CN114048891A - Motor fault prediction method based on gray model and big data processing - Google Patents

Motor fault prediction method based on gray model and big data processing Download PDF

Info

Publication number
CN114048891A
CN114048891A CN202111207925.XA CN202111207925A CN114048891A CN 114048891 A CN114048891 A CN 114048891A CN 202111207925 A CN202111207925 A CN 202111207925A CN 114048891 A CN114048891 A CN 114048891A
Authority
CN
China
Prior art keywords
motor
prediction
data
fault
fault prediction
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
Application number
CN202111207925.XA
Other languages
Chinese (zh)
Inventor
向红先
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chengdu Qingentropy Data Technology Co ltd
Original Assignee
Chengdu Qingentropy Data Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chengdu Qingentropy Data Technology Co ltd filed Critical Chengdu Qingentropy Data Technology Co ltd
Priority to CN202111207925.XA priority Critical patent/CN114048891A/en
Publication of CN114048891A publication Critical patent/CN114048891A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2455—Query execution
    • G06F16/24564—Applying rules; Deductive queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462—Approximate or statistical queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2477—Temporal data queries
    • 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
    • G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G06F17/13—Differential equations
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Optimization (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Business, Economics & Management (AREA)
  • Probability & Statistics with Applications (AREA)
  • Fuzzy Systems (AREA)
  • Computational Linguistics (AREA)
  • Operations Research (AREA)
  • Algebra (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Quality & Reliability (AREA)
  • Computing Systems (AREA)
  • Tourism & Hospitality (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Automation & Control Theory (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)

Abstract

The application discloses a motor fault prediction method based on a gray model and big data processing, which comprises the following steps: 1) inquiring data about motor operation in a large database, acquiring all motor operation fault types, acquiring motor state monitoring abnormal data causing different motor operation fault types, and performing statistical sorting on the acquired data; 2) calculating the possible weight of the motor operation fault caused by various motor state monitoring abnormal data according to the data obtained in the step 1) and forming a motor fault weight matrix; 3) and establishing a grey model for motor fault prediction and a fuzzy judgment rule for motor fault prediction. The invention has the advantages that: the grey model prediction and the fuzzy prediction are combined, so that data inaccuracy caused by single model prediction is prevented, and the prediction precision and effectiveness are improved.

Description

Motor fault prediction method based on gray model and big data processing
Technical Field
The invention relates to a motor fault prediction method based on a gray model and big data processing, and belongs to the field of electrical equipment.
Background
Predictive maintenance of the motor is state-based maintenance. When the motor runs, the main part of the motor is subjected to regular (or continuous) state monitoring and fault diagnosis, the state of the motor is judged, the future development trend of the state of the motor is predicted, a predictive maintenance plan is made in advance according to the state development trend and possible fault modes of the motor, and the time, content, mode and necessary technical and material support of the motor to be repaired are determined. The motor predictive maintenance integrates motor state monitoring, fault diagnosis, state prediction, maintenance decision support and maintenance activities, and is a novel maintenance mode. The fault prediction technology can provide a better theoretical data support for motor predictive maintenance, so that maintenance personnel can judge the state of the motor more intuitively. The failure prediction technology is a new edge subject integrating multiple subjects of mechanical design, electronics, computer, communication, control and the like. At present, no qualitative theory can be used as a reference for the fault diagnosis and prediction of the motor, and the main analysis means includes a statistical prediction technology, a mathematical prediction technology, an intelligent prediction technology, an information fusion prediction technology and the like. Statistical probability speculation, intelligent neural networks and grey theory mathematical models are always important research methods, but the methods have advantages and disadvantages and have certain difficulty in combination.
Disclosure of Invention
The invention aims to overcome the defects of the existing motor fault prediction method and provide a motor fault prediction method based on a gray model and big data processing.
The invention adopts the technical scheme that a motor fault prediction method based on a gray model and big data processing comprises the following steps:
1) inquiring data about motor operation in a large database, acquiring all motor operation fault types, acquiring motor state monitoring abnormal data causing different motor operation fault types, and performing statistical sorting on the acquired data;
2) calculating the possible weight of the motor operation fault caused by various motor state monitoring abnormal data according to the data obtained in the step 1) and forming a motor fault weight matrix;
3) establishing a grey model for motor fault prediction and a fuzzy judgment rule for motor fault prediction;
4) monitoring the running state of the motor, detecting real-time detection data of the running state of the motor for multiple times at certain time intervals within a period of time, taking the real-time detection data of the running state of the motor as input, and outputting a motor fault prediction output quantity I and a motor fault prediction output quantity II through a gray model and a fuzzy judgment rule respectively;
5) establishing a motor fault prediction comprehensive judgment rule according to the gray model and the fuzzy judgment rule established in the step 3);
6) and 4) taking the motor fault prediction output quantity I and the motor fault prediction output quantity II obtained in the step 4) as input, and performing motor fault prediction by using a motor fault prediction comprehensive judgment rule.
Preferably, in the motor fault prediction method based on the gray model and the big data processing, in step 3), the step of establishing the gray model for motor fault prediction includes the following steps:
3-1) marking the motor state monitoring abnormal data causing the same motor operation fault type as an original data sequence x(0)＝(x(0)(1),x(0)(2),…,x(0)(n)), for x(0)Performing accumulation calculation to obtain a generated sequence x(1)＝(x(1)(1),x(1)(2),…,x(1)(n)), wherein
Figure BDA0003307649040000011
k＝1,2,…,n；
3-2) from x(1)Structural sequence Z(1)＝(Z(1)(2),Z(1)(3),…,Z(1)(n)), wherein Z(1)(k)＝ax(1)(k-1)+(1-a)x(1)(k)，k＝2,3,…,n；
Set the whitening equation to
Figure BDA0003307649040000021
Will whitenThe ash differential equation obtained after discretization of the equation is as follows: x is the number of(o)(k)+aZ(1)(k) B, where k is 2,3, …, n; expressed in matrix form as: y ═ B (a, B)TWherein Y ═ x(o)(2),x(o)(3),…,x(o)(n))，
Figure BDA0003307649040000022
3-3) solving parameters a, b,
Figure BDA0003307649040000023
the response of the gray differential equation is:
Figure BDA0003307649040000024
then
Figure BDA0003307649040000025
3-4) according to the data obtained in the step 1), calculating the proportion of the real-time motor state detection data in the step 4) to the total value of the detection data in a certain time period as uiThe sequence formed by the real-time detection data of each motor state in a period of time is u ═ u (u ═1,u1,…,up) P is the number of real-time detection data of each motor state in a period of time; expressing the motor state prediction data in the next time period as V ═ Zu; obtaining a motor fault prediction set possibly caused by motor state prediction data V according to the data statistically sorted in the step 1)
Figure BDA0003307649040000026
In the optimized motor fault prediction method based on the gray model and the big data processing, in the step 3), the process of establishing the fuzzy judgment rule of the motor fault prediction is as follows:
establishing n fuzzy judgment principles, wherein the n fuzzy judgment principles are as follows:
Figure BDA0003307649040000031
monitoring abnormal data input if motor state
Figure BDA0003307649040000032
The motor fault type may be
Figure BDA0003307649040000033
Figure BDA0003307649040000034
Monitoring abnormal data input if motor state
Figure BDA0003307649040000035
The motor fault type may be
Figure BDA0003307649040000036
By analogy, obtain
Figure BDA0003307649040000037
Monitoring abnormal data input if motor state
Figure BDA0003307649040000038
The motor fault type may be
Figure BDA0003307649040000039
Synthesizing n fuzzy decision principles to obtain a fuzzy vector set
Figure BDA00033076490400000310
Each element of the set of (a) describes a degree of membership of the motor condition monitoring anomaly data to various motor fault types.
Preferably, in the motor fault prediction method based on the gray model and the big data processing, in step 5), the process of establishing the motor fault prediction comprehensive judgment rule includes:
the overall rule of comprehensive judgment fuzzy is established as follows:
Figure BDA00033076490400000311
wherein i is 0,2, …, n, j is 1,2, …, n, k is 1,2, …, n;
Figure BDA00033076490400000312
Figure BDA00033076490400000313
is a matrix; when the fuzzy prediction result is
Figure BDA00033076490400000314
The grey model predicts a result of
Figure BDA00033076490400000315
In time, the motor fault prediction comprehensive judgment is expressed as:
Figure BDA00033076490400000316
Figure BDA00033076490400000317
eta is the motor fault weight matrix calculated in the step 2),
Figure BDA00033076490400000318
fuzzy prediction result of presentation award
Figure BDA00033076490400000319
Grey model prediction results
Figure BDA00033076490400000320
And comprehensively considering the obtained fuzzy output.
Preferably, in the motor fault prediction method based on the gray model and the big data processing, the types of the real-time motor monitoring data include motor vibration frequency, motor amplitude, motor phase current, motor voltage, motor zero sequence current and motor three-phase average current.
In the optimized motor fault prediction method based on the gray model and the big data processing, in the step 2), the method for calculating the possible weight of the motor operation fault caused by various motor state monitoring abnormal data and forming the motor fault weight matrix is one of methods such as correlation analysis, variance analysis, regression analysis and cluster analysis.
According to the technical scheme, when the motor is actually applied, the motor is monitored in real time and motor data are acquired. When abnormal data appear in the acquired motor operation data, the motor fault prediction method predicts the motor fault through the detected real-time data, predicts the possible faults of the motor in the next time period and the possibility of various motor faults, facilitates maintenance personnel to maintain the motor in time, and prevents larger accidents.
The motor fault prediction based on the gray model and the motor fault prediction based on the fuzzy prediction model are prediction methods which are small in calculation amount and low in implementation difficulty in the existing prediction methods, but the prediction accuracy is lower compared with other prediction methods. According to the method, the grey model and the fuzzy prediction model are combined and are respectively predicted, and then the grey model and the fuzzy prediction model are comprehensively judged according to the motor fault prediction comprehensive judgment rule, so that the prediction precision can be effectively improved, and a better prediction effect is ensured.
The motor fault weight matrix is added into the prediction budget by calculating the possible weight of motor operation fault caused by various motor state monitoring abnormal data and forming the motor fault weight matrix, so that the step of manual review can be omitted, and the accuracy and effectiveness of prediction output can be improved.
Drawings
Fig. 1 shows a flow chart of a motor fault prediction method of the present invention.
Detailed Description
The technical features of the present invention will be further explained with reference to the accompanying drawings and specific embodiments.
The application relates to a motor fault prediction method based on a gray model and big data processing, which comprises the following steps:
1) inquiring data about motor operation in a large database, acquiring all motor operation fault types, acquiring motor state monitoring abnormal data causing different motor operation fault types, and performing statistical sorting on the acquired data;
2) calculating the possible weight of the motor operation fault caused by various motor state monitoring abnormal data according to the data obtained in the step 1) and forming a motor fault weight matrix;
3) establishing a grey model for motor fault prediction and a fuzzy judgment rule for motor fault prediction;
4) monitoring the running state of the motor, detecting real-time detection data of the running state of the motor for multiple times at certain time intervals within a period of time, taking the real-time detection data of the running state of the motor as input, and outputting a motor fault prediction output quantity I and a motor fault prediction output quantity II through a gray model and a fuzzy judgment rule respectively;
5) establishing a motor fault prediction comprehensive judgment rule according to the gray model and the fuzzy judgment rule established in the step 3);
6) and 4) taking the motor fault prediction output quantity I and the motor fault prediction output quantity II obtained in the step 4) as input, and performing motor fault prediction by using a motor fault prediction comprehensive judgment rule.
In step 3), establishing a gray model for motor fault prediction comprises the following steps:
3-1) marking the motor state monitoring abnormal data causing the same motor operation fault type as an original data sequence x(0)＝(x(0)(1),x(0)(2),…,x(0)(n)), for x(0)Performing accumulation calculation to obtain a generated sequence x(1)＝(x(1)(1),x(1)(2),…,x(1)(n)), wherein
Figure BDA0003307649040000041
k＝1,2,…,n；
3-2) from x(1)Structural sequence Z(1)＝(Z(1)(2),Z(1)(3),…,Z(1)(n)), wherein Z(1)(k)＝ax(1)(k-1)+(1-a)x(1)(k)，k＝2,3,…,n；
Set the whitening equation to
Figure BDA0003307649040000042
Discretizing the whitening equation to obtain a gray differential equation as follows: x is the number of(o)(k)+aZ(1)(k) B, where k is 2,3, …, n; expressed in matrix form as: y ═ B (a, B)TWherein Y ═ x(o)(2),x(o)(3),…,x(o)(n))，
Figure BDA0003307649040000051
3-3) solving parameters a, b,
Figure BDA0003307649040000052
the response of the gray differential equation is:
Figure BDA0003307649040000053
then
Figure BDA0003307649040000054
3-4) according to the data obtained in the step 1), calculating the proportion of the real-time motor state detection data in the step 4) to the total value of the detection data in a certain time period as uiThe sequence formed by the real-time detection data of each motor state in a period of time is u ═ u (u ═1,u1,…,up) P is the number of real-time detection data of each motor state in a period of time; expressing the motor state prediction data in the next time period as V ═ Zu; obtaining a motor fault prediction set possibly caused by motor state prediction data V according to the data statistically sorted in the step 1)
Figure BDA0003307649040000055
In step 3), the process of establishing the fuzzy judgment rule of motor fault prediction is as follows:
establishing n fuzzy judgment principles, wherein the n fuzzy judgment principles are as follows:
Figure BDA0003307649040000056
monitoring abnormal data input if motor state
Figure BDA0003307649040000057
The motor fault type may be
Figure BDA0003307649040000058
Figure BDA0003307649040000059
Monitoring abnormal data input if motor state
Figure BDA00033076490400000510
The motor fault type may be
Figure BDA00033076490400000511
By analogy, obtain
Figure BDA00033076490400000512
Monitoring abnormal data input if motor state
Figure BDA00033076490400000513
The motor fault type may be
Figure BDA00033076490400000514
Synthesizing n fuzzy decision principles to obtain a fuzzy vector set
Figure BDA00033076490400000515
Each element of the set of (a) describes a degree of membership of the motor condition monitoring anomaly data to various motor fault types.
In step 5), the process of establishing the motor fault prediction comprehensive judgment rule comprises the following steps:
the overall rule of comprehensive judgment fuzzy is established as follows:
Figure BDA0003307649040000061
wherein i is 0,2,…,n、j＝1，2，…，n、k＝1，2，…，n；
Figure BDA0003307649040000062
Figure BDA0003307649040000063
Is a matrix; when the fuzzy prediction result is
Figure BDA0003307649040000064
The grey model predicts a result of
Figure BDA0003307649040000065
In time, the motor fault prediction comprehensive judgment is expressed as:
Figure BDA0003307649040000066
Figure BDA0003307649040000067
eta is the motor fault weight matrix calculated in the step 2),
Figure BDA0003307649040000068
fuzzy prediction result of presentation award
Figure BDA0003307649040000069
Grey model prediction results
Figure BDA00033076490400000610
And comprehensively considering the obtained fuzzy output.
The types of the real-time motor monitoring data comprise motor vibration frequency, motor amplitude, motor phase current, motor voltage, motor zero sequence current and motor three-phase average current.
In the step 2), the method for calculating the possible weight of the motor operation fault caused by various motor state monitoring abnormal data and forming the motor fault weight matrix is one of methods such as correlation analysis, variance analysis, regression analysis and cluster analysis.
It is to be understood that the above description is not intended to limit the present invention, and the present invention is not limited to the above examples, and those skilled in the art should understand that they can make various changes, modifications, additions and substitutions within the spirit and scope of the present invention.

Claims (6)

1. A motor fault prediction method based on a gray model and big data processing is characterized in that: the method comprises the following steps:
inquiring data about motor operation in a large database, acquiring all motor operation fault types, acquiring motor state monitoring abnormal data causing different motor operation fault types, and performing statistical sorting on the acquired data;
calculating the possible weight of the motor operation fault caused by various motor state monitoring abnormal data according to the data obtained in the step 1) and forming a motor fault weight matrix;
establishing a grey model for motor fault prediction and a fuzzy judgment rule for motor fault prediction;
monitoring the running state of the motor, detecting real-time detection data of the running state of the motor for multiple times at certain time intervals within a period of time, taking the real-time detection data of the running state of the motor as input, and outputting a motor fault prediction output quantity I and a motor fault prediction output quantity II through a gray model and a fuzzy judgment rule respectively;
establishing a motor fault prediction comprehensive judgment rule according to the gray model and the fuzzy judgment rule established in the step 3);
and 4) taking the motor fault prediction output quantity I and the motor fault prediction output quantity II obtained in the step 4) as input, and performing motor fault prediction by using a motor fault prediction comprehensive judgment rule.
2. The motor fault prediction method based on gray model and big data processing according to claim 1, characterized in that: in step 3), establishing a gray model for motor fault prediction comprises the following steps:
3-1) marking the motor state monitoring abnormal data causing the same motor operation fault type as an original data sequence x(0)＝(x(0)(1),x(0)(2),…,x(0)(n)), for x(0)Performing accumulation calculation to obtain a generated sequence x(1)＝(x(1)(1),x(1)(2),…,x(1)(n)), wherein
Figure FDA0003307649030000011
Figure FDA0003307649030000012
3-2) from x(1)Structural sequence Z(1)＝(Z(1)(2),Z(1)(3),…,Z(1)(n)), wherein Z(1)(k)＝ax(1)(k-1)+(1-a)x(1)(k)，k＝2,3,…,n；
Set the whitening equation to
Figure FDA0003307649030000013
Discretizing the whitening equation to obtain a gray differential equation as follows: x is the number of(o)(k)+aZ(1)(k) B, where k is 2,3, …, n; expressed in matrix form as: y ═ B (a, B)TWherein Y ═ x(o)(2),x(o)(3),…,x(o)(n))，
Figure FDA0003307649030000021
3-3) solving parameters a, b,
Figure FDA0003307649030000022
the response of the gray differential equation is:
Figure FDA0003307649030000023
then
Figure FDA0003307649030000024
3-4) obtaining data according to the step 1), and obtaining the systemCalculating the proportion of the motor state real-time detection data in the step 4) to the total value of the detection data in a certain time period as uiThe sequence formed by the real-time detection data of each motor state in a period of time is u ═ u (u ═1,u1,…,up) P is the number of real-time detection data of each motor state in a period of time; expressing the motor state prediction data in the next time period as V ═ Zu; obtaining a motor fault prediction set possibly caused by motor state prediction data V according to the data statistically sorted in the step 1)
Figure FDA0003307649030000025
3. The motor fault prediction method based on gray model and big data processing according to claim 1, characterized in that: in step 3), the process of establishing the fuzzy judgment rule of motor fault prediction is as follows:
establishing n fuzzy judgment principles, wherein the n fuzzy judgment principles are as follows:
Figure FDA0003307649030000026
monitoring abnormal data input if motor state
Figure FDA0003307649030000027
The motor fault type may be
Figure FDA0003307649030000028
Figure FDA0003307649030000029
Monitoring abnormal data input if motor state
Figure FDA00033076490300000210
The motor fault type may be
Figure FDA00033076490300000211
By analogy, obtain
Figure FDA00033076490300000212
Monitoring abnormal data input if motor state
Figure FDA00033076490300000213
The motor fault type may be
Figure FDA00033076490300000214
Synthesizing n fuzzy decision principles to obtain a fuzzy vector set
Figure FDA00033076490300000215
Figure FDA00033076490300000216
Each element of the set of (a) describes a degree of membership of the motor condition monitoring anomaly data to various motor fault types.
4. Motor fault prediction method based on grey model and big data processing according to claims 2 and 3, characterized in that: in step 5), the process of establishing the motor fault prediction comprehensive judgment rule comprises the following steps:
the overall rule of comprehensive judgment fuzzy is established as follows:
Figure FDA0003307649030000031
wherein i is 0,2, …, n, j is 1,2, …, n, k is 1,2, …, n;
Figure FDA0003307649030000032
Figure FDA0003307649030000033
is a matrix; when the fuzzy prediction result is
Figure FDA0003307649030000034
The grey model predicts a result of
Figure FDA0003307649030000035
In time, the motor fault prediction comprehensive judgment is expressed as:
Figure FDA0003307649030000036
Figure FDA0003307649030000037
eta is the motor fault weight matrix calculated in the step 2),
Figure FDA0003307649030000038
fuzzy prediction result of presentation award
Figure FDA0003307649030000039
Grey model prediction results
Figure FDA00033076490300000310
And comprehensively considering the obtained fuzzy output.
5. The motor fault prediction method based on gray model and big data processing according to claim 1, characterized in that: the types of the real-time motor monitoring data comprise motor vibration frequency, motor amplitude, motor phase current, motor voltage, motor zero sequence current and motor three-phase average current.
6. The motor fault prediction method based on gray model and big data processing according to claim 1, characterized in that: in the step 2), the method for calculating the possible weight of the motor operation fault caused by various motor state monitoring abnormal data and forming the motor fault weight matrix is one of methods such as correlation analysis, variance analysis, regression analysis and cluster analysis.
CN202111207925.XA 2021-10-18 2021-10-18 Motor fault prediction method based on gray model and big data processing Pending CN114048891A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111207925.XA CN114048891A (en) 2021-10-18 2021-10-18 Motor fault prediction method based on gray model and big data processing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111207925.XA CN114048891A (en) 2021-10-18 2021-10-18 Motor fault prediction method based on gray model and big data processing

Publications (1)

Publication Number Publication Date
CN114048891A true CN114048891A (en) 2022-02-15

Family

ID=80205473

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111207925.XA Pending CN114048891A (en) 2021-10-18 2021-10-18 Motor fault prediction method based on gray model and big data processing

Country Status (1)

Country Link
CN (1) CN114048891A (en)

Similar Documents

Publication Publication Date Title
CN111241154B (en) Storage battery fault early warning method and system based on big data
JP5753286B1 (en) Information processing apparatus, diagnostic method, and program
CN112131212A (en) Hybrid cloud scene-oriented time sequence data anomaly prediction method based on ensemble learning technology
JP2020119605A (en) Abnormality detection system, abnormality detection method, abnormality detection program, and method for generating learned model
Lindemann et al. Anomaly detection and prediction in discrete manufacturing based on cooperative LSTM networks
JP2018160093A (en) Abnormality detection system and abnormality detection method
CN114723285B (en) Power grid equipment safety evaluation prediction method
CN113762329A (en) Method and system for constructing state prediction model of large rolling mill
CN109858140B (en) Fault diagnosis method for water chilling unit based on information entropy discrete Bayesian network
CN112462734B (en) Industrial production equipment fault prediction analysis method and model
Jiang et al. A2-LSTM for predictive maintenance of industrial equipment based on machine learning
WO2019209146A1 (en) Method and system for identifying and forecasting the development of faults in equipment
CN109871002B (en) Concurrent abnormal state identification and positioning system based on tensor label learning
CN113627032B (en) Intelligent decision-making method for equipment design/maintenance scheme based on digital twinning
CN107121943B (en) Method and device for obtaining health prediction information of intelligent instrument
CN112434390A (en) PCA-LSTM bearing residual life prediction method based on multi-layer grid search
CN115481726A (en) Industrial robot complete machine health assessment method and system
CN115564182A (en) Power grid analysis method based on power grid resource service middling platform
CN111784537A (en) Power distribution network state parameter monitoring method and device and electronic equipment
Smirnov Intelligent decision support system for the control of complex technical systems
CN117060353A (en) Fault diagnosis method and system for high-voltage direct-current transmission system based on feedforward neural network
Bond et al. A hybrid learning approach to prognostics and health management applied to military ground vehicles using time-series and maintenance event data
JP7062505B2 (en) Equipment management support system
CN114048891A (en) Motor fault prediction method based on gray model and big data processing
CN115600695A (en) Fault diagnosis method of metering equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination