CN110363339B - A method and system for predictive maintenance based on motor parameters - Google Patents
A method and system for predictive maintenance based on motor parameters Download PDFInfo
- Publication number
- CN110363339B CN110363339B CN201910602734.XA CN201910602734A CN110363339B CN 110363339 B CN110363339 B CN 110363339B CN 201910602734 A CN201910602734 A CN 201910602734A CN 110363339 B CN110363339 B CN 110363339B
- Authority
- CN
- China
- Prior art keywords
- motor
- temperature
- vibration
- abnormal
- degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000036541 health Effects 0.000 claims abstract description 47
- 230000002159 abnormal effect Effects 0.000 claims abstract description 41
- 239000013598 vector Substances 0.000 claims abstract description 30
- 239000011159 matrix material Substances 0.000 claims abstract description 27
- 238000004364 calculation method Methods 0.000 claims abstract description 22
- 230000009466 transformation Effects 0.000 claims description 10
- 238000004804 winding Methods 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims 2
- 238000003745 diagnosis Methods 0.000 abstract description 14
- 230000002427 irreversible effect Effects 0.000 abstract description 4
- 238000007689 inspection Methods 0.000 abstract 1
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000013459 approach Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 230000001154 acute effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
-
- 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
- G01R31/343—Testing dynamo-electric machines in operation
-
- 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
- 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
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Control Of Electric Motors In General (AREA)
Abstract
本发明公开了一种基于电机参数进行预测性维护的方法与系统，本发明从电机的局部运行状况出发，采集电机的温度和振动两种无直接联系的非电气采集参数进行交叉计算，采用矩阵特征值向量对电机实时工作状态进行映射，可以实现温度、振动与电机健康度的函数关系，可得出电机局部和综合健康度的线性变化关系，通过判断健康度在一段时间内的变化趋势实现预测性维护，将传统电机故障诊断的诊断时间提前，可以很好的预防电机出现不可逆的损伤。本发明能够更加准确地得出电机的非正常工作状态，将统计计算流独立于实时计算流，降低了采集设备的边缘计算压力，避免了不必要的硬件成本；并且能将预测性维护定位至电机局部，降低了人工检测成本。
The invention discloses a method and system for predictive maintenance based on motor parameters. The invention starts from the local operating conditions of the motor, collects two non-electrical acquisition parameters that are not directly related to the temperature and vibration of the motor for cross calculation, and adopts a matrix The eigenvalue vector maps the real-time working state of the motor, which can realize the functional relationship between temperature, vibration and motor health, and can obtain the linear relationship between the local and comprehensive health of the motor. Predictive maintenance, which advances the diagnosis time of traditional motor fault diagnosis, can well prevent irreversible damage to the motor. The invention can more accurately obtain the abnormal working state of the motor, separate the statistical calculation flow from the real-time calculation flow, reduce the edge calculation pressure of the acquisition device, and avoid unnecessary hardware costs; and can locate the predictive maintenance to the Part of the motor, reducing the cost of manual inspection.
Description
Technical Field
The invention relates to a method and a system for predictive maintenance based on motor parameters, belongs to the field of information, and is suitable for maintenance of industrial fields, teaching equipment in the department of industry and equipment with a motor device.
Background
In the aspect of predictive maintenance of the motor, the state is still in a tentative stage, and no distinct scheme can realize a predictive maintenance platform for unifying motors in various types and industries. In order to realize the construction of the predictive platform, the daily operation health degree of the motor is firstly determined, which needs to count and analyze the daily operation parameters of the motor. The current motor maintenance is based on a fault diagnosis algorithm, and the relative electrical parameters of the motor during operation can be mathematically derived to judge the quality of the operation condition. The algorithm has high real-time requirement, needs to be acquired and calculated instantly, needs to perform a large amount of mathematical calculation in acquisition equipment, not only includes input data of the algorithm calculated by acquired data, but also includes calculation of the algorithm, and has high requirement on hardware of the acquisition equipment for better maintenance effect, and cost is increased exponentially if a large amount of equipment needs to be acquired; secondly, the algorithm can perform fault diagnosis only when the motor system generates acute sudden-change faults, if the health degree of the motor is regarded as a value between 0 and 100, when the traditional fault diagnosis algorithm is applied, the change of the health degree of the motor is usually a sudden reduction of a discrete value, so that the time from the diagnosis of the equipment faults to the irreversible damage of the equipment is too short, and the fault tolerance of the motor is not facilitated; thirdly, the conventional fault diagnosis method usually only performs threshold judgment on one parameter, and has low accuracy and poor robustness.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the defects of the prior art, the invention aims to provide a method and a system for predictive maintenance based on motor parameters, which judge the health degree of the whole motor based on local motor diagnosis, advance the diagnosis time of the traditional motor fault diagnosis, prevent the motor from generating irreversible damage and reduce the hardware requirement of acquisition equipment.
The technical scheme is as follows: in order to achieve the above object, the present invention provides a method for performing predictive maintenance based on motor parameters, comprising the following steps:
(1) loading a temperature sensor and a vibration sensor at each important part of the motor, wherein each important part at least comprises a bearing and a winding;
(2) numbering temperature sensors and vibration sensors from 1 to n, wherein two types of sensors with the same number are arranged at the same position, and the positions are also numbered by 1 to n; collecting and storing the position i (0) during normal operation<i<n +1) is the data of n +1 types in abnormal working, and each group of data respectively consists of a temperature matrix of n rows and 1 column and a vibration matrix of 1 row and n columns:
and [ V ]1 V2 … Vn](ii) a Wherein T is1～TnMeasured values, V, output for the temperature sensors 1-n1～VnMeasured values output by the vibration sensors 1 to n;
(4) multiplying the temperature matrix of each group by the vibration matrix to obtain n +1 n-order square matrixes, calculating the eigenvalue and the eigenvector of each group of n-order square matrixes, and taking the vector formed by the eigenvalue of the n-order square matrixes as a standard eigenvalue vector a corresponding to the working state type of the motori；
(5) Comparing the eigenvalue vector b calculated by real-time data acquisition with n +1 standard eigenvalue vectors respectively to obtain deltai＝|b-ai|，i∈[0,n]N Z and calculating the ratio of the degree of approximation between the actual operating condition and the normal state to the degree of approximation between the normal state and the abnormal state
And the ratio logarithm transformation and the trigonometric function transformation are used for obtaining the local health degree ri；
(6) Calculating comprehensive health degree by local health degree
When the real-time comprehensive health degree is continuously reduced or less thanIf the set threshold value is not in a healthy state, the motor is judged to be in an unhealthy state, and the local health degree r is positionediPositions that are continuously reduced or less than a set threshold are abnormal positions, and predictive maintenance is achieved.
Preferably, the step (2) acquires temperature and vibration data of normal and abnormal operations at different dates or air temperatures, respectively, and the step (5) selects and compares the standard characteristic value corresponding to the current date or air temperature.
Preferably, the degree of local health
Preferably, the method further comprises the step of marking the ratio of the closeness degree of the actual working condition to the normal state to the closeness degree of the abnormal state on the n-polygon graph to obtain an n-polygon working condition comparison graph, and visually showing the trend of the current working state of the motor.
Preferably, in the step (2), abnormal operation parameters are acquired through replacement of motor parts or noise signals are constructed and added to the normal operation parameters to simulate the abnormal operation parameters.
The invention discloses a system for performing predictive maintenance based on motor parameters, which comprises:
each working condition standard characteristic acquisition module is used for numbering a temperature sensor and a vibration sensor from 1 to n, two types of sensors with the same number are arranged at the same position of a motor, the arranged positions at least comprise a bearing and a winding, and the positions are also numbered by 1 to n; collecting and storing the position i (0) during normal operation<i<n +1) is the data of n +1 types in abnormal working, and each group of data respectively consists of a temperature matrix of n rows and 1 column and a vibration matrix of 1 row and n columns:
and [ V ]1 V2 … Vn](ii) a Wherein T is1～TnMeasured values, V, output for the temperature sensors 1-n1～VnMeasured values output by the vibration sensors 1 to n;
and multiplying the temperature matrix of each group by the vibration matrix to obtain n +1 n-order square matrixes, calculating the eigenvalue and the eigenvector of each group of n-order square matrixes, and taking the vector formed by the eigenvalue of the n-order square matrix as the standard eigenvalue vector a corresponding to the working state type of the motori；
A real-time local health degree calculation module for comparing the eigenvalue vector b calculated by the real-time collected data with the n +1 standard eigenvalue vectors to calculate deltai＝|b-ai|，i∈[0,n]N Z and calculating the ratio of the degree of approximation between the actual operating condition and the normal state to the degree of approximation between the normal state and the abnormal state
And the ratio logarithm transformation and the trigonometric function transformation are used for obtaining the local health degree ri；
And an abnormal prediction module for calculating the comprehensive health degree according to the local health degree
When the real-time comprehensive health degree is continuously reduced or is smaller than a set threshold value, the motor is judged to be in an unhealthy state, and the local health degree r is positionediPositions that are continuously reduced or less than a set threshold are abnormal positions, and predictive maintenance is achieved.
Preferably, the system further comprises a working condition comparison diagram drawing module, wherein the working condition comparison diagram drawing module is used for marking the ratio of the degree of approach of the actual working condition to the normal state to the degree of approach of the abnormal state on the n-edge diagram to obtain the n-edge working condition comparison diagram, and visually showing the trend of the current working state of the motor.
Has the advantages that: compared with the prior art, the invention has the following advantages:
1. the invention collects the temperature and vibration parameters of the motor to carry out cross calculation, can more accurately obtain the abnormal working state of the motor, and can avoid collecting electrical parameters, such as current and voltage, which need to be provided with related transmitters during collection and are difficult to be provided on a finished motor;
2. the invention directly collects direct variable quantities such as temperature, vibration and the like, and also includes environmental change factors such as seasons and the like on the basis of statistical calculation, and edge collection equipment can judge weather and air temperature by obtaining a time stamp of local time through month, day and time parameters or directly obtains the air temperature of the day through networking, and distinguishes characteristic values of various seasons and various weathers after statistics and calculation, so that the robustness of the predictive maintenance system is greatly improved;
3. the algorithm calculation is carried out by adopting two streams of real-time calculation and statistical calculation, and the statistical calculation stream is independent of the real-time calculation stream, so that the calculation cost of the edge acquisition equipment is reduced, and the hardware cost is reduced;
4. the invention positions the predictive maintenance to the local part of the motor, is different from the traditional integral fault diagnosis method, improves the robustness of the predictive maintenance method and reduces the manual detection cost;
5. the method has good adaptability in predicting the change of the motor object;
6. the invention can generate an n-edge working condition comparison graph, so that people can intuitively know the health state of each part of the motor.
Drawings
FIG. 1 is a flow chart of a method of an embodiment of the present invention.
Fig. 2 is a comparison diagram of n-edge operating conditions in the embodiment of the present invention.
Detailed Description
The present invention is further illustrated by the following examples, which are intended to be purely exemplary and are not intended to limit the scope of the invention, as various equivalent modifications of the invention will occur to those skilled in the art upon reading the present disclosure and fall within the scope of the appended claims.
As shown in fig. 1, a method for performing predictive maintenance based on motor parameters disclosed in the embodiment of the present invention mainly includes the following steps:
(1) the method comprises the following steps that temperature sensors and vibration sensors are loaded at important parts of a motor to receive data, key collection points of the motor are bearings and windings, and n temperature sensors and n vibration sensors can be respectively arranged at the parts;
(2) the temperature sensor and the vibration sensor can be numbered from 1 to n, two types of sensors with the same number are arranged at the same position, and the positions are also numbered from 1 to n;
(3) collecting data in a period of time and storing the data; the data acquisition is divided into two parts, the first layer is a sensor part, temperature signals and vibration signals can be converted into signal types which can be received by acquisition equipment, such as 4-20mA direct current standard industrial signals, 0-5V voltage signals and the like, data are transmitted to edge acquisition equipment for calculation through a series of protocols, such as an i2c protocol, a single bus protocol and the like, and calculation results are transmitted to a cloud server through the Internet.
(4) N +1 types of data are counted and grouped, namely, when the temperature T and the vibration V are in a normal range and the position i (0)<i<n +1) abnormal operation (temperature TiOr ViValues outside the normal range), each set of data consisting of n rows and 1 column of temperature matrix and 1 row and n columns of vibration matrix respectively:
The values of the two matrices should be taken at the same time. The parameters of the abnormal working scene can be constructed in two modes, the first mode can replace the intact motor parts with damaged motor parts, carry out operation experiments and collect operation parameters, and the scheme has high cost and high data reliability; the second method can use MATLAB to construct noise signal and add it to the operating parameter of normal operation to simulate abnormal operating parameter, and this scheme has lower cost but slightly lower data reliability. The parameters of normal and abnormal working scenes under different dates can be obtained through MATLAB simulation, because the weather of the same place on the same date should be the same or similar, the temperature of each day in the year can be subjected to grouping processing through the MATLAB, the temperature matrix can be corrected according to the temperature array of each day, if the temperature corresponding to the temperature array of the day is increased or decreased by x ℃ compared with that of the previous day, each element of the temperature matrix of the day should also be increased or decreased by x ℃, and the timestamp of the day can be obtained from the Internet.
(5) Multiplying the temperature matrix of each group by the vibration matrix to obtain n +1 n-order square matrixes:
the n-order square matrix represents the correlation between the temperature and the vibration of all n parts at the same time, wherein the main symmetry axis is the correlation between the temperature and the vibration of the same part;
(6) calculating the eigenvalue and eigenvector of each group of n-order square matrix, calculating n eigenvalues and eigenvectors in the complex domain, wherein the vector formed by the n eigenvalues can be expressed as the standard eigenvalue vector a of the current motor working state type (part i is abnormally working or all parts are normally working, and i is 0 during normal working)i＝[λ1 λ2 … λn]If the motor works in the same or similar state, the calculated characteristic value vector is the same as or similar to the standard characteristic value vector of the working state type (through threshold value comparison);
(7) comparing the eigenvalue vector b obtained by calculating the actual collected data at the time t with the n +1 standard eigenvalue vectors respectively to obtain deltai＝|b-ai|，i∈[0,n]∩Z，ΔiIs a quantity, Δ, representing the proximity of the current operating state to the point i in an abnormal operating stateiThe smaller the value of (b), the more the current working state tends to the abnormal state of the part i;
(8) calculated value
By calculating the ratio of the proximity of the actual operating conditions to the normal state to the proximity of the abnormal state, a value σ in the range of (0, + ∞) can be obtained and labeled on the n-gon, as shown in fig. 2. The polygon axes can be displayed by adjusting the type of the axes according to the size of sigma on each axis, and when the sigma difference is large, the polygon axes can be represented by logarithmic axes, and when the difference is small, the polygon axes can be represented by linear axes.
(9) The trend of the current working state of the motor can be intuitively seen from the n-edge diagram, the motor can be in one or more abnormal working states, and the specific abnormal working state part of the motor can be positioned by a program.
(10) Since the included angle between vectors may be close to 180 °, the modulus may be quite large, so performing logarithmic transformation and trigonometric transformation on the calculated σ may result in a local health score:
(11) the comprehensive health degree can be calculated through the local health degree:
(12) and calculating a derivative of the real-time comprehensive health degree, judging that the motor is in an unhealthy state when R' is continuously in a state less than zero for a long time or the R value is too low, and positioning, maintaining and repairing according to a program. If the local health degree riIf the value is judged to be continuously decreased or too low in the program, the part i is considered to be abnormal.
The invention discloses a system for performing predictive maintenance based on motor parameters, which comprises: each working condition standard characteristic acquisition module is used for acquiring and storing n +1 types of data in normal working and abnormal working at the position i, multiplying the temperature matrix of each group by the vibration matrix to obtain n +1 n-order square matrixes, calculating the characteristic value and the characteristic vector of each group of n-order square matrixes, and taking the vector formed by the characteristic values of the n-order square matrixes as the corresponding electric powerStandard eigenvalue vector a of the machine operating state typei(ii) a The real-time local health degree calculation module is used for comparing the characteristic value vector b calculated by the real-time collected data with the n +1 standard characteristic value vectors respectively and calculating the ratio of the approach degree of the actual working condition and the normal state to the approach degree of the abnormal state so as to obtain the local health degree ri(ii) a The working condition comparison diagram drawing module is used for drawing an n-polygon working condition comparison diagram according to the ratio of the approximation degree of the actual working condition and the normal state to the approximation degree of the abnormal state, and visually showing the trend of the current working state of the motor; and the abnormal prediction module is used for calculating the comprehensive health degree through the local health degree, judging whether the motor is in an abnormal state according to the comprehensive health degree and realizing predictive maintenance. The specific implementation details are referred to the above method embodiments, and are not described herein again.
The invention completes the work of motor parameter statistics and algorithm analysis in advance without real-time calculation, thereby reducing the workload of acquisition equipment and avoiding unnecessary hardware cost; the method generates the health degree of the motor in real time, forms a mapping relation between the health degree of the motor and an intuitive hardware acquisition parameter (non-electrical parameter), can be influenced from two aspects of vibration and temperature, and judges the health degree of the motor, wherein the health degree of the motor is a continuously variable quantity in a time domain, and the predictive maintenance can be realized by judging the variation trend of the health degree in a period of time, so that the diagnosis time of the traditional motor fault diagnosis is advanced, the irreversible damage of the motor can be well prevented, and the fault tolerance of the motor is facilitated; the invention starts from the local part of the motor, and carries out cross calculation through two non-electric acquisition parameters without direct connection, thereby improving the accuracy of the algorithm, still judging the health degree of the whole motor through local diagnosis and detection when one motor is changed, and increasing the robustness of the system.
Claims (7)
1. A method for predictive maintenance based on motor parameters, comprising the steps of:
(1) loading a temperature sensor and a vibration sensor at each important part of the motor, wherein each important part comprises a bearing and a winding;
(2) numbering temperature sensors and vibration sensors from 1 to n, wherein two types of sensors with the same number are arranged at the same position, and the positions are also numbered by 1 to n; the method comprises the following steps of collecting and storing temperature and vibration data in normal working and temperature and vibration data in abnormal working at a position i, wherein n +1 types of data are collected, and each group of data respectively consists of a temperature matrix with n rows and 1 column and a vibration matrix with 1 row and n column:
and [ V ]1 V2...Vn](ii) a Wherein T is1～TnMeasured values, V, output for the temperature sensors 1-n1～VnMeasured values output by the vibration sensors 1 to n; when the system works normally, i is set to be 0, and when the system works abnormally, i corresponds to an integer from 1 to n;
(3) multiplying the temperature matrix of each group by the vibration matrix to obtain n +1 n-order square matrixes, calculating the eigenvalue and the eigenvector of each group of n-order square matrixes, and taking the vector formed by the eigenvalue of the n-order square matrixes as a reference eigenvalue vector a corresponding to the working state type of the motori；
(4) Respectively calculating real-time eigenvalue vector b obtained by real-time collected data and n +1 reference eigenvalue vectors aiComparing them to find out Deltai＝|b-ai|，i∈[0，n]N Z, and calculating the degree of closeness delta between the actual operating condition and the normal state0Degree of proximity to actual operating conditions and abnormal conditionsiRatio of
And the ratio logarithm transformation and the trigonometric function transformation are used for obtaining the local health degree ri；
(5) Calculating comprehensive health degree by local health degree
When the real-time comprehensive health degree is continuously reduced or is smaller than a set threshold value, the motor is judged to be inNon-healthy state and locate local health riPositions that are continuously reduced or less than a set threshold are abnormal positions, and predictive maintenance is achieved.
2. A method for predictive maintenance based on motor parameters according to claim 1, characterized in that in step (2) the temperature and vibration data for normal and abnormal operation at different dates or air temperatures are obtained, respectively, and in step (4) the reference eigenvalue vector a corresponding to the current date or air temperature is selectediAnd (6) carrying out comparison.
3. The method of claim 1, wherein the local health is based on a motor parameter
4. The method of claim 1, further comprising labeling a ratio of a degree of proximity between the actual operating condition and the normal state to a degree of proximity between the actual operating condition and the abnormal state on the n-polygon map to obtain an n-polygon comparison map, and visually displaying a trend of the current operating state of the motor.
5. The method of claim 1, wherein the step (2) of collecting abnormal operating parameters by replacing motor parts or adding noise signals to the normal operating parameters simulates the abnormal operating parameters.
6. A system for predictive maintenance based on motor parameters, comprising:
each working condition standard characteristic acquisition module is used for numbering the temperature sensor and the vibration sensor from 1 to n, the two types of sensors with the same number are arranged at the same position of the motor, and the arranged positions at least compriseBearings and windings, the positions also numbered from 1 to n; the method comprises the following steps of collecting and storing n +1 types of data in normal work and abnormal work at a position i, wherein each group of data respectively comprises n rows and 1 column of temperature matrixes and 1 row and n columns of vibration matrixes:
and [ V ]1 V2...Vn](ii) a Wherein T is1～TnMeasured values, V, output for the temperature sensors 1-n1～VnMeasured values output by the vibration sensors 1 to n; when the system works normally, i is set to be 0, and when the system works abnormally, i corresponds to an integer from 1 to n;
and multiplying the temperature matrix of each group by the vibration matrix to obtain n +1 n-order square matrixes, calculating the eigenvalue and the eigenvector of each group of n-order square matrixes, and taking the vector formed by the eigenvalue of the n-order square matrix as the reference eigenvalue vector a corresponding to the working state type of the motori；
A real-time local health degree calculation module for calculating real-time eigenvalue vector b obtained by real-time collected data and n +1 reference eigenvalue vectors aiComparing them to find out Deltai＝|b-ai|，i∈[0，n]N Z, and calculating the degree of closeness delta between the actual operating condition and the normal state0Degree of proximity to actual operating conditions and abnormal conditionsiRatio of
And the ratio logarithm transformation and the trigonometric function transformation are used for obtaining the local health degree ri；
And an abnormal prediction module for calculating the comprehensive health degree according to the local health degree
When the real-time comprehensive health degree is continuously reduced or is smaller than a set threshold value, the motor is judged to be in an unhealthy state, and the local health degree r is positionediPositions that are continuously reduced or less than a set threshold are abnormal positions, and predictive maintenance is achieved.
7. The system for predictive maintenance based on motor parameters of claim 6, further comprising a working condition comparison drawing module for labeling a ratio of a degree of proximity between an actual working condition and a normal state to a degree of proximity between the actual working condition and an abnormal state on the n-polygon map to obtain the n-polygon working condition comparison map, and visually showing a trend of a current working state of the motor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910602734.XA CN110363339B (en) | 2019-07-05 | 2019-07-05 | A method and system for predictive maintenance based on motor parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910602734.XA CN110363339B (en) | 2019-07-05 | 2019-07-05 | A method and system for predictive maintenance based on motor parameters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110363339A CN110363339A (en) | 2019-10-22 |
| CN110363339B true CN110363339B (en) | 2022-03-08 |
Family
ID=68218172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910602734.XA Active CN110363339B (en) | 2019-07-05 | 2019-07-05 | A method and system for predictive maintenance based on motor parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110363339B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111639842B (en) * | 2020-05-20 | 2023-06-20 | 湖北博华自动化系统工程有限公司 | Equipment health assessment method, assessment system and equipment health prediction method |
| CN112731159B (en) * | 2020-12-23 | 2023-09-22 | 江苏省电力试验研究院有限公司 | A method for predicting and locating battery faults in battery compartments of energy storage power stations |
| CN113064075B (en) * | 2021-03-16 | 2023-05-05 | 电子科技大学成都学院 | Motor service life prediction method based on edge calculation and deep learning |
| CN114167282B (en) * | 2021-12-03 | 2022-08-12 | 深圳市双合电气股份有限公司 | Motor fault diagnosis and degradation trend prediction system |
| CN115963798B (en) * | 2023-02-23 | 2023-05-26 | 深圳市玄羽科技有限公司 | Equipment operation control method and system in industrial Internet and electronic equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103471841A (en) * | 2013-09-30 | 2013-12-25 | 国家电网公司 | Method for diagnosing vibration faults of rotary machine |
| CN103743563A (en) * | 2013-08-13 | 2014-04-23 | 华北电力大学（保定） | Fan gear box space failure predicating method based on temperature data |
| KR101432786B1 (en) * | 2013-11-14 | 2014-09-23 | 엠앤디테크놀로지 주식회사 | Fault diagnosis method of motor and system thereof |
| CN106066621A (en) * | 2016-07-27 | 2016-11-02 | 霍州煤电集团有限责任公司 | The anticipation maintenance of a kind of colliery Central Pump Room water pump and long-range control method |
| CN106600095A (en) * | 2016-07-27 | 2017-04-26 | 中国特种设备检测研究院 | Reliability-based maintenance evaluation method |
| CN106640548A (en) * | 2016-12-19 | 2017-05-10 | 北京金风科创风电设备有限公司 | State monitoring method and device for wind generating set |
| CN106895906A (en) * | 2017-03-23 | 2017-06-27 | 西安理工大学 | A kind of feature extracting method of vibration of hydrogenerator set failure |
| CN107247230A (en) * | 2017-07-03 | 2017-10-13 | 浙江大学 | A kind of electric rotating machine state monitoring method based on SVMs and data-driven |
| CN108645451A (en) * | 2018-07-12 | 2018-10-12 | 中铁磁浮科技（成都）有限公司 | Middle speed magnetic suspension train on-line condition monitoring system |
| CN109564426A (en) * | 2016-11-11 | 2019-04-02 | 申克普若赛斯欧洲有限公司 | The operating method and condition monitoring system of the condition monitoring system of bobbing machine |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10638295B2 (en) * | 2015-01-17 | 2020-04-28 | Machinesense, Llc | System and method for turbomachinery preventive maintenance and root cause failure determination |
-
2019
- 2019-07-05 CN CN201910602734.XA patent/CN110363339B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103743563A (en) * | 2013-08-13 | 2014-04-23 | 华北电力大学（保定） | Fan gear box space failure predicating method based on temperature data |
| CN103471841A (en) * | 2013-09-30 | 2013-12-25 | 国家电网公司 | Method for diagnosing vibration faults of rotary machine |
| KR101432786B1 (en) * | 2013-11-14 | 2014-09-23 | 엠앤디테크놀로지 주식회사 | Fault diagnosis method of motor and system thereof |
| CN106066621A (en) * | 2016-07-27 | 2016-11-02 | 霍州煤电集团有限责任公司 | The anticipation maintenance of a kind of colliery Central Pump Room water pump and long-range control method |
| CN106600095A (en) * | 2016-07-27 | 2017-04-26 | 中国特种设备检测研究院 | Reliability-based maintenance evaluation method |
| CN109564426A (en) * | 2016-11-11 | 2019-04-02 | 申克普若赛斯欧洲有限公司 | The operating method and condition monitoring system of the condition monitoring system of bobbing machine |
| CN106640548A (en) * | 2016-12-19 | 2017-05-10 | 北京金风科创风电设备有限公司 | State monitoring method and device for wind generating set |
| CN106895906A (en) * | 2017-03-23 | 2017-06-27 | 西安理工大学 | A kind of feature extracting method of vibration of hydrogenerator set failure |
| CN107247230A (en) * | 2017-07-03 | 2017-10-13 | 浙江大学 | A kind of electric rotating machine state monitoring method based on SVMs and data-driven |
| CN108645451A (en) * | 2018-07-12 | 2018-10-12 | 中铁磁浮科技（成都）有限公司 | Middle speed magnetic suspension train on-line condition monitoring system |
Non-Patent Citations (3)
| Title |
|---|
| 基于健康评估和劣化趋势预测的水电机组故障诊断系统研究;潘罗平;《中国博士学位论文全文数据库 (工程科技Ⅱ辑)》;20140215(第2期);全文 * |
| 基于动态特性分析的机床主轴箱装配故障诊断研究;李凯旋;《中国优秀硕士学位论文全文数据库 (工程科技Ⅰ辑)》;20160715(第7期);全文 * |
| 基于子空间方法的风机齿轮箱故障预测算法;赵洪山，郭伟，邵玲，张兴科;《电力自动化设备》;20150216;第35卷(第3期);第27-35页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110363339A (en) | 2019-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110363339B (en) | A method and system for predictive maintenance based on motor parameters | |
| WO2021004154A1 (en) | Method for predicting remaining life of numerical control machine tool | |
| CN111368428B (en) | Sensor precision degradation fault detection method based on monitoring second-order statistics | |
| CN110889091A (en) | Machine tool thermal error prediction method and system based on temperature sensitive interval segmentation | |
| CN106198020A (en) | Wind turbines bearing failure diagnosis method based on subspace and fuzzy C-means clustering | |
| CN116956047B (en) | Wind turbine generator system performance evaluation system based on wind power generation data | |
| CN116861313B (en) | Kalman filtering working condition identification method and system based on vibration energy trend | |
| CN117406027A (en) | Distribution network fault distance measurement method and system | |
| CN116861503A (en) | Method for constructing digital twin model of power transformer based on big data | |
| KR101998972B1 (en) | Method of analyzing and visualizing the cause of process failure by deriving the defect occurrence index by variable sections | |
| CN110108474B (en) | Online monitoring and evaluating method and system for operation stability of rotary machine | |
| CN118583498B (en) | A method and system for predicting the remaining service life of a rolling bearing | |
| CN118671686B (en) | Magnetic valve type current transformer error state online quantitative evaluation method, device, equipment and medium | |
| CN106250937A (en) | A kind of failure modes diagnostic method based on non-index of similarity | |
| CN109001492A (en) | A kind of train shaft speed sensor method for diagnosing faults | |
| CN112621381A (en) | Intelligent health state evaluation method and device for machine tool feeding system | |
| CN111639715A (en) | Automobile instrument assembly quality prediction method and system based on LS-SVM | |
| CN117907685A (en) | Method and device for measuring resistance value in link signal and computer equipment | |
| CN117592656A (en) | Carbon footprint monitoring method and system based on carbon data accounting | |
| CN115659271A (en) | Sensor abnormality detection method, model training method, system, device, and medium | |
| CN116658433A (en) | Intelligent detection method and system for particle-resistant magnetic pump | |
| CN116486146A (en) | Fault detection method, system, device and medium for rotary mechanical equipment | |
| CN114192583A (en) | Scada platform-based strip steel rolling process quality monitoring method and system | |
| CN111753876A (en) | Product quality detection method based on deep neural network | |
| CN118694002B (en) | Electrical fusion sensing monitoring system based on real-time edge calculation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A method and system for predictive maintenance based on motor parameters Granted publication date: 20220308 Pledgee: Zijin Branch of Nanjing Bank Co.,Ltd. Pledgor: NANJING JRIDGE SOFTWARE DEVELOPMENT CO.,LTD. Registration number: Y2024980053510 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |