CN118091409A - Servo motor fault diagnosis method and system based on data analysis - Google Patents
Servo motor fault diagnosis method and system based on data analysis Download PDFInfo
- Publication number
- CN118091409A CN118091409A CN202410509022.4A CN202410509022A CN118091409A CN 118091409 A CN118091409 A CN 118091409A CN 202410509022 A CN202410509022 A CN 202410509022A CN 118091409 A CN118091409 A CN 118091409A
- Authority
- CN
- China
- Prior art keywords
- torque
- servo motor
- index
- magnetic field
- load
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000007405 data analysis Methods 0.000 title claims abstract description 23
- 238000003745 diagnosis Methods 0.000 title claims abstract description 22
- 230000006698 induction Effects 0.000 claims abstract description 49
- 238000004458 analytical method Methods 0.000 claims description 30
- 238000004364 calculation method Methods 0.000 claims description 22
- 238000005070 sampling Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 5
- 101100001674 Emericella variicolor andI gene Proteins 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 2
- 238000009826 distribution Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000008439 repair process Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
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
- G01R31/343—Testing dynamo-electric machines in operation
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Tests Of Circuit Breakers, Generators, And Electric Motors (AREA)
Abstract
The invention discloses a servo motor fault diagnosis method and a system based on data analysis, which relate to the technical field of servo motors and have the technical key points that: the method comprises the steps of keeping a load unchanged, calculating a torque average value and a torque fluctuation value when a servo motor is in a stable running state, gradually increasing the load, combining the maximum torque output and the torque fluctuation value of each load point, calculating to obtain a torque performance index, dividing the servo motor into a plurality of areas with the same size, calculating to obtain a magnetic induction difference index and a magnetic field intensity difference index of the servo motor through the magnetic induction intensity and the magnetic field intensity of each area, calculating to obtain a magnetic pole offset index by combining the torque performance index, the magnetic induction difference index and the magnetic field intensity difference index, presetting an offset threshold, comparing the magnetic pole offset index with the offset threshold, and making corresponding measures according to the comparison result to avoid serious influence of magnetic pole offset on system performance and safety.
Description
Technical Field
The invention relates to the technical field of servo motors, in particular to a servo motor fault diagnosis method and system based on data analysis.
Background
With the continuous improvement of the industrial automation degree, the servo motor is used as an important driving element in industrial equipment, and the running state of the servo motor is directly related to the performance and stability of the whole system, however, in the actual running process, the servo motor may malfunction due to various reasons, such as electrical faults, mechanical faults, control faults and the like, and if the faults cannot be found and processed in time, the equipment is stopped, the production efficiency is reduced, and even safety accidents are caused.
In the Chinese application with the application publication number of CN115235612A, an intelligent fault diagnosis system of a servo motor and a diagnosis method thereof are disclosed, global frequency domain correlation characteristics of a plurality of frequency domain statistical characteristics of vibration signals of the servo motor to be diagnosed are extracted through Fourier transform and a context encoder, a convolution neural network model is utilized to excavate local deep implicit characteristics of a waveform diagram of the vibration signals of the servo motor to be diagnosed, and when feature information of the two characteristics is fused, data intensive correction based on an attention mechanism is further carried out on the frequency domain correlation characteristics so as to enable classification probability to have self-adaptive dependence on feature vectors of different data densities based on probability expression of a classifier.
In the Chinese application with the application publication number of CN115015752A, a motor fault diagnosis method based on sparse decomposition and a neighborhood swarm algorithm is disclosed, and IM-HHT is utilized to extract the characteristics and signal analysis of a direct current motor. Carrying out sparse decomposition denoising treatment on a motor sampling signal, denoising the motor signal before treatment by utilizing an orthogonal matching pursuit algorithm, and selecting a plurality of optimal atomic linear combinations from an overcomplete dictionary; decomposing a given signal into a plurality of IMFs by using empirical mode decomposition, removing false IMFs by using correlation parameters, and finally performing Hilbert transformation to obtain a Hilbert spectrum of an original signal; selecting features based on a focused Euclidean distance judging method; the square neighborhood is used for selecting a manual bee colony algorithm to finish sequencing the motor signal characteristic factors; and classifying and identifying motor faults through a radial basis classifier.
In combination with the above application of the invention, the prior art has the following disadvantages:
1. The magnetic pole position is used as a key factor of the performance of the servo motor, the accuracy and the optimization degree of the magnetic pole position directly determine the running efficiency and the stability of the motor, however, the importance of the magnetic pole position is often ignored in the prior art when a fault diagnosis task is executed, and the neglect can lead to inaccuracy of fault diagnosis and delay the best opportunity for timely repairing and optimizing the performance of the motor;
2. For the deviation of the magnetic pole position, the evaluation is not limited to a single performance index, but multiple aspects such as torque fluctuation, torque maximum value and magnetic field distribution need to be comprehensively considered, however, the prior art usually only focuses on the performance of a certain aspect, and lacks the comprehensive evaluation of the magnetic pole position deviation, so that the limitation can not accurately judge whether the magnetic pole position reaches the optimal state, thereby limiting the improvement and optimization of the motor performance.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a servo motor fault diagnosis method and a system based on data analysis, which are characterized in that a load is kept unchanged, a torque mean value and a torque fluctuation value of a servo motor in a stable running state are calculated, the load is gradually increased, for each load point, a weight factor of each load point is determined through a hierarchical analysis method, a torque performance index is calculated and obtained by combining the maximum torque output and the torque fluctuation value of each load point, the servo motor is divided into a plurality of areas with the same size, the magnetic induction difference index of the servo motor is calculated and obtained by the magnetic field intensity of each area, the magnetic field intensity difference index of the servo motor is calculated and obtained by combining the torque performance index, the magnetic induction difference index and the magnetic field intensity difference index, a magnetic pole offset index is calculated and obtained, an offset threshold is preset, the magnetic pole offset index and the offset threshold are compared, corresponding measures are taken according to the comparison result, and the problems in the background technology are solved.
In order to achieve the above purpose, the invention is realized by the following technical scheme: a servo motor fault diagnosis method based on data analysis comprises the following steps:
The method comprises the steps of keeping the load unchanged, collecting torque data of the servo motor in a stable running state, constructing a torque data set, and calculating a torque average value and a torque fluctuation value of the servo motor in the stable running state;
Gradually increasing the load, recording the maximum torque output and the torque fluctuation value of each load point, determining the weight factor of each load point through a hierarchical analysis method, and calculating to obtain a torque performance index by combining the maximum torque output and the torque fluctuation value of each load point;
Dividing a servo motor into a plurality of areas with the same size, calculating to obtain a magnetic induction difference index of the servo motor through the magnetic induction intensity of each area, and calculating to obtain a magnetic field intensity difference index of the servo motor through the magnetic field intensity of each area;
and calculating and obtaining a magnetic pole offset index by combining the torque performance index, the magnetic induction difference index and the magnetic field intensity difference index, presetting an offset threshold, comparing the magnetic pole offset index with the offset threshold, and taking corresponding measures according to the comparison result.
Further, torque data of the servo motor are collected through a sensor, the sensor comprises a torque sensor or a torque measuring instrument, the load is kept unchanged in the data collection process, the sampling period of the torque measuring equipment is set, the collected torque data are collected, and a torque data set is constructed.
Further, torque data of the servo motor are obtained, after linear normalization processing, a torque average value and a torque fluctuation value of the servo motor in a stable running state are obtained through calculation, and a corresponding calculation formula is as follows:
；
Wherein, Represents the torque average, tf represents the torque ripple value,/>Representing the torque value, t representing the identity of the sampling period,/>T is a positive integer.
Further, the load is gradually increased, when the load of the servo motor reaches the target load and is kept stable, the maximum torque output and the torque fluctuation value of each load point are recorded, and the weight factor of each load point is determined by a hierarchical analysis method according to the importance of the overall performance evaluation of each load point.
Further, combining the maximum torque output and the torque fluctuation value of each load point, and calculating to obtain a torque performance index after dimensionless treatment, wherein the calculation formula is as follows:
；
wherein TPI represents a torque performance index, Maximum torque value representing the i-th load point,/>Torque ripple value representing the i-th load point,/>The weight factor representing the i-th load point, alpha represents the adjustment factor,/>, andI represents the identity of each load point,/>N is a positive integer.
Further, the magnetic induction difference index of the servo motor is obtained through calculation through the magnetic induction intensity of each area, and the calculation formula is as follows:
；
wherein MDI represents the magnetic induction difference index, The magnetic induction intensity of the region j is represented, j represents the number of each region,/>M is a positive integer.
Further, the magnetic field intensity difference index of the servo motor is calculated and obtained through the magnetic field intensity of each region, and the calculation formula is as follows:
；
wherein MFI represents the index of the difference in magnetic field strength, The magnetic field strength of the region j is represented, j represents the number of each region,/>M is a positive integer.
Further, the torque performance index, the magnetic induction difference index and the magnetic field intensity difference index are combined, and after dimensionless treatment, the magnetic pole offset index is calculated and obtained, and the calculation formula is as follows:
；
Wherein MPI represents a magnetic pole offset index, MDI represents a magnetic induction difference index, MFI represents a magnetic field strength difference index, TPI represents a torque performance index, 、/>/>Representing the weight coefficient,/>，/>，/>。
Further, when the pole offset index is less than the offset threshold, maintaining continuous monitoring of the pole position; when the magnetic pole offset index is greater than or equal to the offset threshold, an early warning is sent out to prompt that urgent measures need to be immediately taken.
A servo motor fault diagnosis system based on data analysis comprises a torque analysis module, a magnetic field analysis module and a magnetic pole deviation analysis module; the torque analysis module is used for keeping the load unchanged, collecting torque data of the servo motor in a stable running state, constructing a torque data set, calculating a torque average value and a torque fluctuation value of the servo motor in the stable running state, gradually increasing the load, recording the maximum torque output and the torque fluctuation value of each load point, determining the weight factor of each load point through a analytic hierarchy process, and calculating to obtain a torque performance index by combining the maximum torque output and the torque fluctuation value of each load point;
The magnetic field analysis module divides the servo motor into a plurality of areas with the same size, calculates and obtains a magnetic induction difference index of the servo motor through the magnetic induction intensity of each area, and calculates and obtains the magnetic field intensity difference index of the servo motor through the magnetic field intensity of each area;
the magnetic pole offset analysis module is used for calculating and obtaining a magnetic pole offset index by combining the torque performance index, the magnetic induction difference index and the magnetic field intensity difference index, presetting an offset threshold value, comparing the magnetic pole offset index with the offset threshold value, and taking corresponding measures according to the comparison result.
The invention provides a servo motor fault diagnosis method and a system based on data analysis, which have the following beneficial effects:
(1) The monitoring of the torque fluctuation value can help to find potential problems in time, if the torque fluctuation suddenly increases, the motor is in fault or is about to be in fault, such as bearing abrasion, magnetic pole position deviation and the like, so that maintenance measures can be taken in advance, faults are avoided, and the downtime and maintenance cost are reduced.
(2) The performance of the motor under different load conditions can be more accurately known by gradually increasing the load, recording the maximum torque output and the torque fluctuation value of each load point and determining the weight factor of each load point by using a hierarchical analysis method, and on the basis, the calculated torque performance index can comprehensively reflect the torque output capacity and the stability of the motor and provide a powerful basis for evaluating whether the magnetic pole position is at the optimal position.
(3) The magnetic induction difference index and the magnetic field intensity difference index are calculated, so that the existence of magnetic pole deviation can be indicated, the degree of the deviation can be quantitatively estimated, and the severity of the magnetic pole deviation can be known by carrying out numerical analysis on the difference index, thereby providing an important reference for making repair measures and predicting potential risks.
(4) By integrating a plurality of indexes to evaluate the magnetic pole position offset, early warning can be provided when the offset happens just or is about to happen; the method is favorable for finding potential problems in time, and avoiding serious influence of magnetic pole deviation on system performance and safety, thereby preventing possible faults or accidents.
Drawings
FIG. 1 is a schematic diagram of steps of a servo motor fault diagnosis method based on data analysis;
FIG. 2 is a schematic flow chart of a servo motor fault diagnosis method based on data analysis;
FIG. 3 is a schematic diagram of a servo motor fault diagnosis system based on data analysis.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the invention provides a servo motor fault diagnosis method based on data analysis, which comprises the following steps:
Step one: the method comprises the steps of keeping the load unchanged, collecting torque data of the servo motor in a stable running state, constructing a torque data set, and calculating a torque average value and a torque fluctuation value of the servo motor in the stable running state;
The first step comprises the following steps:
step 101: keeping the load unchanged, setting a sampling period, collecting torque data of the servo motor through a sensor, and summarizing the collected torque data to construct a torque data set;
specifically, ensuring that the servo motor and a control system thereof work normally, and the servo motor is installed and configured correctly, setting the load condition of the servo motor, ensuring that the load remains unchanged in the data acquisition process, preparing torque measuring equipment such as a torque sensor or a torque measuring instrument, and checking whether the working state of the torque measuring equipment is normal;
the torque measuring equipment is arranged on an output shaft of the servo motor, so that the equipment can accurately measure the torque output by the motor, a sampling period and a data recording mode of the torque measuring equipment are set, and the sampling period can take 1 second, 5 seconds or 10 seconds;
Starting a servo motor and enabling the servo motor to run to a stable state, wherein the stable state means that parameters such as the rotating speed and the torque of the servo motor are kept relatively stable within a certain time, data acquisition is started, torque data of the servo motor are recorded, and no external interference or abnormal event occurs in the data acquisition process;
continuously collecting data for a period of time to obtain enough sample points for subsequent analysis, wherein the length of the collecting time depends on the characteristics of the servo motor and the required data precision, and collecting the collected torque data to construct a torque data set;
Step 102: the method comprises the steps of obtaining torque data of a servo motor, and calculating to obtain a torque average value and a torque fluctuation value of the servo motor in a stable running state after linear normalization processing, wherein a corresponding calculation formula is as follows:
；
Wherein, Represents the torque average, tf represents the torque ripple value,/>Representing the torque value, t representing the identity of the sampling period,/>T is a positive integer.
It should be noted that the magnetic pole position affects the torque ripple, and in the optimum position, the torque ripple is minimal, the motor operates more smoothly, and in the case of deviating from the optimum position, the torque ripple increases, which may affect the stability of the motor.
In use, the contents of steps 101 to 102 are combined:
Monitoring of the torque ripple value can help to find potential problems in time, if the torque ripple suddenly increases, the motor may be involved in a fault or impending fault, such as bearing wear, magnetic pole position offset, etc., which helps to take maintenance measures in advance, avoid faults, and reduce downtime and maintenance costs.
Step two: gradually increasing the load, recording the maximum torque output and the torque fluctuation value of each load point, determining the weight factor of each load point through a hierarchical analysis method, and calculating to obtain a torque performance index by combining the maximum torque output and the torque fluctuation value of each load point;
The second step comprises the following steps:
Step 201: gradually increasing the load, and when the load of the servo motor reaches a target load and keeps stable, stably operating for a period of time, and recording the maximum torque output and the torque fluctuation value of each load point;
it should be noted that, after each load increase, the servo motor is allowed to operate stably for a period of time, then corresponding torque values are recorded, the maximum torque value is found out from the recorded data and is used as the maximum torque output under the current load condition, and the torque fluctuation value is obtained through a calculation method in the step one;
Step 202: according to the importance of the overall performance evaluation of each load point, determining a weight factor of each load point by a hierarchical analysis method, combining the maximum torque output and the torque fluctuation value of each load point, and calculating to obtain a torque performance index after dimensionless processing, wherein the calculation formula is as follows:
；
wherein TPI represents a torque performance index, Maximum torque value representing the i-th load point,/>Torque ripple value representing the i-th load point,/>The weight factor representing the i-th load point, alpha represents the adjustment factor,/>, andI represents the identity of each load point,/>N is a positive integer.
It should be noted that, the difference of the magnetic pole positions directly affects the torque output of the servo motor, when the magnetic pole positions are at the optimal positions, the motor can provide the maximum torque output, so that the motor can cope with larger loads, otherwise, if the magnetic pole positions deviate from the optimal positions, the torque output is reduced, and the performance of the motor is also affected.
In use, the contents of steps 201 to 202 are combined:
The maximum torque output and the torque fluctuation value of each load point are recorded by gradually increasing the load, and the weight factor of each load point is determined by using a hierarchical analysis method, so that the performance of the motor under different load conditions can be known more accurately, and on the basis, the calculated torque performance index can comprehensively reflect the torque output capacity and the stability of the motor, thereby providing a powerful basis for evaluating whether the magnetic pole position is at the optimal position.
Step three: dividing a servo motor into a plurality of areas with the same size, calculating to obtain a magnetic induction difference index of the servo motor through the magnetic induction intensity of each area, and calculating to obtain a magnetic field intensity difference index of the servo motor through the magnetic field intensity of each area;
The third step comprises the following steps:
step 301: dividing a servo motor into a plurality of areas with the same size, and collecting magnetic induction intensity and magnetic field intensity data of each area of the servo motor through a magnetic field measuring sensor;
It should be noted that, in order to accurately analyze the magnetic field distribution of the servo motor, it is necessary to keep the current stable during the measurement, which can be achieved by using a stable power supply, a suitable current controller and suitable filtering measures, and at the same time, it is necessary to calibrate the measurement device before the measurement to ensure the accuracy and reliability thereof;
step 302: the magnetic induction difference index of the servo motor is obtained through calculation through the magnetic induction intensity of each area, and the calculation formula is as follows:
；
wherein MDI represents the magnetic induction difference index, The magnetic induction intensity of the region j is represented, j represents the number of each region,/>M is a positive integer;
It should be noted that, when the magnetic pole position is shifted, the magnetic induction intensity is directly affected, the magnetic pole position is shifted to cause the magnitude and direction of the magnetic induction intensity to change, specifically, the vector direction of the magnetic induction intensity will not keep the original uniform distribution, but may be disordered or distorted, meanwhile, the magnitude of the magnetic induction intensity may also have significant difference at different positions, and no regular change trend is presented;
step 303: the magnetic field intensity difference index of the servo motor is obtained through calculation through the magnetic field intensity of each area, and the calculation formula is as follows:
；
wherein MFI represents the index of the difference in magnetic field strength, The magnetic field strength of the region j is represented, j represents the number of each region,/>M is a positive integer.
It should be noted that, the offset of the magnetic pole position breaks the original magnetic field distribution mode, so that the spatial distribution of the magnetic field intensity is not uniform, which may result in the enhancement of the magnetic field intensity in some areas, the weakening of the magnetic field intensity in other areas, and even the local maximum or minimum of the magnetic field intensity may occur, in addition, the direction of the magnetic field may also change, and the original regular distribution is not maintained any more.
In use, the contents of steps 301 to 303 are combined:
The magnetic induction difference index and the magnetic field intensity difference index are calculated, so that the existence of magnetic pole deviation can be indicated, the degree of the deviation can be quantitatively estimated, and the severity of the magnetic pole deviation can be known by carrying out numerical analysis on the difference index, thereby providing an important reference for making repair measures and predicting potential risks.
Step four: and calculating and obtaining a magnetic pole offset index by combining the torque performance index, the magnetic induction difference index and the magnetic field intensity difference index, presetting an offset threshold, comparing the magnetic pole offset index with the offset threshold, and taking corresponding measures according to the comparison result.
The fourth step comprises the following steps:
Step 401: the method comprises the steps of obtaining a torque performance index, a magnetic induction difference index and a magnetic field intensity difference index of a servo motor, and calculating to obtain a magnetic pole offset index after dimensionless treatment by combining the torque performance index, the magnetic induction difference index and the magnetic field intensity difference index, wherein the calculation formula is as follows:
；
Wherein MPI represents a magnetic pole offset index, MDI represents a magnetic induction difference index, MFI represents a magnetic field strength difference index, TPI represents a torque performance index, 、/>/>Representing the weight coefficient,/>，/>，/>；
Step 402: an offset threshold value is preset, the magnetic pole offset index is compared with the offset threshold value, and corresponding measures are made according to the comparison result, specifically comprising:
When the pole offset index is less than the offset threshold, indicating that the pole position offset is within an acceptable range, the system performance and safety are not significantly affected, at which time conventional monitoring and maintenance measures may be taken, maintaining a continuous view of the pole position, and preparing for further action if necessary;
When the magnetic pole deviation index is larger than or equal to the deviation threshold value, the magnetic pole deviation is indicated to be beyond an acceptable range, and the system performance or safety can be adversely affected, at the moment, early warning is sent, and prompt that urgent measures such as adjusting the magnetic pole position, replacing related parts or taking other necessary repair measures are needed immediately, so that the normal operation and the safety of the system are ensured.
In use, the contents of steps 401 to 402 are combined:
by integrating multiple indices to evaluate the pole position offset, early warning can be provided when the offset is just occurring or is about to occur. This helps to find potential problems in time, avoiding pole shifting from having a serious impact on system performance and safety, thereby preventing possible failures or accidents.
Referring to fig. 3, the invention also provides a servo motor fault diagnosis system based on data analysis, which comprises a torque analysis module, a magnetic field analysis module and a magnetic pole deviation analysis module, wherein the torque analysis module keeps the load unchanged, collects the torque data of the servo motor in a stable running state, constructs a torque data set, calculates the torque mean value and the torque fluctuation value of the servo motor in the stable running state, gradually increases the load, records the maximum torque output and the torque fluctuation value of each load point, determines the weight factor of each load point through a hierarchical analysis method, and combines the maximum torque output and the torque fluctuation value of each load point to calculate and obtain a torque performance index;
The magnetic field analysis module divides the servo motor into a plurality of areas with the same size, calculates and obtains a magnetic induction difference index of the servo motor through the magnetic induction intensity of each area, and calculates and obtains the magnetic field intensity difference index of the servo motor through the magnetic field intensity of each area;
the magnetic pole offset analysis module is used for calculating and obtaining a magnetic pole offset index by combining the torque performance index, the magnetic induction difference index and the magnetic field intensity difference index, presetting an offset threshold value, comparing the magnetic pole offset index with the offset threshold value, and taking corresponding measures according to the comparison result.
In the application, the related formulas are all the numerical calculation after dimensionality removal, and the formulas are one formulas for acquiring a large amount of data and performing software simulation to obtain the latest real situation, and coefficients in the formulas are set by a person skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein can be implemented as a combination of electronic hardware, computer software, and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application.
Claims (10)
1. A servo motor fault diagnosis method based on data analysis is characterized by comprising the following steps:
The method comprises the steps of keeping the load unchanged, collecting torque data of the servo motor in a stable running state, constructing a torque data set, and calculating a torque average value and a torque fluctuation value of the servo motor in the stable running state;
Gradually increasing the load, recording the maximum torque output and the torque fluctuation value of each load point, determining the weight factor of each load point through a hierarchical analysis method, and calculating to obtain a torque performance index by combining the maximum torque output and the torque fluctuation value of each load point;
Dividing a servo motor into a plurality of areas with the same size, calculating to obtain a magnetic induction difference index of the servo motor through the magnetic induction intensity of each area, and calculating to obtain a magnetic field intensity difference index of the servo motor through the magnetic field intensity of each area;
and calculating and obtaining a magnetic pole offset index by combining the torque performance index, the magnetic induction difference index and the magnetic field intensity difference index, presetting an offset threshold, comparing the magnetic pole offset index with the offset threshold, and taking corresponding measures according to the comparison result.
2. The method for diagnosing a servo motor fault based on data analysis according to claim 1, wherein the servo motor torque data is collected by a sensor, the sensor comprises a torque sensor or a torque measuring instrument, the load is kept unchanged during the data collection process, the sampling period of the torque measuring equipment is set, the collected torque data is summarized, and a torque data set is constructed.
3. The servo motor fault diagnosis method based on data analysis according to claim 2, wherein torque data of the servo motor is obtained, the torque mean value and the torque fluctuation value of the servo motor in a stable running state are obtained through calculation after linear normalization processing, and the corresponding calculation formula is as follows:
；
Wherein, Represents the torque average, tf represents the torque ripple value,/>Representing the torque value, t representing the identity of the sampling period,T is a positive integer.
4. The method for diagnosing a failure of a servo motor based on data analysis according to claim 1, wherein the load is gradually increased, and when the load of the servo motor reaches a target load and is kept stable, the maximum torque output and the torque fluctuation value thereof are recorded for each load point, and the weight factor of each load point is determined by a hierarchical analysis method according to the importance of each load point to the overall performance evaluation.
5. The method for diagnosing a fault in a servo motor based on data analysis as claimed in claim 4, wherein the torque performance index is calculated by combining the maximum torque output and the torque fluctuation value of each load point and performing dimensionless processing, and the calculation formula is as follows:
；
wherein TPI represents a torque performance index, Maximum torque value representing the i-th load point,/>Torque ripple value representing the i-th load point,/>The weight factor representing the i-th load point, alpha represents the adjustment factor,/>, andI represents the identity of each load point,/>N is a positive integer.
6. The method for diagnosing a servo motor fault based on data analysis according to claim 1, wherein the magnetic induction difference index of the servo motor is calculated by the magnetic induction intensity of each region, and the calculation formula is as follows:
；
wherein MDI represents the magnetic induction difference index, The magnetic induction intensity of the region j is represented, j represents the number of each region,M is a positive integer.
7. The method for diagnosing a servo motor failure based on data analysis according to claim 6, wherein the magnetic field intensity difference index of the servo motor is calculated by the magnetic field intensity of each region, and the calculation formula is as follows:
；
wherein MFI represents the index of the difference in magnetic field strength, The magnetic field strength of the region j is represented, j represents the number of each region,M is a positive integer.
8. The servo motor fault diagnosis method based on data analysis according to claim 1, wherein the torque performance index, the magnetic induction difference index and the magnetic field intensity difference index are combined, and after dimensionless processing, the magnetic pole offset index is calculated and obtained, and the calculation formula is as follows:
；
Wherein MPI represents a magnetic pole offset index, MDI represents a magnetic induction difference index, MFI represents a magnetic field strength difference index, TPI represents a torque performance index, 、/>/>Representing the weight coefficient,/>，/>，/>。
9. The method for diagnosing a servo motor fault based on data analysis of claim 8, wherein continuous monitoring of the position of the magnetic pole is maintained when the magnetic pole offset index is less than the offset threshold;
When the magnetic pole offset index is greater than or equal to the offset threshold, an early warning is sent out to prompt that urgent measures need to be immediately taken.
10. A servo motor fault diagnosis system based on data analysis for implementing the method of any one of claims 1 to 9, comprising:
the torque analysis module is used for keeping the load unchanged, collecting torque data of the servo motor in a stable running state, constructing a torque data set, calculating a torque average value and a torque fluctuation value of the servo motor in the stable running state, gradually increasing the load, recording the maximum torque output and the torque fluctuation value of each load point, determining the weight factor of each load point through a hierarchical analysis method, and calculating to obtain a torque performance index by combining the maximum torque output and the torque fluctuation value of each load point;
The magnetic field analysis module divides the servo motor into a plurality of areas with the same size, calculates and obtains a magnetic induction difference index of the servo motor through the magnetic induction intensity of each area, and calculates and obtains the magnetic field intensity difference index of the servo motor through the magnetic field intensity of each area;
the magnetic pole offset analysis module is used for calculating and obtaining a magnetic pole offset index by combining the torque performance index, the magnetic induction difference index and the magnetic field intensity difference index, presetting an offset threshold value, comparing the magnetic pole offset index with the offset threshold value, and taking corresponding measures according to the comparison result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410509022.4A CN118091409A (en) | 2024-04-26 | 2024-04-26 | Servo motor fault diagnosis method and system based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410509022.4A CN118091409A (en) | 2024-04-26 | 2024-04-26 | Servo motor fault diagnosis method and system based on data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118091409A true CN118091409A (en) | 2024-05-28 |
Family
ID=91153588
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410509022.4A Withdrawn CN118091409A (en) | 2024-04-26 | 2024-04-26 | Servo motor fault diagnosis method and system based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118091409A (en) |
-
2024
- 2024-04-26 CN CN202410509022.4A patent/CN118091409A/en not_active Withdrawn
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111353482B (en) | LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method | |
| Yang | An intelligent condition-based maintenance platform for rotating machinery | |
| KR101316486B1 (en) | Error detection method and system | |
| EP3764184B1 (en) | Abnormality determination assistance device | |
| JP5538597B2 (en) | Anomaly detection method and anomaly detection system | |
| WO2014034273A1 (en) | Facility status monitoring method and facility status monitoring device | |
| Yan et al. | Fisher’s discriminant ratio based health indicator for locating informative frequency bands for machine performance degradation assessment | |
| CN116593811B (en) | Integrated frequency converter running state monitoring system and monitoring method | |
| CN117458955A (en) | Operation control method and system of motor | |
| CN117786385B (en) | Three-phase asynchronous motor fault monitoring method and system based on twin network | |
| US20220011766A1 (en) | Error-based method for calculating a remaining useful life of an apparatus | |
| CN116561514A (en) | Method, system, device and medium for diagnosing faults of vehicle hub bearing unit | |
| CN117609869A (en) | Intelligent fault diagnosis and self-learning method and system for speed reducer | |
| CN118501692A (en) | Servo motor fault diagnosis method and system | |
| CN112621381B (en) | Intelligent health state evaluation method and device for machine tool feeding system | |
| CN114088389A (en) | Data processing method and related device for gearbox | |
| CN117994955A (en) | Method and device for building and alarming temperature alarm model of hydroelectric generating set | |
| CN111474476B (en) | Motor fault prediction method | |
| CN118091409A (en) | Servo motor fault diagnosis method and system based on data analysis | |
| CN116383750A (en) | Rolling bearing early-stage abnormality detection method based on windowed differential health index | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| Gu et al. | A prediction method of operation trend for large axial-flow fan based on vibration-electric information fusion | |
| CN118245808B (en) | Machine learning-based speed reducer fault diagnosis method and system | |
| CN118331204B (en) | Safety state monitoring method and system for industrial automation control equipment | |
| CN118732671A (en) | Intelligent test system for motor control response time of new energy automobile |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20240528 |
|
| WW01 | Invention patent application withdrawn after publication |