Method and device for evaluating performance of spindle servo motor by using data traceability

Abstract

The present application provides a method and device for evaluating the performance of a spindle servo motor using data traceability, relating to the technical field of servo motors, including: acquiring real-time state data of the motor; based on the motor state registration constraint, mining the state expectation according to the motor control scheme to determine the expected state data of the motor; performing deviation analysis based on the real-time state data of the motor and the expected state data of the motor; performing data traceability to build a motor performance evaluation space; if the motor performance evaluation index is less than the preset motor performance evaluation index, generating a motor performance warning signal. Through the present application, the technical problem in the prior art that the existing motor performance evaluation is difficult to comprehensively identify the factors restricting performance in complex scenarios, resulting in inaccurate evaluation results can be solved. By collecting real-time data, based on motor state registration and deviation analysis, building a motor performance evaluation space, and performing real-time monitoring and warning, the accuracy of performance evaluation is improved.

Description

Technical Field

[0001] This application relates to the technical field of servo motors, and particularly to a method and device for evaluating the performance of a spindle servo motor using data traceability. Background Art

[0002] The spindle servo motor is a key component used in machine tools, industrial robots, and other equipment. Its main function is to control the speed and position of the spindle. Combining servo control systems and motor technology, it can provide high-precision speed control, positioning control, and dynamic response. Therefore, it is widely used in occasions that require precise machining and high dynamic performance. In a complex working environment, the operating state of the motor is affected by multiple factors, such as load fluctuations, temperature changes, vibrations, humidity, external interference, etc. The performance of the motor often exhibits dynamic changes under complex load conditions, especially when there are sudden load changes, high-speed switching, or severe temperature fluctuations. It is very difficult to accurately capture the transient performance of the motor. Traditional evaluation methods may perform well under static or stable working conditions, but they are insufficient in responding to dynamic changes or cannot fully consider the impact of these changes on the motor performance, resulting in inaccurate evaluation results and being unable to reflect the true performance of the motor during actual operation.

[0003] In summary, there is a technical problem in the prior art that since the existing motor performance evaluation is difficult to comprehensively capture all state changes of the motor in a complex environment in a complex scenario, it affects the dynamic adaptation to different loads and working condition changes, resulting in inaccurate evaluation results. Summary of the Invention

[0004] The purpose of this application is to provide a method and device for evaluating the performance of a spindle servo motor using data traceability, so as to solve the technical problem in the prior art that since the existing motor performance evaluation is difficult to comprehensively capture all state changes of the motor in a complex environment in a complex scenario, it affects the dynamic adaptation to different loads and working condition changes, resulting in inaccurate evaluation results.

[0005] In view of the above problems, this application provides a method and device for evaluating the performance of a spindle servo motor using data traceability.

[0006] In a first aspect, the present application provides a method for evaluating the performance of a spindle servo motor using data traceability. The method for evaluating the performance of a spindle servo motor using data traceability is implemented by a device for evaluating the performance of a spindle servo motor using data traceability. Among them, the method for evaluating the performance of a spindle servo motor using data traceability includes: collecting real-time operating parameters and real-time environmental parameters of the spindle servo motor to obtain real-time motor state data; based on motor state registration constraints, performing state expectation mining according to the motor control scheme of the spindle servo motor to determine motor expected state data; performing deviation analysis based on the real-time motor state data and the motor expected state data to obtain a motor state expectation deviation vector; performing data traceability according to the spindle servo motor to build a motor performance evaluation space; calculating a motor performance evaluation index based on the motor state expectation deviation vector and according to the motor performance evaluation space; determining whether the motor performance evaluation index is less than a preset motor performance evaluation index. If the motor performance evaluation index is less than the preset motor performance evaluation index, generating a motor performance warning signal.

[0007] In a second aspect, the present application further provides a device for evaluating the performance of a spindle servo motor using data traceability, which is used to execute the method for evaluating the performance of a spindle servo motor using data traceability as described in the first aspect. Among them, the device for evaluating the performance of a spindle servo motor using data traceability includes: a data acquisition module, which is used to collect real-time operating parameters and real-time environmental parameters of the spindle servo motor to obtain real-time motor state data; an expectation mining module, which is used to perform state expectation mining based on motor state registration constraints and according to the motor control scheme of the spindle servo motor to determine motor expected state data; a deviation analysis module, which is used to perform deviation analysis based on the real-time motor state data and the motor expected state data to obtain a motor state expectation deviation vector; a data traceability module, which is used to perform data traceability according to the spindle servo motor to build a motor performance evaluation space; a performance evaluation module, which is used to calculate a motor performance evaluation index based on the motor state expectation deviation vector and according to the motor performance evaluation space; a signal generation module, which is used to determine whether the motor performance evaluation index is less than a preset motor performance evaluation index. If the motor performance evaluation index is less than the preset motor performance evaluation index, generating a motor performance warning signal.

[0008] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0009] By collecting the real-time operation parameters and real-time environment parameters of the spindle servo motor, the real-time state data of the motor is obtained; based on the motor state registration constraint, state expectation mining is performed according to the motor control scheme of the spindle servo motor to determine the expected state data of the motor; based on the real-time state data of the motor and the expected state data of the motor, deviation analysis is performed to obtain the motor state expectation deviation vector; data tracing is performed according to the spindle servo motor to build a motor performance evaluation space; based on the motor state expectation deviation vector and according to the motor performance evaluation space, a motor performance evaluation index is calculated; it is judged whether the motor performance evaluation index is less than a preset motor performance evaluation index. If the motor performance evaluation index is less than the preset motor performance evaluation index, a motor performance warning signal is generated. That is to say, by collecting the real-time operation parameters and environment parameters of the spindle servo motor, and based on motor state registration and deviation analysis, a motor performance evaluation space is built, so as to perform real-time monitoring and warning, improving the accuracy of motor performance evaluation.

[0010] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically illustrates the embodiments of the present application. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. Brief Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only exemplary, and for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the provided drawings.

[0012] Figure 1 It is a flowchart of the method for evaluating the performance of a spindle servo motor using data tracing in the present application;

[0013] Figure 2 It is a structural diagram of the device for evaluating the performance of a spindle servo motor using data tracing in the present application.

[0014] Description of the reference numerals: data acquisition module 11, expectation mining module 12, deviation analysis module 13, data tracing module 14, performance evaluation module 15, signal generation module 16. Detailed Description of the Embodiments

[0015] By providing a method and device for evaluating the performance of a spindle servo motor using data traceability, the present application solves the technical problem in the prior art that it is difficult to comprehensively capture all state changes of the motor in a complex environment in the existing motor performance evaluation, which affects the dynamic adaptation to different loads and working conditions changes, resulting in inaccurate evaluation results. By collecting the real-time operation parameters and environmental parameters of the spindle servo motor, and based on motor state registration and deviation analysis, a motor performance evaluation space is built, so as to conduct real-time monitoring and early warning, improving the accuracy of motor performance evaluation.

[0016] Next, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described here. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present application. Additionally, it should be noted that for the sake of description, only the parts related to the present application are shown in the drawings rather than all of them.

[0017] Embodiment 1, please refer to the attached Figure 1 drawings. The present application provides a method for evaluating the performance of a spindle servo motor using data traceability. Among them, the method for evaluating the performance of a spindle servo motor using data traceability is applied to a device for evaluating the performance of a spindle servo motor using data traceability. The method for evaluating the performance of a spindle servo motor using data traceability specifically includes the following steps:

[0018] Step 1: Collect the real-time operation parameters and real-time environmental parameters of the spindle servo motor to obtain the real-time state data of the motor.

[0019] Specifically, key data of the motor during operation and parameters of the environment where the motor is located are obtained in real time through various sensors and monitoring devices. The spindle servo motor is a motor used for precision control, usually used for the spindle drive of machine tools, and can provide high-precision and high-speed motion control. The real-time operation parameters refer to a series of performance indicators of the motor during operation, reflecting the immediate working state of the motor, including the motion characteristics, load conditions, and electrical parameters of the motor, such as current, voltage, power, rotational speed, torque, etc. The real-time environmental parameters refer to external factors that affect the operation state of the motor, including environmental temperature, humidity, vibration, electromagnetic interference, etc. The real-time state data of the motor is the combination of operation parameters and environmental parameters, which is a comprehensive description of the current operation status of the motor. By integrating the above two types of data, the actual working state of the motor can be understood in real time, including the performance of the motor under current load, working environment, input voltage, etc. By monitoring the operation parameters of the motor in real time, abnormal situations such as current fluctuations and temperature increases can be detected in time, so as to perform maintenance in advance and avoid sudden failures.

[0020] Step 2: Based on the motor state registration constraint, perform state expectation mining according to the motor control scheme of the main shaft servo motor to determine the motor expected state data.

[0021] Specifically, by accessing the global state record database or historical data set, obtain the normal state data of multiple main shaft servo motors of the same type. From the retrieved normal state records, filter out the normal state data samples that meet the motor state registration constraint according to the motor control scheme, add them to the motor state expectation mining sample domain, and identify the typical working modes or ideal states under the motor control scheme. By analyzing the mined sample domain, calculate its statistical central value (such as the average value or median) to determine the performance indicators of the motor in the ideal state, that is, the motor expected state data. The motor state registration constraint refers to the rules or standards that ensure that when comparing different motor states, these states are measured under the same or comparable conditions. The motor control scheme refers to a series of instructions and parameter settings used to guide the operation of the motor. By performing state expectation mining based on the motor state registration constraint and the motor control scheme to determine the motor expected state data, it helps to establish a clear performance benchmark.

[0022] Step 3: Perform deviation analysis based on the motor real-time state data and the motor expected state data to obtain the motor state expectation deviation vector.

[0023] Specifically, perform vectorization processing on the motor real-time state data and the motor expected state data respectively, that is, represent the multi-dimensional parameters in vector form, compare the motor real-time state data and the motor expected state data, find the differences between the two, and obtain the motor state expectation deviation vector. Deviation analysis is to calculate the differences between the motor real-time state vector and the expected state vector, identify the deviations between the current operating state of the motor and the ideal state, and includes deviation data in multiple dimensions, such as speed deviation, torque deviation, temperature deviation, etc. By performing deviation analysis based on the motor real-time state data and the motor expected state data and obtaining the motor state expectation deviation vector, quantitatively understanding the differences between the actual operating state of the motor and the ideal state helps to accurately evaluate the performance of the motor, timely detect performance deviations, and take corresponding maintenance or optimization measures.

[0024] Step 4: Trace the data according to the main shaft servo motor to build a motor performance evaluation space.

[0025] Specifically, all the expected deviation vector records related to the motor state are retrieved from the historical records according to the main shaft servo motor, including multiple sample motor state expected deviation vectors. Through confidence optimization, the evaluation records with high confidence are screened out. Taking the sample motor state expected deviation vector as the horizontal coordinate axis and the sample motor performance evaluation index as the vertical coordinate axis, the deviation vector and the performance index are mapped into a two-dimensional coordinate system, and a coordinate system for visualizing and analyzing the motor performance is established. The state deviation vector record set and the performance evaluation record set are input into the performance evaluation coordinate system, and a three-dimensional evaluation space is generated according to the performance evaluation indexes corresponding to different deviation vectors, reflecting the performance of the motor under various working states. Through the traceability and multi-dimensional analysis of the motor data, a motor performance evaluation space is built to achieve the all-round monitoring, performance optimization and anomaly detection of the motor operating state.

[0026] Step Five: Based on the motor state expected deviation vector and according to the motor performance evaluation space, calculate the motor performance evaluation index.

[0027] Specifically, the motor state expected deviation vector is input into the motor performance evaluation space, and the distances between the motor state expected deviation vector and each sample motor state expected deviation vector in the motor performance evaluation space are calculated to determine which sample is closest to the current state. Common methods include Euclidean distance, cosine similarity, etc. The purpose of calculating the distance is to find out those historical states that are most similar to the current state, so as to obtain the corresponding performance evaluation index. If the distance is small, it means that the current state of the motor is very similar to the historical sample state, and the performance evaluation index of this historical sample can be used as a reference. Once the historical sample vector closest to the current motor state is found, a central value calculation is performed based on the performance evaluation index of this sample to obtain the motor performance evaluation index, which identifies the overall performance of the current motor in the operating state. By inputting the motor state expected deviation vector into the motor performance evaluation space and calculating the distances between similar vectors, a motor performance evaluation index based on historical data is generated to reflect the current performance status of the motor, which helps to understand the overall situation of the motor performance, timely detect performance deviations, and take corresponding maintenance or optimization measures.

[0028] Step Six: Determine whether the motor performance evaluation index is less than the preset motor performance evaluation index. If the motor performance evaluation index is less than the preset motor performance evaluation index, generate a motor performance warning signal.

[0029] Specifically, a motor performance evaluation index is preset in advance, which represents the minimum acceptable standard of motor performance. If the motor performance index is lower than this preset value, it indicates that the motor may be in an abnormal state or have insufficient performance, and there may be potential hidden risks or faults. The motor performance evaluation index is a comprehensive index calculated for the current performance of the motor, reflecting the operating state and health status of the motor. It is judged whether the motor performance evaluation index is less than the preset motor performance evaluation index. If the performance evaluation index is lower than the threshold value, it means that the performance of the motor has declined, and the operating state may be unstable or abnormal, and thus preventive measures need to be taken. At this time, a motor performance warning signal needs to be generated, aiming to inform the system or operator that the performance of the motor has dropped to an unsafe state and attention or intervention is required. After generating the warning signal, the operator is reminded of the possible problems of the motor through alarm or notification, and is required to check the motor status or take maintenance measures. By monitoring the motor performance evaluation index and generating warning signals, measures can be taken in time when the motor performance deteriorates, reducing the risk of faults.

[0030] Further, step two of the present application includes:

[0031] Based on the spindle servo motor, a global state record retrieval is performed to obtain multiple motor normal state records; based on the motor state registration constraint, according to the motor control scheme, the multiple motor normal state records are mined to establish an expected motor state mining sample domain; based on the expected motor state mining sample domain, a central value calculation is performed to generate the expected motor state data.

[0032] Specifically, by accessing the global state record database or historical data set, the operating historical data of the spindle servo motor is retrieved and analyzed, and the state records of multiple spindle servo motors of the same model under normal working conditions are retrieved and extracted to obtain multiple normal state records of the same type of spindle servo motor. The global state record refers not only to the state data of a single motor, but also to the operating records of the same type of equipment retrieved across multiple motors, enhancing the comprehensiveness and representativeness of the data. The normal state record includes the operating parameters of the motor under fault-free conditions (such as speed, torque, temperature, current, voltage, etc.), which are the performances of the motor under different working conditions and are all in the normal working state.

[0033] Analyze the status records of multiple motors under normal operating conditions using specific algorithms and constraints to identify typical operating modes or ideal states under the motor control scheme. The motor status registration constraint is a rule or standard to ensure effective comparison and matching of status data between different motors, including time synchronization, dimension unification, data standardization, etc., to ensure that different motor status data can be compared and analyzed with each other. The motor control scheme is a series of instructions and parameter settings used to guide the operation of the motor. Mine the normal status records according to the motor control scheme to establish a motor status expectation mining sample domain, which contains multiple working numbers under normal conditions and reflects the performance of multiple motors under various working conditions.

[0034] Analyze the motor status expectation mining sample domain, calculate a representative central value, through statistical methods (such as mean, median, mode, etc.), calculate the representative status value from multiple normal status records in the sample domain, which reflects the expected status of the motor under normal operating conditions. The calculation result of the central value is the expected status data of the motor, which reflects the "ideal state" of the motor under normal operating conditions. For example, assume that a factory uses 10 spindle servo motors of the same model, retrieve the data under normal operating conditions from the operation records of these motors, including parameters such as speed, torque, and temperature. According to the motor control scheme, mine the normal status records of these 10 motors to establish a sample domain containing 1000 data points. Ensure that the timestamps of all records are aligned, the units are consistent, and the data is normalized. In this sample domain, the average value of each parameter is calculated to obtain: average speed: 2900 rpm, average torque: 48 N·m, average temperature: 75 °C, and these average values are used as the motor expected status data. By retrieving the global motor status records, establishing the motor status expectation sample domain, and generating the motor expected status data through the calculation of the central value, the future status of the motor can be accurately predicted.

[0035] Furthermore, the present application further includes the following steps:

[0036] Traverse the normal status records of the multiple motors, extract the normal status record of the first motor, where the normal status record of the first motor includes the first sample motor control scheme and the first motor normal status data sample; perform correlation analysis on the first sample motor control scheme based on the motor control scheme to obtain the first sample status registration coefficient; determine whether the first sample status registration coefficient meets the motor status registration constraint; if the first sample status registration coefficient meets the motor status registration constraint, add the first motor normal status data sample to the motor status expectation mining sample domain.

[0037] Specifically, traverse multiple normal state records of motors, conduct individual inspections, and select a specific motor record as the first normal state record of the motor, including the control scheme of the motor and the corresponding normal state data samples. The normal state record refers to the state data of the motor when it operates according to a predetermined control scheme in a fault-free state, including parameters such as rotational speed, torque, temperature, current, and voltage. Conduct a correlation analysis between the control scheme of the first motor and the standard control scheme to obtain the first sample state registration coefficient, which represents the matching degree between the current motor control scheme and the standard motor control scheme. If this registration coefficient is close to 1, it means that the state of the motor is close to the standard control state and the matching degree is high. The correlation analysis refers to using a specific algorithm to analyze the data, aiming to evaluate the matching degree between the actual control scheme of the motor and the ideal control scheme.

[0038] Judge whether the first sample state registration coefficient meets the motor state registration constraint. If the first sample state registration coefficient meets the motor state registration constraint, it indicates that the similarity between the first sample motor control scheme and other motor control schemes has reached an acceptable level, and this sample can be used as part of the normal state of the motor. Add the first normal state data sample of the motor to the motor state expectation mining sample domain. The motor state expectation mining sample domain is a data set containing multiple normal state data samples of motors, which is used to analyze and determine the expected state of the motor. Through the judgment of the registration coefficient, it is ensured that only high-quality and standard-compliant data is used to establish the expected state model, improving the representativeness and accuracy of the motor state expectation mining sample domain.

[0039] Furthermore, step three of this application includes:

[0040] Perform vectorization processing on the real-time state data of the motor to generate a real-time state vector of the motor; perform vectorization processing on the expected state data of the motor to generate an expected state vector of the motor; based on the expected state vector of the motor, identify the deviation of the real-time state vector of the motor to generate the motor state expectation deviation vector.

[0041] Specifically, the collected real-time motor status data is converted into a vector form. Vectorization is a method of converting data into a vector form to facilitate mathematical calculations and analysis. Various operating parameters of the motor (such as current, voltage, temperature, speed, etc.) are converted into individual components in the vector. The obtained real-time motor status vector contains all the key performance indicators of the motor at a certain moment. Similarly, the desired motor status data is also vectorized to obtain the desired motor status vector, which represents the performance indicators of the motor under ideal or standard operating conditions. Calculate the difference between the real-time motor status vector and the desired status vector to identify the deviation between the current operating state of the motor and the ideal state. The process of deviation identification can be achieved through vector operations, specifically: Motor status desired deviation vector = Real-time motor status vector - Desired motor status vector. Deviation identification refers to comparing the real-time status vector with the desired status vector, finding the difference between the two, and revealing the performance deviation of the motor. By calculating the deviation of each parameter, determine in which aspects the operating state of the motor differs from the desired state.

[0042] In a specific example, assume that the real-time status data of a motor is: speed 1500 rpm, torque 10 N·m, temperature 60 °C, and it is converted into a vector form: [1500, 10, 60]. At the same time, based on historical data and the motor control scheme, the desired state of the motor is determined as: speed 1500 rpm, torque 12 N·m, temperature 55 °C, and the desired state vector form is: [1500, 12, 55]. Calculate the deviation between the real-time status vector and the desired status vector, and the deviation vector is calculated as: [1500 - 1500, 10 - 12, 60 - 55] = [0, -2, 5], indicating that the torque of the motor is 2 Nm lower than the expected value and the temperature is 5 °C higher than the expected value during actual operation. The deviation vector reflects the difference between the actual state and the ideal state of the motor. In this way, the working state of the motor is monitored in real time, and adjustments or warnings are triggered when the deviation is too large to ensure that the motor can operate in the best state. Through vectorization and deviation identification, the actual deviation of the motor performance is quantified, and the difference between the actual operating state and the ideal state of the motor is effectively identified.

[0043] Further, step four of this application includes:

[0044] Perform a global search for desired deviation records based on the spindle servo motor to obtain a record set of motor status desired deviation vectors; perform evaluation record retrieval confidence optimization based on the record set of motor status desired deviation vectors to obtain a record set of motor performance evaluations; use the sample motor status desired deviation vector as the horizontal axis and the sample motor performance evaluation index as the vertical axis to build a motor performance evaluation coordinate system; input the record set of motor status desired deviation vectors and the record set of motor performance evaluations into the motor performance evaluation coordinate system to establish the motor performance evaluation space.

[0045] Specifically, a comprehensive search is conducted on the expected deviation records of the spindle servo motor, which includes the state deviation data of the motor at different time points. The expected deviation record refers to the record of the difference between the actual operating state and the expected state of the motor over a period of time in the past. The global search means searching all the expected deviation records to facilitate the analysis of the overall trend of the motor performance. Through the global search, a set containing multiple motor state expected deviation vectors is obtained, that is, the motor state expected deviation vector record set, which includes the expected deviation data of the motor at different time points or under different working conditions. Through confidence optimization, the evaluation indices with higher confidence are selected from each sample motor state expected deviation vector to obtain the motor performance evaluation record set. Confidence optimization ensures the high quality and credibility of the data used for performance evaluation by evaluating the accuracy and reliability of each record. The motor performance evaluation record set is a set of data obtained through confidence optimization, reflecting the performance evaluation results of the motor at different time points or under different working conditions, usually including the motor performance evaluation indices such as efficiency, stability, failure rate, etc.

[0046] A two-dimensional coordinate system is established, where the horizontal axis represents the motor state expected deviation vector and the vertical axis represents the motor performance evaluation index. The motor state expected deviation vector refers to the degree of difference between the actual state and the expected state of the motor, reflecting the state changes of the motor in each dimension, such as the deviation of temperature, speed, torque, etc. The performance evaluation index refers to the performance evaluation of the motor under a specific state, including the overall efficiency, health status, stability, etc. of the motor. By mapping the deviation vector and the performance index into a two-dimensional coordinate system, a coordinate system for visualizing and analyzing the motor performance is established, intuitively showing the relationship between the motor state deviation and the performance.

[0047] In a specific example, for instance, the expected deviation vectors of a spindle servo motor at different time points are recorded. The expected deviation vector at the first time point is [0.2, 0, 2, -10], the expected deviation vector at the second time point is [0.3, 0, 1, -8], and the expected deviation vector at the third time point is [0.25, 0, 3, -12]. A record set of these expected deviation vectors is obtained through global retrieval, namely [0.2, 0, 2, -10], [0.3, 0, 1, -8], [0.25, 0, 3, -12]. Through evaluating the record retrieval confidence, a motor performance evaluation record set is obtained: Time point 1: 90%, Time point 2: 95%, Time point 3: 85%, indicating that the performance evaluation result at the first time point is 90%, the performance evaluation result at the second time point is 95%, and the performance evaluation result at the third time point is 85%. In the motor performance evaluation coordinate system, these data will be represented as three points. The abscissas are [0.2, 0, 2, -10], [0.3, 0, 1, -8], and [0.25, 0, 3, -12] respectively, and the ordinates are 90, 95, and 85 respectively. Inputting these data points into the motor performance evaluation coordinate system, I can see that these three points are located at different positions in the coordinate system, reflecting the performance states of the motor at different time points. Through the coordinate system, the relationship between the motor performance and the deviation can be visually seen, and based on the data in the evaluation space, the motor performance trend can be accurately predicted, thereby optimizing the maintenance plan and strategy.

[0048] Furthermore, the present application further includes the following steps:

[0049] Traverse the record set of the expected deviation vectors of the motor state, and extract the first sample of the expected deviation vectors of the motor state; perform performance evaluation record retrieval based on the first sample of the expected deviation vectors of the motor state to obtain the first set of historical motor performance evaluation indices; perform confidence calculation based on the first set of historical motor performance evaluation indices to obtain the confidence levels of each evaluation index; based on a predetermined evaluation index confidence level, screen the first set of historical motor performance evaluation indices according to the confidence levels of each evaluation index to obtain the first set of confident motor performance evaluation indices that meet the predetermined evaluation index confidence level; perform central value calculation based on the first set of confident motor performance evaluation indices to obtain the first sample of the motor performance evaluation index, and add the first sample of the motor performance evaluation index to the motor performance evaluation record set.

[0050] Specifically, traverse the motor state expected deviation vector record set, randomly select and extract a sample motor state expected deviation vector as the first sample motor state expected deviation vector, which represents the difference between the actual state and the expected state of the sample motor at a certain moment or under a certain working condition. Retrieve the corresponding performance evaluation index in the historical database to obtain the first historical motor performance evaluation index set, which includes multiple historical motor performance evaluation indexes corresponding to the first sample motor state expected deviation vector, reflecting the performance of the motor at different time points or under different working conditions. Calculate the confidence level for the first historical motor performance evaluation index set to evaluate the reliability of each historical motor performance evaluation index, which is obtained by comprehensively analyzing multiple factors such as the stability of historical data, error range, and data source reliability. The confidence level is a value between 0 and 1, indicating the degree of confidence in the reliability or accuracy of a certain data point or result. The higher the confidence level, the higher the credibility of the evaluation index in describing the motor performance and the more reliable it can be used as a reference. Through the confidence level calculation, a confidence level value is assigned to each evaluation index in the first historical motor performance evaluation index set to obtain the confidence levels of each evaluation index.

[0051] Preset a confidence level threshold, and only the historical evaluation indexes with a confidence level higher than this threshold will be considered credible. Screen out the evaluation indexes in the confidence levels of each evaluation index that are higher than or equal to the predetermined evaluation index confidence level to form the first confidence motor performance evaluation index set, which only contains the motor performance evaluation indexes that meet the confidence level requirements. Conduct statistical analysis on all the evaluation indexes in the first confidence motor performance evaluation index set to calculate a representative value, that is, the central value. The central value can be the average value, median or other statistical indicators, which are used to reflect the central tendency of this group of evaluation indexes. Add the first sample motor performance evaluation index obtained through the central value calculation to the motor performance evaluation record set as a new data point for the motor performance evaluation. Perform the same operation on other sample motor state expected deviation vectors in the motor state expected deviation vector record set, and add the obtained sample motor performance evaluation indexes to the motor performance evaluation record set to form a complete motor performance evaluation record set. Through the confidence level calculation and screening, the quality and reliability of the data used for performance evaluation are improved, ensuring that only high-confidence data is used for performance evaluation and avoiding the influence of low-quality data on the evaluation results.

[0052] Furthermore, step five of this application includes:

[0053] Input the motor state expected deviation vector into the motor performance evaluation space, calculate the distances between the motor state expected deviation vector and each sample motor state expected deviation vector in the motor performance evaluation space, and obtain multiple vector target distances; determine whether the multiple vector target distances are less than the vector target distance threshold; if any one of the multiple vector target distances is less than the vector target distance threshold, generate an identification vector target distance; perform a central value calculation based on the sample motor performance evaluation index corresponding to the identification vector target distance to generate the motor performance evaluation index.

[0054] Specifically, input the motor state expected deviation vector into the motor performance evaluation space for evaluation, calculate the distances between the motor state expected deviation vector and each sample motor state expected deviation vector in the motor performance evaluation space, and use mathematical distance measurement methods (such as Euclidean distance, Manhattan distance, etc.) to calculate the distances between the input motor state expected deviation vector and each sample motor state expected deviation vector in the motor performance evaluation space, obtaining multiple vector target distances, which reflect the degree of difference between the input vector and each sample vector in the space. The multiple vector target distances represent the similarity between the current motor state and the historical sample states. The smaller the distance, the closer the current state is to the state of a certain historical sample. The motor state expected deviation vector is a multi-dimensional vector that describes the difference between the current operating state of the motor and the expected state. The motor performance evaluation space is a previously established multi-dimensional space that contains a large number of sample motor state expected deviation vectors and corresponding performance evaluation indices.

[0055] Preset a critical value, that is, the vector target distance threshold, to measure whether the current motor state is close enough to the historical sample motor state. Determine whether each vector target distance is less than this threshold to determine whether the current motor state matches the states of some samples. If any one of the multiple vector target distances is less than the vector target distance threshold, it is considered that the input motor state expected deviation vector is similar to the corresponding sample motor state expected deviation vector, that is, their positions in the motor performance evaluation space are close. In this case, generate a representation to indicate that the input motor state expected deviation vector is similar to a certain sample vector in the motor performance evaluation space, which can be a simple logical value (such as True or False), or a more complex data structure for recording specific similarity information. Screen out the most valuable historical sample motor states by identifying the vectors that meet the conditions, and avoid using irrelevant data to affect the evaluation results.

[0056] Collect the sample motor performance evaluation indices corresponding to the identified vector target distances, and use a central value calculation method (such as mean, median, etc.) to calculate a representative value, that is, the central value. Through the central value calculation, the motor performance evaluation index is obtained, which represents the overall level of the sample motor performance evaluation indices corresponding to the identified vector target distances and reflects the overall performance of the current motor under the operating state. The goal of the central value calculation is to generate the performance evaluation index of the current motor through the aggregation of multiple historical evaluation indices, ensuring that the evaluation result is representative and credible. Through the distance calculation, it is ensured that only the historical data closest to the current motor state is used to generate the evaluation result, reducing the error of the evaluation result. The vector target distance threshold ensures that only those sample data with a high enough similarity are used for performance evaluation, avoiding the interference of irrelevant data.

[0057] In summary, the spindle servo motor performance evaluation method using data traceability provided by the present application has the following technical effects:

[0058] By collecting the real-time operating parameters and real-time environmental parameters of the spindle servo motor, the real-time state data of the motor is obtained; based on the motor state registration constraint, the state expectation mining is carried out according to the motor control scheme of the spindle servo motor to determine the motor expected state data; based on the real-time state data of the motor and the motor expected state data, the deviation analysis is carried out to obtain the motor state expectation deviation vector; according to the spindle servo motor, the data traceability is carried out to build the motor performance evaluation space; based on the motor state expectation deviation vector, according to the motor performance evaluation space, the motor performance evaluation index is calculated; it is judged whether the motor performance evaluation index is less than the preset motor performance evaluation index. If the motor performance evaluation index is less than the preset motor performance evaluation index, a motor performance warning signal is generated. That is to say, by collecting the real-time operating parameters and environmental parameters of the spindle servo motor, and based on the motor state registration and deviation analysis, the motor performance evaluation space is built, so as to carry out real-time monitoring and warning, improving the accuracy of the motor performance evaluation.

[0059] Embodiment 2, based on the same inventive concept as the spindle servo motor performance evaluation method using data traceability in the foregoing Embodiment 1, the present application also provides a spindle servo motor performance evaluation device using data traceability. Please refer to the appendix Figure 2 The spindle servo motor performance evaluation device using data traceability includes:

[0060] The data acquisition module 11 is used to collect the real-time operating parameters and real-time environmental parameters of the spindle servo motor to obtain the real-time state data of the motor.

[0061] An expected mining module 12, which is configured to perform state expectation mining based on the motor state registration constraint according to the motor control scheme of the main shaft servo motor, and determine the motor expected state data.

[0062] A deviation analysis module 13, which is configured to perform deviation analysis based on the real-time motor state data and the motor expected state data to obtain a motor state expectation deviation vector.

[0063] A data traceability module 14, which is configured to perform data traceability according to the main shaft servo motor and build a motor performance evaluation space.

[0064] A performance evaluation module 15, which is configured to calculate a motor performance evaluation index based on the motor state expectation deviation vector according to the motor performance evaluation space.

[0065] A signal generation module 16, which is configured to determine whether the motor performance evaluation index is less than a preset motor performance evaluation index. If the motor performance evaluation index is less than the preset motor performance evaluation index, a motor performance warning signal is generated.

[0066] Furthermore, the expected mining module 12 in the performance evaluation device of the main shaft servo motor using data traceability is further configured to:

[0067] Perform a global state record retrieval based on the main shaft servo motor to obtain multiple motor normal state records; perform mining on the multiple motor normal state records according to the motor control scheme based on the motor state registration constraint to establish a motor state expectation mining sample domain; perform a central value calculation based on the motor state expectation mining sample domain to generate the motor expected state data.

[0068] Furthermore, the expected mining module 12 in the performance evaluation device of the main shaft servo motor using data traceability is further configured to:

[0069] Traverse the multiple motor normal state records to extract a first motor normal state record, where the first motor normal state record includes a first sample motor control scheme and a first motor normal state data sample; perform an association analysis on the first sample motor control scheme according to the motor control scheme to obtain a first sample state registration coefficient; determine whether the first sample state registration coefficient satisfies the motor state registration constraint; if the first sample state registration coefficient satisfies the motor state registration constraint, add the first motor normal state data sample to the motor state expectation mining sample domain.

[0070] Further, the deviation analysis module 13 in the spindle servo motor performance evaluation device using data traceability is further configured to:

[0071] Perform vectorization processing on the real-time motor state data to generate a real-time motor state vector; perform vectorization processing on the expected motor state data to generate an expected motor state vector; based on the expected motor state vector, perform deviation identification on the real-time motor state vector to generate the expected motor state deviation vector.

[0072] Further, the data traceability module 14 in the spindle servo motor performance evaluation device using data traceability is further configured to:

[0073] Perform a global search for expected deviation records of the spindle servo motor to obtain a set of records of the expected motor state deviation vector; perform confidence optimization on the evaluation record search based on the set of records of the expected motor state deviation vector to obtain a set of motor performance evaluation records; use the sample motor state expected deviation vector as the horizontal axis and the sample motor performance evaluation index as the vertical axis to construct a motor performance evaluation coordinate system; input the set of records of the expected motor state deviation vector and the set of motor performance evaluation records into the motor performance evaluation coordinate system to establish the motor performance evaluation space.

[0074] Further, the data traceability module 14 in the spindle servo motor performance evaluation device using data traceability is further configured to:

[0075] Traverse the set of records of the expected motor state deviation vector to extract the first sample motor state expected deviation vector; perform a performance evaluation record search based on the first sample motor state expected deviation vector to obtain a set of first historical motor performance evaluation indices; perform confidence calculation based on the set of first historical motor performance evaluation indices to obtain the confidence of each evaluation index; based on a predetermined evaluation index confidence, screen the set of first historical motor performance evaluation indices according to the confidence of each evaluation index to obtain a set of first confidence motor performance evaluation indices that meet the predetermined evaluation index confidence; perform a central value calculation based on the set of first confidence motor performance evaluation indices to obtain the first sample motor performance evaluation index, and add the first sample motor performance evaluation index to the set of motor performance evaluation records.

[0076] Further, the performance evaluation module 15 in the spindle servo motor performance evaluation device using data traceability is further configured to:

[0077] Input the expected deviation vector of the motor state into the motor performance evaluation space, calculate the distances between the expected deviation vector of the motor state and the expected deviation vectors of each sample motor state in the motor performance evaluation space, and obtain multiple vector target distances; determine whether the multiple vector target distances are less than the vector target distance threshold; if any one of the multiple vector target distances is less than the vector target distance threshold, generate an identification vector target distance; perform a central value calculation based on the sample motor performance evaluation index corresponding to the identification vector target distance to generate the motor performance evaluation index.

[0078] The various embodiments in this specification are described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The Figure 1 The spindle servo motor performance evaluation method and specific examples using data traceability in the first embodiment are equally applicable to the spindle servo motor performance evaluation device using data traceability in this embodiment. Through the detailed description of the spindle servo motor performance evaluation method using data traceability above, those skilled in the art can clearly understand the spindle servo motor performance evaluation device using data traceability in this embodiment. Therefore, for the sake of simplicity of the specification, it will not be elaborated here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For the relevant parts, please refer to the description in the method section.

[0079] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0080] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. A spindle servo motor performance evaluation method using data traceability, characterized in that: include: Collect the real-time operating parameters and real-time environmental parameters of the spindle servo motor to obtain the real-time status data of the motor; Based on the motor state registration constraint, performing state expectation mining according to the motor control scheme of the spindle servo motor to determine the motor expected state data; Perform deviation analysis based on the real-time state data of the motor and the expected state data of the motor to obtain an expected deviation vector of the motor state; According to the spindle servo motor, data tracing is performed to build a motor performance evaluation space; Based on the motor state expected deviation vector and according to the motor performance evaluation space, calculating a motor performance evaluation index; Determine whether the motor performance evaluation index is less than a preset motor performance evaluation index, and if the motor performance evaluation index is less than the preset motor performance evaluation index, generate a motor performance warning signal; Wherein, performing deviation analysis based on the real-time state data of the motor and the expected state data of the motor to obtain the expected deviation vector of the motor state includes: Performing vectorization processing according to the real-time state data of the motor to generate a real-time state vector of the motor; Performing vectorization processing according to the motor desired state data to generate a motor desired state vector; Based on the motor expected state vector, performing deviation identification on the motor real-time state vector to generate the motor state expected deviation vector; Among them, according to the spindle servo motor, data tracing is performed to build a motor performance evaluation space, including: Perform a global search of the expected deviation record according to the spindle servo motor to obtain a motor state expected deviation vector record set; Performing evaluation record retrieval confidence optimization based on the motor state expected deviation vector record set to obtain a motor performance evaluation record set; A motor performance evaluation coordinate system is constructed with the sample motor state expected deviation vector as the horizontal axis and the sample motor performance evaluation index as the vertical axis; Inputting the motor state expected deviation vector record set and the motor performance evaluation record set into the motor performance evaluation coordinate system to establish the motor performance evaluation space; Wherein, based on the motor state expected deviation vector and according to the motor performance evaluation space, calculating the motor performance evaluation index includes: Inputting the motor state expected deviation vector into the motor performance evaluation space, calculating the distance between the motor state expected deviation vector and each sample motor state expected deviation vector in the motor performance evaluation space, and obtaining a plurality of vector target distances; Determining whether the multiple vector target distances are less than a vector target distance threshold; If any one of the plurality of vector target distances is less than the vector target distance threshold, generating an identification vector target distance; The motor performance evaluation index is generated by performing a concentrated value calculation based on the sample motor performance evaluation index corresponding to the identification vector target distance.

2. The spindle servo motor performance evaluation method using data traceability according to claim 1, characterized in that: Based on the motor state registration constraint, state expectation mining is performed according to the motor control scheme of the spindle servo motor to determine the motor expected state data, including: Performing a global status record search based on the spindle servo motor to obtain multiple motor normal status records; Based on the motor state registration constraint, mining the plurality of motor normal state records according to the motor control scheme to establish a motor state expected mining sample domain; The motor expected state data is generated by performing concentrated value calculation based on the motor expected state mining sample domain.

3. The spindle servo motor performance evaluation method using data traceability as claimed in claim 2, characterized in that: Based on the motor state registration constraint, mining the plurality of motor normal state records according to the motor control scheme to establish a motor state expected mining sample domain, including: Traversing the plurality of motor normal state records, extracting a first motor normal state record, wherein the first motor normal state record includes a first sample motor control scheme and a first motor normal state data sample; Performing correlation analysis on the first sample motor control scheme based on the motor control scheme to obtain a first sample state registration coefficient; determining whether the first sample state registration coefficient satisfies the motor state registration constraint; If the first sample state registration coefficient satisfies the motor state registration constraint, the first motor normal state data sample is added to the motor state expected mining sample domain.

4. The spindle servo motor performance evaluation method using data traceability according to claim 1, characterized in that: Based on the motor state expected deviation vector record set, evaluation record retrieval confidence optimization is performed to obtain a motor performance evaluation record set, including: Traversing the motor state expected deviation vector record set, extracting a first sample motor state expected deviation vector; Retrieving performance evaluation records based on the first sample motor state expected deviation vector to obtain a first historical motor performance evaluation index set; Performing confidence calculation based on the first historical motor performance evaluation index set to obtain confidence of each evaluation index; Based on a predetermined evaluation index confidence, the first historical motor performance evaluation index set is screened according to the confidence of each evaluation index to obtain a first confidence motor performance evaluation index set that meets the predetermined evaluation index confidence; A centralized value calculation is performed according to the first confidence motor performance evaluation index set to obtain a first sample motor performance evaluation index, and the first sample motor performance evaluation index is added to the motor performance evaluation record set.

5. A spindle servo motor performance evaluation device using data traceability, characterized in that: The method for evaluating the performance of a spindle servo motor using data traceability according to any one of claims 1 to 4 is used, and the spindle servo motor performance evaluation device using data traceability comprises: A data acquisition module, wherein the data acquisition module is used to collect real-time operating parameters and real-time environmental parameters of the spindle servo motor to obtain real-time status data of the motor; An expectation mining module, the expectation mining module is used to perform state expectation mining according to the motor control scheme of the spindle servo motor based on the motor state registration constraint to determine the motor expected state data; A deviation analysis module, the deviation analysis module is used to perform deviation analysis based on the real-time state data of the motor and the expected state data of the motor to obtain an expected deviation vector of the motor state; A data tracing module, wherein the data tracing module is used to perform data tracing according to the spindle servo motor and build a motor performance evaluation space; A performance evaluation module, the performance evaluation module is used to calculate a motor performance evaluation index based on the motor state expected deviation vector and the motor performance evaluation space; A signal generating module is used to determine whether the motor performance evaluation index is less than a preset motor performance evaluation index, and if the motor performance evaluation index is less than the preset motor performance evaluation index, generate a motor performance warning signal.

Images