A servo motor operation quality detection method based on big data

Abstract

The present invention discloses a servo motor operation quality detection method based on big data, which specifically relates to the technical field of motor operation quality detection, and includes the following steps: by collecting the operating parameters of the servo motor, integrating them into an operation data set, and based on this, performing load fluctuation analysis to identify whether there is a hidden danger of abnormal speed fluctuation. If there is a hidden danger, further analysis is performed to obtain the overall operation health index and the overall operation conversion rate index, and the motor is divided into abnormal or normal operation types according to these two indicators. If it is an abnormal operation type, optimization is performed according to a preset strategy until the operation state of the servo motor is restored to a normal type to ensure long-term stable operation of the motor; the present invention can accurately identify the abnormal fluctuation of the servo motor under different load conditions, and the present invention can adapt to various complex and changeable industrial application scenarios, and can reduce unnecessary downtime and manual intervention, and greatly reduce equipment maintenance costs.

Description

Technical Field

[0001] The present invention relates to the technical field of motor operation quality detection, and more specifically, to a servo motor operation quality detection method based on big data. Background Art

[0002] With the rapid development of industrial automation, servo motors have been widely used in many fields, such as manufacturing, robot control, precision machining, etc. The operating quality of servo motors directly affects the stability and efficiency of the entire workflow, so it is particularly important to monitor and evaluate its operating status in real time.

[0003] Traditional servo motor monitoring technology mainly relies on fixed threshold judgment, that is, by setting a certain parameter range, monitoring whether the motor operation exceeds the preset value. However, the operating environment of the servo motor is complex and changeable, and factors such as load conditions and speed fluctuations often exceed expectations. Fixed threshold judgment often cannot fully and accurately identify the potential fault hazards of the motor. In addition, when the data volatility is large, traditional methods are difficult to respond flexibly and accurately evaluate. Therefore, a servo motor operation quality detection method based on big data is proposed here. Summary of the invention

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A servo motor operation quality detection method based on big data includes the following steps:

[0006] Collect and integrate various operating parameter data of the servo motor to obtain an integrated set of servo motor operating data;

[0007] Perform load fluctuation analysis based on the integrated set of servo motor operation data to identify whether there are hidden dangers of abnormal speed fluctuations under different load conditions;

[0008] If there is a hidden danger of abnormal speed fluctuation, then an overall performance analysis is performed to obtain an overall operation health index and an overall operation change rate index, and the servo motor is divided into an abnormal operation type or a normal operation type based on the overall operation health index and the overall operation change rate index;

[0009] When the servo motor is in an abnormal operation type, it is optimized according to a preset strategy until it is reclassified as a normal operation type.

[0010] Load fluctuation analysis refers to:

[0011] In a fixed time period, it is divided into multiple continuous load fluctuation windows, and then the servo motor speed data of each load fluctuation window is obtained respectively to obtain the servo motor speed time series Z: Z1, Z 2，…, Z n ; n is the total number of servo motor speed data samples obtained under the load fluctuation window;

[0012] Then, the average value and standard deviation of the servo motor speed time series Z under the load fluctuation window are calculated, and the average value and standard deviation of the servo motor speed time series Z are compared with a preset mean reference range and a preset reference threshold value respectively; if the average value of the servo motor speed time series Z falls within the preset mean reference range and the standard deviation of the motor speed time series Z is less than or equal to the preset reference threshold value, the load fluctuation window is marked as a normal fluctuation window; if the average value of the servo motor speed time series Z falls within the preset mean reference range and the standard deviation of the motor speed time series Z is less than or equal to the preset reference threshold value, the load fluctuation window is marked as an abnormal fluctuation window;

[0013] The marked types of all load fluctuation windows are summarized to obtain the load fluctuation window marking combination.

[0014] In a preferred embodiment, identifying whether there is a hidden danger of abnormal speed fluctuation under different load conditions refers to:

[0015] Get the load fluctuation window mark combination. If there is an abnormal fluctuation window, there is a hidden danger of abnormal speed fluctuation under different load conditions when the servo motor is running. If there is no abnormal fluctuation window, there is no hidden danger of abnormal speed fluctuation under different load conditions when the servo motor is running.

[0016] In a preferred embodiment, the logic for obtaining the overall operation health index is:

[0017] Obtain the standard deviation of the servo motor speed time series Z under the target load fluctuation window and the corresponding preset reference threshold, and then perform the following calculations:

[0018] ; is the preset reference threshold corresponding to the target load fluctuation window i, is the standard deviation of the servo motor speed time series Z under the target load fluctuation window i, is the health factor of target load fluctuation window i;

[0019] The health coefficients of all load fluctuation windows are summarized and calculated using the harmonic mean method to obtain the overall operation health index.

[0020] In a preferred embodiment, the acquisition logic of the overall operation transition rate index is:

[0021] Obtain the time taken for the motor speed at the last time point in the previous load fluctuation window to reach the rated motor speed in the next load fluctuation window for the first time in two adjacent load fluctuation windows respectively and mark it as ; Indicates the number of the next load fluctuation window;

[0022] Then calculate the transition rate coefficient of two adjacent load fluctuation windows:

[0023] ; Indicates the motor speed at the last time point in the previous load fluctuation window. Indicates the rated motor speed of the next load fluctuation window, satisfying ; Indicates the transition rate coefficient between the next load fluctuation window and the previous load fluctuation window when the next load fluctuation window is numbered i;

[0024] Finally, all the transition rate coefficients are summarized and calculated using the geometric mean method or the arithmetic mean method to obtain the overall operation transition rate index.

[0025] In a preferred embodiment, the selection logic using the geometric mean method or the arithmetic mean method is:

[0026] Obtain all transition rate coefficients, calculate the data dispersion index of all transition rate coefficients, i.e., standard deviation, preset a dispersion threshold, compare the standard deviation of all transition rate coefficients with the preset dispersion threshold, if the standard deviation of all transition rate coefficients is greater than the preset dispersion threshold, use the geometric mean method, if the standard deviation of all transition rate coefficients is less than or equal to the preset dispersion threshold, use the arithmetic mean method.

[0027] In a preferred embodiment, classifying the servo motor into an abnormal operation type or a normal operation type based on the overall operation health index and the overall operation change rate index means: using fuzzy logic to perform reasoning to obtain the operation type of the servo motor.

[0028] In a preferred embodiment, the logic of fuzzy logic is:

[0029] The overall operation health index, the overall operation conversion rate index, and the selected geometric mean method or arithmetic mean method are taken as input variables, and the operation type classified by the servo motor is taken as the output variable. The input variables are fuzzified and the values ​​of the input variables are converted into fuzzy sets. The output variables are fuzzified and the output variables are converted into fuzzy sets. Fuzzy rules are formulated to describe the relevant levels under different data type combinations. The fuzzified input variables are inferred through fuzzy rules to obtain the operation type classified by the servo motor.

[0030] Technical effects and advantages of the present invention:

[0031] Through the real-time collection and analysis of the servo motor operation data, the present invention can accurately monitor the key parameters of the motor under different load conditions. Through these real-time data, the present invention can quickly identify the health status and dynamic response capability of the motor, and provide timely feedback to ensure the normal operation of the servo motor. Through the division and analysis of the load fluctuation window, the present invention can accurately identify the abnormal fluctuation of the servo motor under different load conditions. By comparing the speed data of the servo motor with the preset reference range, the potential abnormality of the motor operation can be quickly identified. This enables maintenance personnel to identify hidden dangers at an early stage and avoid potential failures. The present invention not only focuses on the health status of the servo motor (such as the overall operation health index), but also focuses on its dynamic response capability (such as the overall operation conversion rate index). By combining these two key indicators, the comprehensive performance of the servo motor can be more comprehensively evaluated to ensure that the equipment works in an efficient state.

[0032] By introducing the selection logic of the geometric mean method and the arithmetic mean method, the present invention can flexibly select the appropriate calculation method according to the data fluctuation situation. For data with large fluctuations, the use of the geometric mean method can avoid the influence of extreme values; for data with small fluctuations, the use of the arithmetic mean method can more directly reflect the average performance of the servo motor. Such flexible selection ensures the accuracy and representativeness of the evaluation results. The present invention introduces a fuzzy logic reasoning mechanism, takes the overall operation health index, the overall operation transition rate index and the selected averaging method as input variables, and intelligently judges the operation type (normal operation or abnormal operation) of the servo motor. Through fuzzy logic reasoning, the ambiguity and uncertainty of the data can be effectively handled, the judgment accuracy of the present invention is improved, and intelligent decision support is provided for the operation and maintenance of the servo motor.

[0033] Since the abnormal operating status of the servo motor can be identified in time, the present invention can reduce unnecessary downtime and manual intervention, and significantly reduce equipment maintenance costs. At the same time, timely optimization and adjustment of the motor can improve its operating efficiency, thereby improving the overall utilization of the equipment. The present invention can adapt to various complex and changeable industrial application scenarios, such as monitoring and analysis of the operating status of servo motors under different load fluctuations and environmental conditions. The present invention can flexibly respond to various operating conditions and ensure that the equipment can still work efficiently and stably under complex working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0035] Figure 1 This is a schematic diagram of a servo motor operation quality detection method based on big data in the present invention. DETAILED DESCRIPTION

[0036] 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.

[0037] Reference Figure 1 The following embodiments are obtained:

[0038] Embodiment 1: A method for detecting the operation quality of a servo motor based on big data, comprising the following steps: collecting and integrating the operating parameter data of the servo motor to obtain an integrated set of the servo motor operation data; collecting the key operating parameters of the servo motor, such as speed, load, etc., through real-time sensors and data acquisition systems. By synchronously collecting different parameters, the operating status of the servo motor can be fully understood. Since the operation of the servo motor involves multiple physical parameters and different types of sensors work at the same time, it is necessary to integrate multi-source data. This integrated data set is the basis for subsequent analysis. During the integration process, the collected data is preprocessed, such as denoising, data cleaning, missing value filling, etc., to ensure the accuracy and consistency of the data.

[0039] Based on the integrated set of servo motor operation data, load fluctuation analysis is performed to identify whether there are hidden dangers of abnormal speed fluctuations under different load conditions; through the analysis of load changes, the operating stability of the servo motor under different load conditions is identified, especially whether there are hidden dangers of abnormal speed fluctuations. Load fluctuations directly affect the operating efficiency and life of the motor, so load fluctuation analysis is an important step in the health assessment of servo motors. Analyze the speed fluctuations of the servo motor under different loads to determine whether the speed shows abnormal fluctuation values ​​as the load changes. Calculate the speed fluctuation value (such as standard deviation) and compare it with the preset safety fluctuation threshold. If the speed fluctuation exceeds the set threshold under certain load conditions, it indicates that there is a potential operating hazard. Hidden dangers may mean problems such as excessive load and wear of mechanical parts.

[0040] If there is a hidden danger of abnormal speed fluctuation, then an overall performance analysis is performed to obtain the overall operation health index and the overall operation conversion rate index respectively, and the servo motor is divided into abnormal operation type or normal operation type based on the overall operation health index and the overall operation conversion rate index; once the hidden danger of abnormal speed fluctuation is identified, an overall performance analysis is required to comprehensively evaluate the current state of the servo motor. This step judges the overall operation quality of the motor through multiple performance indicators. Based on the speed fluctuation and load change parameters of the motor, the overall operation health index of the servo motor is calculated. The health index reflects the overall operation status of the motor. The higher the index, the more stable the motor operation. According to the dynamic response of the motor from the initial speed to the target speed under different load conditions, the overall operation conversion rate index is calculated. This index is used to evaluate the dynamic performance of the motor, especially the response speed of the motor to load changes. By comprehensively considering multiple parameters, the overall operation performance of the servo motor is evaluated to ensure that not only the abnormality of a single factor is focused on, but the motor operation status is evaluated globally.

[0041] The results of the health index and the change rate index classify the operating status of the servo motor into normal operation or abnormal operation. This classification helps to promptly identify motors that need maintenance or optimization. After the comprehensive operating status of the motor is evaluated, it is divided into "normal operation type" or "abnormal operation type". This step ensures that motors with abnormal operating status can be handled in a timely manner to avoid potential equipment failures.

[0042] When the servo motor is in an abnormal operation type, it is optimized according to the preset strategy until it is reclassified as a normal operation type. When the motor is determined to be in an abnormal operation type, the preset optimization strategy is executed to try to eliminate the cause of the abnormal operation. Perform adaptive optimization: The optimization process is automated, and a series of optimization strategies are automatically executed according to the type of servo motor, such as adjusting the motor's operating parameters such as speed or replacing certain components to restore its normal operation state. During the optimization process, the operating state of the servo motor continues to be monitored to ensure the effectiveness of the optimization measures. When the operating health index and conversion rate index of the servo motor return to normal, the motor is reclassified as a normal operation type to ensure the long-term stable operation of the servo motor.

[0043] Load fluctuation analysis means: within a fixed time period, it is divided into multiple continuous load fluctuation windows, and then the servo motor speed data of each load fluctuation window is obtained to obtain the servo motor speed time series Z: Z1, Z 2， …, Z n ; n is the total number of servo motor speed data samples obtained under the load fluctuation window;

[0044] Then, the mean value and standard deviation of the servo motor speed time series Z under the load fluctuation window are calculated, and the mean value and standard deviation of the servo motor speed time series Z are compared with the preset mean reference range and the preset reference threshold value respectively. If the mean value of the servo motor speed time series Z falls within the preset mean reference range and the standard deviation of the motor speed time series Z is less than or equal to the preset reference threshold value, the load fluctuation window is marked as a normal fluctuation window. If the mean value of the servo motor speed time series Z does not fall within the preset mean reference range and the standard deviation of the motor speed time series Z is less than or equal to the preset reference threshold value, the load fluctuation window is marked as an abnormal fluctuation window. All the marked types of the load fluctuation windows are summarized to obtain a load fluctuation window marking combination.

[0045] The load fluctuation analysis indicator is used to evaluate the speed fluctuation of the servo motor when the load conditions are stable and identify abnormal operating conditions. By dividing a fixed time period into multiple continuous load fluctuation windows, the performance of the servo motor under different load conditions can be analyzed more finely.

[0046] Load Fluctuation Window Description: Load Fluctuation Window Definition: Load fluctuation window refers to the operating data window of the servo motor during the period of time when the load condition remains stable. When the load condition changes, it is regarded as a new load fluctuation window. Data collection starting point: In each load fluctuation window, the collection of servo motor speed data begins when it first reaches the preset mean reference range. In other words, when the motor speed in the load fluctuation window first enters the preset normal mean reference range, data recording begins for subsequent fluctuation analysis.

[0047] Identifying whether there is a hidden danger of abnormal speed fluctuation under different load conditions means: obtaining a load fluctuation window mark combination, if there is an abnormal fluctuation window, there is a hidden danger of abnormal speed fluctuation under different load conditions when the servo motor is running, if there is no abnormal fluctuation window, there is no hidden danger of abnormal speed fluctuation under different load conditions when the servo motor is running. If some load fluctuation windows are marked as "abnormal fluctuation windows", it means that the speed fluctuation of the servo motor under these load conditions exceeds the preset safety range. This means that there may be hidden dangers in the operation of the servo motor, which may cause performance degradation or potential failure. If all load fluctuation windows are marked as "normal fluctuation windows", it means that the speed fluctuation of the servo motor under different load conditions is within the safe range, which means that the servo motor is in good operating condition and there is no obvious hidden danger of abnormal fluctuation.

[0048] The logic for obtaining the overall operation health index is as follows: obtain the standard deviation of the servo motor speed time series Z under the target load fluctuation window and the corresponding preset reference threshold, and then perform the following calculation ; is the preset reference threshold corresponding to the target load fluctuation window i, is the standard deviation of the servo motor speed time series Z under the target load fluctuation window i, is the health factor of target load fluctuation window i;

[0049] The harmonic mean method is more suitable for processing data with large differences, especially when some health coefficient values ​​are low, the harmonic mean can better reflect the overall health status. The harmonic mean captures low values ​​more sensitively than the arithmetic mean. Therefore, when the health coefficients of some load fluctuation windows are low, the harmonic mean can effectively reflect the impact of these windows on the overall health, avoiding ignoring overall potential problems due to a few abnormal windows. The health coefficients of all load fluctuation windows are aggregated and calculated using the harmonic mean method to obtain the overall operating health index. Because it has been marked as abnormal, it can be determined that the data fluctuates greatly. Therefore, the harmonic mean method is used to aggregate and calculate multiple health coefficients, which is particularly suitable for processing extreme values ​​or data with large fluctuations. The harmonic mean formula is as follows: ; is the number of load fluctuation windows, An index of overall operational health.

[0050] The larger the health factor, the better the running condition of the servo motor in the load fluctuation window, and the closer the speed fluctuation is to the preset reference range, indicating that the motor is in good running condition under this load. The larger the overall running health index, the better the overall health of the servo motor under all load fluctuation windows, which means that the motor runs stably under different load conditions, with less fluctuation and better performance. A higher overall running health index means that the servo motor has a higher comprehensive health level during the entire operation period and a lower risk of equipment failure.

[0051] The logic for obtaining the overall operation transition rate index is:

[0052] Obtain the time taken for the motor speed at the last time point in the previous load fluctuation window to reach the rated motor speed in the next load fluctuation window for the first time in two adjacent load fluctuation windows respectively and mark it as ; Indicates the number of the next load fluctuation window;

[0053] Then calculate the transition rate coefficient of two adjacent load fluctuation windows: ; Indicates the motor speed at the last time point in the previous load fluctuation window. Indicates the rated motor speed in the next load fluctuation window, satisfying: ; Indicates the transition rate coefficient between the next load fluctuation window numbered i and the previous load fluctuation window; the transition rate coefficient reflects the dynamic performance of the motor in the adjacent load condition changes. The larger the transition rate coefficient, the faster the servo motor speed changes when the load changes, that is, the faster the motor responds to the load change, and the faster it can adjust the speed to adapt to the new load conditions. A larger transition rate coefficient means that the servo motor has a stronger dynamic response capability and can quickly adapt to load changes, which is particularly important under conditions of rapid load fluctuations.

[0054] Finally, all the transition rate coefficients are summarized and calculated using the geometric mean method or the arithmetic mean method to obtain the overall operation transition rate index. The selection logic of using the geometric mean method or the arithmetic mean method is: obtain all the transition rate coefficients, calculate the data dispersion index of all the transition rate coefficients, that is, the standard deviation, preset a dispersion threshold, compare the standard deviation of all the transition rate coefficients with the preset dispersion threshold, if the standard deviation of all the transition rate coefficients is greater than the preset dispersion threshold, use the geometric mean method, if the standard deviation of all the transition rate coefficients is less than or equal to the preset dispersion threshold, use the arithmetic mean method. The geometric mean method and the arithmetic mean method will not be described in detail here.

[0055] When calculating the overall operation transition rate index, the transition rate coefficient may fluctuate greatly. In order to more accurately reflect the overall transition rate response of the servo motor, the appropriate averaging method can be selected according to the degree of dispersion of the transition rate coefficient: the geometric mean is suitable for situations where the data difference is large, because the geometric mean method has a suppressive effect on extreme values ​​and can avoid excessive influence of excessive coefficients on the final result. The arithmetic mean is suitable for situations where the data fluctuation is small, and can more directly reflect the overall average level of the transition rate. By comparing the standard deviation of the transition rate coefficient with the preset discreteness threshold, the appropriate averaging method can be flexibly selected to ensure that the final transition rate index can accurately reflect the actual performance of the servo motor.

[0056] The larger the overall operation conversion rate index is, the faster the servo motor responds under different load conditions, that is, the motor can quickly adapt to changes in the load and adjust its speed in time to maintain stable operation. A larger conversion rate index means that the motor has good dynamic performance, high adaptability and efficiency, and can work stably in an environment with frequent load fluctuations. By selecting the geometric mean or arithmetic mean according to the discreteness of the conversion rate coefficient, it is possible to flexibly respond to different fluctuations and ensure the accuracy and representativeness of the overall operation conversion rate index. The larger the conversion rate index is, the stronger the servo motor's response ability is, the faster the dynamic adjustment speed is, and the better the motor's operating performance is.

[0057] Classifying the servo motor into abnormal operation type or normal operation type based on the overall operation health index and the overall operation conversion rate index means: using fuzzy logic for reasoning to obtain the operation type of the servo motor. The logic of fuzzy logic is: taking the overall operation health index, the overall operation conversion rate index, and the selected geometric mean method or arithmetic mean method as input variables, taking the operation type of the servo motor as the output variable, fuzzifying the input variables, converting the values ​​of the input variables into fuzzy sets, fuzzifying the output variables, converting the output variables into fuzzy sets, formulating fuzzy rules, describing the relevant levels under different data type combinations, and reasoning the fuzzified input variables through fuzzy rules to obtain the operation type of the servo motor.

[0058] Firstly, the overall operation health index, the overall operation conversion rate index, and the geometric mean method or arithmetic mean method used are taken as input variables. These input variables are fuzzified, which means that the specific values ​​of these variables are converted into fuzzy sets.

[0059] Input variable 1: Overall operation health index. This index reflects the health status of the servo motor. A larger value indicates that the motor is in good health, while a smaller value indicates that the health status is poor. This index can be fuzzy-coded into three levels: "high", "medium" and "low".

[0060] Input variable 2: Overall operation conversion rate index. This index reflects the response speed of the motor when the load changes. A larger value means that the motor speed changes faster and responds promptly; a smaller value means that the motor responds slower. This index can be fuzzy into three levels: "fast", "medium speed" and "slow".

[0061] Input variable three: average calculation method (geometric mean or arithmetic mean). Since the geometric mean method is suitable for large data fluctuations and the arithmetic mean method is suitable for small fluctuations, the choice of this variable also affects the final operation type. We can fuzzify this variable into two states: "geometric" and "arithmetic": if the geometric mean method is used, it means that the data fluctuations are large and the motor operation state may be more unstable. If the arithmetic mean method is used, it means that the data fluctuations are small and the motor operation state may be more stable.

[0062] Fuzzification of output variables: The output variable is the operation type of the servo motor, which is divided into "normal operation type" and "abnormal operation type". The different types of output variables are also fuzzified into fuzzy sets, such as "normal", "slightly abnormal", "severely abnormal", etc.

[0063] Formulate fuzzy rules: According to the combination of input variables, formulate a set of fuzzy rules to describe the operation type of the servo motor under different input combinations. For example: Rule 1: If the health index is "high", the conversion rate is "fast", and the "arithmetic mean method" is used, the motor is classified as "normal operation type". Rule 2: If the health index is "medium", the conversion rate is "medium speed", and the "geometric mean method" is used, the motor is classified as "slight abnormality type". Rule 3: If the health index is "low", the conversion rate is "slow", and the "geometric mean method" is used, the motor is classified as "severe abnormality type".

[0064] Fuzzy reasoning process: The input variables are reasoned through fuzzy rules. Fuzzy reasoning is to derive the corresponding output results by performing logical operations on the fuzzified input variables according to the pre-set fuzzy rules. The reasoning process is to determine the operating status of the servo motor based on the fuzzy combination of different inputs. The output result of the reasoning is a fuzzy set, which needs to be defuzzified to convert the fuzzy set into a clear result, that is, to finally determine whether the servo motor belongs to the "normal operation type" or "abnormal operation type".

[0065] By taking the overall operation health index, the overall operation conversion rate index, and the geometric mean or arithmetic mean method used as input variables and fuzzifying them, fuzzy logic reasoning can more accurately identify the operating status of the servo motor. Combined with different data fluctuations, the present invention can flexibly determine the operating type of the motor, provide more reliable maintenance suggestions, and ensure that the equipment remains stable and efficient in long-term operation.

[0066] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0067] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0068] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0069] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0070] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A servo motor operation quality detection method based on big data, characterized in that: The following steps are involved: Collect and integrate various operating parameter data of the servo motor to obtain an integrated set of servo motor operating data; Perform load fluctuation analysis based on the integrated set of servo motor operation data to identify whether there are hidden dangers of abnormal speed fluctuations under different load conditions; If there is a hidden danger of abnormal speed fluctuation, then an overall performance analysis is performed to obtain an overall operation health index and an overall operation change rate index, and the servo motor is divided into an abnormal operation type or a normal operation type based on the overall operation health index and the overall operation change rate index; When the servo motor is in an abnormal operation type, it is optimized according to the preset strategy until it is reclassified as a normal operation type; The logic for obtaining the overall operation health index is: Obtain the standard deviation of the servo motor speed time series Z under the target load fluctuation window and the corresponding preset reference threshold, and then perform the following calculations: ; is the preset reference threshold corresponding to the target load fluctuation window i, is the standard deviation of the servo motor speed time series Z under the target load fluctuation window i, is the health factor of target load fluctuation window i; The health coefficients of all load fluctuation windows are aggregated and calculated using the harmonic mean method to obtain the overall operation health index; The logic for obtaining the overall operation transition rate index is: Obtain the time taken for the motor speed at the last time point in the previous load fluctuation window to reach the rated motor speed in the next load fluctuation window for the first time in two adjacent load fluctuation windows respectively and mark it as ; Indicates the number of the next load fluctuation window; Then calculate the transition rate coefficient of two adjacent load fluctuation windows: ; Indicates the motor speed at the last time point in the previous load fluctuation window. Indicates the rated motor speed in the next load fluctuation window, satisfying: ; Indicates the transition rate coefficient between the next load fluctuation window and the previous load fluctuation window when the next load fluctuation window is numbered i; Finally, all the transition rate coefficients are summarized and calculated using the geometric mean method or the arithmetic mean method to obtain the overall operation transition rate index; Classifying the servo motor into abnormal operation type or normal operation type based on the overall operation health index and the overall operation change rate index refers to: using fuzzy logic to perform reasoning to obtain the operation type of the servo motor; The logic of fuzzy logic is: The overall operation health index, the overall operation conversion rate index, and the selected geometric mean method or arithmetic mean method are taken as input variables, and the operation type classified by the servo motor is taken as the output variable. The input variables are fuzzified and the values ​​of the input variables are converted into fuzzy sets. The output variables are fuzzified and the output variables are converted into fuzzy sets. Fuzzy rules are formulated to describe the relevant levels under different data type combinations. The fuzzified input variables are inferred through fuzzy rules to obtain the operation type classified by the servo motor.

2. A servo motor operation quality detection method based on big data according to claim 1, characterized in that: Load fluctuation analysis refers to: In a fixed time period, it is divided into multiple continuous load fluctuation windows, and then the servo motor speed data of each load fluctuation window is obtained respectively to obtain the servo motor speed time series Z: , ,…, ; n is the total number of servo motor speed data samples obtained under the load fluctuation window; Then, the average value and standard deviation of the servo motor speed time series Z under the load fluctuation window are calculated, and the average value and standard deviation of the servo motor speed time series Z are compared with a preset mean reference range and a preset reference threshold value respectively; if the average value of the servo motor speed time series Z falls within the preset mean reference range and the standard deviation of the motor speed time series Z is less than or equal to the preset reference threshold value, the load fluctuation window is marked as a normal fluctuation window; if the average value of the servo motor speed time series Z falls within the preset mean reference range and the standard deviation of the motor speed time series Z is less than or equal to the preset reference threshold value, the load fluctuation window is marked as an abnormal fluctuation window; The marked types of all load fluctuation windows are summarized to obtain the load fluctuation window marking combination.

3. A servo motor operation quality detection method based on big data according to claim 2, characterized in that: Identifying whether there is a hidden danger of abnormal speed fluctuation under different load conditions means: Get the load fluctuation window mark combination. If there is an abnormal fluctuation window, there is a hidden danger of abnormal speed fluctuation under different load conditions when the servo motor is running. If there is no abnormal fluctuation window, there is no hidden danger of abnormal speed fluctuation under different load conditions when the servo motor is running.

4. The servo motor operation quality detection method based on big data according to claim 3 is characterized in that: The logic for choosing between using the geometric mean or the arithmetic mean is: Obtain all transition rate coefficients, calculate the data dispersion index of all transition rate coefficients, i.e., standard deviation, preset a dispersion threshold, compare the standard deviation of all transition rate coefficients with the preset dispersion threshold, if the standard deviation of all transition rate coefficients is greater than the preset dispersion threshold, use the geometric mean method, if the standard deviation of all transition rate coefficients is less than or equal to the preset dispersion threshold, use the arithmetic mean method.

Images