CN113052232A - Motor fault analysis method and system - Google Patents
Motor fault analysis method and system Download PDFInfo
- Publication number
- CN113052232A CN113052232A CN202110307733.XA CN202110307733A CN113052232A CN 113052232 A CN113052232 A CN 113052232A CN 202110307733 A CN202110307733 A CN 202110307733A CN 113052232 A CN113052232 A CN 113052232A
- Authority
- CN
- China
- Prior art keywords
- matrix
- sensor data
- data matrix
- virtual
- fault
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 55
- 239000011159 matrix material Substances 0.000 claims abstract description 170
- 238000003745 diagnosis Methods 0.000 claims abstract description 16
- 238000012847 principal component analysis method Methods 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims abstract description 13
- 238000005070 sampling Methods 0.000 claims abstract description 4
- 230000000295 complement effect Effects 0.000 claims abstract 2
- 238000006243 chemical reaction Methods 0.000 claims description 14
- 238000000034 method Methods 0.000 claims description 14
- 230000004927 fusion Effects 0.000 claims description 9
- 238000005315 distribution function Methods 0.000 claims description 8
- 230000001133 acceleration Effects 0.000 claims description 4
- 238000006073 displacement reaction Methods 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a motor fault analysis method, wherein m sensors are provided for detecting m parameters of a motor rotor, each sensor collects n groups of data of the motor rotor operation condition according to a certain sampling frequency to obtain an n x m actual sensor data matrix A, the actual sensor data matrix A is processed by a principal component analysis method to obtain an n x k virtual sensor data matrix B after dimension reduction, and the n x k virtual sensor data matrix B after dimension reduction is subjected to complementary analysis to obtain a fault type with the maximum probability. According to the invention, after the actual sensor data matrix A is subjected to dimension reduction processing, a fault diagnosis model is constructed based on the virtual sensor data matrix B for fault analysis, so that the calculated amount of the actual sensor data by the system is effectively reduced, the calculation speed of the system is improved, the motor fault analysis accuracy is improved, and the system operation cost is reduced. The invention also provides a motor fault analysis system.
Description
Technical Field
The invention relates to the technical field of fault diagnosis, in particular to a motor fault analysis method and system.
Background
Whether the motor operates normally or not directly influences the normal operation of an enterprise. If the motor quality is not high and faults occur frequently, the normal production operation of workshop production can be influenced. The motor rotor is a moving part in the motor and is acted by axial electromagnetic force, centrifugal force, thermal bending disturbance force and the like during operation, so that the motor rotor fault is a main fault during the operation of the motor.
When fault diagnosis is performed on a motor rotor, a rotating speed sensor, a vibration displacement sensor, a vibration acceleration sensor and other sensors are commonly mounted on a motor to detect the system state, so that data of various sensors are required to be fused when fault prediction and analysis are performed on the motor rotor.
The Chinese patent No. CN110261771B, No. 03/07/2020/03/s on granted date, and the patent name "a failure diagnosis method based on sensor complementation analysis" provides a failure diagnosis method based on sensor complementation analysis, which analyzes the complementarity among sensors aiming at different failure types according to the historical data of the detection result of each sensor, and constructs a multi-sensor data fusion model based on the complementation analysis result; and analyzing the motor rotor fault based on the constructed multi-sensor fusion model to obtain the motor rotor fault type.
The more types of sensors are added in the fault diagnosis method, the more the accuracy of the fault analysis of the motor rotor is improved; in actual production, in order to improve the accuracy of motor rotor fault analysis, corresponding sensor types need to be added, but when the system is used for data processing, high-dimensional matrix calculation and subsequent other calculation generate a large amount of calculation; the system slows down the data processing, increasing the cost of machine operation.
Therefore, a new fault analysis scheme is needed to be proposed to increase the speed of the system for data processing, and simultaneously increase the accuracy of the system for fault analysis of the motor rotor, and reduce the running cost of the machine.
Disclosure of Invention
In order to solve the problem that the speed of a system for processing data is changed slowly and the running cost of a machine is increased due to the fact that data of a plurality of sensors are fused when a motor rotor is analyzed in the prior art, the invention provides a motor fault analysis method, firstly, real sensor data is preprocessed by a principal component analysis method to obtain principal component components of the sensor data, namely a virtual sensor data matrix, the complementarity among the virtual sensors when different fault types are analyzed, and a multi-virtual sensor data fusion model is constructed on the basis of a complementarity analysis result; and analyzing the motor rotor fault based on the constructed multi-virtual-sensor fusion model to obtain the motor rotor fault type. The invention can effectively reduce the calculated amount of the system to the sample data of the sensor, improve the calculation speed of the system to the data, simultaneously improve the accuracy rate of the motor fault analysis and reduce the running cost of the system.
The invention discloses a motor fault analysis method according to the purpose of the invention, which comprises the following steps:
providing m sensors for detecting m parameters of the motor rotor, wherein each sensor collects n groups of data of the motor rotor operation condition according to a certain sampling frequency to obtain an n x m actual sensor data matrix A,
processing the actual sensor data matrix A by using a principal component analysis method to obtain a virtual sensor data matrix B of n x k after dimensionality reduction,
carrying out complementarity analysis on the n x k virtual sensor data matrix B after dimensionality reduction to obtain a fault type with the maximum probability;
wherein m, n and k are natural numbers, and m > k.
Preferably, the processing the actual sensor data matrix a by using a principal component analysis method to obtain a reduced-dimension n × k virtual sensor data matrix B includes:
standardizing the actual sensor data matrix A to obtain a standardized actual sensor data matrix Z of n × m;
calculating a covariance matrix D of the normalized n x m actual sensor data matrix Z from the normalized n x m actual sensor data matrix Z;
calculating to obtain an eigenvalue matrix and an eigenvector matrix of the covariance matrix D according to the covariance matrix D;
selecting eigenvectors corresponding to the largest k eigenvalues from the eigenvalue matrix of the covariance matrix D to obtain a conversion matrix; wherein said k is less than said m;
and performing matrix calculation on the actual sensor data matrix A of n x m according to the conversion matrix to obtain a virtual sensor data matrix B of n x k after dimensionality reduction.
Preferably, the actual sensor data matrix a is normalized to obtain a normalized n × m actual sensor data matrix Z; the method comprises the following steps:
calculating a mean value u of the actual sensor data matrix AjSum variance σj，
Using the formula:
wherein u isj、σjMean and variance of jth sensor data; obtaining a normalized n x m actual sensor data matrix Z ═ (Z)ij)n×m。
Preferably, the processing the actual sensor data matrix a by using a principal component analysis method to obtain a reduced-dimension n × k virtual sensor data matrix B includes:
singular value decomposition processing is carried out on the actual sensor data matrix A to obtain a characteristic value matrix and a characteristic vector matrix of the actual sensor data matrix A;
selecting eigenvectors corresponding to the largest k eigenvalues from the eigenvalue matrix of the actual sensor data matrix A to obtain a conversion matrix; wherein said k is less than said m;
and performing matrix calculation on the n x m actual sensor data matrix A according to the conversion matrix to obtain an n x k virtual sensor data matrix B after dimensionality reduction.
Preferably, the eigenvectors corresponding to the largest k eigenvalues are selected from the eigenvalue matrix of the covariance matrix D to obtain a conversion matrix; wherein said k is less than said m; the method comprises the following steps:
setting a main component accumulated contribution rate threshold value t according to a formula
Obtaining the k value, wherein t is a natural number.
Preferably, the performing complementarity analysis on the virtual sensor data matrix B of n × k after the dimensionality reduction to obtain a fault type with the maximum probability includes:
1) acquiring a fault diagnosis matrix of each virtual sensor according to the n x k virtual sensor data matrix B after dimensionality reduction; acquiring a preference relation matrix of each virtual sensor by using the fault diagnosis matrix of each virtual sensor;
2) acquiring the complementarity vector of the virtual sensors by the preference relation matrix of each virtual sensor;
3) for an unknown fault, obtaining a group of probability distribution according to the diagnosis result of each virtual sensor, and constructing a probability matrix; constructing a Basic Probability distribution function (BPA) according to the Probability matrix; obtaining a fused basic probability distribution function through a BPA fusion formula; and obtaining the fault type with the maximum probability according to the fused basic probability function distribution function.
Preferably, the virtual sensor complementarity vector is obtained by the preference relation matrix of each virtual sensor through a hierarchical analysis method.
The invention also provides a motor fault analysis method system, which comprises m sensors, a data dimension reduction module and a complementarity analysis module;
the m sensors are used for detecting m parameters of the motor rotor, each sensor collects n groups of data of the motor rotor operation condition according to a certain frequency to obtain an n x m actual sensor data matrix A,
the data dimension reduction module is used for processing the actual sensor data matrix A by using a principal component analysis method to obtain a virtual sensor data matrix B of n x k after dimension reduction, wherein k is smaller than m;
and the complementarity analysis module performs complementarity analysis on the n x k virtual sensor data matrix B after dimensionality reduction to obtain a fault type with the maximum probability, wherein m, n and k are natural numbers.
Preferably, the system further comprises a display screen, wherein the display screen is connected with the complementarity analyzing module and is used for displaying the fault type.
Preferably, the m sensors include a rotation speed sensor, a vibration displacement sensor, and a vibration acceleration sensor.
The invention has the beneficial effects that:
1. firstly, preprocessing real sensor data by using a principal component analysis method to obtain data of virtual sensors, analyzing complementarity among the virtual sensors aiming at different fault types, and constructing a multi-virtual sensor data fusion model based on a complementarity analysis result; and analyzing the motor rotor fault based on the constructed multi-virtual-sensor fusion model to obtain the motor rotor fault type. The invention can effectively reduce the calculation amount of the system to the sensor sample data, and the system can still keep higher calculation speed under the condition of more sensor types;
2. as more sensor types can be added for carrying out fault analysis and prediction on the motor rotor, the accuracy of fault analysis is effectively improved, and the running cost of the system is reduced.
Drawings
FIG. 1 is a flow chart of a motor fault analysis method of the present invention;
FIG. 2 is a block diagram of a motor fault analysis system according to the present invention;
Detailed Description
The present invention will be described in detail with reference to the specific embodiments shown in the drawings, which are not intended to limit the present invention, and structural, methodological, or functional changes made by those skilled in the art according to the specific embodiments are included in the scope of the present invention.
As shown in fig. 1, the present invention discloses a motor fault analysis method, which includes:
s1: providing m sensors for detecting m parameters of the motor rotor, and acquiring n groups of data of the motor rotor operation condition by each sensor according to a certain sampling frequency to obtain an n x m actual sensor data matrix A;
s2: processing the actual sensor data matrix A by using a principal component analysis method to obtain a virtual sensor data matrix B of n x k after dimensionality reduction; the principle of principal component analysis is to try to recombine original variables into a group of new several independent comprehensive variables, and simultaneously, according to actual needs, a few comprehensive variables can be taken out to reflect the information statistical method of the original variables as much as possible.
Specifically, firstly, the actual sensor data matrix a is standardized to obtain a standardized actual sensor data matrix Z of n × m; more specifically, the mean value u of the actual sensor data matrix A is calculatedjSum variance σj，
Using the formula:
wherein u isj、σjMean and variance of jth sensor data; obtaining a normalized n x m actual sensor data matrix Z ═ (Z)ij)n×m。
Calculating a covariance matrix D of the normalized n x m actual sensor data matrix Z according to the normalized n x m actual sensor data matrix Z;
calculating by using the covariance matrix D to obtain an eigenvalue matrix and an eigenvector matrix of the covariance matrix D;
selecting eigenvectors corresponding to the largest k eigenvalues from an eigenvalue matrix of the covariance matrix D to obtain a conversion matrix; wherein said k is less than said m; more specifically, by setting a principal component cumulative contribution rate threshold t, a k value is obtained by formula (1), and the specific formula (1) is as follows:
wherein λ isiIs the ith eigenvalue in the eigenvalue matrix of the covariance matrix D.
And performing matrix calculation on the actual sensor data matrix A of n x m according to a conversion matrix to obtain a virtual sensor data matrix B of n x k after dimensionality reduction.
For the actual sensor data matrix a processed by the principal component analysis method to obtain the virtual sensor data matrix B of n × k after dimensionality reduction, another specific embodiment includes:
singular value decomposition processing is carried out on the actual sensor data matrix A to obtain a characteristic value matrix and a characteristic vector matrix of the actual sensor data matrix A;
selecting eigenvectors corresponding to the largest k eigenvalues from an eigenvalue matrix of an actual sensor data matrix A to obtain a conversion matrix; wherein k is less than m;
and performing matrix calculation on the n x m actual sensor data matrix A according to the conversion matrix to obtain an n x k virtual sensor data matrix B after dimension reduction.
S3: carrying out complementarity analysis on the n x k virtual sensor data matrix B after dimensionality reduction to obtain a fault type with the maximum probability; wherein m, n and k are natural numbers, and m > k. In particular, the method comprises the following steps of,
1) acquiring a fault diagnosis matrix of each virtual sensor according to the n x k virtual sensor data matrix B after dimensionality reduction; acquiring a preference relation matrix of each virtual sensor by using the fault diagnosis matrix of each virtual sensor;
2) acquiring a virtual sensor complementarity vector by each virtual sensor preference relation matrix; in a preferred embodiment, the virtual sensor complementarity vector is obtained by a hierarchical analysis method through preference relation matrixes of the virtual sensors.
3) For an unknown fault, obtaining a group of probability distribution from the diagnosis result of each virtual sensor, and constructing a probability matrix; constructing a Basic Probability allocation function (BPA) according to the Probability matrix; obtaining a fused basic probability distribution function through a BPA fusion formula; and obtaining the fault type with the maximum probability according to the fused basic probability function distribution function.
The invention also discloses a motor fault analysis method system, which comprises m sensors 21, a data dimension reduction module 22 and a complementarity analysis module 23;
the m sensors 21 are used for detecting m parameters of the motor rotor, each sensor collects n groups of data of the motor rotor operation condition according to a certain frequency to obtain an n x m actual sensor data matrix A,
the data dimension reduction module 22 is used for processing the actual sensor data matrix A by using a principal component analysis method to obtain a virtual sensor data matrix B of n x k after dimension reduction, wherein k is smaller than m;
and the complementarity analysis module 23 is used for carrying out complementarity analysis on the virtual sensor data matrix B of n × k after dimensionality reduction to obtain a fault type with the maximum probability, wherein m, n and k are natural numbers.
In a specific embodiment, the motor fault analysis method system further includes a display screen connected to the complementarity analysis module for displaying fault types.
In one embodiment, the m sensors include a rotation speed sensor, a vibration displacement sensor and a vibration acceleration sensor.
It should be noted that, in the following description,
1. since the calculated transformation matrix is calculated by each existing sensor, the transformation matrix needs to be recalculated once the number of sensors is increased, decreased or the model of the motor is replaced.
2. The dimension reduction method provided by the invention needs a certain relation among the sensors, and the measured fault type can not be directly and correspondingly measured by a single sensor, so that the fault of the motor rotor detected by the method is not easy to be measured and diagnosed by the single sensor, such as fault types of unbalance, asymmetry, support seat looseness and the like.
Firstly, preprocessing real sensor data to obtain a virtual sensor data matrix, constructing a fault diagnosis model based on the virtual sensor data matrix, and predicting and analyzing the fault type of a motor rotor; the invention can effectively reduce the calculated amount of the system to the sample data of the sensor, improve the calculating speed of the system, simultaneously improve the accuracy rate of the motor fault analysis and reduce the running cost of the system.
Although the preferred embodiments of the present invention have been disclosed for illustrative purposes, those skilled in the art will appreciate that various modifications, additions and substitutions are possible, without departing from the scope and spirit of the invention as disclosed in the accompanying claims.
Claims (10)
1. A motor fault analysis method is characterized in that: comprises that
Providing m sensors for detecting m parameters of the motor rotor, wherein each sensor collects n groups of data of the motor rotor operation condition according to a certain sampling frequency to obtain an n x m actual sensor data matrix A,
processing the actual sensor data matrix A by using a principal component analysis method to obtain a virtual sensor data matrix B of n x k after dimensionality reduction,
carrying out complementarity analysis on the n x k virtual sensor data matrix B after dimensionality reduction to obtain a fault type with the maximum probability;
wherein m, n and k are natural numbers, and m > k.
2. The method according to claim 1, wherein the step of processing the actual sensor data matrix a by a principal component analysis method to obtain a reduced-dimension n × k virtual sensor data matrix B comprises:
standardizing the actual sensor data matrix A to obtain a standardized actual sensor data matrix Z of n × m;
calculating a covariance matrix D of the normalized n x m actual sensor data matrix Z from the normalized n x m actual sensor data matrix Z;
calculating to obtain an eigenvalue matrix and an eigenvector matrix of the covariance matrix D according to the covariance matrix D;
selecting eigenvectors corresponding to the largest k eigenvalues from the eigenvalue matrix of the covariance matrix D to obtain a conversion matrix; wherein said k is less than said m;
and performing matrix calculation on the actual sensor data matrix A of n x m according to the conversion matrix to obtain a virtual sensor data matrix B of n x k after dimensionality reduction.
3. The method according to claim 2, wherein the actual sensor data matrix a is normalized to obtain a normalized n × m actual sensor data matrix Z; the method comprises the following steps:
calculating a mean value u of the actual sensor data matrix AjSum variance σj，
Using the formula:
wherein u isj、σjMean and variance of jth sensor data; obtaining a normalized n x m actual sensor data matrix Z ═ (Z)ij)n×m。
4. The method according to claim 1, wherein the step of processing the actual sensor data matrix a by a principal component analysis method to obtain a reduced-dimension n × k virtual sensor data matrix B comprises:
singular value decomposition processing is carried out on the actual sensor data matrix A to obtain a characteristic value matrix and a characteristic vector matrix of the actual sensor data matrix A;
selecting eigenvectors corresponding to the largest k eigenvalues from the eigenvalue matrix of the actual sensor data matrix A to obtain a conversion matrix; wherein said k is less than said m;
and performing matrix calculation on the n x m actual sensor data matrix A according to the conversion matrix to obtain an n x k virtual sensor data matrix B after dimensionality reduction.
5. The motor fault analysis method according to claim 2, wherein eigenvectors corresponding to the largest k eigenvalues are selected from the eigenvalue matrix of the covariance matrix D to obtain a conversion matrix; wherein said k is less than said m; the method comprises the following steps:
setting a main component accumulated contribution rate threshold value t according to a formula
Obtaining the k value, wherein t is a natural number.
6. The method according to claim 1, wherein the performing a complementary analysis on the reduced n × k virtual sensor data matrix B to obtain a fault type with a maximum probability comprises:
1) acquiring a fault diagnosis matrix of each virtual sensor according to the n x k virtual sensor data matrix B after dimensionality reduction; acquiring a preference relation matrix of each virtual sensor by using the fault diagnosis matrix of each virtual sensor;
2) acquiring the complementarity vector of the virtual sensors by the preference relation matrix of each virtual sensor;
3) for an unknown fault, obtaining a group of probability distribution according to the diagnosis result of each virtual sensor, and constructing a probability matrix; constructing a Basic Probability distribution function (BPA) according to the Probability matrix; obtaining a fused basic probability distribution function through the virtual sensor complementarity vector and a BPA fusion formula; and obtaining the fault type with the maximum probability according to the fused basic probability function distribution function.
7. The motor fault analysis method of claim 6, wherein: and acquiring the complementarity vector of the virtual sensor by the preference relation matrix of each virtual sensor through a hierarchical analysis method.
8. A motor fault analysis method system is characterized in that: the system comprises m sensors, a data dimension reduction module and a complementarity analysis module;
the m sensors are used for detecting m parameters of the motor rotor, each sensor collects n groups of data of the motor rotor operation condition according to a certain frequency to obtain an n x m actual sensor data matrix A,
the data dimension reduction module is used for processing the actual sensor data matrix A by using a principal component analysis method to obtain a virtual sensor data matrix B of n x k after dimension reduction, wherein k is smaller than m;
and the complementarity analysis module performs complementarity analysis on the n x k virtual sensor data matrix B after dimensionality reduction to obtain a fault type with the maximum probability, wherein m, n and k are natural numbers.
9. The motor fault analysis method system according to claim 8, wherein: the device also comprises a display screen, wherein the display screen is connected with the complementarity analysis module and is used for displaying the fault type.
10. The motor fault analysis method system according to claim 8, wherein: the m sensors comprise a rotating speed sensor, a vibration displacement sensor and a vibration acceleration sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110307733.XA CN113052232A (en) | 2021-03-23 | 2021-03-23 | Motor fault analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110307733.XA CN113052232A (en) | 2021-03-23 | 2021-03-23 | Motor fault analysis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113052232A true CN113052232A (en) | 2021-06-29 |
Family
ID=76514414
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110307733.XA Pending CN113052232A (en) | 2021-03-23 | 2021-03-23 | Motor fault analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113052232A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114460466A (en) * | 2022-04-12 | 2022-05-10 | 杭州杰牌传动科技有限公司 | Virtual sensor equipment for transmission monitoring and monitoring method thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110243497A (en) * | 2019-05-29 | 2019-09-17 | 北京暖云科技有限公司 | A kind of sensor fault diagnosis method and system based on principal component analysis |
| CN110243590A (en) * | 2019-06-25 | 2019-09-17 | 中国民航大学 | A kind of Fault Diagnosis Approach For Rotor Systems learnt based on principal component analysis and width |
| CN110261771A (en) * | 2019-06-21 | 2019-09-20 | 西北工业大学 | A kind of method for diagnosing faults based on the analysis of sensor complementarity |
| CN110262458A (en) * | 2019-06-28 | 2019-09-20 | 佛山科学技术学院 | Fault characteristic information extracts the method and system with initial failure early warning |
-
2021
- 2021-03-23 CN CN202110307733.XA patent/CN113052232A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110243497A (en) * | 2019-05-29 | 2019-09-17 | 北京暖云科技有限公司 | A kind of sensor fault diagnosis method and system based on principal component analysis |
| CN110261771A (en) * | 2019-06-21 | 2019-09-20 | 西北工业大学 | A kind of method for diagnosing faults based on the analysis of sensor complementarity |
| CN110243590A (en) * | 2019-06-25 | 2019-09-17 | 中国民航大学 | A kind of Fault Diagnosis Approach For Rotor Systems learnt based on principal component analysis and width |
| CN110262458A (en) * | 2019-06-28 | 2019-09-20 | 佛山科学技术学院 | Fault characteristic information extracts the method and system with initial failure early warning |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114460466A (en) * | 2022-04-12 | 2022-05-10 | 杭州杰牌传动科技有限公司 | Virtual sensor equipment for transmission monitoring and monitoring method thereof |
| CN114460466B (en) * | 2022-04-12 | 2022-08-05 | 杭州杰牌传动科技有限公司 | Virtual sensor equipment for transmission monitoring and monitoring method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111914883B (en) | Spindle bearing state evaluation method and device based on deep fusion network | |
| US7539597B2 (en) | Diagnostic systems and methods for predictive condition monitoring | |
| AU2002246994B2 (en) | Diagnostic systems and methods for predictive condition monitoring | |
| Kwan et al. | A novel approach to fault diagnostics and prognostics | |
| JP6828807B2 (en) | Data analysis device, data analysis method and data analysis program | |
| AU2002246994A1 (en) | Diagnostic systems and methods for predictive condition monitoring | |
| CN111474475B (en) | Motor fault diagnosis system and method | |
| CN111538311B (en) | Flexible multi-state self-adaptive early warning method and device for mechanical equipment based on data mining | |
| CN111665066B (en) | Equipment fault self-adaptive upper and lower early warning boundary generation method based on convolutional neural network | |
| US12007745B2 (en) | Apparatus for predicting equipment damage | |
| CN110261771B (en) | Fault diagnosis method based on sensor complementarity analysis | |
| CN113579851B (en) | Non-stationary drilling process monitoring method based on adaptive segmented PCA | |
| CN111964909A (en) | Rolling bearing operation state detection method, fault diagnosis method and system | |
| CN118094452B (en) | Card sending motor rotating speed abnormality detection method based on full-flow monitoring | |
| US7243265B1 (en) | Nearest neighbor approach for improved training of real-time health monitors for data processing systems | |
| CN113052232A (en) | Motor fault analysis method and system | |
| CN111622815A (en) | Blade crack online measurement method based on blade tip timing and naive Bayes optimization | |
| CN111474476B (en) | Motor fault prediction method | |
| CN113591984A (en) | Method and device for detecting equipment operation event, electronic equipment and storage medium | |
| CN115659271A (en) | Sensor abnormality detection method, model training method, system, device, and medium | |
| CN118518311B (en) | Impact detection equipment and method for hydrogen fuel cell | |
| CN118561118B (en) | Elevator running state judging method, system, medium and electronic equipment | |
| Alghassi | Generalized Anomaly Detection Algorithm Based on Time Series Statistical Features | |
| CN118861728A (en) | State evaluation method of mine electromechanical equipment based on data analysis | |
| CN116242465A (en) | Dynamic vehicle weighing method and 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210629 |