CN111260024B - Fault detection method and system based on combination of long-term memory and typical correlation - Google Patents
Fault detection method and system based on combination of long-term memory and typical correlation Download PDFInfo
- Publication number
- CN111260024B CN111260024B CN202010017077.5A CN202010017077A CN111260024B CN 111260024 B CN111260024 B CN 111260024B CN 202010017077 A CN202010017077 A CN 202010017077A CN 111260024 B CN111260024 B CN 111260024B
- Authority
- CN
- China
- Prior art keywords
- long
- term memory
- neural network
- memory neural
- fault detection
- 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
- 230000007787 long-term memory Effects 0.000 title claims abstract description 91
- 238000001514 detection method Methods 0.000 title claims abstract description 74
- 238000013528 artificial neural network Methods 0.000 claims abstract description 104
- 230000015654 memory Effects 0.000 claims abstract description 49
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000013507 mapping Methods 0.000 claims abstract description 9
- 239000013598 vector Substances 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 29
- 239000011159 matrix material Substances 0.000 claims description 26
- 230000006870 function Effects 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 8
- 238000010219 correlation analysis Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 230000006403 short-term memory Effects 0.000 claims description 5
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000000844 transformation Methods 0.000 claims description 3
- 230000017105 transposition Effects 0.000 claims description 3
- 241000764238 Isis Species 0.000 claims 1
- 230000008569 process Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000491 multivariate analysis Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2263—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Abstract
The application relates to the technical field of fault detection, and discloses a fault detection method and system based on long-term memory and typical correlation so as to fully analyze the dynamic and nonlinear characteristics of faults, thereby realizing fault detection; the method comprises the steps of obtaining a first long-term memory neural network for constructing a corresponding input set and a second long-term memory neural network for constructing a corresponding output set; analyzing a linear mapping relation between the first long-term memory neural network and the second long-term memory neural network by adopting a typical correlation method, and optimizing the first long-term memory neural network and the second long-term memory neural network; utilizing the typical correlation of the first long-term memory neural network output layer and the second long-term memory neural network output layer to analyze residual vectors between the first long-term memory neural network output layer and the second long-term memory neural network output layer, and setting a detection threshold; and acquiring real-time operation data of the object to be analyzed, inputting the real-time operation data into the first long-period memory neural network and the second long-period memory neural network to calculate detection statistics of the real-time data, and comparing the detection statistics of the real-time data with a detection threshold value to realize fault detection.
Description
Technical Field
The application relates to the technical field of fault detection, in particular to a fault detection method and system based on long-term memory and typical correlation.
Background
As automation technology and system security requirements increase, fault detection and performance monitoring of the system becomes increasingly important. Model-based fault detection methods have gained widespread acceptance over the past decades. But the performance of such methods depends on the accuracy of the model. Meanwhile, due to the development of sensor technology and information technology, data acquisition becomes easier and easier, and abundant system operation data are accumulated in the acquisition process. Therefore, data-driven process monitoring and fault detection technology becomes a research hotspot in the field of fault detection.
Currently, fault detection methods based on multivariate analysis, such as principal component analysis, partial least squares, and typical correlation analysis, are mostly used. However, the analysis principle of these methods is that by looking for linear transformation of the data set, the constructed features cannot reflect the dynamic and nonlinear relations in the complex system.
Disclosure of Invention
The application aims to provide a fault detection method and system based on combination of long-term memory and typical correlation, so as to fully analyze dynamic and nonlinear characteristics of faults, thereby realizing fault detection.
In order to achieve the above object, the present application provides a fault detection method based on a combination of long-term memory and typical correlation, comprising:
s1: acquiring historical normal operation data of an object to be analyzed as an input set, and acquiring corresponding output of each group of historical normal operation data as an output set;
s2: constructing a first long-term memory neural network corresponding to the input set and a second long-term memory neural network corresponding to the output set;
s3: analyzing the mapping relation between the first long-period memory neural network and the second long-period memory neural network by adopting a typical correlation method, and calculating a correlation coefficient according to the mapping relation;
s4: optimizing the first long-term memory neural network and the second long-term memory neural network according to the correlation linear coefficient, and training the first long-term memory neural network and the second long-term memory neural network by using a back propagation algorithm until the first long-term memory neural network and the second long-term memory neural network which meet the set convergence are obtained;
s5: inputting the first time sequence training set into the first long-short-term memory neural network conforming to the set convergence, inputting the second time sequence training set into the second long-short-term memory neural network conforming to the set convergence, analyzing residual vectors between the first long-term memory neural network and the second long-term memory neural network by using typical correlation of output layers of the first long-term memory neural network and the second long-term memory neural network, constructing detection statistics according to the residual vectors, and setting a detection threshold according to the detection statistics;
s6: and acquiring real-time operation data of an object to be analyzed, inputting the real-time operation data into the first long-term memory neural network and the second long-term memory neural network which meet the convergence, calculating to obtain detection statistics of the real-time data, comparing the detection statistics of the real-time data with the detection threshold, and if the detection statistics of the real-time data exceed the detection threshold, judging that the fault occurs.
Preferably, the S2 specifically includes:
establishing a first time sequence training set of the input set and a second time sequence training set of the output set according to a preset time span;
and constructing the first long-short-term memory neural network according to the first time sequence training set, and constructing the second long-term memory neural network according to the second time sequence training set.
Preferably, the output layers of the first long-term memory neural network and the second long-term memory neural network output the same data dimension.
Preferably, the first long-term memory neural network or the second long-term memory neural network comprises an LSTM layer, a max pooling layer, a Dropout layer and a fully connected layer.
Preferably, the S3 includes:
s31: outputting the characteristic data of the first long-short-term memory networkAnd the characteristic data outputted by the second long-short-term memory network +.>Normalization processing is carried out to obtain normalized characteristic data +.>
S32: calculation ofIs of covariance matrix sigma 1 、Σ 2 Sum sigma 12 Searching for linear transformations using a classical correlation analysis such that +.>And->Possessing the greatest correlation.
Preferably, the S4 includes:
s41: constructing a matrix M and carrying out singular value decomposition on the matrix M as follows:
in the method, in the process of the application,the method is characterized in that the method is a diagonal matrix, the sum of diagonal elements of the diagonal matrix is corr, corr represents the similarity degree of two groups of data after linear transformation, R is a left matrix, V is a right singular matrix, and T represents matrix transposition;
s42: the first long-period memory network and the second long-period memory network use the maximized correlation coefficient as an optimization target, and the network parameters are jointly trained by adopting a back propagation algorithm.
Preferably, the S5 includes:
s51, estimating T by adopting a nuclear density estimation algorithm 2 The probability distribution of the statistics, using the radial basis function, is as follows:
wherein K (g) represents a radial basis function, and g represents an argument of the radial basis function;
setting confidence alpha, T 2 The threshold UCLs of the statistic is calculated by the formulaObtained by the method, wherein
Wherein x is k K=1, 2, …, M is the sample value of x, h is the bandwidth value of the kernel function, b is the argument, and M represents the number of samples of x.
As a general technical idea, the present application also provides a fault detection system based on a combination of long-term memory and typical correlation, which comprises a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.
The application has the following beneficial effects:
the application provides a fault detection method and a fault detection system based on combination of long-term memory and typical correlation, wherein the method comprises the steps of obtaining historical normal operation data of an object to be analyzed as an input set, and obtaining corresponding output of each group of historical normal operation data as an output set; constructing a first long-term memory neural network corresponding to the input set and a second long-term memory neural network corresponding to the output set; analyzing the mapping relation between the first long-term memory neural network and the second long-term memory neural network by adopting a typical correlation method, and calculating a correlation coefficient according to the linear mapping relation; optimizing the first long-period memory neural network and the second long-period memory neural network according to the correlation coefficient, and training the first long-period memory neural network and the second long-period memory neural network by using a back propagation algorithm until the first long-period memory neural network and the second long-period memory neural network which meet the set convergence are obtained; inputting a first time sequence training set into a first long-short-term memory neural network conforming to the set convergence, inputting a second time sequence training set into a second long-short-term memory neural network conforming to the set convergence, analyzing residual vectors between the first long-term memory neural network and the second long-term memory neural network by using typical correlation of output layers of the first long-term memory neural network and the second long-term memory neural network, constructing detection statistics according to the residual vectors, and setting a detection threshold according to the detection statistics; and acquiring real-time operation data of the object to be analyzed, inputting the real-time operation data into the first long-term memory neural network and the second long-term memory neural network which meet the convergence, calculating to obtain detection statistics of the real-time data, comparing the detection statistics of the real-time data with a detection threshold, and if the detection statistics of the real-time data exceed the detection threshold, considering that faults occur, and fully analyzing dynamic and nonlinear characteristics generating faults so as to realize fault detection.
The application will be described in further detail with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:
FIG. 1 is a flow chart of a fault detection method based on a combination of long-term and short-term memory and exemplary correlations in accordance with a preferred embodiment of the application;
FIG. 2 is a schematic diagram of a closed loop continuous stirred tank reactor in accordance with a preferred embodiment of the present application;
fig. 3 is an effect diagram of the fault 6 of the preferred embodiment of the present application detected by the CCA method;
fig. 4 is a graph showing the effect of the detection of the fault 6 by the LSTM-CCA method according to the preferred embodiment of the present application.
Detailed Description
Embodiments of the application are described in detail below with reference to the attached drawings, but the application can be implemented in a number of different ways, which are defined and covered by the claims.
Example 1
As shown in fig. 1, the present embodiment provides a fault detection method based on a combination of long-term memory and typical correlation, including:
s1: acquiring historical normal operation data of an object to be analyzed as an input set, and acquiring corresponding output of each group of historical normal operation data as an output set;
s2: constructing a first long-term memory neural network corresponding to the input set and a second long-term memory neural network corresponding to the output set;
s3: analyzing the mapping relation between the first long-term memory neural network and the second long-term memory neural network by adopting a typical correlation method, and calculating a correlation coefficient according to the mapping relation;
s4: optimizing the first long-period memory neural network and the second long-period memory neural network according to the correlation coefficient, and training the first long-period memory neural network and the second long-period memory neural network by using a back propagation algorithm until the first long-period memory neural network and the second long-period memory neural network which meet the set convergence are obtained;
s5: inputting a first time sequence training set into a first long-short-term memory neural network conforming to the set convergence, inputting a second time sequence training set into a second long-short-term memory neural network conforming to the set convergence, analyzing residual vectors between the first long-term memory neural network and the second long-term memory neural network by using typical correlation of output layers of the first long-term memory neural network and the second long-term memory neural network, constructing detection statistics according to the residual vectors, and setting a detection threshold according to the detection statistics;
s6: and acquiring real-time operation data of the object to be analyzed, inputting the real-time operation data into the first long-term memory neural network and the second long-term memory neural network which meet the convergence, calculating to obtain detection statistics of the real-time data, comparing the detection statistics of the real-time data with a detection threshold, and if the detection statistics of the real-time data exceed the detection threshold, judging that the fault occurs.
According to the fault detection method based on the combination of long-term memory and typical correlation, the typical correlation analysis is combined with the neural network, nonlinear transformation is learned by utilizing the parameter training of the network, and the dynamic and nonlinear characteristics of faults can be fully analyzed, so that fault detection is realized. Can be applied to complex and dynamically changing nonlinear systems.
Specifically, a fault-free historical operation training set is selected, wherein each sample comprises system input data U and output data Y:
wherein U represents an input set, U m T Representing the elements of the input set,
a matrix representing m x a;
wherein Y represents an output set, Y m T Representing the elements in the output set and,
a matrix representing m x b;
scaling U, Y to [0,1, respectively]In between, training is conveniently performed after the neural network is input, and scaled system input data is obtainedOutput data->
Selecting proper time span k according to a certain rule of system input and output existence, and utilizingAnd->Constructing a time sequence training set U s 、Y s The time sequence of the input network at the t time is as follows:
as a preferred implementation manner of this embodiment, the S2 specifically includes:
establishing a first time sequence training set of the input set and a second time sequence training set of the output set according to a preset time span;
and constructing the first long-short-term memory neural network according to the first time sequence training set, and constructing the second long-term memory neural network according to the second time sequence training set.
As a preferred implementation of this embodiment, the output layers of the first long-short-term memory neural network and the second long-short-term memory neural network output the same data dimension.
As a preferred implementation of this embodiment, the first long-term memory neural network or the second long-term memory neural network includes an LSTM layer, a max pooling layer, a Dropout layer, and a full connection layer. The specific network structure is as follows: LSTM (n 1 unit) - > Dropout- > LSTM (n 2 unit) - > Dropout () - > LSTM (n 3 units) - > MaxPooling- > full connectivity layer (n 4 nodes) - > output layer (n 5 nodes).
As a preferred implementation manner of this embodiment, the S3 includes:
s31: outputting the characteristic data of the first long-short-term memory networkAnd the characteristic data outputted by the second long-short-term memory network +.>Normalization processing is carried out to obtain normalized characteristic data +.>
S32: calculation ofIs of covariance matrix sigma 1 、Σ 2 Sum sigma 12 Searching for linear transformations using a classical correlation analysis such that +.>And->Possessing the greatest correlation.
As a preferred implementation manner of this embodiment, the S4 includes:
s41: constructing a matrix M and carrying out singular value decomposition on the matrix M as follows:
in the method, in the process of the application,the method is characterized in that the method is a diagonal matrix, the sum of diagonal elements of the diagonal matrix is corr, corr represents the similarity degree of two groups of data after linear transformation, R is a left matrix, V is a right singular matrix, and T represents matrix transposition;
s42: the first long-period memory network and the second long-period memory network use the maximized correlation coefficient as an optimization target, and the network parameters are jointly trained by adopting a back propagation algorithm.
As a preferred implementation manner of this embodiment, the S5 includes:
s51, estimating T by adopting a nuclear density estimation algorithm 2 The probability distribution of the statistics, using the radial basis function, is as follows:
where K (g) represents a radial basis function and g represents an argument of the radial basis function.
Setting confidence alpha, T 2 The threshold UCLs of the statistic is calculated by the formulaObtained by the method, wherein
Wherein x is k K=1, 2, …, M is the sample value of x, h is the bandwidth value of the kernel function, b is the argument, and M represents the number of samples of x.
The fault detection method based on the combination of long-term and short-term memory and typical correlation is applicable to all reactors driven by data, and in this embodiment, the method of the present application is further described and verified by taking a closed-loop Continuous Stirred Tank Reactor (CSTR) as shown in fig. 2 as an example.
The schematic diagram of the CSTR is shown in fig. 2, and the system reaction model can be abstracted as follows:
wherein the system input is u= [ C ] i T i T ci ] T The system output is y= [ ct T c Q c ] T ，ν i Is process noise, k is a constantThe remaining parameters are shown in Table 1.
Table 1 constant values in CSTR model
The example considers 6 minor fault scenarios as shown in table 2:
TABLE 2 6 micro-faults under CSTR model
The present example uses the system input and output data set obtained by running the CSTR model to experimentally verify the feasibility and effectiveness of the present application.
Running a CSTR model simulates that the reaction occurs for 20 hours to produce a normal data set and a fault data set, all system variables are sampled every 1min, and certain random disturbances are given to the input variables to simulate the real situation as much as possible, while increasing the dynamics and nonlinearity of the overall system. The fault dataset was generated by introducing a corresponding fault after 200min of remaining fault free. For each fault, a fault detection method (LSTM-CCA) and a CCA method based on long-term short-term memory (LSTM) feature extraction and typical correlation analysis for fault detection are respectively established by using 1200 fault-free samples, and finally verification is carried out by using a fault data set, and performance evaluation of fault detection adopts index fault False Alarm Rate (FAR) and fault omission rate (MDR) class measurement, as shown in Table 3:
TABLE 3 6 micro-faults under CSTR model
The calculation formulas of the fault False Alarm Rate (FAR) and the fault omission rate (MDR) are as follows:
wherein UCLs represent thresholds calculated during the offline training phase. The detection effects of the fault 6 by the CCA method and the LSTM-CCA method are shown in fig. 3 and 4.
Example 2
In correspondence with the above-described method embodiment 1, the present embodiment provides a fault detection system based on a combination of long-term and short-term memory and typical correlation, including a memory, a processor, and a computer program stored on the memory and executable on the processor, which when executed, implements the steps of the above-described method.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (7)
1. A fault detection method based on a combination of long-term memory and canonical correlation, comprising:
s1: acquiring historical normal operation data of an object to be analyzed as an input set, and acquiring corresponding output of each group of historical normal operation data as an output set;
s2: constructing a first long-term memory neural network corresponding to the input set and a second long-term memory neural network corresponding to the output set;
s3: analyzing the mapping relation between the first long-period memory neural network and the second long-period memory neural network by adopting a typical correlation method, and calculating a correlation coefficient according to the mapping relation;
s4: optimizing the first long-term memory neural network and the second long-term memory neural network according to the correlation coefficient, and training the first long-term memory neural network and the second long-term memory neural network by using a back propagation algorithm until the first long-term memory neural network and the second long-term memory neural network which meet the set convergence are obtained;
s5: inputting a first time sequence training set into the first long-short-term memory neural network conforming to the set convergence, inputting a second time sequence training set into the second long-short-term memory neural network conforming to the set convergence, analyzing residual vectors between the first long-term memory neural network and the second long-term memory neural network by using typical correlation of output layers of the first long-term memory neural network and the second long-term memory neural network, constructing detection statistics according to the residual vectors, and setting a detection threshold according to the detection statistics;
s6: acquiring real-time operation data of an object to be analyzed, inputting the real-time operation data into the first long-term memory neural network and the second long-term memory neural network which meet the convergence, calculating to obtain detection statistics of the real-time data, comparing the detection statistics of the real-time data with the detection threshold, and if the detection statistics of the real-time data exceed the detection threshold, regarding the real-time data as faults;
the step S3 comprises the following steps:
s31: outputting the characteristic data i output by the first long-short-term memory network o1 ∈R n5 And the characteristic data i output by the second long-short-term memory network o2 ∈R n5 Normalization processing is carried out to obtain normalized characteristic dataAnd calculates a covariance matrix Σ 1 、Σ 2 Sum sigma 12 ：
Σ 1 ＝E{(i o1 -μ 1 )(i o1 -μ 1 ) T }
Σ 2 ＝E{(i o2 -μ 2 )(i o2 -μ 2 ) T }
Σ 12 ＝E{(i o1 -μ 1 )(i o2 -μ 2 ) T }
Wherein mu is 1 Sum mu 2 Respectively isIs the average value of (2);
s32: searching for linear transformations using a canonical correlation analysis enablesAnd->Possessing the greatest correlation.
2. The fault detection method based on a combination of long-term memory and canonical correlation of claim 1, wherein S2 specifically includes:
establishing a first time sequence training set of the input set and a second time sequence training set of the output set according to a preset time span;
and constructing the first long-short-term memory neural network according to the first time sequence training set, and constructing the second long-term memory neural network according to the second time sequence training set.
3. The fault detection method based on a combination of long-term memory and canonical correlation according to claim 1 or 2, wherein the output layers of the first long-term memory neural network and the second long-term memory neural network output the same data dimension.
4. The fault detection method based on a combination of long-term memory and canonical correlation according to claim 1, wherein the first long-term memory neural network or the second long-term memory neural network includes an LSTM layer, a max pooling layer, a Dropout layer, and a full connection layer.
5. The fault detection method based on a combination of long-term memory and canonical correlation of claim 1, wherein S4 includes:
s41: constructing a matrix M and carrying out singular value decomposition on the matrix M as follows:
in the formula, Σ epsilon R n5×n5 The method is characterized in that the method is a diagonal matrix, the sum of diagonal elements of the diagonal matrix is corr, corr represents the similarity degree of two groups of data after linear transformation, R is a left matrix, V is a right singular matrix, and T represents matrix transposition;
s42: the first long-period memory network and the second long-period memory network use the maximized correlation coefficient as an optimization target, and the network parameters are jointly trained by adopting a back propagation algorithm.
6. The fault detection method based on a combination of long-term memory and canonical correlation of claim 1, wherein S5 includes:
s51, estimating T by adopting a nuclear density estimation algorithm 2 The probability distribution of the statistics, using the radial basis function, is as follows:
wherein K (g) represents a radial basis function, and g represents an argument of the radial basis function;
setting confidence alpha, T 2 The threshold UCLs of the statistic is calculated by the formulaObtained by the method, wherein
Wherein x is k K=1, 2, …, M is the sample value of x, h is the bandwidth value of the kernel function, b is the argument, and M represents the number of samples of x.
7. A fault detection system based on a combination of long and short term memory and typical correlation comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of the preceding claims 1 to 6 when said computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010017077.5A CN111260024B (en) | 2020-01-08 | 2020-01-08 | Fault detection method and system based on combination of long-term memory and typical correlation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010017077.5A CN111260024B (en) | 2020-01-08 | 2020-01-08 | Fault detection method and system based on combination of long-term memory and typical correlation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111260024A CN111260024A (en) | 2020-06-09 |
| CN111260024B true CN111260024B (en) | 2023-11-24 |
Family
ID=70954127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010017077.5A Active CN111260024B (en) | 2020-01-08 | 2020-01-08 | Fault detection method and system based on combination of long-term memory and typical correlation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111260024B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113255219B (en) * | 2021-05-28 | 2021-10-12 | 浙江浙能技术研究院有限公司 | Generator bar vibration optimization method based on correction long-time and short-time memory neural network |
| CN113985173B (en) * | 2021-10-27 | 2024-03-15 | 哈尔滨工业大学 | PFC fault detection method based on statistical characteristic typical correlation analysis |
| CN114578011A (en) * | 2022-03-07 | 2022-06-03 | 上海蓝长科技集团有限公司 | Water quality monitoring method based on multi-sensor multi-source data fusion |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019024083A1 (en) * | 2017-08-04 | 2019-02-07 | Nokia Technologies Oy | Artificial neural network |
| CN109753896A (en) * | 2018-12-20 | 2019-05-14 | 西安电子科技大学 | A kind of unsupervised heterologous method for detecting change of remote sensing image based on general character autocoder |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7660774B2 (en) * | 2005-05-31 | 2010-02-09 | Honeywell International Inc. | Nonlinear neural network fault detection system and method |
| US9807473B2 (en) * | 2015-11-20 | 2017-10-31 | Microsoft Technology Licensing, Llc | Jointly modeling embedding and translation to bridge video and language |
| US10482379B2 (en) * | 2016-07-29 | 2019-11-19 | Google Llc | Systems and methods to perform machine learning with feedback consistency |
| US20190096525A1 (en) * | 2017-09-26 | 2019-03-28 | Owned Outcomes Inc. | Patient data management system |
| US11157782B2 (en) * | 2017-11-16 | 2021-10-26 | International Business Machines Corporation | Anomaly detection in multidimensional time series data |
| US10771488B2 (en) * | 2018-04-10 | 2020-09-08 | Cisco Technology, Inc. | Spatio-temporal anomaly detection in computer networks using graph convolutional recurrent neural networks (GCRNNs) |
-
2020
- 2020-01-08 CN CN202010017077.5A patent/CN111260024B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019024083A1 (en) * | 2017-08-04 | 2019-02-07 | Nokia Technologies Oy | Artificial neural network |
| CN109753896A (en) * | 2018-12-20 | 2019-05-14 | 西安电子科技大学 | A kind of unsupervised heterologous method for detecting change of remote sensing image based on general character autocoder |
Non-Patent Citations (3)
| Title |
|---|
| Mallinar, Neil等.Deep Canonically Correlated LSTMs.Machine Learning.2018,全文. * |
| 董洁 ; 孙瑞琪 ; 彭开香 ; 唐鹏.自动编码器与典型相关分析方法联合驱动的工业过程质量监测.控制理论与应用.2019,(第009期),全文. * |
| 赵航 ; .典型相关分析和神经网络相结合的早期火灾识别.科技通报.2013,(第05期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111260024A (en) | 2020-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111260024B (en) | Fault detection method and system based on combination of long-term memory and typical correlation | |
| CN111914873A (en) | Two-stage cloud server unsupervised anomaly prediction method | |
| US8378816B2 (en) | System and method to assess signal similarity with applications to diagnostics and prognostics | |
| CN114297936A (en) | Data anomaly detection method and device | |
| CN111680725B (en) | Gas sensor array multi-fault isolation algorithm based on reconstruction contribution | |
| CN109522948A (en) | A kind of fault detection method based on orthogonal locality preserving projections | |
| CN111652290A (en) | Detection method and device for confrontation sample | |
| CN110837872B (en) | Industrial control network intrusion detection method and system | |
| CN114363195A (en) | Network flow prediction early warning method for time and spectrum residual convolution network | |
| CN114897138A (en) | System fault diagnosis method based on attention mechanism and depth residual error network | |
| CN114611409A (en) | Method and device for establishing power distribution terminal abnormity detection model | |
| CN114003900A (en) | Network intrusion detection method, device and system for secondary system of transformer substation | |
| Deng et al. | Detecting intelligent load redistribution attack based on power load pattern learning in cyber-physical power systems | |
| CN116827685B (en) | Dynamic defense strategy method of micro-service system based on deep reinforcement learning | |
| CN111026087B (en) | Weight-containing nonlinear industrial system fault detection method and device based on data | |
| Su et al. | KPI anomaly detection method for Data Center AIOps based on GRU-GAN | |
| Cui et al. | Using EBGAN for anomaly intrusion detection | |
| CN111797732B (en) | Video motion identification anti-attack method insensitive to sampling | |
| CN113051809A (en) | Virtual health factor construction method based on improved restricted Boltzmann machine | |
| Li et al. | Fault Diagnosis to Nuclear Power Plant System Based on Time-Series Convolution Neural Network | |
| CN116915477B (en) | Error data injection attack detection method and device based on typical variable analysis, electronic equipment and computer readable storage medium | |
| CN117171778B (en) | Access flow control method and system for database | |
| Xu et al. | Data balancing technique based on AE-Flow model for network instrusion detection | |
| CN113890109B (en) | Multi-wind power plant power daily scene generation method with time-space correlation | |
| CN115865458B (en) | Network attack behavior detection method, system and terminal based on LSTM and GAT algorithm |
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 |