CN117784656A - Abnormal data intelligent supervision system and method based on data monitoring - Google Patents
Abnormal data intelligent supervision system and method based on data monitoring Download PDFInfo
- Publication number
- CN117784656A CN117784656A CN202311580002.8A CN202311580002A CN117784656A CN 117784656 A CN117784656 A CN 117784656A CN 202311580002 A CN202311580002 A CN 202311580002A CN 117784656 A CN117784656 A CN 117784656A
- Authority
- CN
- China
- Prior art keywords
- matrix
- data
- abnormal
- equipment
- characteristic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 133
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012544 monitoring process Methods 0.000 title claims abstract description 22
- 239000011159 matrix material Substances 0.000 claims abstract description 373
- 238000012545 processing Methods 0.000 claims abstract description 111
- 239000002131 composite material Substances 0.000 claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims abstract description 17
- 230000009467 reduction Effects 0.000 claims description 58
- 230000015556 catabolic process Effects 0.000 claims description 44
- 238000006731 degradation reaction Methods 0.000 claims description 44
- 230000005856 abnormality Effects 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 20
- 238000013507 mapping Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000012423 maintenance Methods 0.000 claims description 12
- 239000000523 sample Substances 0.000 claims description 12
- 230000002441 reversible effect Effects 0.000 claims description 9
- 238000012546 transfer Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 6
- 238000011084 recovery Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 8
- 230000009471 action Effects 0.000 description 3
- 238000013524 data verification Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
Classifications
-
- 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]
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of data analysis, in particular to an abnormal data intelligent supervision system and method based on data monitoring, comprising the following steps: the device comprises a data receiving and transmitting module, a matrix processing module, a characteristic analysis module, an abnormal positioning module and a component scaling module, wherein the data receiving and transmitting module is used for transmitting and receiving matrix data, the matrix processing module is used for fitting a composite matrix and outputting a processing matrix, the characteristic analysis module is used for judging whether a final processing matrix has data processing errors, the abnormal positioning module is used for positioning node equipment with error steps, and the component scaling module is used for scaling the processing matrix of abnormal equipment.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to an abnormal data intelligent supervision system and method based on data monitoring.
Background
The intelligent industrial control refers to a technology and a method for realizing automation and optimizing production by realizing digital monitoring and adjustment on equipment, systems or processes in the industrial production process, and comprises the operations of controlling, measuring, adjusting and the like on various production equipment. The intelligent industrial control comprises the following steps: after the industrial control probe acquires data, the data is sent to each node device for processing in a matrix form, and the final processed matrix is executed at the industrial control terminal.
Because the bottom operation is performed in a matrix mode when the industrial control system performs data processing, the process of processing data by the node equipment can be expressed as a process of multiplying input data by a processing matrix to obtain an output matrix, but in a set of mature intelligent industrial control system, the node equipment often has tens or hundreds of errors in the process of processing the matrix, so that the situation of data dislocation, data deletion or data mess is caused.
However, because the flow of data processing is linear, information can only be transmitted in one direction in sequence, most node devices only have the functions of processing and transmitting data, and abnormal conditions of input data cannot be judged, so that the industrial control terminal executes instructions in disorder. The conventional abnormal supervision system reduces the probability of accidental errors through multiple checking operations, but lacks an effective management means for the abnormality caused by the self-failure of the equipment, can not realize positioning and abnormality removal on the node equipment generating the abnormality, and can not lighten the influence caused by abnormal data.
Disclosure of Invention
The invention aims to provide an abnormal data intelligent supervision system and method based on data monitoring, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: an abnormal data intelligent supervision system based on data monitoring, comprising: the device comprises a data receiving and transmitting module, a matrix processing module, a characteristic analysis module, an abnormality positioning module and a component scaling module;
the data receiving and transmitting module is used for extracting matrix characteristics, transmitting and receiving matrix data among node devices and extracting matrix row and column widths;
the matrix processing module is used for carrying out multiplication operation on the data matrix and the characteristic matrix of the node equipment after receiving the data matrix sent by the previous flow, obtaining a composite matrix and completing the processing process of the node equipment on the composite matrix;
the characteristic analysis module is used for analyzing the characteristic values and the characteristic vectors of the matrix after the industrial control terminal receives the final data matrix, performing gradual inverse operation on the data matrix according to the characteristic matrix of each node device to obtain a multi-dimensional transfer matrix, and then judging whether the data processing errors exist or not by calculating the characteristic values of the transfer matrix, and inputting the final transfer matrix into the execution terminal for execution when the errors do not exist;
the abnormal positioning module is used for positioning the node equipment with the error step according to the times of performing inverse operation on the data matrix when the data processing error exists, calculating the deviation value of the equipment, adding an abnormal record of the equipment, and informing the number of the abnormal equipment to a maintenance personnel;
the component scaling module is used for calculating the degradation coefficient of the abnormal equipment according to the deviation value and the abnormal frequency of the abnormal equipment, scaling the processing matrix of the equipment according to the degradation coefficient, and reducing the influence of the equipment abnormality on a final result.
Further, the data transceiver module includes: a matrix extraction unit and a signal receiving and transmitting unit;
the matrix extraction unit is used for obtaining an initial matrix through the industrial control probe and extracting the row-column width of the matrix;
the signal receiving and transmitting unit is used for receiving the data matrix sent by the previous device and sending the processed matrix information to the next device.
Further, the matrix processing module includes: the characteristic fitting unit and the engineering operation unit;
the characteristic fitting unit is used for multiplying the characteristic matrix of the equipment by the data matrix after receiving the data matrix, and fitting the equipment characteristic into the data matrix to obtain a composite matrix;
the engineering operation unit is used for taking the composite matrix as an input matrix, performing data processing on the input node equipment, and outputting the processed data matrix.
Further, the feature analysis module includes: the device comprises an inversion characteristic unit, a solution fitting unit and an abnormality judging unit;
the inversion characteristic unit is used for calculating inverse matrixes of characteristic matrixes of all node equipment and calculating characteristic values and characteristic vectors of the inverse matrixes;
the solution fitting unit is used for calculating the characteristic value of the data matrix after the industrial control terminal receives the final data matrix, and multiplying the characteristic value with the inverse matrix of the characteristic matrix of each node device successively to obtain a plurality of reduction matrices;
the abnormality judging unit is used for calculating the characteristic value of a reduction matrix after fitting each solution, comparing the characteristic value of the reduction matrix and the characteristic value of the characteristic matrix with the characteristic value of the last reduction matrix, and judging whether abnormality exists in the processing process.
Further, the anomaly locating module includes: the device comprises an inversion analysis unit, a characteristic recovery unit and a deviation recording unit;
the inversion analysis unit is used for determining the number of the abnormal equipment according to the reduction step number of the reduction matrix after the abnormality is found, and notifying maintenance personnel of the number of the abnormal equipment;
the characteristic recovery unit is used for requesting the former node equipment of the abnormal equipment to send a data matrix, continuously analyzing the data matrix and judging the abnormal condition of other equipment;
the deviation recording unit is used for adding an abnormal record of the abnormal equipment and calculating a deviation coefficient of the abnormal equipment according to the characteristic value of the reduction matrix.
Further, the component scaling module includes: a degradation calculation unit and a simplified processing unit;
the degradation calculation unit is used for calculating a degradation matrix of the equipment according to the abnormal frequency and the deviation coefficient of the abnormal equipment;
the simplified processing unit is used for multiplying the matrix ready for inputting the abnormal equipment with the degradation matrix, multiplying the matrix with the inverse matrix of the degradation matrix after the node equipment obtains the final data matrix, and recovering the data of the final data matrix, so that the influence of the abnormal equipment on the final result is reduced before the abnormal equipment is maintained.
An abnormal data intelligent supervision method based on data monitoring comprises the following steps:
s100, numbering all node devices according to the flow sequence of data processing, and distributing a unique feature matrix for each node device by an industrial control terminal and calculating the inverse matrix of the feature matrix;
s200, after the industrial control probe acquires initial data, according to the number of the node equipment, a matrix for recording the initial data is sent to the first node equipment, after the first node equipment receives the initial data matrix, the characteristic matrix of the first node equipment is multiplied right after the initial data matrix, a composite matrix is obtained, the composite matrix is used as input matrix input equipment for processing, and a primary processing matrix is output;
s300, the first node equipment sends the primary processing matrix to the second node equipment according to the serial number sequence, the second node equipment takes the primary processing matrix as an initial data matrix, the step S200 is repeated to obtain a secondary processing matrix, and the like, and after all the node equipment finishes processing, a final processing matrix is obtained;
s400, the control terminal receives the final processing matrix, calculates the characteristic value of the final processing matrix, sequentially multiplies the final processing matrix by the inverse matrix of the characteristic matrix of each node device according to the reverse sequence of the serial number to obtain a plurality of reduction matrices, arranges all the reduction matrices from small to large according to the reduction times, and calculates the ratio of the characteristic value of each reduction matrix to the characteristic value of the last reduction matrix;
s500, determining whether the data is abnormal or not according to the ratio and the characteristic value of the characteristic matrix of each node device, giving the number of the abnormal device when the data is determined to be abnormal, calculating the degradation coefficient of the abnormal device, obtaining a degradation matrix according to the degradation coefficient, and scaling the data processing process of the abnormal device by using the degradation matrix.
Further, step S100 includes:
s101, numbering all node devices according to a flow sequence of data processing, wherein the numbering result is recorded as a data set X, X= {1,2, …, n }, n is the number of the node devices, n is an integer, and n is more than or equal to 2;
s102, generating n different feature matrixes by the industrial control terminal, wherein the feature matrixes are reversible matrixes, and the feature values of all the feature matrixes are different;
assigning the feature matrix to each node device, and marking the assignment result as a data set Y, Y= { A 1 ，A 2 ，…，A n The data set Y and the data set X form a mapping relation, A 1 、A 2 And A n Respectively representing the feature matrixes distributed to the node devices with the numbers of 1,2 and n, and the mapping relation of the rest elements and the like;
s103, the industrial control terminal calculates inverse matrixes of the feature matrixes, and a data set Z, Z= { A is formed by calculation results 1 -1 ，A 2 -1 ，…，A n -1 The data set Z and the data set Y form a mapping relation, A 1 -1 ，A 2 -1 And A n -1 Respectively represent the characteristic matrix A 1 ，A 2 And A n The inverse of the mapping relationship of the remaining elements and so on;
s104, calculating eigenvalues of each eigenvalue matrix, and recording the calculation result as a data set R, R= { R 1 ，r 2 ，…，r n The data set R and the data set Y form a mapping relation, R 1 ，r 2 And r n Respectively represent the characteristic matrix A 1 ，A 2 And A n And the mapping relation of the rest elements is similar.
Further, step S200 includes:
step S201, an industrial control probe acquires initial data, the initial data is sent to node equipment with the number of 1 in a matrix form, and the initial data matrix is marked as Q;
step S202, after receiving the initial data matrix, the node device 1 executes operation T 1 ＝Q·A 1 The T is 1 For the composite matrix of node device 1, T will be 1 As an input matrix, the node device 1 performs an operation according to its own operation program to obtain a primary processing matrix Q 1 。
The characteristic matrix fitting is carried out at the input end, so that the condition that the characteristic fitting fails due to the self-failure of the equipment is effectively avoided.
Further, step S300 includes:
step S301, the node device 1 sends the primary processing matrix to the node device 2, and the node device 2 executes operation T 2 ＝Q 1 ·A 2 The T is 2 For the composite matrix of node device 2, T will be 2 As an input matrix, the node device 2 performs an operation according to its own operation program to obtain a secondary processing matrix Q 2 ；
S302, repeating the steps until the node equipment n finishes matrix processing to obtain a final processing matrix Q n Matrix Q n And sending the data to the industrial control terminal.
The invention performs data verification design on the industrial control terminal, also ensures that all the commands submitted and executed are real and effective, avoids the occurrence of the condition of disordered instruction and error reporting, helps an industrial control system to discover and solve problems in time, improves the production efficiency and reduces the abnormal risk.
Further, step S400 includes:
s401, the industrial control terminal receives Q n After that, calculate Q n Is the characteristic value t of (2) n+1 Then the following operation is executed to calculate the reduction matrix:
wherein P is m Representing a reduction matrix corresponding to node equipment with the number of m, wherein m is E X, A n-i -1 Representing the n-i th element in the data set Z;
s402, calculating eigenvalues of each reduction matrix, and recording the calculation result as a data set T, T= { T 1 ,t 2 ,…t m ,…,t n }, t is m Representing the reduction matrix P m Corresponding characteristic values;
s403, verifying the accuracy of the feature value processing according to the following formula:
wherein N is m Representing a state parameter of node device m, said N m E {0,1}, IFS is a logical judgment function,as the judgment formula in the logic judgment function, if the judgment formula is established, N is m =1, if the judgment formula is not established, N m ＝0；
Generating a verification sequence K according to the reverse sequence of numbers, wherein the K= [ n, n-1, …,1]Substituting the elements in the sequence K into m in the above formula in turn to obtain a resulting state sequence L, where l= [ N ] n ,N n-1 ,…,N 1 ]The elements in the sequence L are in one-to-one correspondence with the elements in the sequence K;
s404, judging whether the elements in the sequence L are 1 in sequence, if the elements in the sequence L are all 1, judging that the data is not abnormal, and reducing the matrix P n As the final execution matrix, sending the final execution matrix to an execution terminal for execution;
when the value of one element in the sequence L is found to be 0, judging that the data is abnormal, marking the position of the element in the sequence L as g, marking the node equipment with the number g as abnormal equipment, informing maintenance personnel to maintain the equipment g, adding an abnormal record of the node equipment g, and turning to the step S500.
Further, step S500 includes:
s501, calculating a deviation value e of the node equipment g, whereinWherein t is g+1 Representing a reduction matrix eigenvalue, r corresponding to node equipment with the number of g+1 g Representing the characteristic value of the characteristic matrix of the node equipment g;
acquiring a historical abnormal record of the node equipment g, and if the total recorded number is b in a preset time range T, the abnormal frequency V=b/T of the node equipment g;
step S502, calculating a degradation coefficient J of the node equipment g according to the following formula:
wherein V0 is a fault-tolerant frequency preset by the system;
step S503. Calculating a degradation matrix W, where W=J.E.A g Wherein E is an identity matrix, A g Is a characteristic matrix of the node device g and a reduction degradation matrix W -1 ＝1/J·A g -1 Wherein Ag is -1 The inverse matrix of the characteristic matrix of the equipment g;
before the abnormal equipment g is maintained, W is used for replacing the characteristic matrix of the node equipment g -1 Instead of the inverse of the characteristic matrix of the node apparatus g, and in the process of executing step S404 thereafter, let N g ＝1；
The processed reduction matrix P n And the final execution matrix is sent to an execution terminal for execution.
According to the method and the device, the processing process of the abnormal equipment can be scaled according to the historical processing condition and the data deviation value of the abnormal equipment, and the influence of the abnormal node equipment on the production process and the equipment performance is reduced.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention can provide the operational identity characteristic for each data processing device, judges whether the data matrix is abnormal or not at the industrial control terminal, positions the abnormal devices, discovers and positions the abnormal devices by checking the abnormal data, informs maintenance personnel to check the abnormal reasons, discovers the operation problems of the devices in time and adopts corresponding maintenance and optimization measures, thereby reducing the influence of the data processing abnormality on the production process and the device performance.
2. The invention does not need to operate the data step by step, does not need to install a data accounting device on the node equipment, has lower hardware requirement, performs data verification design on the industrial control terminal, also ensures that all the commands submitted and executed are real and effective, avoids the occurrence of the condition of disordered instruction and error reporting, helps the industrial control system to find and solve the problems in time, improves the production efficiency and reduces the abnormal risk.
3. The invention can scale the processing process of the abnormal equipment according to the historical processing condition of the abnormal equipment, reduce the influence of the abnormal node equipment on the production process and the equipment performance, analyze and mine the data in the industrial control system, and take corresponding improvement measures to improve the production efficiency and the equipment utilization rate.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of an abnormal data intelligent supervision system based on data monitoring;
fig. 2 is a schematic step diagram of an abnormal data intelligent supervision method based on data monitoring.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides the following technical solutions: an abnormal data intelligent supervision system based on data monitoring, comprising: the device comprises a data receiving and transmitting module, a matrix processing module, a characteristic analysis module, an abnormality positioning module and a component scaling module;
the data receiving and transmitting module is used for extracting matrix characteristics, transmitting and receiving matrix data among node devices and extracting matrix row and column widths;
the data transceiver module comprises: a matrix extraction unit and a signal receiving and transmitting unit;
the matrix extraction unit is used for obtaining an initial matrix through the industrial control probe and extracting the row-column width of the matrix;
the signal receiving and transmitting unit is used for receiving the data matrix sent by the previous device and sending the processed matrix information to the next device.
The matrix processing module is used for carrying out multiplication operation on the data matrix and the characteristic matrix of the node equipment after receiving the data matrix sent by the previous flow, obtaining a composite matrix and completing the processing process of the node equipment on the composite matrix;
the matrix processing module comprises: the characteristic fitting unit and the engineering operation unit;
the characteristic fitting unit is used for multiplying the characteristic matrix of the equipment by the data matrix after receiving the data matrix, and fitting the equipment characteristic into the data matrix to obtain a composite matrix;
the engineering operation unit is used for taking the composite matrix as an input matrix, performing data processing on the input node equipment, and outputting the processed data matrix.
The characteristic analysis module is used for analyzing the characteristic values and the characteristic vectors of the matrix after the industrial control terminal receives the final data matrix, performing gradual inverse operation on the data matrix according to the characteristic matrix of each node device to obtain a multi-dimensional transfer matrix, and then judging whether the data processing errors exist or not by calculating the characteristic values of the transfer matrix, and inputting the final transfer matrix into the execution terminal for execution when the errors do not exist;
the feature analysis module comprises: the device comprises an inversion characteristic unit, a solution fitting unit and an abnormality judging unit;
the inversion characteristic unit is used for calculating inverse matrixes of characteristic matrixes of all node equipment and calculating characteristic values and characteristic vectors of the inverse matrixes;
the solution fitting unit is used for calculating the characteristic value of the data matrix after the industrial control terminal receives the final data matrix, and multiplying the characteristic value with the inverse matrix of the characteristic matrix of each node device successively to obtain a plurality of reduction matrices;
the abnormality judging unit is used for calculating the characteristic value of a reduction matrix after fitting each solution, comparing the characteristic value of the reduction matrix and the characteristic value of the characteristic matrix with the characteristic value of the last reduction matrix, and judging whether abnormality exists in the processing process.
The abnormal positioning module is used for positioning the node equipment with the error step according to the times of performing inverse operation on the data matrix when the data processing error exists, calculating the deviation value of the equipment, adding an abnormal record of the equipment, and informing the number of the abnormal equipment to a maintenance personnel;
the abnormality locating module includes: the device comprises an inversion analysis unit, a characteristic recovery unit and a deviation recording unit;
the inversion analysis unit is used for determining the number of the abnormal equipment according to the reduction step number of the reduction matrix after the abnormality is found, and notifying maintenance personnel of the number of the abnormal equipment;
the characteristic recovery unit is used for requesting the former node equipment of the abnormal equipment to send a data matrix, continuously analyzing the data matrix and judging the abnormal condition of other equipment;
the deviation recording unit is used for adding an abnormal record of the abnormal equipment and calculating a deviation coefficient of the abnormal equipment according to the characteristic value of the reduction matrix.
The component scaling module is used for calculating the degradation coefficient of the abnormal equipment according to the deviation value and the abnormal frequency of the abnormal equipment, scaling the processing matrix of the equipment according to the degradation coefficient, and reducing the influence of the equipment abnormality on a final result.
The component scaling module includes: a degradation calculation unit and a simplified processing unit;
the degradation calculation unit is used for calculating a degradation matrix of the equipment according to the abnormal frequency and the deviation coefficient of the abnormal equipment;
the simplified processing unit is used for multiplying the matrix ready for inputting the abnormal equipment with the degradation matrix, multiplying the matrix with the inverse matrix of the degradation matrix after the node equipment obtains the final data matrix, and recovering the data of the final data matrix, so that the influence of the abnormal equipment on the final result is reduced before the abnormal equipment is maintained.
As shown in fig. 2, an abnormal data intelligent supervision method based on data monitoring includes the following steps:
s100, numbering all node devices according to the flow sequence of data processing, and distributing a unique feature matrix for each node device by an industrial control terminal and calculating the inverse matrix of the feature matrix;
the step S100 includes:
s101, numbering all node devices according to a flow sequence of data processing, wherein the numbering result is recorded as a data set X, X= {1,2, …, n }, n is the number of the node devices, n is an integer, and n is more than or equal to 2;
s102, generating n different feature matrixes by the industrial control terminal, wherein the feature matrixes are reversible matrixes, and the feature values of all the feature matrixes are different;
assigning the feature matrix to each node device, and marking the assignment result as a data set Y, Y= { A 1 ，A 2 ，…，A n The data set Y and the data set X form a mapping relation, A 1 、A 2 And A n Respectively representing the feature matrixes distributed to the node devices with the numbers of 1,2 and n, and the mapping relation of the rest elements and the like;
s103, the industrial control terminal calculates inverse matrixes of the feature matrixes, and a data set Z, Z= { A is formed by calculation results 1 -1 ，A 2 -1 ，…，A n -1 The data set Z and the data set Y form a mapping relation, A 1 -1 ，A 2 -1 And A n -1 Respectively represent the characteristic matrix A 1 ，A 2 And A n The inverse of the mapping relationship of the remaining elements and so on;
s104, calculating eigenvalues of each eigenvalue matrix, and recording the calculation result as a data set R, R= { R 1 ，r 2 ，…，r n -said datasetR and data set Y form mapping relation, R 1 ，r 2 And r n Respectively represent the characteristic matrix A 1 ，A 2 And A n And the mapping relation of the rest elements is similar.
S200, after the industrial control probe acquires initial data, according to the number of the node equipment, a matrix for recording the initial data is sent to the first node equipment, after the first node equipment receives the initial data matrix, the characteristic matrix of the first node equipment is multiplied right after the initial data matrix, a composite matrix is obtained, the composite matrix is used as input matrix input equipment for processing, and a primary processing matrix is output;
step S200 includes:
step S201, an industrial control probe acquires initial data, the initial data is sent to node equipment with the number of 1 in a matrix form, and the initial data matrix is marked as Q;
step S202, after receiving the initial data matrix, the node device 1 executes operation T 1 ＝Q·A 1 The T is 1 For the composite matrix of node device 1, T will be 1 As an input matrix, the node device 1 performs an operation according to its own operation program to obtain a primary processing matrix Q 1 。
S300, the first node equipment sends the primary processing matrix to the second node equipment according to the serial number sequence, the second node equipment takes the primary processing matrix as an initial data matrix, the step S200 is repeated to obtain a secondary processing matrix, and the like, and after all the node equipment finishes processing, a final processing matrix is obtained;
step S300 includes:
step S301, the node device 1 sends the primary processing matrix to the node device 2, and the node device 2 executes operation T 2 ＝Q 1 ·A 2 The T is 2 For the composite matrix of node device 2, T will be 2 As an input matrix, the node device 2 performs an operation according to its own operation program to obtain a secondary processing matrix Q 2 ；
S302, repeating the steps until the node equipment n finishes matrix processing to obtain a final processing matrix Q n Matrix is formedQ n And sending the data to the industrial control terminal.
S400, the control terminal receives the final processing matrix, calculates the characteristic value of the final processing matrix, sequentially multiplies the final processing matrix by the inverse matrix of the characteristic matrix of each node device according to the reverse sequence of the serial number to obtain a plurality of reduction matrices, arranges all the reduction matrices from small to large according to the reduction times, and calculates the ratio of the characteristic value of each reduction matrix to the characteristic value of the last reduction matrix;
step S400 includes:
s401, the industrial control terminal receives Q n After that, calculate Q n Is the characteristic value t of (2) n+1 Then the following operation is executed to calculate the reduction matrix:
wherein P is m Representing a reduction matrix corresponding to node equipment with the number of m, wherein m is E X, A n-i -1 Representing the n-i th element in the data set Z;
s402, calculating eigenvalues of each reduction matrix, and recording the calculation result as a data set T, T= { T 1 ,t 2 ,…t m ,…,t n }, t is m Representing the reduction matrix P m Corresponding characteristic values;
s403, verifying the accuracy of the feature value processing according to the following formula:
wherein N is m Representing a state parameter of node device m, said N m E {0,1}, IFS is a logical judgment function,as the judgment formula in the logic judgment function, if the judgment formula is established, N is m =1, if the judgment formula is not established, N m ＝0；
Press-braidingThe reverse order of numbers generates a verification sequence K, which k= [ n, n-1, …,1]Substituting the elements in the sequence K into m in the above formula in turn to obtain a resulting state sequence L, where l= [ N ] n ,N n-1 ,…,N 1 ]The elements in the sequence L are in one-to-one correspondence with the elements in the sequence K;
s404, judging whether the elements in the sequence L are 1 in sequence, if the elements in the sequence L are all 1, judging that the data is not abnormal, and reducing the matrix P n As the final execution matrix, sending the final execution matrix to an execution terminal for execution;
when the value of one element in the sequence L is found to be 0, judging that the data is abnormal, marking the position of the element in the sequence L as g, marking the node equipment with the number g as abnormal equipment, informing maintenance personnel to maintain the equipment g, adding an abnormal record of the node equipment g, and turning to the step S500.
S500, determining whether the data is abnormal or not according to the ratio and the characteristic value of the characteristic matrix of each node device, giving the number of the abnormal device when the data is determined to be abnormal, calculating the degradation coefficient of the abnormal device, obtaining a degradation matrix according to the degradation coefficient, and scaling the data processing process of the abnormal device by using the degradation matrix.
Step S500 includes:
s501, calculating a deviation value e of the node equipment g, whereinWherein t is g+1 Representing a reduction matrix eigenvalue, r corresponding to node equipment with the number of g+1 g Representing the characteristic value of the characteristic matrix of the node equipment g;
acquiring a historical abnormal record of the node equipment g, and if the total recorded number is b in a preset time range T, the abnormal frequency V=b/T of the node equipment g;
step S502, calculating a degradation coefficient J of the node equipment g according to the following formula:
wherein V0 is a fault-tolerant frequency preset by the system;
step S503. Calculating a degradation matrix W, where W=J.E.A g Wherein E is an identity matrix, A g Is a characteristic matrix of the node device g and a reduction degradation matrix W -1 ＝1/J·A g -1 Wherein Ag is -1 The inverse matrix of the characteristic matrix of the equipment g;
before the abnormal equipment g is maintained, W is used for replacing the characteristic matrix of the node equipment g -1 Instead of the inverse of the characteristic matrix of the node apparatus g, and in the process of executing step S404 thereafter, let N g ＝1；
The processed reduction matrix P n And the final execution matrix is sent to an execution terminal for execution.
Examples:
an industrial control system comprises 3 node devices, which are respectively node device 1, node device 2 and node device 3 according to the sequence of the execution flow, wherein the initial data matrix acquired by the industrial control probe is thatThe processing matrices of node devices 1,2 and 3 are respectively +.>And->The feature matrix is +.>And->The eigenvalues are 1,2 and 3, respectively, and the inverse matrices are +.>And->
The industrial control probe firstly matrices initial dataTransmitting the data to the node device 1 along the bus, wherein the node device 1 performs characteristic fitting to obtain an input matrix +.>After processing, an output matrix is obtained>After the output matrix is sent to the node device 2, the output +.>The retransmission to the node device 3 gives the final output +.>
If there is no equipment abnormality, thenRestoring to obtain correct output matrix +.>
If there is equipment abnormality, the resulting data matrix isThe inverse matrices of the node devices 3, 2 and 1 are multiplied in sequence, and the resulting reduction matrices are +.>And->Calculating the characteristic value to obtain that the node equipment 2 is abnormal, and notifying maintenance personnel to repair;
before the device 2 is repaired, calculating the degradation coefficient of the device 2 to be 1/2, and the degradation matrix to beThe restoration of the output matrix takes place instead of the feature matrix of the device 2.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An abnormal data intelligent supervision method based on data monitoring is characterized by comprising the following steps:
s100, numbering all node devices according to the flow sequence of data processing, and distributing a unique feature matrix for each node device by an industrial control terminal and calculating the inverse matrix of the feature matrix;
s200, after the industrial control probe acquires initial data, according to the number of the node equipment, a matrix for recording the initial data is sent to the first node equipment, after the first node equipment receives the initial data matrix, the characteristic matrix of the first node equipment is multiplied right after the initial data matrix, a composite matrix is obtained, the composite matrix is used as input matrix input equipment for processing, and a primary processing matrix is output;
s300, the first node equipment sends the primary processing matrix to the second node equipment according to the serial number sequence, the second node equipment takes the primary processing matrix as an initial data matrix, the step S200 is repeated to obtain a secondary processing matrix, and the like, and after all the node equipment finishes processing, a final processing matrix is obtained;
s400, the control terminal receives the final processing matrix, calculates the characteristic value of the final processing matrix, sequentially multiplies the final processing matrix by the inverse matrix of the characteristic matrix of each node device according to the reverse sequence of the serial number to obtain a plurality of reduction matrices, arranges all the reduction matrices from small to large according to the reduction times, and calculates the ratio of the characteristic value of each reduction matrix to the characteristic value of the last reduction matrix;
s500, determining whether the data is abnormal or not according to the ratio and the characteristic value of the characteristic matrix of each node device, giving the number of the abnormal device when the data is determined to be abnormal, calculating the degradation coefficient of the abnormal device according to the deviation value and the history of the abnormal device, obtaining the degradation matrix according to the degradation coefficient, and scaling the data processing process of the abnormal device by using the degradation matrix.
2. The abnormal data intelligent supervision method based on data monitoring according to claim 1, wherein the abnormal data intelligent supervision method comprises the following steps:
the step S100 includes:
s101, numbering all node devices according to a flow sequence of data processing, wherein the numbering result is recorded as a data set X, X= {1,2, …, n }, n is the number of the node devices, n is an integer, and n is more than or equal to 2;
s102, generating n different feature matrixes by the industrial control terminal, wherein the feature matrixes are reversible matrixes, and the feature values of all the feature matrixes are different;
assigning the feature matrix to each node device, and marking the assignment result as a data set Y, Y= { A 1 ，A 2 ，…，A n The data set Y and the data set X form a mapping relation, A 1 、A 2 And A n Respectively representing the feature matrixes distributed to the node devices with the numbers of 1,2 and n, and the mapping relation of the rest elements and the like;
s103, the industrial control terminal calculates inverse matrixes of the feature matrixes, and a data set Z, Z= { A is formed by calculation results 1 -1 ，A 2 -1 ，…，A n -1 The data set Z and the data set Y form a mapping relation, A 1 -1 ，A 2 -1 And A n -1 Respectively represent the characteristic matrix A 1 ，A 2 And A n The inverse of the mapping relationship of the remaining elements and so on;
s104, calculating eigenvalues of each eigenvalue matrix, and recording the calculation result as a data set R, R= { R 1 ，r 2 ，…，r n The data set R and the data set Y form a mapping relation, R 1 ，r 2 And r n Respectively represent the characteristic matrix A 1 ，A 2 And A n And the mapping relation of the rest elements is similar.
3. The abnormal data intelligent supervision method based on data monitoring according to claim 2, wherein the abnormal data intelligent supervision method is characterized by comprising the following steps:
step S200 includes:
step S201, an industrial control probe acquires initial data, the initial data is sent to node equipment with the number of 1 in a matrix form, and the initial data matrix is marked as Q;
step S202, after receiving the initial data matrix, the node device 1 executes operation T 1 ＝Q·A 1 The T is 1 For the composite matrix of node device 1, T will be 1 As an input matrix, the node device 1 performs an operation according to its own operation program to obtain a primary processing matrix Q 1 ；
Step S300 includes:
step S301, the node device 1 sends the primary processing matrix to the node device 2, and the node device 2 executes operation T 2 ＝Q 1 ·A 2 The T is 2 For the composite matrix of node device 2, T will be 2 As an input matrix, the node device 2 performs an operation according to its own operation program to obtain a secondary processing matrix Q 2 ；
S302, repeating the steps until the node equipment n finishes matrix processing to obtain a final processing matrix Q n Matrix Q n And sending the data to the industrial control terminal.
4. The abnormal data intelligent supervision method based on data monitoring according to claim 3, wherein:
step S400 includes:
s401, the industrial control terminal receives Q n After that, calculate Q n Is the characteristic value t of (2) n+1 Then the following operation is executed to calculate the reduction matrix:
wherein P is m Representing a reduction matrix corresponding to node equipment with the number of m, wherein m is E X, A n-i -1 Representing the n-i th element in the data set Z;
s402, calculating eigenvalues of each reduction matrix, and recording the calculation result as a data set T, T= { T 1 ,t 2 ,…t m ,…,t n }, t is m Representing the reduction matrix P m Corresponding characteristic values;
s403, verifying the accuracy of the feature value processing according to the following formula:
wherein N is m Representative node arrangementPreparing state parameters of m, the N m E {0,1}, IFS is a logical judgment function,as the judgment formula in the logic judgment function, if the judgment formula is established, N is m =1, if the judgment formula is not established, N m ＝0；
Generating a verification sequence K according to the reverse sequence of numbers, wherein the K= [ n, n-1, …,1]Substituting the elements in the sequence K into m in the above formula in turn to obtain a resulting state sequence L, where l= [ N ] n ,N n-1 ,…,N 1 ]The elements in the sequence L are in one-to-one correspondence with the elements in the sequence K;
s404, judging whether the elements in the sequence L are 1 in sequence, if the elements in the sequence L are all 1, judging that the data is not abnormal, and reducing the matrix P n As the final execution matrix, sending the final execution matrix to an execution terminal for execution;
when the value of one element in the sequence L is found to be 0, judging that the data is abnormal, marking the position of the element in the sequence L as g, marking the node equipment with the number g as abnormal equipment, informing maintenance personnel to maintain the equipment g, adding an abnormal record of the node equipment g, and turning to the step S500.
5. The abnormal data intelligent supervision method based on data monitoring according to claim 4, wherein the abnormal data intelligent supervision method comprises the following steps:
step S500 includes:
s501, calculating a deviation value e of the node equipment g, whereinWherein t is g+1 Representing a reduction matrix eigenvalue, r corresponding to node equipment with the number of g+1 g Representing the characteristic value of the characteristic matrix of the node equipment g;
acquiring a historical abnormal record of the node equipment g, and if the total recorded number is b in a preset time range T, the abnormal frequency V=b/T of the node equipment g;
step S502, calculating a degradation coefficient J of the node equipment g according to the following formula:
wherein V0 is a fault-tolerant frequency preset by the system;
step S503. Calculating a degradation matrix W, where W=J.E.A g Wherein E is an identity matrix, A g Is a characteristic matrix of the node device g and a reduction degradation matrix W -1 ＝1/J·A g -1 Wherein Ag is -1 The inverse matrix of the characteristic matrix of the equipment g;
before the abnormal equipment g is maintained, W is used for replacing the characteristic matrix of the node equipment g -1 Instead of the inverse of the characteristic matrix of the node apparatus g, and in the process of executing step S404 thereafter, let N g ＝1；
The processed reduction matrix P n And the final execution matrix is sent to an execution terminal for execution.
6. An abnormal data intelligent supervision system based on data monitoring is characterized by comprising the following modules: the device comprises a data receiving and transmitting module, a matrix processing module, a characteristic analysis module, an abnormality positioning module and a component scaling module;
the data receiving and transmitting module is used for extracting matrix characteristics, transmitting and receiving matrix data among node devices and extracting matrix row and column widths;
the matrix processing module is used for carrying out multiplication operation on the data matrix and the characteristic matrix of the node equipment after receiving the data matrix sent by the previous flow, obtaining a composite matrix and completing the processing process of the node equipment on the composite matrix;
the characteristic analysis module is used for analyzing the characteristic values and the characteristic vectors of the matrix after the industrial control terminal receives the final data matrix, performing gradual inverse operation on the data matrix according to the characteristic matrix of each node device to obtain a multi-dimensional transfer matrix, and then judging whether the data processing errors exist or not by calculating the characteristic values of the transfer matrix, and inputting the final transfer matrix into the execution terminal for execution when the errors do not exist;
the abnormal positioning module is used for positioning the node equipment with the error step according to the times of performing inverse operation on the data matrix when the data processing error exists, calculating the deviation value of the equipment, adding an abnormal record of the equipment, and informing the number of the abnormal equipment to a maintenance personnel;
the component scaling module is used for calculating the degradation coefficient of the abnormal equipment according to the deviation value and the abnormal frequency of the abnormal equipment, scaling the processing matrix of the equipment according to the degradation coefficient, and reducing the influence of the equipment abnormality on a final result.
7. The abnormal data intelligent supervision system based on data monitoring according to claim 6, wherein:
the data transceiver module comprises: a matrix extraction unit and a signal receiving and transmitting unit;
the matrix extraction unit is used for obtaining an initial matrix through the industrial control probe and extracting the row-column width of the matrix;
the signal receiving and transmitting unit is used for receiving the data matrix sent by the previous device and sending the processed matrix information to the next device;
the matrix processing module comprises: the characteristic fitting unit and the engineering operation unit;
the characteristic fitting unit is used for multiplying the characteristic matrix of the equipment by the data matrix after receiving the data matrix, and fitting the equipment characteristic into the data matrix to obtain a composite matrix;
the engineering operation unit is used for taking the composite matrix as an input matrix, performing data processing on the input node equipment, and outputting the processed data matrix.
8. The abnormal data intelligent supervision system based on data monitoring according to claim 7, wherein:
the feature analysis module comprises: the device comprises an inversion characteristic unit, a solution fitting unit and an abnormality judging unit;
the inversion characteristic unit is used for calculating inverse matrixes of characteristic matrixes of all node equipment and calculating characteristic values and characteristic vectors of the inverse matrixes;
the solution fitting unit is used for calculating the characteristic value of the data matrix after the industrial control terminal receives the final data matrix, and multiplying the characteristic value with the inverse matrix of the characteristic matrix of each node device successively to obtain a plurality of reduction matrices;
the abnormality judging unit is used for calculating the characteristic value of a reduction matrix after fitting each solution, comparing the characteristic value of the reduction matrix and the characteristic value of the characteristic matrix with the characteristic value of the last reduction matrix, and judging whether abnormality exists in the processing process.
9. The abnormal data intelligent supervision system based on data monitoring according to claim 8, wherein: the abnormality locating module includes: the device comprises an inversion analysis unit, a characteristic recovery unit and a deviation recording unit;
the inversion analysis unit is used for determining the number of the abnormal equipment according to the reduction step number of the reduction matrix after the abnormality is found, and notifying maintenance personnel of the number of the abnormal equipment;
the characteristic recovery unit is used for requesting the former node equipment of the abnormal equipment to send a data matrix, continuously analyzing the data matrix and judging the abnormal condition of other equipment;
the deviation recording unit is used for adding an abnormal record of the abnormal equipment and calculating a deviation coefficient of the abnormal equipment according to the characteristic value of the reduction matrix.
10. The abnormal data intelligent supervision system based on data monitoring according to claim 9, wherein:
the component scaling module includes: a degradation calculation unit and a simplified processing unit;
the degradation calculation unit is used for calculating a degradation matrix of the equipment according to the abnormal frequency and the deviation coefficient of the abnormal equipment;
the simplified processing unit is used for multiplying the matrix ready for inputting the abnormal equipment with the degradation matrix, obtaining a final data matrix by the node equipment, and then multiplying the final data matrix with the inverse matrix of the degradation matrix to recover the data of the final data matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311580002.8A CN117784656A (en) | 2023-11-24 | 2023-11-24 | Abnormal data intelligent supervision system and method based on data monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311580002.8A CN117784656A (en) | 2023-11-24 | 2023-11-24 | Abnormal data intelligent supervision system and method based on data monitoring |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117784656A true CN117784656A (en) | 2024-03-29 |
Family
ID=90393509
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311580002.8A Pending CN117784656A (en) | 2023-11-24 | 2023-11-24 | Abnormal data intelligent supervision system and method based on data monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117784656A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016189062A (en) * | 2015-03-30 | 2016-11-04 | 有限責任監査法人トーマツ | Abnormality detection device, abnormality detection method and network abnormality detection system |
| CN109932904A (en) * | 2019-03-06 | 2019-06-25 | 东方证券股份有限公司 | Monitoring abnormal state and control system based on feature selecting and pivot control |
| CN114648076A (en) * | 2022-04-11 | 2022-06-21 | 杭州电子科技大学 | Unsupervised learning battery production process abnormal fluctuation detection method |
| CN114793019A (en) * | 2022-05-31 | 2022-07-26 | 南京国电南思科技发展股份有限公司 | Secondary equipment visual supervision system based on big data analysis |
| CN116483015A (en) * | 2023-06-21 | 2023-07-25 | 深圳市华磊迅拓科技有限公司 | Workshop equipment monitoring method, device, equipment and storage medium |
| CN116804964A (en) * | 2022-03-18 | 2023-09-26 | 腾讯科技（深圳）有限公司 | Data processing method, device, electronic equipment and readable storage medium |
| CN117032415A (en) * | 2023-06-29 | 2023-11-10 | 兴容(上海)信息技术股份有限公司 | Equipment data supervision system and method based on temperature change |
-
2023
- 2023-11-24 CN CN202311580002.8A patent/CN117784656A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016189062A (en) * | 2015-03-30 | 2016-11-04 | 有限責任監査法人トーマツ | Abnormality detection device, abnormality detection method and network abnormality detection system |
| CN109932904A (en) * | 2019-03-06 | 2019-06-25 | 东方证券股份有限公司 | Monitoring abnormal state and control system based on feature selecting and pivot control |
| CN116804964A (en) * | 2022-03-18 | 2023-09-26 | 腾讯科技（深圳）有限公司 | Data processing method, device, electronic equipment and readable storage medium |
| CN114648076A (en) * | 2022-04-11 | 2022-06-21 | 杭州电子科技大学 | Unsupervised learning battery production process abnormal fluctuation detection method |
| CN114793019A (en) * | 2022-05-31 | 2022-07-26 | 南京国电南思科技发展股份有限公司 | Secondary equipment visual supervision system based on big data analysis |
| CN116483015A (en) * | 2023-06-21 | 2023-07-25 | 深圳市华磊迅拓科技有限公司 | Workshop equipment monitoring method, device, equipment and storage medium |
| CN117032415A (en) * | 2023-06-29 | 2023-11-10 | 兴容(上海)信息技术股份有限公司 | Equipment data supervision system and method based on temperature change |
Non-Patent Citations (1)
| Title |
|---|
| 林超;郑霖;张文辉;邓小芳;: "基于随机矩阵理论的WSN异常节点定位算法", 计算机工程, no. 01, 15 January 2020 (2020-01-15), pages 157 - 163 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109597967A (en) | A kind of electric system distribution transforming power station load data abnormality detection and restorative procedure | |
| CN101847007B (en) | Process for determining competing cause event probability and/or system availability during the simultaneous occurrence of multiple events | |
| CN110703723B (en) | System, method, and non-transitory computer-readable storage medium | |
| CN112862127B (en) | Sensor data exception handling method and device, electronic equipment and medium | |
| WO2022134911A1 (en) | Diagnosis method and apparatus, and terminal and storage medium | |
| US11830091B2 (en) | Methods for production line electricity management based on an industrial internet of things, systems and storage mediums thereof | |
| AU2019348202A1 (en) | System and method for robotic agent management | |
| CN116032557A (en) | Method and device for updating deep learning model in network security anomaly detection | |
| CN113900894A (en) | Method, system, equipment and medium for predicting large-scale cluster state | |
| CN114461439A (en) | Fault diagnosis method, device, equipment and storage medium | |
| CN110750455B (en) | Intelligent online self-updating fault diagnosis method and system based on system log analysis | |
| CN117784656A (en) | Abnormal data intelligent supervision system and method based on data monitoring | |
| CN114661025A (en) | Improved fault variable identification technique for data-driven fault detection within a process plant | |
| CN108537423B (en) | Bayes method for processing logarithmic normal distribution reliability data of nuclear power plant | |
| CN117195451A (en) | Bridge monitoring data restoration method based on graph theory | |
| CN115169426B (en) | Anomaly detection method and system based on similarity learning fusion model | |
| CN116016114A (en) | Fault processing method and device, nonvolatile storage medium and electronic equipment | |
| Li et al. | Evaluation of throughput in serial production lines with non-exponential machines | |
| Glasserman et al. | Comparing Markov chains simulated in parallel | |
| CN110991765A (en) | Monitoring method and device for prediction model of industrial production and electronic equipment | |
| CN117495357B (en) | Electric power data supervision system and method based on big data | |
| CN117387925B (en) | Damper performance continuous test method and system | |
| CN116028078B (en) | Software remote upgrading method based on VPN technology | |
| CN117278096B (en) | Gray multi-state communication satellite dynamic reliability assessment method | |
| CN116956720B (en) | Industrial digital twin simulation operation and maintenance system |
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 |