CN114185321B - Electric actuator fault diagnosis method for improving multi-classification twin support vector machine - Google Patents
Electric actuator fault diagnosis method for improving multi-classification twin support vector machine Download PDFInfo
- Publication number
- CN114185321B CN114185321B CN202111001164.2A CN202111001164A CN114185321B CN 114185321 B CN114185321 B CN 114185321B CN 202111001164 A CN202111001164 A CN 202111001164A CN 114185321 B CN114185321 B CN 114185321B
- Authority
- CN
- China
- Prior art keywords
- data
- classification
- wavelet packet
- fault
- support vector
- 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
- 238000012706 support-vector machine Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000003745 diagnosis Methods 0.000 title claims abstract description 34
- 239000013598 vector Substances 0.000 claims abstract description 65
- 238000012360 testing method Methods 0.000 claims abstract description 26
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000004458 analytical method Methods 0.000 claims abstract description 15
- 230000000694 effects Effects 0.000 claims abstract description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 20
- 230000001575 pathological effect Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 230000001105 regulatory effect Effects 0.000 description 4
- 238000007796 conventional method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a fault diagnosis method for an electric actuator for improving a multi-classification twin support vector machine, which adopts the health state of the electric actuator and data under the fault state as an original data set; and carrying out wavelet packet analysis on the data to extract feature vectors and constructing a training sample set and a test sample set. And putting the training sample set into a multi-twin support vector machine fault diagnosis model to obtain a classifier, and putting the test sample set into the classifier to obtain a fault diagnosis result. According to the invention, the wavelet packet analysis method is used for extracting the characteristics of the data, so that the modal aliasing during the fault data of the complex actuator can be eliminated, the weak data component submerged in the strong data is separated, the experimental error is effectively reduced, and the fault diagnosis effect is remarkably improved.
Description
Technical Field
The invention belongs to the technical field of state monitoring of electric actuators of gas turbines, and particularly relates to a fault diagnosis method for an electric actuator for improving a multi-classification twin support vector machine.
Background
The electric actuator is used as an actuating mechanism of a control instruction, has a complex internal structure, is easy to fail, and has higher technical requirements on field maintenance personnel. The electric regulating valve is in various severe working environments such as high temperature, high pressure, inflammability and explosiveness for a long time, various faults are very easy to occur, the performance and the operation level of the system are influenced, and even the problems of economy and safety are caused. The method is based on the fact that faults occurring in the operation process of the regulating valve are found in time and corresponding measures are taken, and the method is a basis for guaranteeing safe, reliable and stable operation of an automatic control system in an industrial process. At present, the electric regulating valve is monitored according to parameters transmitted by the field device in real time, and the generated data can be subjected to fault diagnosis and classification, so that the device operates normally.
When the electric regulating valve fails, the data can change slightly, and a large amount of environment, system noise information and the like are doped. When the traditional twin support vector machine faces to the tiny change of data, the type of fault is difficult to accurately distinguish, so that the accuracy and the reliability of acquiring the data are improved, and the noise is reduced. On the basis of energy decomposition of data in wavelet packet analysis, feature vectors are extracted, and simultaneously, a multi-classification twin support vector machine method is adopted to diagnose tiny, compound and progressive faults.
Therefore, a new approach is needed to diagnose various industrial actuator fault monitoring and actuator, control valve micro-faults.
Disclosure of Invention
Aiming at the problems in the background technology, the invention provides an electric actuator fault diagnosis method for improving a multi-classification twin support vector machine, which is characterized by comprising the following steps:
step 1, acquiring data F (t) of a gas turbine electric actuator in a health state and data F (t) of a fault state under different working conditions as an original data set;
step 2, extracting feature vectors from the original data set by wavelet packet analysis;
step 3, performing pathological test on the feature vector, normalizing the feature vector, constructing a training sample set and a test sample set, and storing and recording unknown fault types;
and 4, training and testing by utilizing the multi-classification twin support vector machine to complete fault diagnosis.
The step 2 comprises the following steps:
step 21, determining the decomposition layer number of the wavelet packet and reconstructing the wavelet packet;
step 22, extracting data feature vectors by utilizing a wavelet packet algorithm;
step 23, optimizing the parameters of the multi-classification support vector machine by utilizing a wavelet packet extraction feature vector technology;
the extracting the feature vector from the wavelet packet analysis data in step 22 includes:
step 221, coefficient decomposition of the original data sets F (t), F (t): the wavelet packet decomposition recurrence method is used as follows:
wherein mu j,n (m) wavelet packet coefficients of wavelet packet function phi (t), j being the scale, u j,n (k) As decomposition coefficient in scale, μ j,2n (m) is an approximation of the scale j, μ j,2n+1 (m) is an approximation coefficient of scale j+1, h is a low-pass filter coefficient, g is a high-pass filter coefficient, and k is a decomposition order (k=0, 1..n);
step 222, reconstructing coefficients of the original data sets F (t), F (t): the inverse discrete wavelet packet transform method is used as follows:
wherein, h (m-2 k) and g (m-2 k) are wavelet vectors, and m is the data length;
step 223, calculating the energy of the original data sets F (t), F (t) in the frequency band, where the energy formula corresponding to each node of the third layer can be obtained in step 222 as follows:
wherein x is jk { j=0, 1..7; k=0, 1..n } reconstructed dataThe magnitude of the discrete points;
step 224, from step 223, the feature vector is constructed as follows:
and analyzing the data by utilizing the wavelet packet, wherein the decomposition layer number is 3, and the feature vector is 8.
The step 3 comprises the following steps:
step 31, detecting whether the data exist in a fault type library by using a pathological double factor, wherein the relation is as follows;
wherein E is a feature vector, n is the number of feature vectors, x is two-dimensional function interpolation, p and q are pathological double-factor coefficients, and W is a detection parameter. When W is 0 or more, the fault type is known; when W is less than 0, the fault type is unknown;
and 32, caching the unknown data into a fault type library, marking as fn, and marking the fault type.
After the step 32, a step 33 is performed to normalize each line of the extracted feature vectors by wavelet packet analysis, and the relation is as follows:
wherein A is ij Representing elements of the ith row and jth column in the matrix, A i ' j Is an element in the transformed feature matrix; and dividing the feature vector normalization result into a training set and a testing set, and inputting the training set and the testing set serving as feature vectors into a multi-classification twin support vector machine classifier for feature recognition to perform network self-learning training and testing.
The step 4 is divided into:
step 41, establishing a multi-classification twin support vector machine model; step 41 comprises: step 411 and step 412;
step 411, adding Lagrangian multiplier formula α for i constraints i Setting up Lagrange function as follows:
wherein y is i (w T x i +b) 1 is i constraint conditions, alpha is input data, b is constraint parameter, w i Is a normal vector;
step 412, constructing an ith hyperplane of the classifier based on step 411:
distinguishing the linear and nonlinear situations of the data: for low-dimensional data, distinguishing in a visual mode; for high-dimensional data, distinguishing through superposition theorem;
and calculating the ith hyperplane:
when the data is linear, the calculation method is as follows:
wherein w is calculated i Is the normal vector of the ith hyperplane, f i G is the offset, g i Is punishment parameter of positive value, xi i Is more than or equal to 0 as a constraint condition,and->Column vector of all elements 1, A i 、B i Respectively the ith hyperplane fitting coefficient of the two classifiers;
when the data is nonlinear, the calculation method is as follows:
wherein u is i Is the normal vector of the ith hyperplane, f i G is the offset, g i Is punishment parameter of positive value, xi i Is more than or equal to 0 as a constraint condition,and->Column vector of all elements 1, A i 、B i The ith hyperplane fitting coefficient of the two classifiers is N, C as a kernel function fixed parameter;
step 42, according to step 412, a decision function Lable (x) of the multi-classification twin support vector machine is obtained as follows:
when the data is linear:
when the data is nonlinear:
and (3) taking a decision function obtained through training and testing of the multi-classification twin support vector machine as a fault diagnosis classification result, and comparing the fault diagnosis result with an initially set fault type and fault intensity to judge the effect of the fault diagnosis method to be verified.
The invention has the beneficial effects that:
1. wavelet packet analysis is added into the traditional multi-classification twin support vector machine, and feature vectors are extracted, so that the recognition of the multi-classification twin support vector machine model is improved.
2. The method can accurately judge and classify various states, including faults with extremely small changes of valve opening data, such as motor faults, valve blockage and the like.
Drawings
FIG. 1 is a flow chart of a method of fault diagnosis of an electric actuator of an improved multi-class twinning support vector machine of the present invention;
FIG. 2 is a block diagram of an electric actuator of the present invention;
FIG. 3 is a wavelet packet analysis feature vector diagram used in the present invention;
FIG. 4 is a schematic diagram of a wavelet packet analysis architecture used in the present invention;
FIG. 5 is a diagram showing the diagnostic effect of a fault diagnosis method of the improved multi-classification twin support vector machine of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The embodiment of the invention shown in fig. 1 comprises: the gas turbine electric actuator and fault diagnosis for the gas turbine electric actuator specifically comprises the following steps:
step 1, acquiring data F (t) of a gas turbine electric actuator in a health state and data F (t) of a fault state under different working conditions as an original data set;
step 2, extracting feature vectors from the original data sets F (t) and F (t) by wavelet packet analysis;
step 3, performing pathological test on the feature vector, normalizing the feature vector, constructing a training sample set and a test sample set, and storing the unknown fault type into a fault type library;
and 4, training and testing by utilizing the multi-classification twin support vector machine to complete fault diagnosis.
Wherein the step 2 is divided into:
step 21, determining the decomposition layer number of the wavelet packet and reconstructing the wavelet packet;
step 22, extracting data feature vectors by utilizing a wavelet packet algorithm;
and step 23, optimizing the parameters of the multi-classification support vector machine by utilizing a wavelet packet extraction feature vector technology.
Wavelet packet analysis data in step 22 extracts feature vectors: the method comprises the following specific steps of data coefficient decomposition, coefficient reconstruction, frequency bandwidth energy calculation and eigenvector generation:
step 221, coefficient decomposition of the original data sets F (t), F (t): the wavelet packet decomposition recurrence method is used as follows:
wherein mu j,n (m) wavelet packet coefficients of wavelet packet function phi (t), j being the scale, u j,n (k) As decomposition coefficient in scale, μ j,2n (m) is an approximation of the scale j, μ j,2n+1 (m) is an approximation coefficient of scale j+1, h is a low-pass filter coefficient, g is a high-pass filter coefficient, and k is a decomposition order (k=0, 1..n).
Step 222, reconstructing coefficients of the original data sets F (t), F (t): the inverse discrete wavelet packet transform method is used as follows:
where h (m-2 k), g (m-2 k) are wavelet vectors, and m is the data length.
Step 223, calculating the energy of the original data sets F (t), F (t) in the frequency band, where the energy formula corresponding to each node of the third layer can be obtained in step 222 as follows:
wherein x is jk { j=0, 1..7; k=0, 1..n } reconstructed dataThe magnitude of the discrete points.
Step 224, from step 223, the feature vector is constructed as follows:
further, as shown in fig. 4, the data is analyzed by wavelet packet, the number of decomposition layers is 3, and the feature vector is 8.
Step 3 is feature vector screening, and is further divided into: step 31, feature vector pathological test, step 32, namely saving and recording unknown fault types, and step 33, namely normalizing each row of feature vectors, wherein the steps are as follows:
step 31, detecting whether the data exist in a fault type library by using a pathological double factor, wherein the relation is as follows;
wherein E is a feature vector, n is the number of feature vectors, x is two-dimensional function interpolation, p and q are pathological double-factor coefficients, and W is a detection parameter. When W is 0 or more, the fault type is known; when W is less than 0, the fault type is unknown.
Step 32, using the setlocal calling program in matlab to cache the unknown data into the fault type library, marking as fn, and marking the fault type for calling in the later fault diagnosis, as shown in table 1.
TABLE 1 fault type library
Fault serial number | Fault name |
F1 | Valve plug |
F2 | Sinking of valves or valve seats |
F3 | Valve plug or seat erosion |
F4 | Bearing friction increase |
F5 | External leakage |
F6 | Internal leakage |
F7 | Excessive voltage |
F8 | Push rod torsion of actuator |
F9 | Loosening of frames or shelves |
F10 | Spring failure |
F11 | Electrical converter failure |
F12 | Valve stem displacement sensor failure |
F13 | Pressure sensor failure |
F14 | Locator feedback failure |
F15 | Failure of an electrical bypass valve |
Step 33, analyzing each row of the extracted feature vectors by the normalized wavelet packet, wherein the relation is as follows:
wherein A is ij Representing elements of the ith row and jth column in the matrix, A i ' j Is an element in the transformed feature matrix. And dividing the feature vector normalization result into a training set and a testing set, and inputting the training set and the testing set serving as feature vectors into a multi-classification twin support vector machine classifier for feature recognition to perform network self-learning training and testing.
Wherein the step 4 is divided into:
performing multi-classification twin support vector machine training, comprising: step 41, a multi-classification twin support vector machine model is built, and step 42 obtains a fault diagnosis classification result through a decision function, specifically as follows:
and step 41, establishing a multi-classification twin support vector machine model. The specific method comprises the following steps:
step 411, adding Lagrangian multiplier formula α for i constraints i Setting up Lagrange function as follows:
wherein y is i (w T x i +b) 1 is i constraint conditions, alpha is input data, b is constraint parameter, w i Is a normal vector.
Step 412, constructing an ith hyperplane of the classifier based on step 411:
distinguishing the linear and nonlinear situations of the data: for low-dimensional data, distinguishing in a visual mode; for high-dimensional data, distinguishing through superposition theorem;
and calculating the ith hyperplane:
when the data is linear, the calculation method is as follows:
wherein w is calculated i Is the normal vector of the ith hyperplane, f i G is the offset, g i Is punishment parameter of positive value, xi i Is more than or equal to 0 as a constraint condition,and->Column vector of all elements 1, A i 、B i The i-th hyperplane fitting coefficients of the two classifiers are respectively.
When the data is nonlinear, the calculation method is as follows:
wherein u is i Is the normal vector of the ith hyperplane, f i G is the offset, g i Is punishment parameter of positive value, xi i Is more than or equal to 0 as a constraint condition,and->Column vector of all elements 1, A i 、B i The ith hyperplane fitting coefficient of each classifier is N, C, which is a kernel function fixed parameter.
Step 42, according to step 412, a decision function Lable (x) of the multi-classification twin support vector machine is obtained as follows:
when the data is linear:
when the data is nonlinear:
and the decision function Lable (x) obtained through training and testing of the multi-classification twin support vector machine is used as a fault diagnosis classification result, and the fault diagnosis result is compared with the fault type and the fault strength which are initially set to judge the effect of the fault diagnosis method to be verified.
Aiming at the defect of data analysis of the traditional multi-classification twin support vector machine, the invention optimizes decision parameters of the multi-classification twin support vector machine by utilizing wavelet packet analysis and extracts characteristics of electric actuator data. And the unknown fault types are stored and recorded, then the feature vectors are normalized to form a training set and a testing set of the multi-classification twin support vector machine, and the decision function parameters can be automatically adjusted to carry out diagnosis classification on the data.
According to the diagnosis method for the improved multi-classification twin support vector machine, provided by the invention, the modal aliasing during the fault data of the complex actuator can be eliminated through wavelet packet analysis, and the weak data component submerged in the strong data can be separated, so that the experimental error is effectively reduced. Meanwhile, when the fault data is unknown, the new data is input into the fault type library by utilizing the pathological test so as to be used later, and a plurality of problems caused by the fact that the unknown data cannot be accurately diagnosed are solved. The multi-classification twin support vector machine can rapidly diagnose a plurality of faults at one time, has small error and high convergence speed when performing fault classification tasks, and can more efficiently complete the classification tasks.
Table 1 shows the comparison of the fault diagnosis results of the method of the present invention and other methods, and the innovation of the method is that the fault can be diagnosed rapidly, and based on the same group of data, the method only takes 1.708s, and compared with the traditional method, the diagnosis speed is improved by nearly 6 times. The method has the highest accuracy rate of 94.341 percent, and compared with the traditional method, the diagnosis accuracy rate is improved by nearly 10 percent. When unknown faults exist, the method can be accurately stripped, faults cannot be diagnosed by mistake, the defect that the traditional diagnosis method cannot be completely classified is overcome, and the fault diagnosis effect when fault data contain the unknown faults is greatly improved.
The comparison of the accuracy and time results of the present invention with the conventional methods is shown in Table 2.
Table 1 comparison of the results of the present invention with the results of the conventional methods
Algorithm | Accuracy/% | Time/s |
SVM | 83.051 | 10.235 |
WPT-SVM | 87.232 | 9.753 |
TWSVM | 90.702 | 7.924 |
WPT-TWSVM | 91.250 | 7.285 |
OVA-TWSVM | 90.980 | 2.008 |
WPT-OVA-TWSVM | 94.341 | 1.708 |
Claims (2)
1. An electric actuator fault diagnosis method for improving a multi-classification twin support vector machine is characterized by comprising the following steps:
step 1, acquiring data F (t) of a gas turbine electric actuator in a health state and data F (t) of a fault state under different working conditions as an original data set;
step 2, extracting feature vectors from the original data set by wavelet packet analysis;
step 3, performing pathological test on the feature vector, normalizing the feature vector, constructing a training sample set and a test sample set, and storing and recording unknown fault types;
step 4, training and testing by utilizing a multi-classification twin support vector machine to complete fault diagnosis;
the step 3 comprises the following steps:
step 31, detecting whether the data exist in a fault type library by using a pathological double factor, wherein the relation is as follows;
wherein E is a feature vector, n is the number of feature vectors, x is two-dimensional function interpolation, p and q are pathological double-factor coefficients, and W is a detection parameter; when W is 0 or more, the fault type is known; when W is less than 0, the fault type is unknown;
step 32, caching the unknown data into a fault type library, marking as fn, and marking the fault type;
after step 32, step 33 is performed to normalize each line of the extracted feature vectors by wavelet packet analysis, and the relation is as follows:
wherein A is ij Representing elements of the ith row and jth column in the matrix, A i ' j Is an element in the transformed feature matrix; dividing the feature vector normalization result into a training set and a testing set, and inputting the training set and the testing set as feature vectors into a multi-classification twin support vector machine classifier for feature recognition to perform network self-learning training and testing;
the step 4 is divided into:
step 41, establishing a multi-classification twin support vector machine model; step 41 comprises: step 411 and step 412;
step 411, adding Lagrangian multiplier formula α for i constraints i Setting up Lagrange function as follows:
wherein y is i (w T x i +b) is more than or equal to 1, i constraint conditions, alpha is input data, b is constraint parameters, and w is a normal vector;
step 412, constructing an ith hyperplane of the classifier based on step 411:
distinguishing the linear and nonlinear situations of the data: for low-dimensional data, distinguishing in a visual mode; for high-dimensional data, distinguishing through superposition theorem;
and calculating the ith hyperplane:
when the data is linear, the calculation method is as follows:
wherein w is calculated i Is the normal vector of the ith hyperplane, f i G is the offset, g i Is punishment parameter of positive value, xi i Is more than or equal to 0 as a constraint condition,and->Column vector of all elements 1, A i 、B i Respectively the ith hyperplane fitting coefficient of the two classifiers;
when the data is nonlinear, the calculation method is as follows:
wherein u is i Is the normal vector of the ith hyperplane, f i For the purpose of offsetAmount g i Is punishment parameter of positive value, xi i Is more than or equal to 0 as a constraint condition,and->Column vector of all elements 1, A i 、B i The ith hyperplane fitting coefficient of the two classifiers is N, C as a kernel function fixed parameter;
step 42, according to step 412, a decision function Lable (x) of the multi-classification twin support vector machine is obtained as follows:
when the data is linear:
when the data is nonlinear:
and (3) taking a decision function obtained through training and testing of the multi-classification twin support vector machine as a fault diagnosis classification result, and comparing the fault diagnosis result with an initially set fault type and fault intensity to judge the effect of the fault diagnosis method to be verified.
2. The method for diagnosing a failure of an electric actuator by improving a multi-class twinning support vector machine according to claim 1, wherein said step 2 comprises:
step 21, determining the decomposition layer number of the wavelet packet and reconstructing the wavelet packet;
step 22, extracting data feature vectors by utilizing a wavelet packet algorithm;
step 23, optimizing the parameters of the multi-classification support vector machine by utilizing a wavelet packet extraction feature vector technology;
the extracting the data feature vector by using the wavelet packet algorithm in the step 22 includes:
step 221, coefficient decomposition of the original data sets F (t), F (t): the wavelet packet decomposition recurrence method is used as follows:
wherein mu j,n (m) wavelet packet coefficients of wavelet packet function phi (t), j being the scale, u j,n (k) As decomposition coefficient in scale, μ j,2n (m) is an approximation of a scale of 2n, μ j,2n+1 (m) is an approximation coefficient of a scale 2n+1, h is a low-pass filter coefficient, g is a high-pass filter coefficient, k is a decomposition level number k=0, 1..n;
step 222, reconstructing coefficients of the original data sets F (t), F (t): the inverse discrete wavelet packet transform method is used as follows:
wherein, h (m-2 k) and g (m-2 k) are wavelet vectors, and m is the data length;
step 223, calculating the energy of the original data sets F (t), F (t) in the frequency band, where the energy formula corresponding to each node of the third layer can be obtained in step 222 as follows:
wherein x is jk { j=0, 1..7; k=0, 1..n } reconstructed dataThe magnitude of the discrete points;
step 224, from step 223, the feature vector is constructed as follows:
and analyzing the data by utilizing the wavelet packet, wherein the decomposition layer number is 3, and the feature vector is 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111001164.2A CN114185321B (en) | 2021-08-30 | 2021-08-30 | Electric actuator fault diagnosis method for improving multi-classification twin support vector machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111001164.2A CN114185321B (en) | 2021-08-30 | 2021-08-30 | Electric actuator fault diagnosis method for improving multi-classification twin support vector machine |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114185321A CN114185321A (en) | 2022-03-15 |
CN114185321B true CN114185321B (en) | 2023-12-22 |
Family
ID=80601043
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111001164.2A Active CN114185321B (en) | 2021-08-30 | 2021-08-30 | Electric actuator fault diagnosis method for improving multi-classification twin support vector machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114185321B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115978466A (en) * | 2022-12-27 | 2023-04-18 | 重庆市荣冠科技有限公司 | Fluid pipeline leakage detection method based on class imbalance improved twin support vector machine |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102539159A (en) * | 2010-12-24 | 2012-07-04 | 中国船舶研究设计中心 | Fault diagnosis method for valve mechanism of diesel engine |
CN107101813A (en) * | 2017-04-26 | 2017-08-29 | 河北工业大学 | A kind of frame-type circuit breaker mechanical breakdown degree assessment method based on vibration signal |
CN108537260A (en) * | 2018-03-29 | 2018-09-14 | 上海交通大学 | A kind of crane transmission axis method for diagnosing faults and system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11049011B2 (en) * | 2016-11-16 | 2021-06-29 | Indian Institute Of Technology Delhi | Neural network classifier |
-
2021
- 2021-08-30 CN CN202111001164.2A patent/CN114185321B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102539159A (en) * | 2010-12-24 | 2012-07-04 | 中国船舶研究设计中心 | Fault diagnosis method for valve mechanism of diesel engine |
CN107101813A (en) * | 2017-04-26 | 2017-08-29 | 河北工业大学 | A kind of frame-type circuit breaker mechanical breakdown degree assessment method based on vibration signal |
CN108537260A (en) * | 2018-03-29 | 2018-09-14 | 上海交通大学 | A kind of crane transmission axis method for diagnosing faults and system |
Non-Patent Citations (7)
Title |
---|
A hybrid intelligent multi-fault detection method for rotating machinery based on RSGWPT, KPCA and Twin SVM;Zhiwen Liu;《ISA Transactions》;第66卷;249-261 * |
EEMD Method and TWSVM for Fault Diagnosis of Roller Bearings;Guo Xiaoxuan;《PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON MANAGEMENT, COMPUTER AND EDUCATION INFORMATIZATION》;第25卷;102-106 * |
Research on Fault Diagnosis of Electric Control Valve Based on WPT-TWSVM;Zhaoya Li;《2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC)》;649-654 * |
基于SPSO优化Multiple Kernel-TWSVM的滚动轴承故障诊断;徐冠基;《振动.测试与诊断》;第39卷(第5期);973-979+1130 * |
基于孪生支持向量机的齿轮箱故障诊断;刘军科;《自动化技术与应用》;第39卷(第7期);5-10 * |
基于小波包能量分析及改进支持向量机的风机机械故障诊断;许小刚;《动 力 工 程 学 报》;第33卷(第8期);606-612 * |
基于支持向量机的风机齿轮箱故障诊断的研究;刘军科;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》(第1期);C042-454 * |
Also Published As
Publication number | Publication date |
---|---|
CN114185321A (en) | 2022-03-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107505133B (en) | The probability intelligent diagnosing method of rolling bearing fault based on adaptive M RVM | |
CN111914883B (en) | Spindle bearing state evaluation method and device based on deep fusion network | |
CN112257530B (en) | Rolling bearing fault diagnosis method based on blind signal separation and support vector machine | |
CN113642754B (en) | Complex industrial process fault prediction method based on RF noise reduction self-coding information reconstruction and time convolution network | |
CN110348150B (en) | Fault detection method based on correlation probability model | |
CN109710983B (en) | Diesel engine cylinder layered fault diagnosis method based on key performance indexes | |
CN111523081B (en) | Aeroengine fault diagnosis method based on enhanced gate control circulating neural network | |
CN111780800B (en) | Method and system for monitoring, isolating and reconstructing sensor fault | |
CN113537328B (en) | Rotary machine fault diagnosis method and device based on deep learning | |
CN108490923A (en) | The design method of small fault detection and positioning for electric traction system | |
CN110348468A (en) | A kind of bearing inferior health recognition methods of the strong reconstruct edge noise reduction autocoder of Method Using Relevance Vector Machine optimization | |
CN109298633A (en) | Chemical production process fault monitoring method based on adaptive piecemeal Non-negative Matrix Factorization | |
CN114048688A (en) | Method for predicting service life of bearing of wind power generator | |
CN114091525A (en) | Rolling bearing degradation trend prediction method | |
CN114462508A (en) | Power transformer health state assessment method based on multi-mode neural network | |
CN114185321B (en) | Electric actuator fault diagnosis method for improving multi-classification twin support vector machine | |
CN114861349A (en) | Rolling bearing RUL prediction method based on model migration and wiener process | |
CN113703422B (en) | Gas turbine pneumatic actuator fault diagnosis method based on feature analysis processing | |
Jianhui et al. | New fault diagnosis method for rolling bearing based on PCA | |
CN113409213A (en) | Plunger pump fault signal time-frequency graph noise reduction enhancement method and system | |
CN114818811B (en) | Aeroengine rolling bearing fault diagnosis method based on twin network metric learning | |
Xiao et al. | Fault state identification of rolling bearings based on deep transfer convolutional autoencoder and a new health indicator | |
CN116028865A (en) | Aeroengine fault diagnosis method based on feature amplification | |
CN116610940A (en) | Equipment fault diagnosis system based on wavelet transformation and deep neural network | |
Zhi-hong et al. | Sensor fault diagnosis based on wavelet analysis and LSTM neural network |
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 |