Method and system for predicting and analyzing service life of stepping motor based on big data

Abstract

The invention relates to the technical field of data processing, in particular to a stepping motor service life prediction analysis method and system based on big data, and the method comprises the steps: obtaining a plurality of operation data sequences in the operation process of a motor, and dividing each operation data sequence into a plurality of data segments with the same length based on a preset length; constructing a regression model of each operation data through support vector regression, and predicting the service life of the motor according to predicted values output by all the regression models; and in the construction process of the regression model, taking the adjustment factor of each data segment of any operation data as a weight, weighting the insensitive loss of the corresponding data segment, and performing data regression according to the weighted insensitive loss. The accuracy of the constructed regression model can be improved, and accurate prediction of the service life of the motor is realized.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and more specifically, to a method and system for predicting and analyzing the life of a stepper motor based on big data. Background Art

[0002] Stepper motors are widely used in a variety of precision machinery due to their high precision, good controllability and excellent reliability. However, during long-term high-load operation, stepper motors will face problems such as wear, aging and potential failures. These factors will not only affect the operating efficiency of the equipment, but may also threaten production safety. In order to improve the accuracy and effectiveness of maintenance, the operation status of the motor is monitored in real time with the help of big data analysis technology, and the motor life is evaluated in combination with the prediction model. It can effectively predict potential failures and optimize maintenance timing, thereby improving the reliability of the equipment, production efficiency and preventive maintenance level.

[0003] In the related technology, for example, a patent application document with publication number CN111382546A discloses a method for predicting the life of a generator insulation system based on support vector machine modeling. The method includes: using the aging time as input to establish six non-destructive electrical parameter prediction models for the stator bars of the generator, predicting the six non-destructive electrical parameters in units of five aging cycles, and then bringing the results into the established support vector machine-based generator insulation residual breakdown field strength life prediction model until the prediction result is lower than the critical residual field strength, and obtaining the generator life.

[0004] However, the above scheme does not take into account the influence of data of different importance when constructing the support vector machine regression model, and cannot make the important data have a higher fitting accuracy, which leads to the low accuracy of the constructed support vector machine regression model, and the low accuracy of the predicted value determined based on the support vector machine regression model, which in turn leads to the inability to accurately predict the life of the generator. Summary of the invention

[0005] In order to solve the problem that the motor life cannot be accurately predicted due to the low accuracy of the prediction model, the present invention provides a stepper motor life prediction analysis method and system based on big data.

[0006] According to a first aspect of the present invention, a stepper motor life prediction and analysis method based on big data is provided, comprising: Acquire multiple operation data sequences during the operation of the motor, and divide each operation data sequence into a number of data segments of the same length based on a preset length; A regression model for each operating data is constructed by support vector regression, and the motor life is predicted based on the predicted values ​​output by all regression models. In the process of constructing the regression model, the adjustment factor of each data segment of any operating data is used as a weight, the insensitive loss of the corresponding data segment is weighted, and data regression is performed based on the weighted insensitive loss. The method for obtaining the adjustment factor includes: Use any data segment as a test set for cross-validation, obtain the residuals of each data in the data segment, and calculate the degree of fluctuation of the data segment: ; For the The first item of operation data The degree of fluctuation of each data segment; is the standard deviation of the data segment; The average standard deviation of all data segments for this run; For the data segment The residual of the data; is the amount of data in this data segment; is the natural exponential function; Quantify the difference between the ratio of the average residuals of the data segment and the data segment of the corresponding period in the remaining operating data and the ratio of the overall residuals of the corresponding two operating data to obtain the abnormality degree of the data segment and calculate the adjustment factor of the data segment. The adjustment factor is positively correlated with the degree of fluctuation and the degree of abnormality.

[0007] When constructing a regression model for each item of operating data through support vector regression, the present invention can utilize the adjustment factor of the data segment of each item of operating data to adaptively adjust the insensitive loss of the corresponding data segment, so that the data segment with a smaller adjustment factor passes through a lower insensitive loss, thereby improving the regression accuracy, and the data segment with a larger adjustment factor passes through a higher insensitive loss, thereby reducing the impact of the regression result of the corresponding data segment on the overall regression result, thereby ensuring the accuracy of the constructed regression model, and thus achieving accurate prediction of the motor life.

[0008] Preferably, the abnormality degree satisfies the following relationship: ; In the formula, For the The first item of operation data The degree of abnormality of each data segment; For the The first item of operation data The average residual of the data segment; For the The first item of operation data The average residual of the data segment; For the The average residual of all data segments of the running data; For the The average residual of all data segments of the running data; is the total number of running data items.

[0009] When calculating the degree of abnormality, the present invention utilizes the feature that the regression effects between data segments with the same ordinal number in each item of operating data are similar, so that the possibility of the existence of abnormal data in each data segment can be accurately evaluated.

[0010] Preferably, when constructing a regression model for each item of operating data by support vector regression, the regression label of each regression model is the remaining life of the motor.

[0011] The present invention can predict the life of the motor through different types of operating data, thereby ensuring the accuracy of the predicted life of the motor.

[0012] Preferably, when any data segment of any item of running data is used as a test set for cross-validation of support vector regression, the method further comprises: All remaining data segments of the running data are used as training sets to determine the cross-validation results of the test set based on the regression model trained on the training set.

[0013] Preferably, the method for obtaining the adjustment factor includes: The fluctuation degree and the abnormality degree of any data segment are obtained, and the fluctuation degree and the abnormality degree of the data segment are multiplied to obtain the adjustment factor of the data segment.

[0014] The present invention can set a larger adjustment factor for a data segment with a larger degree of fluctuation and abnormality, thereby reducing the impact of abnormal data by increasing the insensitive loss of the corresponding data segment.

[0015] Preferably, the multiple operating data sequences include a current data sequence, a temperature data sequence, a rotation speed data sequence, a vibration intensity data sequence and an output torque data sequence.

[0016] Preferably, predicting the motor life according to the predicted values ​​output by all regression models includes: Obtain all the constructed regression models, input the current, temperature, speed, vibration intensity and output torque of the motor at the current moment during operation into the corresponding regression model, and output the predicted value of each operation data; The average value of the motor life determined based on the predicted value of each operating data is taken as the final motor life.

[0017] The present invention can improve the accuracy of the constructed regression model, thereby realizing accurate prediction of the life of the motor.

[0018] According to a second aspect of the present invention, a stepper motor life prediction and analysis system based on big data is provided. The system includes a memory and a processor. A computer program is stored in the memory. The processor executes the computer program to implement the steps of the first aspect of the present invention.

[0019] The present invention has the following effects: 1. When constructing a regression model for each operating data through support vector regression, the present invention can adaptively adjust the insensitive loss of each data segment of each operating data, so that the data segment with a larger adjustment factor has a larger sensitive loss, thereby reducing the impact of abnormal data, and the data segment with a smaller adjustment factor has a smaller sensitive loss, thereby improving the regression accuracy of the corresponding data segment, ensuring the accuracy of the constructed regression model, and thus accurately predicting the life of the motor.

[0020] 2. The present invention integrates various data and calculates the adjustment factors of each data segment, thereby ensuring the accuracy of the adjustment factors, thereby enabling accurate adaptation to insensitive losses when building a regression model. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 It is a schematic diagram of the steps of a method for predicting and analyzing the life of a stepper motor based on big data in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] 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 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0023] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0024] Reference Figure 1 The stepper motor life prediction and analysis method based on big data includes steps S1 and S2, which are as follows: S1: Acquire multiple operation data sequences during the operation of the motor, and divide each operation data sequence into a number of data segments with the same length based on a preset length.

[0025] In an exemplary embodiment of the present invention, the plurality of operating parameter sequences include a current data sequence, a temperature data sequence, a rotation speed data sequence, a vibration intensity data sequence, and an output torque data sequence.

[0026] It should be noted that the current, temperature, speed, vibration intensity and output torque during the operation of the motor can reflect the operating stability of the stepper motor, so the data that can reflect the operating stability of the stepper motor can be used as the data basis to predict the life of the stepper motor. Of course, the appropriate type of data can also be selected according to the specific situation. This embodiment does not specifically limit the selected data type, as long as it can reflect the operating stability of the stepper motor.

[0027] Specifically, the current, temperature, speed, vibration intensity and output torque of the motor during operation can be collected within a certain sampling period (such as within one month) and at a certain sampling frequency (such as once per hour) to obtain multiple operation data sequences during the operation of the motor. This embodiment does not specifically limit the sampling period and sampling frequency.

[0028] Optionally, the current data during the operation of the motor can be collected by an ammeter arranged in the motor power supply system, the temperature data during the operation of the motor can be collected by a thermometer arranged around the motor, the speed data during the operation of the motor can be measured by a tachometer, the vibration intensity data during the operation of the motor can be collected by a vibration sensor, and the output torque during the operation of the motor can be obtained by a torque sensor. This embodiment does not specifically limit the installation location and type of equipment for collecting data.

[0029] Optionally, the preset length can be recorded as , and then use the preset length Starting from the first data of each running data sequence, the interception length is to divide each operation data sequence into multiple data segments of the same length, thereby obtaining multiple data segments for each operation data. =10. This embodiment does not specifically limit the size of the preset length.

[0030] It should be noted that the data segments with the same sequence number in each item of operating data correspond to the same sampling period.

[0031] S2: A regression model for each operating data item is constructed through support vector regression, and the motor life is predicted based on the predicted values ​​output by all regression models. In the process of constructing the regression model, the adjustment factor of each data segment of any operating data item is used as a weight, the insensitive loss of the corresponding data segment is weighted, and data regression is performed based on the weighted insensitive loss.

[0032] In an exemplary embodiment of the present invention, when a regression model for each item of operating data is constructed by support vector regression, the regression label of each regression model is the remaining life of the motor.

[0033] It should be noted that when predicting the life of a motor by support vector regression, the traditional support vector regression algorithm usually directly uses all the collected data for regression modeling, so as to obtain the prediction of the motor life by the regression model. However, in the process of constructing the regression model, directly using all the data for regression does not fully take into account the importance of certain important features in the data, resulting in low fitting accuracy of key data, which in turn affects the overall accuracy of the regression model, resulting in the inability to accurately predict the life of the motor based on the obtained regression model. Therefore, the present invention improves the process of constructing a regression model by support vector regression, and the specific improvement is: using the calculated adjustment factor, adaptively adjusting the insensitive loss of each data segment of each operating data, so that the data segment with a lower adjustment factor can obtain a higher regression accuracy through a lower insensitive loss, so that a regression model with higher accuracy can be constructed based on the data regression results of each operating data, and an accurate prediction of the motor life can be achieved.

[0034] Among them, epsilon-insensitive loss is a component of the support vector regression (SVR) algorithm, which defines the tolerance error range. In the insensitive loss function, the loss is penalized only when the error between the predicted value and the actual value exceeds the specified tolerance range (i.e., insensitive loss). In other words, the lower the insensitive loss, the higher the regression accuracy.

[0035] Specifically, the adjustment factor of any data segment can be determined by the following steps: Step 1: Use any data segment as a test set for cross-validation, obtain the residuals of each data in the data segment, and calculate the degree of fluctuation of the data segment; It should be noted that the result of cross-validation of any data segment of any operating data as a test set can reflect the degree of fit between the data segment and all other data segments of the operating data. The data segment with a higher degree of fit indicates that it performs better in the regression model, and the fluctuation of the data will affect the fitting effect of the data, which is specifically manifested as: the more drastic the fluctuation of the data in the data segment, the greater the residual of each data in the data segment. Therefore, the present invention utilizes this feature to evaluate the fluctuation of the corresponding data segment by obtaining the residual of each data in each data segment. Among them, the process of cross-validation of support vector regression based on the test set is a prior art, and this embodiment will not be described in detail here.

[0036] In an exemplary embodiment of the present invention, when any data segment of any item of running data is used as a test set for cross-validation of support vector regression, the method further includes: All remaining data segments of the running data are used as training sets to determine the cross-validation results of the test set based on the regression model trained on the training set.

[0037] Furthermore, after determining the residuals of each data in each data segment, the degree of fluctuation of any data segment can be calculated. Specifically, the degree of fluctuation satisfies the following relationship: ; In the formula, For the The first item of operation data The degree of fluctuation of each data segment; is the standard deviation of the data segment; The average standard deviation of all data segments for this run; When the data segment is used as a test set, the first The residual of the data; is the amount of data in this data segment; is a natural exponential function, where the natural exponential function refers to a function with a natural constant An exponential function with base .

[0038] in, Reflects the The first item of operation data The standard deviation of the data segment is The ratio of the average standard deviation of all data in the data segment. The larger the value, the more drastic the fluctuation of the data in the data segment, and the greater the fluctuation degree of the corresponding data segment.

[0039] Reflects the The first item of operation data In the data segment The normalized value of the residual of each data; Reflects the The first item of operation data The sum of the normalized residuals when the data segments are used as test sets for cross-validation. The larger the value, the worse the fit between the data in the data segment and all other data segments of the running data, that is, the poorer the performance of the data segment in the regression model, which further indicates that the data in the data segment fluctuates more violently, and the corresponding degree of fluctuation of the data segment is larger.

[0040] Optionally, when the fluctuation degree of any data segment is large, the possibility of abnormal data existing in the data segment is relatively large. Therefore, when performing support vector regression based on the data segment, a larger insensitive loss should be set to avoid using overly precise regression for the data segment to affect the accuracy of the overall regression model.

[0041] Step 2: Quantify the difference between the ratio of the average residual of the data segment and the data segment of the corresponding period in the remaining operation data and the ratio of the overall residual of the corresponding two operation data to obtain the abnormality degree of the data segment; It should be noted that for each data segment of each operating data, a curve regression can be performed on the motor life according to each operating data, and the regression results obtained according to each operating data should be similar. If there is a significant difference in the regression effect between any data segment of any operating data and the remaining data segments of the corresponding time period, then the data segment is likely to contain abnormal data. Therefore, the present invention uses this feature to calculate the degree of abnormality of each data segment.

[0042] Specifically, the degree of abnormality of any data segment satisfies the following relationship: ; In the formula, For the The first item of operation data The degree of abnormality of each data segment; For the The first item of operation data The average residual of the data segment; For the The first item of operation data The average residual of the data segment; For the The average residual of all data segments of the running data; For the The average residual of all data segments of the running data; is the total number of running data items.

[0043] in, Reflects the Item operation data and The first item of operation data The ratio of the average residuals of the data segments; Reflects the Item operation data and The ratio of the overall residuals of the running data is When the value of is large, it means The value of The difference in the values ​​of The relationship between the individual data segments does not match the overall relationship between the two operating data.

[0044] Quantified the The first item of operation data The first data segment and other data The difference between the ratio of the average residual of the data segment and the ratio of the overall residual of the corresponding two running data. The larger the value, the The first item of operation data The regression effect of the data segment is similar to the regression effect of the other running data. The regression effects of the data segments are quite different, which shows that The first item of operation data A data segment is more likely to contain abnormal data, and the corresponding data segment has a greater degree of abnormality.

[0045] Optionally, when the degree of abnormality of any data segment of any running data is relatively large, a relatively large insensitive loss should be set when performing support vector regression based on the data segment to reduce the impact of the abnormal data on the regression result.

[0046] In another embodiment, the difference between the ratio of the average residual of any data segment of any item of operating data and the data segments of the corresponding time period in the remaining items of operating data and the ratio of the overall residuals of the corresponding two items of operating data can also be quantified in other ways, such as by taking the absolute value and then averaging it.

[0047] Step 3: Calculate the adjustment factor for the data segment. The adjustment factor is positively correlated with both the degree of fluctuation and the degree of abnormality.

[0048] In an exemplary embodiment of the present invention, the determination of the adjustment factor of any data segment may be achieved by the following steps: The fluctuation degree and abnormality degree of any data segment of any operation data are obtained, and the fluctuation degree of the data segment and the abnormality degree of the data segment are multiplied to obtain the adjustment factor of the data segment.

[0049] Optionally, when the fluctuation degree of any data segment of any item of operating data is large and the degree of abnormality of the data segment is also large, it means that the data in the data segment deviates greatly from all other data of the operating data. Setting a larger adjustment factor can appropriately increase the insensitivity loss of the data segment, thereby preventing the result of support vector regression based on the data segment from affecting the overall regression accuracy.

[0050] In another embodiment, the adjustment factor of each data segment of each item of operating data may also be calculated by other calculation methods, such as by a summation calculation method instead of a product calculation method.

[0051] Furthermore, the adjustment factor determination method can be used to calculate the adjustment factor of each data segment of each operation data, and then the adjustment factor of each data segment of any operation data is used as a weight to weight the insensitive loss of the corresponding data segment to obtain the insensitive loss of each data segment of each operation data. In this embodiment, the initial values ​​of the insensitive loss of all data segments are , this embodiment does not specifically limit the initial value of the insensitive loss of each data segment.

[0052] Next, the process of building a regression model for each running data using support vector regression is described: Firstly, based on the fluctuation degree and abnormality degree of each data segment of each operating data, the adjustment factor of the corresponding data segment is calculated, and then the adjusted insensitive loss of each data segment of each operating data is adaptively obtained based on the adjustment factor.

[0053] Afterwards, all data segments of any item of operating data are used as training sets, the remaining life of the motor corresponding to each data in each data segment is used as the regression label, and the adjusted insensitive loss of each data segment is used as the input feature. Data regression is performed based on the training set, regression label and input feature to obtain the regression model of the operating data, and then the regression model of all items of operating data is determined.

[0054] It should be noted that the process of constructing a regression model of data by using support vector regression is a prior art and will not be described in detail in this embodiment.

[0055] Furthermore, after the regression model of each operation data is obtained, the motor life can be predicted according to the predicted values ​​output by all regression models. In an exemplary embodiment of the present invention, the prediction of the motor life can be achieved by the following steps: Obtain all the constructed regression models, input the current, temperature, speed, vibration intensity and output torque of the motor at the current moment during operation into the corresponding regression model, and output the motor life predicted by each operating data; take the average value of the motor life predicted based on each operating data as the final life of the motor.

[0056] The present invention can adaptively adjust the insensitivity loss of different data segments when performing support vector regression, so that data segments without abnormal data can obtain higher regression accuracy through lower insensitivity loss, and data segments with abnormal data can obtain higher insensitivity loss through higher insensitivity loss, thereby reducing the impact of abnormal data on regression results, ensuring the accuracy of the constructed regression model, and thus achieving accurate prediction of motor life.

[0057] The present invention also provides a stepper motor life prediction and analysis system based on big data. The system includes a memory and a processor, and a computer program is stored in the memory. The computer program integrates the functions of the stepper motor life prediction and analysis method based on big data. When the computer program is executed, the stepper motor life prediction and analysis method based on big data can improve the accuracy of the constructed regression model and achieve accurate prediction of the motor life.

[0058] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0059] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A stepper motor life prediction and analysis method based on big data, characterized in that: include: Acquire multiple operation data sequences during the operation of the motor, and divide each operation data sequence into a number of data segments of the same length based on a preset length; A regression model for each operating data is constructed by support vector regression, and the motor life is predicted according to the predicted values ​​output by all regression models; in the process of constructing the regression model, the adjustment factor of each data segment of any operating data is used as a weight, the insensitive loss of the corresponding data segment is weighted, and data regression is performed according to the weighted insensitive loss; the method for obtaining the adjustment factor includes: Use any data segment as a test set for cross-validation, obtain the residuals of each data in the data segment, and calculate the degree of fluctuation of the data segment: ; For the The first item of operation data The degree of fluctuation of each data segment; is the standard deviation of the data segment; The average standard deviation of all data segments for this run; For the data segment The residual of the data; is the amount of data in this data segment; is the natural exponential function; Quantify the difference between the ratio of the average residuals of the data segment and the data segment of the corresponding period in the remaining operating data and the ratio of the overall residuals of the corresponding two operating data to obtain the abnormality degree of the data segment and calculate the adjustment factor of the data segment. The adjustment factor is positively correlated with the degree of fluctuation and the degree of abnormality.

2. The stepper motor life prediction and analysis method based on big data according to claim 1 is characterized in that: The abnormality degree satisfies the following relationship: ； In the formula, For the The first item of operation data The degree of abnormality of each data segment; For the The first item of operation data The average residual of the data segment; For the The first item of operation data The average residual of the data segment; For the The average residual of all data segments of the running data; For the The average residual of all data segments of the running data; is the total number of running data items.

3. The stepper motor life prediction and analysis method based on big data according to claim 1 is characterized in that: When constructing a regression model for each operating data item through support vector regression, the regression label of each regression model is the remaining life of the motor.

4. The stepper motor life prediction and analysis method based on big data according to claim 1 is characterized in that: When any data segment of any item of running data is used as a test set for cross-validation of support vector regression, the method further includes: All remaining data segments of the running data are used as training sets, so as to determine the cross-validation result of the test set based on the regression model trained by the training set.

5. The stepper motor life prediction and analysis method based on big data according to claim 1 is characterized in that: The method for obtaining the adjustment factor includes: The fluctuation degree and abnormality degree of any data segment of any operation data are obtained, and the fluctuation degree of the data segment and the abnormality degree of the data segment are multiplied to obtain the adjustment factor of the data segment.

6. The stepper motor life prediction and analysis method based on big data according to claim 1 is characterized in that: The plurality of operation data sequences include a current data sequence, a temperature data sequence, a rotation speed data sequence, a vibration intensity data sequence and an output torque data sequence.

7. The stepper motor life prediction and analysis method based on big data according to claim 6 is characterized in that: The motor life is predicted based on the predicted values ​​output by all regression models, including: Obtain all the regression models constructed, input the current, temperature, speed, vibration intensity and output torque of the motor at the current moment during operation into the corresponding regression model, and output the motor life predicted by each operation data; The average value of the motor life predicted based on each operating data is taken as the final life of the motor.

8. The stepper motor life prediction and analysis system based on big data is characterized by: The stepper motor life prediction and analysis system based on big data includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps of the stepper motor life prediction and analysis method based on big data as described in any one of claims 1 to 7.

Images