Health monitoring method and system of servo motor and electronic equipment

By collecting the acoustic emission signals of servo motors in industrial sites, conducting principal component analysis and comparison of Mahayana distances, the problem of difficulty in accurately monitoring early failures of servo motors in the existing technology is solved, and accurate monitoring and real-time monitoring of the operating status of servo motors is achieved. Assessment avoids production downtime and economic losses.

CN119044758AInactive Publication Date: 2024-11-29ANHUI ENG UNIV IND INNOVATION TECH RES CO LTD +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411147383.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-21
Publication Date
2024-11-29
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

It is difficult to accurately monitor the early micro-failures of servo motors in industrial sites in the prior art, especially in noisy environments. Traditional methods such as current detection and vibration detection are insufficient to effectively detect deep fine crack failures.

Method used

By collecting the acoustic emission signals of the servo motor, performing principal component analysis of time domain characteristic parameters and comparing the Mahayana distance, establishing a database to determine whether the signal is a fault signal, and achieving accurate monitoring of the operating status of the servo motor.

Benefits of technology

Realize the real-time health status evaluation of the servo motor, can promptly detect operational failures, avoid production downtime, reduce economic losses, and simplify data analysis through dimensionality reduction processing, improving the accuracy and efficiency of detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119044758A_ABST
    Figure CN119044758A_ABST
Patent Text Reader

Abstract

The invention discloses a health monitoring method and system for a servo motor and electronic equipment. The health monitoring method comprises the following steps: acquiring an acoustic emission signal generated by the servo motor by using a sensor; extracting time domain characteristic parameters related to the operation state of the servo motor, and extracting principal components; the method comprises the following steps: extracting acoustic emission signals within a period of time in a health state and a fault state of the servo motor, processing the acoustic emission signals, extracting a principal component data set of time domain characteristic parameters related to the health state or the fault state of the servo motor, and establishing a principal component database; whether an acoustic emission signal collected in an industrial field belongs to a fault signal or a healthy signal is calculated through mahalanobis distance comparison, and the operation state of the servo motor is judged. According to the method, after dimension reduction processing is carried out on time domain characteristic parameters of extracted acoustic emission signals of the robot, whether signals collected on an industrial site belong to fault signals or healthy signals is calculated through mahalanobis distance comparison, and the running state of a servo motor is judged.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of signal processing technology, and in particular to a health monitoring method, system and electronic equipment for a servo motor. Background Art

[0002] Servo motors are an important part of industrial robots and are mainly used in the transmission system of industrial robots. When a motor fails during operation, it will seriously affect the working efficiency of the industrial robot. In serious cases, the entire production line will be paralyzed, causing huge economic losses. Therefore, the health status monitoring of industrial robot servo motors has very important economic value.

[0003] Traditional methods for monitoring the health status of industrial robot motors usually monitor parameters such as current, vibration, and temperature. However, current detection is not sensitive enough for small-scale faults. Vibration detection is not accurate enough for deep and fine crack faults, and cannot detect early minor faults of motors.

[0004] Acoustic emission testing technology is a non-destructive testing method that can evaluate the health of materials by detecting tiny sound wave signals inside them. Acoustic emission testing technology is a method of evaluating the health of servo motors by analyzing the acoustic emission signals emitted by servo motors when industrial robots are working. It can achieve non-stop testing of servo motors.

[0005] Acoustic emission detection technology still has some difficulties and challenges. For example, it is very difficult to obtain clear results in noisy industrial sites because background noise will affect the readings. In order to ensure accurate results, noise reduction technology is needed to filter out excess noise, but it is still impossible to completely remove the noise signal. There are many methods for data noise reduction in the prior art, and most data noise reduction methods are relatively complex. Therefore, a new servo motor health monitoring method is needed that can accurately monitor the operating status of the servo motor through acoustic emission signals. Summary of the invention

[0006] In order to overcome the defects and shortcomings of the prior art, at least one purpose of the present invention is to provide a servo motor health monitoring method, system and electronic equipment. After the time domain characteristic parameters of the extracted robot acoustic emission signal are reduced in dimension, the Mahalanobis distance is used to compare and calculate whether the signal collected at the industrial site is a fault signal or a healthy signal, so as to judge the operating status of the servo motor and realize accurate monitoring of the servo motor.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present application provides a servo motor health monitoring method, comprising the following steps:

[0009] S1: Collecting acoustic emission signals, using sensors to collect acoustic emission signals generated by servo motors, and converting them into electrical signals;

[0010] S2: signal processing, receiving the electrical signal from the acoustic emission sensor, extracting the time domain characteristic parameters related to the running state of the servo motor, and performing principal component analysis on the time domain characteristic parameters to extract the principal components;

[0011] S3: Establish a database, extract the acoustic emission signals of the servo motor in a healthy state and a period of time under a fault state, process the acoustic emission signals, extract the principal component data set of the time domain characteristic parameters related to the healthy state or fault state of the servo motor, and establish a database of principal components;

[0012] S4: Monitoring and analysis: by comparing the Mahalanobis distance, it is calculated whether the acoustic emission signal collected at the industrial site is a fault signal or a healthy signal, and the operating status of the servo motor is determined.

[0013] In a possible implementation of the first aspect, step S4 specifically includes:

[0014] The acoustic emission signal emitted by the servo motor is received in real time, the acoustic emission signal within a preset time period is intercepted, and the acoustic emission signal is processed to extract the principal component data set of the time domain characteristic parameters related to the servo motor. The Mahalanobis distance between the principal component data set and the healthy data set and the fault data set in the database is calculated respectively, so as to determine whether the servo motor has a fault.

[0015] In a possible implementation of the first aspect above, when the Mahalanobis distance between the principal component data set of the monitored servo motor and the healthy data set in the database is significantly smaller than the Mahalanobis distance between the principal component data set and the fault data set in the database, it indicates that the servo motor is in a healthy state at this time; if the Mahalanobis distance between the principal component data set of the monitored servo motor and the healthy data set in the database is significantly larger than the Mahalanobis distance between the principal component data set and the fault data set in the database, it indicates that the servo motor is in a fault state at this time.

[0016] In a possible implementation of the first aspect above, if the Mahalanobis distance between the principal component data set of the monitored servo motor and the healthy data set in the database is not much different from the Mahalanobis distance between the principal component data set and the fault data set in the database, the acoustic emission signal within a preset time is intercepted again, and after repeating the acoustic emission signal processing step, the operating status of the servo motor is judged again by calculating the Mahalanobis distance between the healthy data set and the fault data set in the database.

[0017] In a possible implementation of the first aspect above, the principal component analysis method comprises the following steps:

[0018] S21: Centralize the time domain characteristic parameter data related to the operating state of the servo motor.

[0019]

[0020] x ij represents the data in the i-th row and j-th column, m represents the number of rows of data, and X ij Represents x ij Centralized data;

[0021] S22: Calculate the covariance matrix C of the data after center processing,

[0022]

[0023] Use an unbiased estimate when calculating the covariance matrix of the data This makes the result closer to the true value. n comes from the number of columns in the data matrix, X represents the data after center processing, and T here is an operation symbol in linear algebra, which means matrix transpose.

[0024] In a possible implementation of the first aspect, the present invention further includes:

[0025] Step S5: Output the result. When the Mahalanobis distance between the principal component data set constructed by the relevant characteristic parameters of the monitored servo motor operating status and the fault data set in the database is significantly smaller than the Mahalanobis distance between the principal component data set and the healthy data set in the database, it is determined that the servo motor is in a fault state and an alarm is issued.

[0026] When the Mahalanobis distance between the principal component data set constructed by the relevant characteristic parameters of the monitored servo motor operating status and the healthy data set in the database is significantly smaller than the Mahalanobis distance between the principal component data set and the fault data set in the database, the servo motor is judged to be in a healthy state and no subsequent processing is performed.

[0027] In a possible implementation of the first aspect, there are multiple acoustic emission sensors, which are respectively disposed at different parts of the servo motor;

[0028] And / or, the sensor is a piezoelectric ceramic sensor.

[0029] In a second aspect, an embodiment of the present application provides a servo motor health monitoring system for implementing the steps of the servo motor health monitoring method described above;

[0030] The system includes:

[0031] The signal acquisition module is used to collect the acoustic emission signal emitted by the servo motor and convert the acoustic emission signal into an electrical signal to be transmitted to the signal processing module;

[0032] The signal processing module includes a signal denoising module, a parameter extraction module and a principal component analysis module. The signal denoising module is used to perform denoising on the input acoustic emission signal; the parameter extraction module is used to calculate the time domain characteristic parameters of the denoised acoustic emission signal; the principal component analysis module is used to perform principal component analysis on the extracted time domain characteristic parameters to obtain several principal components with high correlation with the operating state of the servo motor.

[0033] In a possible implementation of the second aspect, the method further includes:

[0034] A database module, used for collecting and storing healthy data sets and fault data sets in different health states and fault states of the servo motor;

[0035] The signal monitoring module is used to intercept the acoustic emission signal received and processed by the signal processing module within a preset time period, construct a principal component data set corresponding to the servo motor state within the period by extracting characteristic parameters, and calculate the Mahalanobis distance between the principal component data set and the healthy data set and fault data set in the database, and determine whether the servo motor has a fault by the Mahalanobis distance.

[0036] In a third aspect, an embodiment of the present application provides an electronic device, comprising: one or more processors; one or more memories; the one or more memories storing one or more programs, and when the one or more programs are executed by the one or more processors, the electronic device executes the above-mentioned servo motor health monitoring method.

[0037] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0038] (1) Acoustic emission detection technology is a dynamic non-destructive detection method that can perform fault diagnosis when the industrial robot is in working condition without affecting production efficiency. Moreover, acoustic emission detection technology can detect acoustic emission signals generated by some minor faults such as cracks in the material. Based on acoustic emission technology, the present invention designs a method for diagnosing faults of industrial robot servo motors, which can effectively prevent serious damage to industrial robots and even shutdown problems.

[0039] (2) The present invention can capture and analyze the acoustic emission signals generated during the operation of the robot servo motor in real time, provide instant health status assessment, and promptly detect operating faults of the servo motor to avoid accidents.

[0040] (3) Since the Mahalanobis distance (MD) can accurately measure the correlation between data of different units in different dimensions and the similarity between different data groups, the present invention calculates whether the acoustic emission signal collected at the industrial site is a fault signal or a healthy signal through Mahalanobis distance comparison, and determines the operating status of the servo motor.

[0041] (4) The present invention realizes dimensionality reduction processing of the extracted time domain characteristic parameter data group through principal component analysis technology. The time domain characteristic parameters associated with the operating status of the servo motor are linearly recombined into several comprehensive indicators (i.e., principal components) through principal component analysis. It plays the role of dimensionality reduction and simplification of data while retaining the main information of the original variables, making it easier to grasp the main contradictions. By extracting the principal components, it is possible to reflect the overall servo motor acoustic emission signal data through fewer comprehensive variables, which can more simply and directly reflect the servo motor signal data status, and then judge the operating status of the servo motor. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 The figure is a schematic diagram of a process framework of a servo motor health monitoring method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] See also Figure 1 In a first aspect, an embodiment of the present application provides a servo motor health monitoring method, comprising the following steps:

[0045] S1: Collecting acoustic emission signals, using sensors to collect acoustic emission signals generated by the servo motor and converting them into electrical signals; in this embodiment, multiple sensors can be set, and multiple sensors are respectively set at various parts of the servo motor to monitor the acoustic emission signals generated by the robot's servo motor during operation, so as to achieve real-time monitoring of the operating status of the servo motor of the industrial robot without stopping the machine, and the detection is more accurate and effective. The sensor can be a piezoelectric ceramic sensor, an ultrasonic sensor, a sonar sensor, a surface acoustic wave sensor, etc.

[0046] The acoustic emission signal emitted by the servo motor is collected to the lower computer through the acoustic emission sensor and the preamplifier, and the lower computer is mainly responsible for signal collection. The signal acquisition module is composed of an acoustic emission sensor, a preamplifier and a DS-5 acoustic emission instrument. Since the acoustic emission signal generated by the servo motor is relatively weak, the servo motor acoustic emission signal collected by the sensor is converted into an electrical signal, and the electrical signal is amplified and processed, and the relatively weak signal emitted by the servo motor can be converted into an electrical signal that can be processed, which is convenient for subsequent signal processing. The main function of the lower computer in this embodiment is to collect the acoustic emission signal, and convert the acoustic emission signal into an electrical signal data to be transmitted to the upper computer.

[0047] S2: signal processing, receiving the electrical signal from the acoustic emission sensor, extracting the time domain characteristic parameters related to the running state of the servo motor, and performing principal component analysis on the time domain characteristic parameters to extract the principal component. In the present embodiment, the host computer realizes the dimensionality reduction processing of the extracted time domain characteristic parameter data group by the principal component analysis technology. The time domain characteristic parameters associated with the running state of the servo motor are linearly combined into several comprehensive indicators (i.e., principal components) by principal component analysis. It plays the role of dimensionality reduction and simplification of data under the premise of retaining the main information of the original variables, and it is easier to grasp the main contradiction. By extracting the principal component, it is possible to realize the overall reflection of the servo motor acoustic emission signal data by fewer comprehensive variables, which can more simply and directly reflect the servo motor signal data status, and then judge the running state of the servo motor.

[0048] S3: Establish a database, extract the acoustic emission signals of the servo motor in a healthy state and a period of time under a fault state, process the acoustic emission signals, extract the principal component data set of the time domain characteristic parameters related to the healthy state or fault state of the servo motor, and establish a database of principal components;

[0049] S4: Monitoring and analysis, through the comparison of Mahalanobis distance, it is calculated whether the acoustic emission signal collected at the industrial site is a fault signal or a healthy signal, and the operating status of the servo motor is determined. Since Mahalanobis distance (MD) can accurately measure the correlation between different dimensions and different units of data, as well as the similarity between different data groups. Specifically, it includes:

[0050] The acoustic emission signal emitted by the servo motor is received in real time, the acoustic emission signal within a preset time period is intercepted, and the acoustic emission signal is processed to extract the principal component data set of the time domain characteristic parameters related to the servo motor. The Mahalanobis distance between the principal component data set and the healthy data set and the fault data set in the database is calculated respectively, so as to determine whether the servo motor has a fault.

[0051] When the Mahalanobis distance between the principal component data set of the servo motor collected by on-site monitoring and the healthy data set in the database is significantly smaller than the Mahalanobis distance between the principal component data set and the fault data set in the database, it indicates that the servo motor is in a healthy state at this time; if the Mahalanobis distance between the principal component data set of the servo motor collected by on-site monitoring and the healthy data set in the database is significantly larger than the Mahalanobis distance between the principal component data set and the fault data set in the database, it indicates that the servo motor is in a fault state at this time.

[0052] If the Mahalanobis distance between the principal component data set of the servo motor collected by on-site monitoring and the healthy data set in the database is not much different from the Mahalanobis distance between the principal component data set and the fault data set in the database, the acoustic emission signal within a preset time is intercepted again, and after repeating the acoustic emission signal processing steps, the Mahalanobis distance between the healthy data set and the fault data set in the database is calculated again to determine the operating status of the servo motor. To prevent the situation where the collected signal is half healthy and half faulty, at this time, only one more set of data needs to be collected for Mahalanobis distance calculation to determine whether the signal is a healthy signal or a faulty signal, so as to accurately determine the operating status of the servo motor.

[0053] In a possible implementation of the first aspect, the method further includes step S5: outputting a result, when the Mahalanobis distance between the principal component data set constructed by the characteristic parameters related to the monitored operation status of the servo motor and the fault data set in the database is significantly smaller than the Mahalanobis distance between the principal component data set and the healthy data set in the database, it is determined that the servo motor is in a fault state and an alarm is issued;

[0054] When the Mahalanobis distance between the principal component data set constructed by the relevant characteristic parameters of the monitored servo motor operating status and the healthy data set in the database is significantly smaller than the Mahalanobis distance between the principal component data set and the fault data set in the database, the servo motor is judged to be in a healthy state and no subsequent processing is performed.

[0055] In a possible implementation of the first aspect above, the principal component analysis method comprises the following steps:

[0056] S21: Centralize the time domain characteristic parameter data related to the operating state of the servo motor.

[0057]

[0058] x ij represents the data in the i-th row and j-th column, m represents the number of rows of data, and X ij Represents x ij Centralized data;

[0059] S22: Calculate the covariance matrix C of the data after center processing,

[0060]

[0061] Use an unbiased estimate when calculating the covariance matrix of the data Make the result closer to the true value, n comes from the number of columns in the data matrix, and X represents the data after center processing. Find the data eigenvalues ​​and corresponding eigenvectors of the covariance matrix C, and set the three eigenvectors corresponding to the first three principal component eigenvalues ​​from large to small to be retained.

[0062] Table 1 Time domain characteristic parameters of servo motor at four different speeds in healthy state

[0063]

[0064] Table 2 is the decentralized data table of Table 1

[0065]

[0066] Table 3 is the time domain characteristic parameter table of the servo motor under four different speeds under fault conditions

[0067]

[0068] Table 4 is the decentralized data table of Table 3

[0069]

[0070] Table 5 Time domain characteristic parameter data of the control group (healthy signals at four different speeds)

[0071]

[0072] (1) According to the data in Tables 1 to 5, the mean and covariance matrix of the reference data are calculated respectively: The mean vector of the principal component of the health data is: [0.299 0.0827 0.0097]

[0074] The mean vector of the principal components of the fault data is:

[0075] [-0.238 0.197 -0.0463]

[0076] The covariance matrix of the principal components of the health data is:

[0077] 0.0115 -0.0275 -0.00323

[0078] -0.0275 0.104 -0.000893

[0079] -0.00323 -0.000893 0.111

[0080] The covariance matrix of the principal components of the fault data is;

[0081] 0.0482 0.052 -0.0123 0.0521 0.068 0.0101

[0083] -0.0123 0.0101 0.109

[0084] Substituting the above data into the Mahalanobis distance calculation formula (3) can obtain the result.

[0085] Mahalanobis distance

[0086] e1 is the data that needs to be judged (the control group, i.e., the data collected under the healthy condition at the industrial site);

[0087] C -1 is the covariance matrix of the reference data (the four groups of healthy data and the four groups of fault data in Tables 1 to 4 above); u1 is the mean of the reference data.

[0088] (2) Calculate the Mahalanobis distance between the discrimination control data and each reference data. The set of data with the smallest Mahalanobis distance is the discrimination result. The calculation results are as follows:

[0089] The Mahalanobis distance from the control group data to the healthy data is 1.805

[0090] The Mahalanobis distance from the control group data to the fault data is 11.109

[0091] Since the control group selected data under the healthy condition of the servo motor, it can be verified that the monitoring method of this embodiment can effectively determine whether the collected industrial site signal appears to be a fault signal, and then determine the operating condition of the industrial robot servo motor.

[0092] In a second aspect, an embodiment of the present application provides a servo motor health monitoring system, which is used to implement the steps of the above-mentioned servo motor health monitoring method; wherein the system includes:

[0093] The signal acquisition module is used to collect the acoustic emission signal emitted by the servo motor and convert the acoustic emission signal into an electrical signal and transmit it to the signal processing module; wherein the signal acquisition module includes:

[0094] A sensor for collecting acoustic emission signals emitted by the robot;

[0095] A preamplifier is used to amplify the acoustic emission signal collected by the sensor;

[0096] The acoustic emission detector is used to receive the amplified electrical signal after being processed by the preamplifier and transmit it to the signal processing module for signal processing.

[0097] The signal processing module includes a signal denoising module, a parameter extraction module and a principal component analysis module. The signal denoising module is used to perform denoising on the input acoustic emission signal to eliminate interference signals such as environmental noise at the industrial site and gear friction in the servo motor; the parameter extraction module is used to calculate the time domain characteristic parameters of the acoustic emission signal after denoising; the principal component analysis module is used to perform principal component analysis on the extracted time domain characteristic parameters to obtain several principal components with high correlation with the operating status of the servo motor.

[0098] In a possible implementation of the first aspect, the present invention further includes:

[0099] A database module, used for collecting and storing healthy data sets and fault data sets in different health states and fault states of the servo motor;

[0100] The signal monitoring module is used to intercept the acoustic emission signal received and processed by the signal processing module within a preset time period, construct a principal component data set corresponding to the servo motor state within the period by extracting characteristic parameters, and calculate the Mahalanobis distance between the principal component data set and the healthy data set and fault data set in the database, and determine whether the servo motor has a fault by the Mahalanobis distance.

[0101] In a third aspect, an embodiment of the present application provides an electronic device, comprising: one or more processors; one or more memories; one or more memories storing one or more programs, and when one or more programs are executed by one or more processors, the electronic device executes the above-mentioned servo motor health monitoring method.

[0102] The specific implementation of each module in this embodiment can refer to the above-mentioned method embodiment, which will not be described one by one here; it should be noted that the system provided in this embodiment is only illustrated by the division of the above-mentioned functional modules. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure can be divided into different functional modules to complete all or part of the functions described above.

[0103] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0104] It should be noted that, in the description of this application, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0105] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0106] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented with hardware, as in another embodiment, it can be implemented with any one of the following techniques well known in the art or a combination thereof.

[0107] A person skilled in the art may understand that all or part of the steps of the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0108] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0109] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0110] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A servo motor health monitoring method, characterized in that: The following steps are involved: S1: Collecting acoustic emission signals, using sensors to collect acoustic emission signals generated by servo motors, and converting them into electrical signals; S2: signal processing, receiving the electrical signal from the acoustic emission sensor, extracting the time domain characteristic parameters related to the running state of the servo motor, and performing principal component analysis on the time domain characteristic parameters to extract the principal components; S3: Establish a database, extract the acoustic emission signals of the servo motor in a healthy state and a period of time under a fault state, process the acoustic emission signals, extract the principal component data set of the time domain characteristic parameters related to the healthy state or fault state of the servo motor, and establish a database of principal components; S4: Monitoring and analysis: by comparing the Mahalanobis distance, it is calculated whether the acoustic emission signal collected at the industrial site is a fault signal or a healthy signal, and the operating status of the servo motor is determined.

2. A servo motor health monitoring method according to claim 1, characterized in that: Step S4 specifically includes: The acoustic emission signal emitted by the servo motor is received in real time, the acoustic emission signal within a preset time period is intercepted, and the acoustic emission signal is processed to extract the principal component data set of the time domain characteristic parameters related to the servo motor. The Mahalanobis distance between the principal component data set and the healthy data set and the fault data set in the database is calculated respectively, so as to determine whether the servo motor has a fault.

3. A servo motor health monitoring method according to claim 2, characterized in that: When the Mahalanobis distance between the principal component data set of the monitored servo motor and the healthy data set in the database is significantly smaller than the Mahalanobis distance between the principal component data set and the fault data set in the database, it indicates that the servo motor is in a healthy state at this time; if the Mahalanobis distance between the principal component data set of the monitored servo motor and the healthy data set in the database is significantly larger than the Mahalanobis distance between the principal component data set and the fault data set in the database, it indicates that the servo motor is in a fault state at this time.

4. A servo motor health monitoring method according to claim 3, characterized in that: If the Mahalanobis distance between the principal component data set of the monitored servo motor and the healthy data set in the database is not much different from the Mahalanobis distance between the principal component data set and the fault data set in the database, the acoustic emission signal within a preset time is intercepted again, and after repeating the acoustic emission signal processing steps, the operating status of the servo motor is judged again by calculating the Mahalanobis distance between the healthy data set and the fault data set in the database.

5. The servo motor health monitoring method according to claim 1, characterized in that: The principal component analysis method includes the following steps: S21: Centralize the time domain characteristic parameter data related to the operating state of the servo motor. x ij represents the data in the i-th row and j-th column, m represents the number of rows of data, and X ij Represents x ij Centralized data; S22: Calculate the covariance matrix C of the data after center processing, Use an unbiased estimate when calculating the covariance matrix of the data Make the result closer to the true value, n comes from the number of columns of the data matrix, and X represents the data after center processing.

6. A servo motor health monitoring method according to any one of claims 1 to 5, characterized in that: Also includes: Step S5: Output the result. When the Mahalanobis distance between the principal component data set constructed by the relevant characteristic parameters of the monitored servo motor operating status and the fault data set in the database is significantly smaller than the Mahalanobis distance between the principal component data set and the healthy data set in the database, it is determined that the servo motor is in a fault state and an alarm is issued. When the Mahalanobis distance between the principal component data set constructed by the relevant characteristic parameters of the monitored servo motor operating status and the healthy data set in the database is significantly smaller than the Mahalanobis distance between the principal component data set and the fault data set in the database, the servo motor is judged to be in a healthy state and no subsequent processing is performed.

7. The servo motor health monitoring method according to claim 1, characterized in that: There are multiple acoustic emission sensors, which are respectively arranged at different parts of the servo motor; And / or, the sensor is a piezoelectric ceramic sensor.

8. A servo motor health monitoring system, characterized in that: Steps for implementing a servo motor health monitoring method according to any one of claims 1 to 7; the system comprises: The signal acquisition module is used to collect the acoustic emission signal emitted by the servo motor and convert the acoustic emission signal into an electrical signal to be transmitted to the signal processing module; The signal processing module includes a signal denoising module, a parameter extraction module and a principal component analysis module. The signal denoising module is used to perform denoising on the input acoustic emission signal; the parameter extraction module is used to calculate the time domain characteristic parameters of the denoised acoustic emission signal; the principal component analysis module is used to perform principal component analysis on the extracted time domain characteristic parameters to obtain several principal components with high correlation with the operating state of the servo motor.

9. A robot acoustic emission signal noise reduction system according to claim 8, characterized in that: Also includes: A database module, used for collecting and storing healthy data sets and fault data sets in different health states and fault states of the servo motor; The signal monitoring module is used to intercept the acoustic emission signal received and processed by the signal processing module within a preset time period, construct a principal component data set corresponding to the servo motor state within the period by extracting characteristic parameters, and calculate the Mahalanobis distance between the principal component data set and the healthy data set and fault data set in the database, and determine whether the servo motor has a fault by the Mahalanobis distance.

10. An electronic device, characterized in that: include: one or more processors; One or more memories; the one or more memories store one or more programs, and when the one or more programs are executed by the one or more processors, the electronic device executes the servo motor health monitoring method described in any one of claims 1 to 7.

Citation Information

Cited By

  • Mechanical turntable damage monitoring method and system based on combination of acoustic emission technology and SVM (Support Vector Machine) damage classification

    CN120177631A