CN115508703A - Multi-source information fusion motor fault diagnosis method and system - Google Patents
Multi-source information fusion motor fault diagnosis method and system Download PDFInfo
- Publication number
- CN115508703A CN115508703A CN202211136132.8A CN202211136132A CN115508703A CN 115508703 A CN115508703 A CN 115508703A CN 202211136132 A CN202211136132 A CN 202211136132A CN 115508703 A CN115508703 A CN 115508703A
- Authority
- CN
- China
- Prior art keywords
- variable
- motor
- matrix
- total
- variables
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000003745 diagnosis Methods 0.000 title claims abstract description 34
- 230000004927 fusion Effects 0.000 title claims abstract description 28
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 239000011159 matrix material Substances 0.000 claims description 69
- 238000012360 testing method Methods 0.000 claims description 24
- 238000006073 displacement reaction Methods 0.000 claims description 21
- 230000036760 body temperature Effects 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 description 11
- 238000012847 principal component analysis method Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000000513 principal component analysis Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 238000009776 industrial production Methods 0.000 description 3
- 238000004804 winding Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/34—Testing dynamo-electric machines
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- 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
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Tests Of Circuit Breakers, Generators, And Electric Motors (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a motor fault diagnosis method and system based on multi-source information fusion, and relates to the field of motor fault diagnosis, wherein the method comprises the following steps: acquiring current operation data of each variable of a motor; preprocessing and standardizing current operation data of all variables of the motor to obtain processed data; performing data fusion on the processed data to obtain the statistics of the total variable; judging whether the statistic of the total variable exceeds a control limit or not; if so, determining the contribution rate of each variable to the statistic of the total variable under the current running state of the motor; aiming at any variable, judging whether the contribution rate of the variable in the current running state of the motor is greater than the contribution rate of the variable in the normal running state of the motor; and if so, determining that the part corresponding to the variable has a fault. The invention effectively improves the fault identification accuracy.
Description
Technical Field
The invention relates to the field of motor fault diagnosis, in particular to a motor fault diagnosis method and system based on multi-source information fusion.
Background
In industrial production, there is a high demand for the safety of motor equipment. Unplanned downtime of electrical equipment can have a significant impact on industrial production, not only can result in equipment outages and lost productivity, but can also pose a serious threat to employee life and enterprise assets. Therefore, it is necessary to conduct intensive research on the failure diagnosis of the motor as a reactive maintenance means for the motor device.
The type of fault of an ac motor depends on the physical structure of the motor and the operating environment of the motor, and almost all types of faults develop according to a fixed tendency or mode of failure, i.e., from a slight initial sign of failure to complete failure of the equipment or components, resulting in equipment or system shutdown. As with most devices, motor failure can occur in its infancy with some specific signal or characteristic change. With the increasing complexity of equipment systems, the presentation of equipment conditions is more difficult to be transparent, and some fault information of the equipment is more difficult to be visually detected. Therefore, the conventional analysis and diagnosis method has the problem of low accuracy of fault identification.
Disclosure of Invention
The invention aims to provide a motor fault diagnosis method and system based on multi-source information fusion.
In order to achieve the purpose, the invention provides the following scheme:
a multi-source information fused motor fault diagnosis method comprises the following steps:
obtaining current operation data of each variable of the motor, wherein the variable comprises the following steps: current variable, voltage variable, rotating speed variable, displacement variable, vibration variable and body temperature variable;
preprocessing and standardizing current operation data of all variables of the motor to obtain processed data;
performing data fusion on the processed data to obtain the statistics of the total variable;
judging whether the statistic of the total variable exceeds a control limit or not to obtain a first judgment result; the control limit is related to the mathematical expectation and variance of normal statistics, and the normal statistics are statistics of total variables obtained when the motor normally runs;
if the first judgment result is yes, determining the contribution rate of each variable to the statistic of the total variable under the current running state of the motor;
aiming at any variable, judging whether the contribution rate of the variable in the current running state of the motor is greater than that of the variable in the normal running state of the motor or not to obtain a second judgment result;
and if the second judgment result is yes, determining that the part corresponding to the variable has a fault.
Optionally, the calculation formula of the statistics of the total variable is as follows:
wherein SPE is the statistic of total variable, n is the total number of variables, x j Is the jth variable, x new In the case of a new variable, the value of,
is a test data matrix which is a matrix consisting of characteristic parameters obtained after pretreatment of current, voltage, rotor rotation speed, rotating shaft displacement, vibration and body temperature,
for transposing the test data matrix, α is the first inherent matrix, α T Is a transpose of the first inherent matrix.
Optionally, the calculation formula of the statistics of the total variable is as follows:
wherein, T 2 Is the statistic of the total variable, tr is the trace of the matrix,
is a test data matrix which is a matrix consisting of characteristic parameters obtained after pretreatment of current, voltage, rotor rotation speed, rotating shaft displacement, vibration and body temperature,
for transposing the test data matrix, α is the first inherent matrix, α T Is the transpose of the first eigen matrix and lambda is the second eigen matrix.
Optionally, the calculation formula of the control limit is as follows:
A＝μ+3σ
wherein A is a control limit, mu is a mathematical expectation corresponding to the statistic of the total variable obtained when the motor normally operates, and sigma is a variance corresponding to the statistic of the total variable obtained when the motor normally operates.
Optionally, the calculation formula of the contribution ratio is as follows:
wherein, C SPE,new，i The contribution rate of the ith parameter to the statistic SPE of the total variable is shown, n is the total number of the variables, x j Is the jth variable, x new In the case of a new variable, the value of,
is a test data matrix which is a matrix consisting of characteristic parameters obtained after preprocessing of current, voltage, rotor rotating speed, rotating shaft displacement, vibration and body temperature,
for transposing the test data matrix, α is the first inherent matrix, α T As a transpose of the first inherent matrix, v i Is the ith variable.
Optionally, the calculation formula of the contribution ratio is as follows:
wherein,
statistic T of total variable for ith parameter 2 V. contribution of i For the ith variable, tr is the trace of the matrix,
is a test data matrix which is a matrix consisting of characteristic parameters obtained after preprocessing of current, voltage, rotor rotating speed, rotating shaft displacement, vibration and body temperature,
for transposing the test data matrix, α T Is the transpose of the first eigen matrix and λ is the second eigen matrix.
The invention also provides a multi-source information fusion motor fault diagnosis system, which comprises:
the data acquisition unit is used for acquiring current operation data of each variable of the motor, wherein the variable comprises: current variable, voltage variable, rotating speed variable, displacement variable, vibration variable and body temperature variable;
the data processing unit is used for preprocessing and standardizing the current operation data of each variable of the motor to obtain processed data;
the data fusion unit is used for carrying out data fusion on the processed data to obtain the statistics of the total variable;
the first judgment unit is used for judging whether the statistic of the total variable exceeds the control limit or not to obtain a first judgment result; the control limit is related to the mathematical expectation and variance of normal statistics, and the normal statistics are statistics of total variables obtained when the motor normally runs;
the contribution rate determining unit is used for determining the contribution rate of each variable to the statistics of the total variable in the current running state of the motor when the first judgment result is yes;
the second judgment unit is used for judging whether the contribution rate of the variable in the current running state of the motor is greater than the contribution rate of the variable in the normal running state of the motor or not according to any variable to obtain a second judgment result;
and a failure determination unit, configured to determine that a failure occurs at a location corresponding to the variable when the second determination result is yes.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a multi-source information fusion motor fault diagnosis method and system, wherein the method comprises the following steps: acquiring current operation data of each variable of the motor, wherein the variable comprises the following steps: current variable, voltage variable, rotating speed variable, displacement variable, vibration variable and body temperature variable; preprocessing and standardizing current operation data of all variables of the motor to obtain processed data; performing data fusion on the processed data to obtain the statistic of the total variable; judging whether the statistic of the total variable exceeds a control limit or not to obtain a first judgment result; the control limit is related to the mathematical expectation and the variance of normal statistics, and the normal statistics are statistics of total variables obtained when the motor operates normally; if the first judgment result is yes, determining the contribution rate of each variable to the statistics of the total variable in the current running state of the motor; aiming at any variable, judging whether the contribution rate of the variable in the current running state of the motor is greater than the contribution rate of the variable in the normal running state of the motor to obtain a second judgment result; and if the second judgment result is yes, determining that the part corresponding to the variable has a fault. According to the method, the contribution rate of all variables to the total variable statistic is obtained for fault identification and fault diagnosis, so that data reconstruction and iterative approximate calculation in the traditional principal component analysis method are avoided, and the fault identification accuracy rate is effectively improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart of a multi-source information fusion motor fault diagnosis method provided in embodiment 1 of the present invention;
fig. 2 is a block diagram of a multi-source information fusion motor fault diagnosis system provided in embodiment 2 of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
The requirements of the current industry on the working condition, the stop time and the like of the motor are higher and higher, the traditional fault prediction method cannot completely meet the requirements of the current industrial production, and an effective method for predicting the fault of the motor in the current production environment must be researched.
With the continuous development of computer technology, the expert system theory is gradually perfected, the artificial intelligence algorithms such as machine learning and deep learning become more and more mature, and the complex equipment system diagnosis and intelligent maintenance method also gradually fuses the signal processing technology and the theoretical methods such as a feature extraction method, artificial intelligence algorithm modeling and knowledge modeling.
The motor fault prediction and health management mainly comprises the steps of collecting various data of a motor system by using various sensors, monitoring the state of the motor, diagnosing the motor fault, predicting the service life of the motor and managing the motor system by means of intelligent algorithms such as signal processing, machine learning, expert systems and the like.
In most industrial system PHM applications, it is difficult to build mathematical or physical models of complex industrial equipment or systems, and the parameters of the fault diagnosis model are complex. However, since the state information and the failure information of the device are hidden in the sensor history data at each stage of the operation and maintenance of the device or the system, these data become a key point for grasping the system state. The PHM collects characteristic indexes and parameters related to motor attributes based on a sensor technology, associates equipment information, operation records, environmental information and historical states of the motor, performs detection, analysis and prediction by means of an artificial intelligence algorithm and a model, and provides the current running state, whether a fault occurs, the fault type, the residual service life and the like of a motor system, so that decision information is provided for maintenance and repair of the motor.
Among them, the PHM (fault prediction and Health Management) uses various data generated in the industrial system, and implements systematic engineering for detecting, predicting and managing the Health status of a complex industrial system by signal processing, data analysis and other operation means. The PHM technology can maintain the safety and reliability of mechanical equipment, saves maintenance and guarantee cost, is proposed for meeting the requirements of autonomous guarantee and autonomous diagnosis, and is the upgrading development of state-based maintenance CBM (condition based maintenance). The method emphasizes state perception in asset equipment management, monitors equipment health condition and frequent fault areas and periods, and predicts the occurrence of faults through data monitoring and analysis, thereby greatly improving operation and maintenance efficiency.
In the field of maintenance of industrial equipment, a method of diagnosing a fault by Principal Component Analysis (PCA) is widely used. By the fault diagnosis method, when a fault is detected, fault parameters causing the fault can be quickly found out, then the fault reason is analyzed, the part or the subsystem where the fault is located is quickly positioned, and the time for removing the system fault is greatly shortened. The method is a linear mapping algorithm and is a linear space transformation method based on a linear algebra theory. Therefore, the principal component analysis method is often not effective when applied to the detection of device faults with nonlinear characteristics.
Another fault diagnosis method has certain advantages over Principal Component Analysis (KPCA) in nonlinear fault detection, in that a Kernel Principal Component Analysis (KPCA) method is used for fault diagnosis. The method maps the vector X to be analyzed into a high-dimensional space F through nonlinear mapping to obtain mapping data, and then performs linear analysis on the mapping data in the high-dimensional space to obtain the nonlinear component of the vector X to be analyzed. However, the kernel principal component analysis method has a drawback that it is difficult to identify a potential failure variable in a nonlinear situation, and the use of the data reconstruction method for the kernel principal component analysis method has disadvantages such as a large amount of calculation, a large reconstruction error, and low accuracy in multivariate diagnosis.
According to the technical problem, the invention provides the motor fault diagnosis method and system with multi-source information fusion, dependence on a motor physical model is reduced, the motor state is identified through key performance indexes of the motor, data reconstruction and iterative approximate calculation in the traditional principal component analysis method are avoided, and the fault identification accuracy is effectively improved.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Example 1:
referring to fig. 1, the present invention provides a multi-source information fusion motor fault diagnosis method, including the following steps:
s1: obtaining current operation data of each variable of the motor, wherein the variable comprises the following steps: current variable, voltage variable, rotating speed variable, displacement variable, vibration variable and body temperature variable;
s2: preprocessing and standardizing current operation data of all variables of the motor to obtain processed data;
it should be noted that, the present invention first preprocesses and standardizes data from different sources to achieve the objective of multivariate data fusion. The method comprises the steps of obtaining electric parameter values such as current and voltage, mechanical parameter data such as rotor rotating speed, rotating shaft displacement and vibration, body temperature and the like through different types of sensors such as a current sensor, a voltage sensor, a rotating speed sensor, a displacement sensor, a vibration sensor and a temperature sensor, simply calculating original data of a motor by using multi-source state information data according to physical knowledge of the motor to obtain performance indexes of different angles, and accordingly identifying the current operating state of the motor, wherein the motor parameter performance index obtaining method and the data standardization and preprocessing mode are shown in tables 1-4.
TABLE 1 Motor Electrical parameter Performance index
TABLE 2 electric parameter and motor fault correspondence table
| Stator winding short/open phase | A1、A3、A6、A7、A9 |
| Stator winding locked rotor | A1、A5 |
| Phase failure of stator winding | A2、A4、A6 |
| Rotor broken bar | A10 |
| Rotor mass imbalance | A11 |
| Misalignment of rotor | A12、A13 |
| Air gap static eccentricity | A12、A14 |
| Air gap dynamic eccentricity | A12、A15 |
| Capacitance/cable isolation problem | A1、A3、A5 |
| Motor linker, terminal loosening and contact failure | A3、A4、A8 |
| Bearing failure of motor | A16、A17、A18、A19 |
| Oil film whirl | A20 |
| Other faults | A3、A4、A6、A7 |
TABLE 3 Performance index of mechanical parameters of motor
TABLE 4 Motor mechanical parameter and motor fault correspondence table
| Rotor mass imbalance | B5 |
| Misalignment of rotor | B7 |
| Typical loosening, foundation loosening | B1、B2、B6 |
| Loosening caused by rocking motion or structural fracture and bearing base fracture | B1、B2、B7 |
| Looseness caused by loose bearings or improper fit between parts | B1、B2、B8、B9 |
| Belt/transmission failure | B5、B7 |
| Bearing failure of motor | B1、B2、B10、B11、B12、B13 |
| Gear failure | B1、B2、B5、B14 |
| Other mechanical faults | B1、B2、B3、B4、B5 |
S3: performing data fusion on the processed data to obtain the statistic of the total variable;
s4: judging whether the statistic of the total variable exceeds a control limit or not to obtain a first judgment result; the control limit is related to the mathematical expectation and variance of normal statistics, and the normal statistics are statistics obtained when the motor normally runs;
s5: if the first judgment result is yes, determining the contribution rate of each variable to the statistics of the total variable in the current running state of the motor;
s6: aiming at any variable, judging whether the contribution rate of the variable in the current running state of the motor is greater than that of the variable in the normal running state of the motor or not to obtain a second judgment result;
s7: and if the second judgment result is yes, determining that the part corresponding to the variable has a fault.
As a possible implementation, the calculation formula of the statistic of the total variable is as follows:
wherein SPE is the statistic of total variable, n is the total number of variables, x j Is the jth variable, x new In the case of a new variable, the value of,
is a test data matrix which is preprocessed by current, voltage, rotor speed, rotary shaft displacement, vibration and body temperatureThe matrix composed of the characteristic parameters obtained later,
for transposing the test data matrix, α is the first inherent matrix, α T Is a transpose of the first inherent matrix.
As another possible implementation, the calculation formula of the statistics of the total variables is as follows:
wherein, T 2 Is the statistic of the total variable, tr is the trace of the matrix,
is a test data matrix which is a matrix consisting of characteristic parameters obtained after preprocessing of current, voltage, rotor rotating speed, rotating shaft displacement, vibration and body temperature,
for transposing the test data matrix, α is the first inherent matrix, α T Is the transpose of the first eigen matrix and λ is the second eigen matrix.
When the motor works normally, the statistics SPE of the total variable or the statistics T of the total variable under the normal running state are used 2 Acquisition calculations are performed to obtain control limits. Wherein, the statistic SPE of the total variable or the statistic T of the total variable 2 Subject to a normal distribution, the control limit can be calculated from this: a = μ +3 σ; wherein A is a control limit, mu is a mathematical expectation corresponding to the statistic of the total variable obtained when the motor normally operates, and sigma is a variance corresponding to the statistic of the total variable obtained when the motor normally operates.
In the running process of the motor, when the collected statistics of the total variables exceed the control limit, the motor is indicated to be in fault, and a characteristic extraction stage is started.
In the feature extraction stage, the ratio of each variable to the total variable is calculatedStatistic SPE or statistic T of total variable 2 The contribution ratio of (c).
The contribution rate of the ith variable to the statistic SPE of the total variable is as follows:
wherein, C SPE,new，i The contribution rate of the ith parameter to the statistic SPE of the total variable is shown, n is the total number of the variables, x j Is the jth variable, x new Is a new variable, and is a new variable,
is a test data matrix which is a matrix consisting of characteristic parameters obtained after pretreatment of current, voltage, rotor rotation speed, rotating shaft displacement, vibration and body temperature,
for transposing the test data matrix, α is the first inherent matrix, α T Is a transpose of the first inherent matrix, v i Is the ith variable.
Statistic T of ith variable to total variable 2 The contribution rate of (c) is:
wherein,
statistic T of total variable for ith parameter 2 Contribution ratio of v i For the ith variable, tr is the trace of the matrix,
is a test data matrix which is a matrix consisting of characteristic parameters obtained after pretreatment of current, voltage, rotor rotation speed, rotating shaft displacement, vibration and body temperature,
for transposing the test data matrix, α T Is the transpose of the first eigen matrix and lambda is the second eigen matrix.
It should be noted that, in the stages of state detection, fault diagnosis and maintenance decision, the statistic SPE of the total variable or the statistic T of the total variable is calculated 2 The contribution rate of the motor is identified, wherein the variable with the contribution rate larger than the contribution rate under the normal operation condition is a fault variable, and the fault corresponding to the change amount of the motor is shown. Statistic SPE for total variable and statistic T for total variable 2 The variable with the largest contribution rate must be the same variable because only the fault variable leads to the statistic SPE of the total variable or the statistic T of the total variable 2 The control limit is exceeded. Therefore, the fault type and the fault occurrence position can be obtained, and maintenance decisions can be provided for users in time.
In conclusion, the method carries out fault identification and fault diagnosis by calculating the contribution rate of all variables to the total variable statistic, avoids data reconstruction and iterative approximate calculation in the traditional principal component analysis method, and effectively improves the fault identification accuracy.
Example 2:
referring to fig. 2, the present invention provides a multi-source information fused motor fault diagnosis system, which includes:
the data acquisition unit 1 is used for acquiring current operation data of each variable of the motor, wherein the variable comprises: current variables, voltage variables, rotating speed variables, displacement variables, vibration variables and machine body temperature variables;
the data processing unit 2 is used for preprocessing current operation data of all variables of the motor and standardizing the data to obtain processed data;
the data fusion unit 3 is used for carrying out data fusion on the processed data to obtain the statistic of the total variable;
the first judging unit 4 is used for judging whether the statistic of the total variable exceeds the control limit to obtain a first judging result; the control limit is related to the mathematical expectation and variance of normal statistics, and the normal statistics are statistics of total variables obtained when the motor normally runs;
the contribution rate determining unit 5 is configured to determine, when the first determination result is yes, a contribution rate of each variable to a statistic of the total variable in the current operation state of the motor;
the second judgment unit 6 is used for judging whether the contribution rate of the variable in the current running state of the motor is greater than the contribution rate of the variable in the normal running state of the motor or not according to any variable to obtain a second judgment result;
and a failure determination unit 7, configured to determine that a failure occurs in a location corresponding to the variable when the second determination result is yes.
In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the description of the method part.
The principle and the embodiment of the present invention are explained by applying specific examples, and the above description of the embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the foregoing, the description is not to be taken in a limiting sense.
Claims (7)
1. A multi-source information fusion motor fault diagnosis method is characterized by comprising the following steps:
obtaining current operation data of each variable of the motor, wherein the variable comprises the following steps: current variables, voltage variables, rotating speed variables, displacement variables, vibration variables and machine body temperature variables;
preprocessing and standardizing current operation data of all variables of the motor to obtain processed data;
performing data fusion on the processed data to obtain the statistics of the total variable;
judging whether the statistic of the total variable exceeds a control limit or not to obtain a first judgment result; the control limit is related to the mathematical expectation and variance of normal statistics, and the normal statistics are statistics of total variables obtained when the motor normally runs;
if the first judgment result is yes, determining the contribution rate of each variable to the statistic of the total variable under the current running state of the motor;
aiming at any variable, judging whether the contribution rate of the variable in the current running state of the motor is greater than the contribution rate of the variable in the normal running state of the motor to obtain a second judgment result;
and if the second judgment result is yes, determining that the part corresponding to the variable has a fault.
2. The multi-source information fusion motor fault diagnosis method according to claim 1, characterized in that the calculation formula of the statistics of the total variables is as follows:
wherein SPE is the statistic of total variable, n is the total number of variables, x j Is the jth variable, x new K is a test data matrix which is a matrix consisting of characteristic parameters obtained after pretreatment of current, voltage, rotor rotating speed, rotating shaft displacement, vibration and body temperature,
for transposing the test data matrix, α is the first inherent matrix, α T Is a transpose of the first inherent matrix.
3. The multi-source information fusion motor fault diagnosis method according to claim 1, characterized in that the calculation formula of the statistics of the total variables is as follows:
wherein, T 2 Is the statistic of the total variable, tr is the trace of the matrix,
is a test data matrix which is a matrix consisting of characteristic parameters obtained after preprocessing of current, voltage, rotor rotating speed, rotating shaft displacement, vibration and body temperature,
for transposing the test data matrix, α is the first inherent matrix, α T Is the transpose of the first eigen matrix and λ is the second eigen matrix.
4. The multi-source information fusion motor fault diagnosis method according to claim 1, wherein the calculation formula of the control limit is as follows:
A＝μ+3σ
wherein A is a control limit, mu is a mathematical expectation corresponding to the statistic of the total variable obtained when the motor normally operates, and sigma is a variance corresponding to the statistic of the total variable obtained when the motor normally operates.
5. The multi-source information-fused motor fault diagnosis method according to claim 2, wherein the contribution ratio is calculated by the following formula:
wherein, C SPE,new，i The contribution rate of the ith parameter to the statistic SPE of the total variable is shown, n is the total number of the variables, x j Is the jth variable, x new Is a new variable, and is a new variable,
is a test data matrix which is a matrix consisting of characteristic parameters obtained after preprocessing of current, voltage, rotor rotating speed, rotating shaft displacement, vibration and body temperature,
for transposing the test data matrix, α is the first inherent matrix, α T As a transpose of the first inherent matrix, v i Is the ith variable.
6. The multi-source information-fused motor fault diagnosis method according to claim 3, wherein the contribution ratio is calculated by the following formula:
wherein,
statistic T of total variable for ith parameter 2 V. contribution of i For the ith variable, tr is the trace of the matrix,
is a test data matrix which is a matrix consisting of characteristic parameters obtained after pretreatment of current, voltage, rotor rotation speed, rotating shaft displacement, vibration and body temperature,
for transposing the test data matrix, α T Is the transpose of the first eigen matrix and lambda is the second eigen matrix.
7. A multi-source information fusion motor fault diagnosis system is characterized by comprising:
the data acquisition unit is used for acquiring current operation data of each variable of the motor, wherein the variable comprises: current variable, voltage variable, rotating speed variable, displacement variable, vibration variable and body temperature variable;
the data processing unit is used for preprocessing current operation data of all variables of the motor and standardizing the data to obtain processed data;
the data fusion unit is used for carrying out data fusion on the processed data to obtain the statistic of the total variable;
the first judgment unit is used for judging whether the statistic of the total variable exceeds the control limit or not to obtain a first judgment result; the control limit is related to the mathematical expectation and variance of normal statistics, and the normal statistics are statistics of total variables obtained when the motor normally runs;
the contribution rate determining unit is used for determining the contribution rate of each variable to the statistic of the total variable in the current running state of the motor when the first judgment result is yes;
the second judgment unit is used for judging whether the contribution rate of the variable in the current running state of the motor is greater than the contribution rate of the variable in the normal running state of the motor or not according to any variable to obtain a second judgment result;
and a failure determining unit, configured to determine that a failure occurs at a location corresponding to the variable when the second determination result is yes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211136132.8A CN115508703A (en) | 2022-09-19 | 2022-09-19 | Multi-source information fusion motor fault diagnosis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211136132.8A CN115508703A (en) | 2022-09-19 | 2022-09-19 | Multi-source information fusion motor fault diagnosis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115508703A true CN115508703A (en) | 2022-12-23 |
Family
ID=84503850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211136132.8A Pending CN115508703A (en) | 2022-09-19 | 2022-09-19 | Multi-source information fusion motor fault diagnosis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115508703A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116413595A (en) * | 2023-01-30 | 2023-07-11 | 中国人民解放军陆军装甲兵学院 | Method and device for detecting eccentric rotor of synchronous reluctance motor based on vibration test |
| CN117233602A (en) * | 2023-11-07 | 2023-12-15 | 迈为技术(珠海)有限公司 | Aging detection method of crystal-piercing machine and crystal-piercing machine |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1217056A (en) * | 1996-02-29 | 1999-05-19 | 监控技术有限公司 | Multiple sensor apparatus and method for monitoring turbomachine |
| CN203224222U (en) * | 2013-04-08 | 2013-10-02 | 成都赛腾自动化工程有限公司 | Multi-directional monitoring device for displacement of high speed motor shaft |
| CN106568565A (en) * | 2016-10-28 | 2017-04-19 | 山东大学 | Rotating machine vibration on-line monitoring device and rotating machine vibration on-line monitoring method |
| CN107192948A (en) * | 2017-06-08 | 2017-09-22 | 安徽省化工设计院 | A kind of low-tension motor multi-parameter monitoring devices and its running situation evaluation method |
| CN109861250A (en) * | 2019-03-21 | 2019-06-07 | 东南大学 | A kind of oscillation of power type identification method based on electric system multidimensional characteristic |
| CN111325159A (en) * | 2020-02-25 | 2020-06-23 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Fault diagnosis method and device, computer equipment and storage medium |
| CN112200104A (en) * | 2020-10-15 | 2021-01-08 | 重庆科技学院 | Chemical engineering fault diagnosis method based on novel Bayesian framework for enhanced principal component analysis |
| CN112434558A (en) * | 2020-10-23 | 2021-03-02 | 北京航空航天大学 | Adaptive fault monitoring method based on +/-x sigma boundary interval model |
| CN113420691A (en) * | 2021-06-30 | 2021-09-21 | 昆明理工大学 | Mixed domain characteristic bearing fault diagnosis method based on Pearson correlation coefficient |
-
2022
- 2022-09-19 CN CN202211136132.8A patent/CN115508703A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1217056A (en) * | 1996-02-29 | 1999-05-19 | 监控技术有限公司 | Multiple sensor apparatus and method for monitoring turbomachine |
| CN203224222U (en) * | 2013-04-08 | 2013-10-02 | 成都赛腾自动化工程有限公司 | Multi-directional monitoring device for displacement of high speed motor shaft |
| CN106568565A (en) * | 2016-10-28 | 2017-04-19 | 山东大学 | Rotating machine vibration on-line monitoring device and rotating machine vibration on-line monitoring method |
| CN107192948A (en) * | 2017-06-08 | 2017-09-22 | 安徽省化工设计院 | A kind of low-tension motor multi-parameter monitoring devices and its running situation evaluation method |
| CN109861250A (en) * | 2019-03-21 | 2019-06-07 | 东南大学 | A kind of oscillation of power type identification method based on electric system multidimensional characteristic |
| CN111325159A (en) * | 2020-02-25 | 2020-06-23 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Fault diagnosis method and device, computer equipment and storage medium |
| CN112200104A (en) * | 2020-10-15 | 2021-01-08 | 重庆科技学院 | Chemical engineering fault diagnosis method based on novel Bayesian framework for enhanced principal component analysis |
| CN112434558A (en) * | 2020-10-23 | 2021-03-02 | 北京航空航天大学 | Adaptive fault monitoring method based on +/-x sigma boundary interval model |
| CN113420691A (en) * | 2021-06-30 | 2021-09-21 | 昆明理工大学 | Mixed domain characteristic bearing fault diagnosis method based on Pearson correlation coefficient |
Non-Patent Citations (1)
| Title |
|---|
| 刘闯: "《数据驱动的电机故障诊断与预测系统的设计与实现》", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, pages 10 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116413595A (en) * | 2023-01-30 | 2023-07-11 | 中国人民解放军陆军装甲兵学院 | Method and device for detecting eccentric rotor of synchronous reluctance motor based on vibration test |
| CN117233602A (en) * | 2023-11-07 | 2023-12-15 | 迈为技术(珠海)有限公司 | Aging detection method of crystal-piercing machine and crystal-piercing machine |
| CN117233602B (en) * | 2023-11-07 | 2024-01-30 | 迈为技术(珠海)有限公司 | Aging detection method of crystal-piercing machine and crystal-piercing machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Paolanti et al. | Machine learning approach for predictive maintenance in industry 4.0 | |
| Wang et al. | A novel statistical time-frequency analysis for rotating machine condition monitoring | |
| CN115508703A (en) | Multi-source information fusion motor fault diagnosis method and system | |
| Yang | An intelligent condition-based maintenance platform for rotating machinery | |
| Zhang et al. | SCADA-data-based wind turbine fault detection: A dynamic model sensor method | |
| Soylemezoglu et al. | Mahalanobis-Taguchi system as a multi-sensor based decision making prognostics tool for centrifugal pump failures | |
| CN112727965B (en) | Fault monitoring method and device for brake of coal mining machine | |
| Cheng et al. | High-accuracy unsupervised fault detection of industrial robots using current signal analysis | |
| CN113359682B (en) | Equipment fault prediction method, device, equipment fault prediction platform and medium | |
| CN112257943A (en) | Power plant induced draft fan fault early warning method based on MSET and deviation degree | |
| CN110987166A (en) | Method, device, equipment and storage medium for predicting health state of rotating machine | |
| Wang et al. | Weighted K-NN classification method of bearings fault diagnosis with multi-dimensional sensitive features | |
| PETERKA et al. | DIAGNOSTICS OF AUTOMATED TECHNOLOGICAL DEVICES. | |
| Chen et al. | An integrated framework for statistical change detection in running status of industrial machinery under transient conditions | |
| da Silva Arantes et al. | A novel unsupervised method for anomaly detection in time series based on statistical features for industrial predictive maintenance | |
| Calabrese et al. | An event based machine learning framework for predictive maintenance in industry 4.0 | |
| EP4423582A1 (en) | System, apparatus and method for monitoring condition of an asset in technical installation | |
| Zhou et al. | A summary of health prognostics methods for industrial robots | |
| Das et al. | Performance monitoring and failure prediction of industrial equipments using artificial intelligence and machine learning methods: A survey | |
| Nadakatti et al. | Artificial intelligence‐based condition monitoring for plant maintenance | |
| EP3961335A1 (en) | System, apparatus and method for estimating remaining useful life of a bearing | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| Ou et al. | Online shock sensing for rotary machinery using encoder signal | |
| Yun et al. | Fault diagnosis of wind turbine pitch system based on multiblock KPCA algorithm | |
| Rosli et al. | Application of principal component analysis vs. Multiple linear regression in resolving influential factor subject to air booster compressor Motor failure |
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 |