceeding the control limit indicates the ith sample x, compared with the control limit 1-alpha (alpha is 0.99), respectivelynewiA fault occurs.
Specific monitoring results are shown in fig. 3 and table 4.
The monitoring result of the faults in the chemical production process can be obtained through the circulation of the two steps.
The fault 10 is caused by the volume concentration QCFaults caused by changes are introduced into 201 th to 1200 th sample points, and the physical quantity of the faults is 5. The detection results based on the ONPE and FDONPE methods are shown in fig. 3, 4, and 5, where the dotted line indicates the control limit and the solid line indicates the value of the statistic.
From the detection result of the failure 10, it can be seen that N is passed2Statistics shows that the detection result of FDONPE reaches 86 percent, while N of ONPE2The statistic was only 58% detected, it is evident that FDONPE is inThe detection result of the statistic is obviously improved, so that the FDONPE method is superior to the ONPE method, and the subblock results of the FDONPE method are analyzed, wherein the detection results of the subblocks 1,2,5,6 and 10 are shown inAnd BICSPEThe detection rate of the statistic is ideal, the 5 sub-blocks all contain the variable 5, and the detection results of the remaining sub-blocks without the variable 5 are not ideal, so that the variable 5 is a responsible variable of the fault 10, and the variable 5 corresponds to the cooling water temperature QCThis verifies the feasibility of the method of the invention.
Through the analysis, in the fault 10, the FDONPE method is superior to the ONPE method, and more accurate information can be provided for monitoring personnel.
Experimental example: a CSTR model is adopted to simulate chemical production based on a distributed ONPE model (FDONPE)The specific application of the process fault monitoring method is that table 1 lists physical quantities acquired by 7 physical quantity monitoring points in the CSTR process, table 2 lists 10 faults highly related to the physical quantity data acquired by the 7 physical quantity monitoring points, table 3 lists blocking results of the process physical quantities through the SNR algorithm, and table 4 shows fault monitoring accuracy rates (in the case of monitoring the 10 faults by respectively adopting PCA, NMF, NPE, ONPE and FDONPE) (the fault monitoring accuracy rate is shown in the table Wherein T is2,N2,SPE,BICSPERespectively, monitoring statistics for different methods.
TABLE 1 CSTR System physical quantity information
TABLE 2 CSTR System 1O Process failures
TABLE 3 variable selection results for faults
Table 4 shows the fault monitoring results of 10 types of faults in the chemical production process using the PCA process monitoring method, the NPE process monitoring method, the ONPE process monitoring method, and the FDONPE process monitoring method in the CSTR simulation system. It can be seen that the fdonne process monitoring method shows the highest fault detection rate in most fault modes and has better performance in the modes of faults 8, 9 and 10, compared to the NPE process monitoring method or the onne process monitoring method.
TABLE 4 Fault detection accuracy comparison
The present invention is described in detail with reference to the examples above; however, it will be understood by those skilled in the art that various changes in the specific parameters of the embodiments described above may be made or equivalents may be substituted for elements thereof without departing from the scope of the present invention, so as to form various embodiments, which are not limited to the specific parameters of the embodiments described above, and the detailed description thereof is omitted here.
Claims (2)
1. A method for constructing a fault-related distributed orthogonal neighborhood preserving embedded model in a CSTR process is characterized by comprising the following steps:
(1) obtaining n historical normal samples of the physical quantity monitored by m physical quantity monitoring points in the CSTR process, and constructing a matrix X' belonging to the Rm×nSubtracting the mean value of all sample data in the row from each row of X', and dividing the mean value by the standard deviation of all sample data in the row to obtain a matrix X e Rm×n;
(2) Using SNR algorithm to pick out the variable related to each fault to form B sub-blocks [ X ]1,X2,…,XB]And the global variable X is considered as a new block, constituting in total B +1 sub-blocks [ X1,…,XB+1]Sub-blockSub-block samplesdb(B-1, 2, …, B +1) is the subblock Xb(B ═ 1,2, …, B +1) the number of physical quantities, B being the number of known failure types;
in this step, sub-blocks X are divided for historical normal databThe method of (B ═ 1,2, …, B) is:
collecting a set of historical failure data setsXfThe data in (1) is collected in an operation mode in which a certain failure occurs in the system; wherein m isfIs the number of variables, nfIs the number of samples;
SNR is the ratio of signal s to noise e in a system, and each variable i (i ═ 1, …, m)f) SNR of (1)iThe calculation is as follows:
in the formula (I), the compound is shown in the specification,Xf(i, j) is XfValue in ith row and jth column, Xf(i,: means X)fThe vector of row i; SNRiIt is the signal-to-noise ratio of the ith variable in a certain failure operation mode, which reflects the change degree of the ith variable after failure, and is higher than each variable i (i is 1, …, m)f) SNR of (1)iIs selected in relation to { SNR }i,i=1,…,mfThe variables corresponding to the first C maximum values in the previous step are taken as the relevant variables of the fault;
(3) obtaining each sub-block X based on ONPE modelb(B-1, 2, …, B +1) projection matrixAnd calculating the historical normal sample of each sub-blockStatistic of (2)And statistics SPEb,i(i=1,…,n);
Wherein, ai(i=1,…,gb) Is the projection vector of the b-th sub-block, gbIs the dimension reduction, Λ, of the b-th sub-blockb=YbYb T/(n-1),Yb=Ab TXb,yb,i=Ab Txb,i(i=1,2,…,n);
In this step, each sub-block X is calculated based on the ONPE modelb(B-1, 2, …, B +1) projection matrixComprises the following steps:
(3a) construction of neighborhood set Sb: for some normal history sample point xb,i(i ═ 1,2, …, n), calculating Euclidean distances to other sample points, and then selecting k with the minimum Euclidean distance to the sample pointbPoints constitute a neighborhood set
(3b) Determining a weight coefficient matrix Wb:
By a minimization functionObtaining a spatial neighborhood set SbIs given by the weight coefficient matrix Wb:
Wherein the content of the first and second substances,represents a sample xb,iThe j-th proximity point, WbijIs a matrix WbRow i and column j of (1), representing a sampleFor reconstructed sample xb,iThe weight coefficient of (a); the constraint condition isIf sampleIs not xb,iNeighborhood of (1), then Wbij=0;
(3c) Establishing an objective function J (y)b):
J(Ab)=minAb TXbMbXb TAb (6)
wherein M isb=(Ib-Wb)T(Ib-Wb);
Adding constraint conditions on the basis of the formula (6): a. theb TXbXb TAb=Ib,The lagrange multiplier method is utilized to contain constraints to solve the optimization problem, and the formula (6) can be converted into the following generalized eigenvalue solving problem, namely:
XbMbXb TAb=λbXbXb TAb (7)
solving equation (7) yields:
1)ab,1is (X)bXb T)-1XbMbXb TThe feature vector corresponding to the minimum feature value of (1);
2)ab,i(i=2,…,gb) Is Qb (i)The feature vector corresponding to the minimum feature value of (1);
Qb (i)={Ib-(XbXb T)-1ab (i-1)[Gb (i-1)]T}(XbXb T)-1XbMbXb T (8)
in the formula, Gb (i-1)=[ab (i-1)]T(XbXb T)-1ab (i-1);ab (i-1)=[ab,1,ab,2,…ab,i-1];
Determining all a from the formula (8)b,i(i=1,…,gb) To obtain a projection matrix Ab;
2. A CSTR process fault monitoring method based on FDONPE, which adopts the construction method of the model as claimed in claim 1, and comprises the following steps:
firstly, acquiring n1 measurement samples of the physical quantity of m physical quantity monitoring points in the chemical production process on line,
and constructing a measurement matrix X'new∈Rm×n1Prepared from X'newSubtracting the average value of all sample data in the ith row of the matrix X' from each value in the ith (i-1, …, n1) row in (a), and dividing the average value by the standard deviation of all sample data in the ith row to obtain preprocessed Xnew;
Handle XnewCorresponds to the sub-block of step (2) in claim 1, forming B +1 sub-blocks [ X ]1,new,…,XB+1,new]Sub-blockSub-block samples
② calculating each sub-block X by using fault monitoring method of ONPE modelb,newX of the ith (i ═ 1,2, …, n1) measurement sample of (a)b,newiStatisticsStatistics SPEb,newi;
SPEb,newi=xb,newi(Ib-Ab TAb)[xb,newi(Ib-Ab TAb)]T (10)
Wherein, Λb=(Ab TXb,new)(Ab TXb,new)T/(n1-1),yb,newi=Ab Txb,newi(i=1,2,…,n1);
Constructing the ith measurement sample x based on Bayesian inferencenewi(i=1,...,n1)∈RmBayes statistic of (d):
n and F represent normal and fault conditions, statistics, respectivelyAnd statistics SPEb,newiThe probabilities under normal and fault conditions are respectively:
PSPE(xb,newi)=PSPE(xb,newi|N)PSPE(N)+PSPE(xb,newi|F)PSPE(F) (14)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010969145.8A CN112180893B (en) | 2020-09-15 | 2020-09-15 | Construction method of fault-related distributed orthogonal neighborhood preserving embedded model in CSTR process and fault monitoring method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010969145.8A CN112180893B (en) | 2020-09-15 | 2020-09-15 | Construction method of fault-related distributed orthogonal neighborhood preserving embedded model in CSTR process and fault monitoring method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112180893A CN112180893A (en) | 2021-01-05 |
CN112180893B true CN112180893B (en) | 2021-07-13 |
Family
ID=73921192
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010969145.8A Active CN112180893B (en) | 2020-09-15 | 2020-09-15 | Construction method of fault-related distributed orthogonal neighborhood preserving embedded model in CSTR process and fault monitoring method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112180893B (en) |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101713983B (en) * | 2009-11-23 | 2011-12-21 | 浙江大学 | Semiconductor process monitoring method based on independent component analysis and Bayesian inference |
US20150323938A1 (en) * | 2014-05-09 | 2015-11-12 | Honeywell International Inc. | Temperature-based level detection and control method and apparatus |
CN107885914A (en) * | 2017-10-25 | 2018-04-06 | 华东理工大学 | Industrial reactor running status visualizes on-line monitoring method |
CN108762228B (en) * | 2018-05-25 | 2020-08-04 | 江南大学 | Distributed PCA-based multi-working-condition fault monitoring method |
US10928807B2 (en) * | 2018-06-21 | 2021-02-23 | Honeywell International Inc. | Feature extraction and fault detection in a non-stationary process through unsupervised machine learning |
CN109062189B (en) * | 2018-08-30 | 2020-06-30 | 华中科技大学 | Industrial process fault diagnosis method for complex fault |
CN109298633A (en) * | 2018-10-09 | 2019-02-01 | 郑州轻工业学院 | Chemical production process fault monitoring method based on adaptive piecemeal Non-negative Matrix Factorization |
CN109189028A (en) * | 2018-10-15 | 2019-01-11 | 江南大学 | PCA method for diagnosing faults based on muti-piece information extraction |
CN109407652B (en) * | 2018-12-10 | 2020-03-06 | 中国石油大学(华东) | Multivariable industrial process fault detection method based on main and auxiliary PCA models |
CN109870986B (en) * | 2019-02-28 | 2021-09-28 | 天津大学 | On-line control method of stirred tank reactor based on neural network and data drive |
CN110674461B (en) * | 2019-09-20 | 2022-09-16 | 郑州轻工业学院 | Chemical production process monitoring method based on multi-block projection non-negative matrix decomposition |
CN111639304B (en) * | 2020-06-02 | 2023-02-21 | 江南大学 | CSTR fault positioning method based on Xgboost regression model |
-
2020
- 2020-09-15 CN CN202010969145.8A patent/CN112180893B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN112180893A (en) | 2021-01-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108062565B (en) | Double-principal element-dynamic core principal element analysis fault diagnosis method based on chemical engineering TE process | |
CN110083860B (en) | Industrial fault diagnosis method based on relevant variable selection | |
CN111638707B (en) | Intermittent process fault monitoring method based on SOM clustering and MPCA | |
CN108958226B (en) | TE process fault detection method based on survival information potential-principal component analysis algorithm | |
CN111368428B (en) | Sensor precision degradation fault detection method based on monitoring second-order statistics | |
CN108919755B (en) | Distributed fault detection method based on multiple nonlinear cross relation models | |
CN109165242B (en) | Fault diagnosis and early warning method based on entropy sorting and space-time analysis | |
KR20120039160A (en) | Prediction and fault detection method and system for performance monitoring of plant instruments using principal component analysis, response surface method, fuzzy support vector regression and generalized likelihood ratio test | |
CN108549908A (en) | Chemical process fault detection method based on more sampled probability core principle component models | |
CN114757269A (en) | Complex process refined fault detection method based on local subspace-neighborhood preserving embedding | |
Luo et al. | Key-performance-indicators-related fault subspace extraction for the reconstruction-based fault diagnosis | |
CN112149054B (en) | Construction and application of orthogonal neighborhood preserving embedding model based on time sequence expansion | |
CN112180893B (en) | Construction method of fault-related distributed orthogonal neighborhood preserving embedded model in CSTR process and fault monitoring method thereof | |
CN117290800A (en) | Timing sequence anomaly detection method and system based on hypergraph attention network | |
CN116661410A (en) | Large-scale industrial process fault detection and diagnosis method based on weighted directed graph | |
CN113253682B (en) | Nonlinear chemical process fault detection method | |
CN115909535A (en) | Blast furnace ironmaking process monitoring method based on RBNCVA | |
CN111914886B (en) | Nonlinear chemical process monitoring method based on online brief kernel learning | |
He et al. | Fault detection and health assessment of equipment based on fuzzy DPCA spatial eigenvalue similarity | |
Huang et al. | Dynamic plant-wide process monitoring based on distributed slow feature analysis with inter-unit dissimilarity | |
CN113076211B (en) | Quality-related fault diagnosis and false alarm feedback method based on fault reconstruction | |
CN117688496B (en) | Abnormality diagnosis method, system and equipment for satellite telemetry multidimensional time sequence data | |
Li et al. | Industrial Process Fault Detection Based on Entropy Score Contribution Analysis | |
Zhu et al. | A Cyber-Physical monitoring and diagnosis scheme of energy consumption in Plant-Wide chemical processes | |
Liu et al. | Research on Fault Detection Method Based on Improved Euclidean Distance Control |
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 |