High-speed motor torque testing method and system based on power parameters
By monitoring the power of high-speed motors in real time and combining the efficiency model, the torque value of high-speed motors is calculated using the support vector machine model, solving the problems of torque testing accuracy and stability of high-speed motors in the existing technology, and achieving an efficient and low-cost testing method.
Patent Information
- Application Number
- CN202411817078.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-11
- Publication Date
- 2025-04-11
AI Technical Summary
The existing high-speed motor torque testing methods have reduced accuracy under high-speed rotation conditions, poor stability, high cost, and complex operation, making it difficult to meet the requirements of high-precision testing.
By monitoring the input power and output power of the high-speed motor in real time, combined with the high-speed motor efficiency model, the real-time torque value of the high-speed motor is indirectly calculated using the support vector machine model.
High-precision torque measurement under high-speed rotation conditions is achieved, which improves the stability and efficiency of the test, and reduces the cost of testing and operational complexity.
Smart Images
Figure CN119807870A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of mechanical testing, and in particular, relates to a high-speed motor torque testing method and system based on power parameters. Background Art
[0002] In the field of high-speed motor torque testing, traditional testing methods mainly rely on strain gauge measurement, torque sensor or direct measurement of the output torque of the high-speed motor shaft. These methods perform well in low-speed or medium-speed high-speed motor testing, but face many challenges in high-speed motor testing. In particular, vibration, temperature changes under high-speed rotation, and dynamic effects caused by high speed make it difficult for traditional methods to accurately and stably measure torque values. In addition, existing high-speed motor torque testing systems are often complex in structure, expensive, and require a long test preparation time, which limits their widespread application in industrial production.
[0003] The existing technical solutions still have the following disadvantages:
[0004] Limited accuracy: Under high-speed rotation conditions, the accuracy of traditional measurement methods drops significantly, making it difficult to meet high-precision testing requirements.
[0005] Poor stability: Vibration and temperature changes have a significant impact on the measurement results, resulting in large fluctuations in test results.
[0006] High cost: High-precision torque sensors and complex data acquisition systems increase testing costs.
[0007] Complex operation: The calibration, installation and subsequent data processing before the test are cumbersome, affecting the test efficiency. Summary of the invention
[0008] The present invention proposes a high-speed motor torque test method and system based on power parameters. The method monitors the input power and output power of the high-speed motor in real time and combines the high-speed motor efficiency model to indirectly calculate the real-time torque value of the high-speed motor. The specific steps are as follows:
[0009] S1. Collect parameter data of high-speed motors under different working conditions to obtain raw data, pre-process the raw data to obtain pre-processed data; extract all important working conditions and high-speed motor efficiency data corresponding to each working condition from the pre-processed data, and construct working condition data sets and high-speed motor efficiency data sets; extract characteristic variables in all working conditions and construct working condition characteristic matrix;
[0010] S2. Construct an initial support vector machine model, set relevant parameters, divide the working condition feature matrix into a working condition feature training matrix and a working condition feature test matrix, set a working condition feature training label set and a working condition feature test label set; input the working condition feature training matrix and the working condition feature training label set into the initial support vector machine for training to obtain a trained support vector machine model; input the working condition feature test matrix into the trained support vector machine model for testing and optimization to obtain a final support vector machine model;
[0011] S3. Collect real-time operating condition data, pre-process the real-time operating condition data, and obtain pre-processed real-time operating condition data; extract features to obtain real-time operating condition characteristic variable data, input the real-time operating condition characteristic variable data into the final vector machine model, and obtain the real-time operating condition high-speed motor efficiency data; calculate the actual output power of the high-speed motor based on the input power data and the real-time operating condition high-speed motor efficiency data, and calculate the torque value of the high-speed motor.
[0012] Preferably, the S1 comprises the following steps:
[0013] S11, collecting data of input voltage, input current and output power of the high-speed motor under different load, speed and temperature conditions to obtain raw data, removing abnormal values and erroneous data in the raw data, and performing standardization processing to obtain preprocessed data;
[0014] S12, extract all important working conditions and the high-speed motor efficiency data corresponding to each working condition from the preprocessed data, and construct a working condition data set a={a1, a2, ..., a i ,...,a m}、High-speed motor efficiency data set b={b1,b2,...,b i ,...,b m}where a i represents the i-th working condition in the working condition data set, b i represents the high-speed motor efficiency corresponding to the i-th working condition in the working condition data set, and m represents the number of working conditions in the working condition data set is m;
[0015] S13, extract the characteristic variables in all working conditions and construct the working condition characteristic matrix A, as follows:
[0016]
[0017] Among them, A in represents the nth characteristic variable of the i-th operating condition in the operating condition characteristic matrix;
[0018] By collecting and preprocessing data, the accuracy and reliability of subsequent analysis can be ensured; removing outliers and erroneous data can prevent these untrue or erroneous data from having a negative impact on model training and prediction results; classifying the original data according to different working conditions and extracting the corresponding efficiency data will help with subsequent model training and performance analysis; by extracting characteristic variables from all working conditions and constructing a working condition feature matrix, input data can be provided for subsequent machine learning models.
[0019] Preferably, S2 comprises the following steps:
[0020] S21. Construct an initial support vector machine model, set the regularization parameter to b, and set the kernel function to the Gaussian kernel function, as follows. The function expression is as follows:
[0021] K(x,y)=exp(-c||xy|| 2 )
[0022] Among them, x and y represent data sample points of two different working conditions, and c represents the parameter of the Gaussian kernel function;
[0023] S22, set the training error threshold d; set the training data ratio to s1 and the test data ratio to s2, and divide the working condition feature matrix A into the working condition feature training matrix B and the working condition feature test matrix C according to the training data ratio s1 and the test data ratio s2, as follows,
[0024]
[0025] Among them, B in represents the nth characteristic variable of the i-th working condition in the working condition feature training matrix, o represents a total of o working conditions in the working condition feature training matrix, C in represents the nth characteristic variable of the i-th working condition in the working condition feature test matrix, and p represents that there are p kinds of working conditions in the working condition feature training matrix;
[0026] Set the working condition feature training label set to g = {g1, g2, ..., g i ,...,g o}、Working condition characteristic test label set j={j1,j2,...,j i ,...,j p}; where g i represents the high-speed motor efficiency corresponding to the i-th working condition in the condition feature training matrix, j i represents the high-speed motor efficiency corresponding to the i-th working condition in the condition characteristic test matrix;
[0027] S23, inputting the operating condition feature training matrix B and the operating condition feature training label set g into an initial support vector machine for training to obtain a trained support vector machine model;
[0028] S24, inputting the working condition characteristic test matrix into the trained support vector machine model for testing and optimization to obtain a final support vector machine model;
[0029] By constructing the initial support vector machine model, a basis can be provided for subsequent training and optimization; setting regularization parameters and kernel functions can help control the complexity and generalization ability of the model, thereby improving the prediction accuracy of the model; by setting the training error threshold and the training data ratio, the training process of the model can be controlled; dividing the operating condition feature matrix into a training matrix and a test matrix can help evaluate the performance and generalization ability of the model. By setting the operating condition feature training label set and the test label set, real efficiency data can be provided for the model as the target of training and testing.
[0030] Preferably, the S23 comprises the following steps:
[0031] S231, inputting the working condition feature training matrix B and the working condition feature training label set g into the initial support vector machine for training to optimize the hyperplane e in the initial support vector machine; when the training error of the working condition feature training matrix B and the working condition feature training label set in the initial support vector machine is less than the training error threshold d, stopping the training to obtain a trained support vector machine model;
[0032] By training and optimizing the support vector machine model, the model's prediction accuracy for high-speed motor efficiency can be improved.
[0033] Preferably, the S24 comprises the following steps:
[0034] S241, randomly initialize the position of the particle swarm h={h1,h2,...,h i ,...,h Np}, where h i represents the initial position of the ith particle, Np is the number of particles; the initialization particle velocity v = {v1,v2,...,v i ,...,v Np}, where v i represents the i-th velocity; initialize the optimal position of each particle f={f1,f2,...,f i ,...,f Np}, where f i represents the best position reached by the ith particle; initialize the global best position l to any position in f; set the maximum number of iterations to f′, and the performance of the global best position reaches the target value f″;
[0035] S242, for each particle, update the speed Where t represents the current moment, t+1 represents the next moment, j is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers ranging from 0 to 1, and f i t is the optimal position reached by the ith particle at time t, l t is the global optimal position reached by the ith particle at time t;
[0036] Update Location The updated position is used as a new hyperplane to obtain an updated hyperplane, and the updated hyperplane is used to train the trained support vector machine model and evaluate the performance. If the updated position The performance is better than f i t , then update f i If the new position The performance is not better than f i t , keep the original f i ; At time t+1, traverse the historical best position f of all particles i , and select the position with the best performance as the new global optimal position l t +1 ;
[0037] S243, repeat S2232, when the performance of the global best position reaches the target value f″ or the number of iterations reaches f′, stop the iteration process, output the learning rate value corresponding to the global best position, and obtain the optimal hyperplane;
[0038] S244, using the optimal hyperplane as the hyperplane of the trained support vector machine model to obtain a final support vector machine model;
[0039] By using the particle swarm optimization algorithm, the optimal hyperplane parameters can be effectively searched, thereby improving the performance of the support vector machine model; by randomly initializing the position, speed and optimal position of the particle swarm, a variety of initial solutions can be provided for the subsequent search process, and by updating the speed and position, the optimal solution can be gradually approached; when updating the speed, the inertia weight, learning factor and random number are considered to balance the capabilities of global search and local search; when updating the position, the updated hyperplane is used to train the support vector machine model and the performance is evaluated to ensure that the search process is moving in the direction of the optimal solution.
[0040] Preferably, the S231 includes the following steps:
[0041] S2311, the training error of the initial support vector machine is calculated using a missing function, and the function expression is as follows:
[0042]
[0043] Where x1 is the number of working conditions in the working condition training matrix; y i is the true label of the i-th working condition, which takes the value of 0 or 1; is the predicted probability of the i-th operating condition, indicating the probability that the model predicts that the operating condition belongs to category 1;
[0044] The training error is calculated by the missing function, and the training effect of the initial support vector machine model can be evaluated.
[0045] Preferably, S3 comprises the following steps:
[0046] S31, using a high-precision power analyzer to collect real-time operating condition data, checking the real-time operating condition data, eliminating abnormal values and erroneous data, and obtaining pre-processed real-time operating condition data;
[0047] S32, extracting characteristic variable data of the working condition in the pre-processed real-time working condition data to obtain the characteristic variable data of the real-time working condition, inputting the characteristic variable data of the real-time working condition into the final support vector machine model to obtain the high-speed motor efficiency data of the real-time working condition;
[0048] S33, calculating the actual output power of the high-speed motor according to the input power data and the high-speed motor efficiency data of the real-time working condition, and calculating the torque value of the high-speed motor accordingly;
[0049] By inputting the real-time working condition characteristic variable data into the final support vector machine model, the high-speed motor efficiency data of the real-time working condition is obtained, and the torque value of the high-speed motor is further calculated.
[0050] A high-speed motor torque test system based on power parameters, including a data collection module, a support vector machine model training optimization module, and a support vector machine model application module;
[0051] The data collection module collects parameter data of the high-speed motor under different working conditions, pre-processes the parameter data, extracts all important working conditions, characteristic variables in all working conditions and high-speed motor efficiency data corresponding to each working condition from the pre-processed data, constructs a working condition data set and a high-speed motor efficiency data set, and constructs a working condition feature matrix;
[0052] The support vector machine model training and optimization module is used to construct an initial support vector machine model, set relevant parameters, and use the operating condition feature matrix and the label matrix to train and optimize the initial support vector machine model to obtain a final support vector machine model;
[0053] The support vector machine model application module is used to collect real-time operating condition data, extract features, obtain real-time operating condition characteristic variable data, input the real-time operating condition characteristic variable data into the final support vector machine model, obtain the real-time operating condition high-speed motor efficiency data, calculate the actual output power of the high-speed motor, and calculate the torque value of the high-speed motor.
[0054] The present invention has the following beneficial effects:
[0055] The present invention collects parameter data of high-speed motors under different working conditions, pre-processes the original data, extracts characteristic variables in all working conditions, constructs a working condition characteristic matrix, and constructs a working condition data set and a high-speed motor efficiency data set; thus, data quality can be improved and the accuracy and reliability of subsequent analysis can be ensured.
[0056] The present invention tests and optimizes by inputting a working condition feature test matrix into a trained support vector machine model to obtain a final support vector machine model, sets relevant parameters, and tests and optimizes by inputting a working condition feature test matrix into a trained support vector machine model; this helps to evaluate the performance and generalization ability of the model, and provides a necessary basis for subsequent model applications, can optimize the performance of the support vector machine model, helps to improve the prediction accuracy and generalization ability of the model, and can verify the performance and generalization ability of the model.
[0057] The present invention collects real-time working condition data, pre-processes the real-time working condition data, extracts characteristic variables in the real-time working condition, constructs real-time working condition characteristic variable data, inputs the real-time working condition characteristic variable data into the final support vector machine model, and according to the input power data and the high-speed motor efficiency data of the real-time working condition; it helps to improve the prediction accuracy and generalization ability of the model, improve the data quality, ensure the accuracy and reliability of subsequent analysis to provide necessary information for subsequent model prediction, and obtain the high-speed motor efficiency data of the real-time working condition. This helps to evaluate the operating state of the high-speed motor in real time and calculate the actual output power and torque value of the high-speed motor.
[0058] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS
[0059] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.
[0060] Figure 1 The present invention is a flowchart of a high-speed motor torque testing method and system based on power parameters. DETAILED DESCRIPTION
[0061] The following will be combined with the drawings in the embodiments of the invention to clearly and completely describe the technical solutions in the embodiments of the invention. Obviously, the described embodiments are only part of the embodiments of the invention, not all of the embodiments. Based on the embodiments in the invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the invention.
[0062] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.
[0063] Embodiment 1:
[0064] See also Figure 1 The present invention discloses a high-speed motor torque testing method based on power parameters, comprising the following steps:
[0065] S1. Collect parameter data of high-speed motors under different working conditions to obtain raw data, pre-process the raw data to obtain pre-processed data; extract all important working conditions and high-speed motor efficiency data corresponding to each working condition from the pre-processed data, and construct working condition data sets and high-speed motor efficiency data sets; extract characteristic variables in all working conditions and construct working condition characteristic matrix;
[0066] The S1 comprises the following steps:
[0067] S11, collecting data of input voltage, input current and output power of the high-speed motor under different load, speed and temperature conditions to obtain raw data, removing abnormal values and erroneous data in the raw data, and performing standardization processing to obtain preprocessed data;
[0068] S12, extract all important working conditions and the high-speed motor efficiency data corresponding to each working condition from the preprocessed data, and construct a working condition data set a={a1, a2, ..., a i ,...,a m}、High-speed motor efficiency data set b={b1,b2,...,b i ,...,b m}where a i represents the i-th working condition in the working condition data set, b i represents the high-speed motor efficiency corresponding to the i-th working condition in the working condition data set, and m represents the number of working conditions in the working condition data set is m;
[0069] S13, extract the characteristic variables in all working conditions and construct the working condition characteristic matrix A, as follows:
[0070]
[0071] Among them, A in represents the nth characteristic variable of the i-th operating condition in the operating condition characteristic matrix;
[0072] S2. Construct an initial support vector machine model, set relevant parameters, divide the working condition feature matrix into a working condition feature training matrix and a working condition feature test matrix, set a working condition feature training label set and a working condition feature test label set; input the working condition feature training matrix and the working condition feature training label set into the initial support vector machine for training to obtain a trained support vector machine model; input the working condition feature test matrix into the trained support vector machine model for testing and optimization to obtain a final support vector machine model;
[0073] The S2 comprises the following steps:
[0074] S21. Construct an initial support vector machine model, set the regularization parameter to b, and set the kernel function to the Gaussian kernel function, as follows. The function expression is as follows:
[0075] K(x,y)=exp(-c||xy|| 2 )
[0076] Among them, x and y represent data sample points of two different working conditions, and c represents the parameter of the Gaussian kernel function;
[0077] S22, set the training error threshold d; set the training data ratio to s1 and the test data ratio to s2, and divide the working condition feature matrix A into the working condition feature training matrix B and the working condition feature test matrix C according to the training data ratio s1 and the test data ratio s2, as follows,
[0078]
[0079] Among them, B in represents the nth characteristic variable of the i-th working condition in the working condition feature training matrix, o represents a total of o working conditions in the working condition feature training matrix, C in represents the nth characteristic variable of the i-th working condition in the working condition feature test matrix, and p represents that there are p kinds of working conditions in the working condition feature training matrix;
[0080] Set the working condition feature training label set to g = {g1, g2, ..., g i ,...,g o}、Working condition characteristic test label set j={j1,j2,...,j i ,...,jp}; where g i represents the high-speed motor efficiency corresponding to the i-th working condition in the condition feature training matrix, j i represents the high-speed motor efficiency corresponding to the i-th working condition in the condition characteristic test matrix;
[0081] S23, inputting the operating condition feature training matrix B and the operating condition feature training label set g into an initial support vector machine for training to obtain a trained support vector machine model;
[0082] The S23 comprises the following steps:
[0083] S231, inputting the working condition feature training matrix B and the working condition feature training label set g into the initial support vector machine for training to optimize the hyperplane e in the initial support vector machine; when the training error of the working condition feature training matrix B and the working condition feature training label set in the initial support vector machine is less than the training error threshold d, stopping the training to obtain a trained support vector machine model;
[0084] The S231 includes the following steps:
[0085] S2311, the training error of the initial support vector machine is calculated using a missing function, and the function expression is as follows:
[0086]
[0087] Where x1 is the number of working conditions in the working condition training matrix; y i is the true label of the i-th working condition, which takes the value of 0 or 1; is the predicted probability of the i-th operating condition, indicating the probability that the model predicts that the operating condition belongs to category 1;
[0088] S24, inputting the working condition characteristic test matrix into the trained support vector machine model for testing and optimization to obtain a final support vector machine model;
[0089] The S24 comprises the following steps:
[0090] S241, randomly initialize the position of the particle swarm h={h1,h2,...,h i ,...,h Np}, where h i represents the initial position of the ith particle, Np is the number of particles; the initialization particle velocity v = {v1,v2,...,v i ,...,v Np}, where v i represents the i-th velocity; initialize the optimal position of each particle f={f1,f2,...,f i ,...,fNp}, where f i represents the best position reached by the ith particle; initialize the global best position l to any position in f; set the maximum number of iterations to f′, and the performance of the global best position reaches the target value f″;
[0091] S242, for each particle, update the speed Where t represents the current moment, t+1 represents the next moment, j is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers ranging from 0 to 1, and f i t is the optimal position reached by the ith particle at time t, l t is the global optimal position reached by the ith particle at time t;
[0092] Update Location The updated position is used as a new hyperplane to obtain an updated hyperplane, and the updated hyperplane is used to train the trained support vector machine model and evaluate the performance. If the updated position The performance is better than f i t , then update f i If the new position The performance is not better than f i t , keep the original f i ; At time t+1, traverse the historical best position f of all particles i , and select the position with the best performance as the new global optimal position l t +1 ;
[0093] S243, repeat S2232, when the performance of the global best position reaches the target value f″ or the number of iterations reaches f′, stop the iteration process, output the learning rate value corresponding to the global best position, and obtain the optimal hyperplane;
[0094] S244, using the optimal hyperplane as the hyperplane of the trained support vector machine model to obtain a final support vector machine model;
[0095] S3, collecting real-time working condition data, preprocessing the real-time working condition data, and obtaining preprocessed real-time working condition data; extracting features, obtaining real-time working condition characteristic variable data, inputting the real-time working condition characteristic variable data into the final vector machine model, and obtaining the high-speed motor efficiency data of the real-time working condition; calculating the actual output power of the high-speed motor according to the input power data and the high-speed motor efficiency data of the real-time working condition, and calculating the torque value of the high-speed motor;
[0096] The S3 comprises the following steps:
[0097] S31, using a high-precision power analyzer to collect real-time operating condition data, checking the real-time operating condition data, eliminating abnormal values and erroneous data, and obtaining pre-processed real-time operating condition data;
[0098] S32, extracting characteristic variable data of the working condition in the pre-processed real-time working condition data to obtain the characteristic variable data of the real-time working condition, inputting the characteristic variable data of the real-time working condition into the final vector machine model, and obtaining the high-speed motor efficiency data of the real-time working condition;
[0099] S33. Calculate the actual output power of the high-speed motor according to the input power data and the efficiency data of the high-speed motor in real-time working condition, and calculate the torque value of the high-speed motor accordingly.
[0100] Embodiment 2:
[0101] A high-speed motor torque test system based on power parameters, including a data collection module, a support vector machine model training optimization module, and a support vector machine model application module;
[0102] The data collection module collects parameter data of the high-speed motor under different working conditions, pre-processes the parameter data, extracts all important working conditions, characteristic variables in all working conditions and high-speed motor efficiency data corresponding to each working condition from the pre-processed data, constructs a working condition data set and a high-speed motor efficiency data set, and constructs a working condition feature matrix;
[0103] The support vector machine model training and optimization module is used to construct an initial support vector machine model, set relevant parameters, and use the operating condition feature matrix and the label matrix to train and optimize the initial support vector machine model to obtain a final support vector machine model;
[0104] The support vector machine model application module is used to collect real-time operating condition data, extract features, obtain real-time operating condition characteristic variable data, input the real-time operating condition characteristic variable data into the final support vector machine model, obtain the real-time operating condition high-speed motor efficiency data, calculate the actual output power of the high-speed motor, and calculate the torque value of the high-speed motor.
[0105] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0106] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.
Claims
1. A high-speed motor torque test method based on power parameters, characterized in that: The following steps are involved: S1. Collect parameter data of the high-speed motor under different working conditions to obtain raw data, and pre-process the raw data to obtain pre-processed data; Extract all important working conditions and the high-speed motor efficiency data corresponding to each working condition from the preprocessed data, and construct working condition data sets and high-speed motor efficiency data sets; extract characteristic variables in all working conditions and construct a working condition characteristic matrix; S2. Construct an initial support vector machine model, set relevant parameters, divide the working condition feature matrix into a working condition feature training matrix and a working condition feature test matrix, set a working condition feature training label set and a working condition feature test label set; input the working condition feature training matrix and the working condition feature training label set into the initial support vector machine for training to obtain a trained support vector machine model; input the working condition feature test matrix into the trained support vector machine model for testing and optimization to obtain a final support vector machine model; S3, collecting real-time operating condition data, preprocessing the real-time operating condition data, and obtaining preprocessed real-time operating condition data; Features are extracted to obtain real-time operating condition characteristic variable data, and the real-time operating condition characteristic variable data is input into the final vector machine model to obtain the high-speed motor efficiency data of the real-time operating condition; based on the input power data and the high-speed motor efficiency data of the real-time operating condition, the actual output power of the high-speed motor is calculated, and the torque value of the high-speed motor is calculated.
2. A high-speed motor torque testing method based on power parameters according to claim 1, characterized in that: The S1 comprises the following steps: S11, collecting data of input voltage, input current and output power of the high-speed motor under different load, speed and temperature conditions to obtain raw data, removing abnormal values and erroneous data in the raw data, and performing standardization processing to obtain preprocessed data; S12, extract all important working conditions and the high-speed motor efficiency data corresponding to each working condition from the preprocessed data, and construct a working condition data set a={a1, a2, ..., a i ,...,a m }、High-speed motor efficiency data set b={b1,b2,...,b i ,...,b m }where a i represents the i-th working condition in the working condition data set, b i represents the high-speed motor efficiency corresponding to the i-th working condition in the working condition data set, and m represents the number of working conditions in the working condition data set is m; S13, extract the characteristic variables in all working conditions and construct the working condition characteristic matrix A, as follows: Among them, A in Represents the nth characteristic variable of the i-th operating condition in the operating condition characteristic matrix.
3. A high-speed motor torque testing method based on power parameters according to claim 1, characterized in that: The S2 comprises the following steps: S21. Construct an initial support vector machine model, set the regularization parameter to b, and set the kernel function to the Gaussian kernel function, as follows. The function expression is as follows: K(x,y)=exp(-c||x-y|| 2 ) Among them, x and y represent data sample points of two different working conditions, and c represents the parameter of the Gaussian kernel function; S22, set the training error threshold d; set the training data ratio to s1 and the test data ratio to s2, and divide the working condition feature matrix A into the working condition feature training matrix B and the working condition feature test matrix C according to the training data ratio s1 and the test data ratio s2, as follows, Among them, B in represents the nth characteristic variable of the i-th working condition in the working condition feature training matrix, o represents a total of o working conditions in the working condition feature training matrix, C in represents the nth characteristic variable of the i-th working condition in the working condition feature test matrix, and p represents that there are p kinds of working conditions in the working condition feature training matrix; Set the working condition feature training label set to g = {g1, g2, ..., g i ,...,g o }、Working condition characteristic test label set j={j1,j2,...,j i ,...,j p }; where g i represents the high-speed motor efficiency corresponding to the i-th working condition in the condition feature training matrix, j i represents the high-speed motor efficiency corresponding to the i-th working condition in the condition characteristic test matrix; S23, inputting the operating condition feature training matrix B and the operating condition feature training label set g into an initial support vector machine for training to obtain a trained support vector machine model; S24, inputting the working condition characteristic test matrix into the trained support vector machine model for testing and optimization to obtain a final support vector machine model.
4. A high-speed motor torque testing method based on power parameters according to claim 3, characterized in that: The S23 comprises the following steps: S231. Input the operating condition feature training matrix B and the operating condition feature training label set g into the initial support vector machine for training to optimize the hyperplane e in the initial support vector machine; when the training error of the operating condition feature training matrix B and the operating condition feature training label set in the initial support vector machine is less than the training error threshold d, stop the training to obtain a trained support vector machine model.
5. The high-speed motor torque testing method based on power parameters according to claim 3 is characterized in that: The S24 comprises the following steps: S241, randomly initialize the position of the particle swarm h={h1,h2,...,h i ,...,h Np }, where h i represents the initial position of the ith particle, Np is the number of particles; the initialization particle velocity v = {v1,v2,...,v i ,...,v Np }, where v i represents the i-th velocity; initialize the optimal position of each particle f={f1,f2,...,f i ,...,f Np }, where f i represents the best position reached by the ith particle; initialize the global best position l to any position in f; set the maximum number of iterations to f′, and the performance of the global best position reaches the target value f″; S242, for each particle, update the speed Where t represents the current moment, t+1 represents the next moment, j is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers in the range of 0 to 1, is the optimal position reached by the ith particle at time t, l t is the global optimal position reached by the ith particle at time t; Update Location The updated position is used as a new hyperplane to obtain an updated hyperplane, and the updated hyperplane is used to train the trained support vector machine model and evaluate the performance. If the updated position The performance is better than Then update f i , if the new position The performance is not better than Keep the original f i ; At time t+1, traverse the historical best position f of all particles i , and select the position with the best performance as the new global optimal position l t+1 ; S243, repeat S2232, when the performance of the global best position reaches the target value f″ or the number of iterations reaches f′, stop the iteration process, output the learning rate value corresponding to the global best position, and obtain the optimal hyperplane; S244: Using the optimal hyperplane as the hyperplane of the trained support vector machine model to obtain a final support vector machine model.
6. A high-speed motor torque testing method based on power parameters according to claim 4, characterized in that: The S231 includes the following steps: S2311, the training error of the initial support vector machine is calculated using a missing function, and the function expression is as follows: Where x1 is the number of working conditions in the working condition training matrix; y i is the true label of the i-th working condition, which takes the value of 0 or 1; is the predicted probability of the i-th operating condition, indicating the probability that the model predicts that the operating condition belongs to category 1.
7. A high-speed motor torque testing method based on power parameters according to claim 1, characterized in that: The S3 comprises the following steps: S31, using a high-precision power analyzer to collect real-time operating condition data, checking the real-time operating condition data, eliminating abnormal values and erroneous data, and obtaining pre-processed real-time operating condition data; S32, extracting characteristic variable data of the working condition in the pre-processed real-time working condition data to obtain the characteristic variable data of the real-time working condition, inputting the characteristic variable data of the real-time working condition into the final support vector machine model to obtain the high-speed motor efficiency data of the real-time working condition; S33. Calculate the actual output power of the high-speed motor according to the input power data and the efficiency data of the high-speed motor in real-time working condition, and calculate the torque value of the high-speed motor accordingly.
8. A high-speed motor torque test system based on power parameters according to any one of claims 1 to 7, characterized in that: Data collection module, support vector machine model training and optimization module, support vector machine model application module; The data collection module collects parameter data of the high-speed motor under different working conditions, pre-processes the parameter data, extracts all important working conditions, characteristic variables in all working conditions and high-speed motor efficiency data corresponding to each working condition from the pre-processed data, constructs a working condition data set and a high-speed motor efficiency data set, and constructs a working condition feature matrix; The support vector machine model training and optimization module is used to construct an initial support vector machine model, set relevant parameters, and use the operating condition feature matrix and the label matrix to train and optimize the initial support vector machine model to obtain a final support vector machine model; The support vector machine model application module is used to collect real-time operating condition data, extract features, obtain real-time operating condition characteristic variable data, input the real-time operating condition characteristic variable data into the final support vector machine model, obtain the real-time operating condition high-speed motor efficiency data, calculate the actual output power of the high-speed motor, and calculate the torque value of the high-speed motor.