Detection data analysis system for permanent magnet motor routine test bench

Abstract

The invention discloses a detection data analysis system for a permanent magnet motor routine test bed, and relates to the technical field of detection data analysis. The system comprises a data acquisition module used for acquiring detection data of a test motor in a routine test bench, and a data processing module used for processing the detection data to acquire data to be analyzed. The data analysis module is used for performing data analysis on the to-be-analyzed data to obtain an analysis result and visually representing the analysis result; and the data storage module is used for storing the analysis result and establishing a decision model. According to the invention, the detection data of the test motor is obtained, and inconsistent data and defect data in the data are processed, so that the analysis of the detection data is ensured to be reliable; by analyzing the processed data and establishing the decision model, the accuracy and the high efficiency of motor performance evaluation in the test process are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of detection data analysis, and particularly relates to a detection data analysis system for a permanent magnet motor routine test bench. Background Art

[0002] The permanent magnet motor routine test bench is a device used for performing conventional tests on permanent magnet motors. It is used to test various performance indicators of permanent magnet motors during routine tests, such as voltage, current, power, output torque, vibration, temperature, and speed response, etc. Through these tests, the working state and quality of the permanent magnet motor are evaluated, and it is checked whether it meets the design requirements and standards. However, usually, the obtained detection data will have problems such as errors, inconsistent data, and large amounts of data, resulting in inaccurate and inefficient analysis and evaluation of the detection data. Summary of the Invention

[0003] The purpose of the present invention is to provide a detection data analysis system for a permanent magnet motor routine test bench. By acquiring the detection data of the test motor and processing the inconsistent data and defective data in the data, the reliability of the analysis of the detection data is ensured; by analyzing the processed data and establishing a decision-making model, the accuracy and high efficiency of the motor performance evaluation during the test process are improved.

[0004] The purpose of the present invention can be achieved by the following technical solutions:

[0005] In a first aspect, an embodiment of the present application provides a detection data analysis system for a permanent magnet motor routine test bench, including a data acquisition module, a data processing module, a data analysis module, and a data storage module that are communicatively connected in sequence;

[0006] The data acquisition module is used to acquire the detection data of the test motor in the routine test bench;

[0007] The data processing module is used to perform data processing on the detection data to obtain data to be analyzed;

[0008] The data analysis module is used to perform data analysis on the data to be analyzed, obtain an analysis result, and visually represent it;

[0009] The data storage module is used to store the analysis result and establish a decision-making model;

[0010] Among them, the decision-making model is used to combine the actual parameters of the test motor and formulate a test decision; the test decision is applied to the routine test bench;

[0011] Among them, the data acquisition module performs data acquisition in a distributed data acquisition manner;

[0012] Adopt a data synchronization algorithm during the distributed data acquisition process;

[0013] Among them, the data analysis module uses the multiple linear regression method to establish a multiple linear regression model and conducts data analysis through it;

[0014] Establishing the multiple linear regression model includes the following steps:

[0015] S21, determine the dependent variable of the test motor;

[0016] S22, select independent variables from the data to be analyzed to generate an independent variable set; the independent variables are associated with the dependent variable;

[0017] S23, analyze the independent variable set and use the multiple linear regression method to establish a model to generate the multiple linear regression model;

[0018] S24, evaluate and optimize the multiple linear regression model to obtain the variable relationship between the independent variable and the dependent variable.

[0019] Preferably, the data acquisition module includes a data test cabinet, data acquisition instruments, and several sensors.

[0020] Preferably, the detected data includes: voltage, current, power, temperature, vibration, rotation speed, and power factor.

[0021] Preferably, regarding the data synchronization algorithm, it specifically includes the following steps:

[0022] S11, select a data source and collect the detected data;

[0023] S12, select a data synchronization protocol and communicate and synchronize between the data sources;

[0024] S13, determine the synchronization period and synchronization strategy;

[0025] S14, perform data transmission and reception and resolve data conflicts;

[0026] S15, record the data transmission log and process abnormal data.

[0027] Preferably, the data processing module uses the TSNN algorithm to process the missing data in the detected data.

[0028] Preferably, according to the TSNN algorithm, the final calculation formula for obtaining the data missing estimation value is expressed as:

[0029]

[0030] Among them, represents the spatio-temporal estimated value; s i represents the sensor node; u miss represents the moment; represents the spatial estimated value of the data missing value calculated using two spatial nearest neighbor values; represents the temporal estimated value of the data missing value calculated using two temporal nearest neighbor values; λ represents the spatio-temporal coefficient; NA represents the missing value.

[0031] Preferably, the spatio-temporal coefficient is used to represent the contribution ratio of the spatio-temporal estimated value, and its calculation formula is expressed as:

[0032]

[0033] Among them, N(S, V i ) represents the spatial missing value, N(T, V i ) represents the temporal missing value; VG represents the auxiliary window group, W is the observation window; V i represents the auxiliary window, U miss is the missing data set;

[0034] Among them, the spatial missing value is expressed as:

[0035] The temporal missing value is expressed as:

[0036] RMSE(S, V i ) represents the spatial precision, RMSE(T, V i ) represents the temporal precision.

[0037] Preferably, RMSE is used as the evaluation index for continuous data, and it is expressed as:

[0038] Among them, N MV represents the total number of missing data; V a represents the actual value of the missing data; V e represents the estimated value of the missing data.

[0039] Preferably, in step S23, the multiple linear regression model is expressed as:

[0040] y1 = β0 + β1x t1 + β2x t2 +... + β p x tp + ε t ;

[0041] Among them, β0 is the constant term; β1, β2,..., βp is the regression coefficient; ε t represents the random error; y1 represents the dependent variable; x t1 、x t2 、...、x tp are independent variables.

[0042] Preferably, in step S24, the multiple linear regression model is evaluated and optimized, specifically including the following steps:

[0043] S241, perform a significance test on the multiple linear regression model and each coefficient of the independent variables;

[0044] S242, perform a diagnostic analysis on the residuals of the multiple linear regression model to obtain a residual analysis result;

[0045] S243, optimize the multiple linear regression model according to the residual analysis result;

[0046] S244, evaluate the optimized multiple linear regression model according to the data to be analyzed.

[0047] The beneficial effects of the present invention are as follows:

[0048] (1) By obtaining the detection data of the test motor and processing the inconsistent data and defective data in the data, the present invention ensures the reliability of the analysis of the detection data; by analyzing the processed data and establishing a decision model, the accuracy and high efficiency of the motor performance evaluation in the test process are improved.

[0049] (2) In the data acquisition module, the present invention adopts a distributed data acquisition method to obtain detection data, avoiding the problems of increased interference, reduced data acquisition efficiency and fault tolerance caused by the large number of measurement and control points of the permanent magnet motor during the motor test process, reducing the time and delay of data acquisition, improving the efficiency, reliability and fault tolerance rate of data acquisition, and thus ensuring the synchronization and high quality in the data acquisition process.

[0050] (3) In the distributed data acquisition method, the present invention adopts a data synchronization algorithm to reduce the inconsistent data existing between multiple acquisition nodes during the distributed acquisition process, thereby ensuring the consistency of data acquisition; the present invention also adopts a conflict detection scheme for comparing previous values to detect and resolve the data conflict situations that occur during the data synchronization process.

[0051] (4) The data processing module of the present invention uses the TSNN algorithm to process and fill the defective data in the detection data, so as to obtain a higher filling accuracy while increasing the filling rate of missing data.

[0052] (5) The present invention uses the method of multiple linear regression to establish a multiple linear regression model, and analyzes the detection data through this model to obtain the relationship between the variables affecting the motor performance; by constructing and optimizing the multiple linear regression model, the adaptability of the model is improved, so that it can better describe the relationship between the independent variable and the dependent variable; by analyzing and optimizing the residuals of the model, the error and deviation of the model are reduced, and the prediction accuracy and generalization ability of the model are improved; through the significance test of the model, it can be determined whether there is a significant relationship between the independent variable and the dependent variable, so as to avoid the occurrence of selecting invalid independent variables or overfitting phenomena; it helps to ensure that the constructed multiple linear regression model is accurate, reliable and reasonable in prediction and interpretation, and improves the adaptability and prediction accuracy of the model.

[0053] (6) The present invention combines the actual parameters of the test motor and the analysis results of the data analysis module through establishing a decision-making model and formulates a test decision; through the explanation of the multiple linear regression model for the relationship between the independent variable and the dependent variable, accurate decisions are provided for the routine test bench, so that the tester can dynamically adjust the test method of the test motor according to the decision, and further ensure the accuracy and reliability of the test motor during the test process. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] For a better understanding and implementation, the technical solutions of the present application will be described in detail below with reference to the accompanying drawings.

[0055] Figure 1 It is a schematic structural diagram of a detection data analysis system for a permanent magnet motor routine test bench provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the exemplary embodiments will be described in detail herein, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of methods and systems consistent with some aspects of the present application as detailed in the appended claims.

[0057] The terms used in the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "the" and "said" used in the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to any or all possible combinations of one or more of the associated listed items.

[0058] The following will, in conjunction with the accompanying drawings and preferred embodiments, elaborate in detail on the specific implementation manners, features and effects of the present invention.

[0059] Please refer to Figure 1 , an embodiment of the present application provides a detection data analysis system for a permanent magnet motor routine test bench, including a data acquisition module, a data processing module, a data analysis module and a data storage module that are communicatively connected in sequence;

[0060] The data acquisition module is used to obtain the detection data of the test motor in the routine test bench;

[0061] The data processing module is used to process the detection data to obtain the data to be analyzed;

[0062] The data analysis module is used to analyze the data to be analyzed, obtain the analysis result and visually represent it;

[0063] The data storage module is used to store the analysis result and establish a decision model;

[0064] Wherein, the decision model is used to combine the actual parameters of the test motor and formulate a test decision;

[0065] The test decision is applied to the routine test bench.

[0066] Specifically, the present application first collects the detection data of the test motor from the routine test bench, then processes the detection data to generate the data to be processed and form a set of data to be processed; then analyzes the data to be analyzed, generates the corresponding analysis result and visually displays it according to the analysis result; finally stores the above analysis result and establishes a decision model based on it. The model is used to combine the actual parameters of the test motor and formulate a test decision accordingly. The test decision can, to a certain extent, reflect the defects existing in the test process of the test motor on the routine test bench, so that the test bench can adjust the test method in real time, and further enable the test motor to achieve better test results during the test process.

[0067] It should be noted that the routine test bench in this application is used to perform performance tests on permanent magnet motors, and the detection system composed of the routine test bench includes a routine test bench and a power supply, a test motor and an information interface connected thereto respectively; and the main test items of the routine test bench used in this application include: no-load back electromotive force measurement, load current test, rotary transformer zero angle measurement, steering test, vibration measurement; and the routine test bench also has the ability to perform routine tests on asynchronous motors, and the routine test items of asynchronous motors that can be implemented include: stall test, running-in test, no-load test, vibration test, speed sensor waveform test, temperature rise test, coil heating test, etc. The data generated in the above test is collected and acquired through the above information interface and the data acquisition module of this embodiment.

[0068] Each of the above modules will be described in detail below.

[0069] Regarding the data acquisition module, it is mainly composed of a data test cabinet, a data acquisition instrument and several sensors; during the motor test, since the permanent magnet motor has many measurement and control points in the test system, if a centralized test and control method is adopted, a large number of sensor signal cables will enter the operation room, which will lead to increased interference and make wiring, maintenance and expansion difficult, reducing the efficiency and fault tolerance of data acquisition. Therefore, this embodiment adopts a distributed data acquisition method to solve the above-mentioned measurement and control problems.

[0070] In the distributed data collection process, firstly, several collection nodes are arranged on the test bench, because the detection data include: voltage, current, power, temperature, vibration, rotation speed and power factor, etc., and the above detection data have different characteristics, so different collection nodes will be arranged according to different detection data during data collection; then, the detection data is collected simultaneously through several collection nodes to ensure the synchronization of the detection data; and the time and delay of data collection are reduced through distributed data collection, so as to improve the efficiency, reliability and fault tolerance of data collection. However, collecting data through several collection nodes may cause data inconsistency problems between multiple collection nodes, so this embodiment also adopts a data synchronization algorithm to ensure the consistency of detection data during the collection process.

[0071] The data synchronization algorithm specifically includes the following steps:

[0072] S11, selecting a data source and collecting the detection data;

[0073] Wherein, the data sources include but are not limited to several sensors and controllers of the permanent magnet motor;

[0074] S12, selecting a data synchronization protocol and performing communication and synchronization between the data sources;

[0075] Among them, the data synchronization protocol includes but is not limited to TCP / IP protocol, MQTT (Message Queuing Telemetry Transport) and WebSocket protocol, etc.; the specific protocol is selected according to the sensor, controller and network system, and this embodiment does not make specific limitations.

[0076] S13, determining the synchronization cycle and synchronization strategy;

[0077] Among them, different synchronization cycles are set according to the needs of data collection and the frequency of data changes, that is, the time for performing a data synchronization operation.

[0078] S14, transmitting and receiving data, and resolving data conflicts;

[0079] During the data synchronization process, data conflicts may occur, that is, multiple data sources update the same data at the same time; therefore, it is necessary to define appropriate conflict resolution strategies, such as latest update priority, manual intervention, etc.; this embodiment uses a conflict detection scheme that compares previous values to detect and resolve data conflicts;

[0080] S15, record data transmission logs and process abnormal data;

[0081] Handle abnormal situations in data synchronization, such as data transmission failure, data source unavailability, etc., and record relevant logs for troubleshooting and analysis.

[0082] In general, after being processed by the above data synchronization algorithm, the data inconsistency problem that occurs during the data collection process can be solved, thereby ensuring that the data collected at multiple collection nodes are consistent and accurate.

[0083] Regarding the data processing module, the detection data obtained through the above-mentioned data acquisition module may have some defects, such as some missing values, duplicate values and abnormal values. Therefore, in order to solve the data defects, the data processing module of this embodiment will process the above-mentioned detection data and eliminate the defective data therein, so as to obtain data that meets the system requirements and has consistency and integrity, and name it as the data to be analyzed.

[0084] Specifically, the above data processing module adopts a missing data imputation algorithm for wireless sensor networks based on temporal and spatial nearest neighbor values (Temporal and Spatial Nearest Neighbor Values Based Missing Data Imputation, TSNN) to impute the missing data in the above data, thereby obtaining a high imputation accuracy while increasing the missing data imputation rate.

[0085] In this embodiment, according to the above TSNN algorithm, the final calculation formula for the data missing estimation value is obtained, and this formula is expressed as:

[0086]

[0087] Wherein, represents the finally obtained spatio-temporal estimation value; s i represents the sensor node; u miss represents the moment; represents the spatial estimation value of the data missing value calculated using two spatial nearest neighbor values; represents the temporal estimation value of the data missing value calculated using two temporal nearest neighbor values; λ represents the spatio-temporal coefficient; NA represents the missing value.

[0088] Wherein, the spatio-temporal coefficient λ is used to describe the contribution ratio of the spatio-temporal estimation value, and its calculation formula is expressed as:

[0089] Wherein, N(S, V i ) represents the spatial missing value, N(T, V i ) represents the temporal missing value; VG represents the auxiliary window group, W is the observation window; V i represents the auxiliary window, U miss is the set of missing data;

[0090] Wherein, the spatial missing value is expressed as:

[0091] The temporal missing value is expressed as: RMSE(S, V i ) represents the spatial precision, and RMSE(T, V i ) represents the temporal precision.

[0092] Furthermore, RMSE represents the root mean square error, which is used as an evaluation index for continuous data in this embodiment, and is expressed as:

[0093] Wherein, NMV represents the total number of missing data; V a represents the actual value of the missing data; V e represents the estimated value of the missing data.

[0094] The data processing module of this application calculates the estimated value of the missing measurement data of the sensor node at a moment by adopting the TSNN algorithm. For the missing measurement values that occur on this node, the Spatial Nearest Neighbor’s Value in Geometrical Distance (SGNNV), the Spatial Nearest Neighbors Value in Data Distance (SDNNV), the Temporal Nearest Neighbor’s Value in Time Distance (TTNNV), and the Temporal Nearest Neighbors Value in Data Distance (TDNNV) are respectively called to calculate the four spatio-temporal nearest neighbor values of all non-missing measurement values in the sample set, and these are used as training data to construct a regression equation system and calculate the regression coefficients and the fitting metric R value. According to the corresponding calculation formulas, the estimated value of the missing measurement data is obtained for data filling, so that the TSNN algorithm obtains better adaptability, thereby effectively improving the filling rate of the algorithm.

[0095] It should be noted that the above TSNN algorithm can fill the missing data in the detection data, and it can be any type of data in the detection data. For example, the TSNN algorithm can be used to fill the missing data of temperature, or it can also be used to fill data such as current or voltage.

[0096] Regarding the data analysis module, the data to be analyzed is obtained through the above data processing module, and then the analysis result is obtained after data analysis; in this embodiment, because there are certain correlation relationships and correlations in the current, voltage, temperature and other data in the above detection data, such as: the changes in voltage, current and rotational speed will cause temperature changes, and the above detection data is an influencing factor affecting the performance of the permanent magnet motor and cannot be analyzed and discussed separately. Therefore, this embodiment adopts the method of multiple linear regression to establish a multiple linear regression model, and analyzes the above data through this model, that is: by establishing a multiple linear regression model to analyze multiple influencing factors in the detection data as independent variables and analyze their relationship with the motor performance as the dependent variable.

[0097] Specifically, to establish a multiple linear regression model, the following steps are included:

[0098] S21, determine the dependent variable of the test motor;

[0099] Optionally select one of the performance, efficiency, etc. of the test motor as the dependent variable;

[0100] S22, select independent variables from the data to be analyzed to generate a set of independent variables;

[0101] Among them, the independent variables are associated with the dependent variable;

[0102] Specifically: In this embodiment, the data that can be used as independent variables selected from the data to be analyzed is associated with the above-mentioned dependent variable, that is: the selected independent variables are the influencing factors of the above-mentioned dependent variable. For example, abnormalities in temperature, voltage, and current will also cause changes in the motor performance, etc.

[0103] S23, analyze the set of independent variables and use the multiple linear regression method to establish a model to generate a multiple linear regression model;

[0104] S24, evaluate and optimize the multiple linear regression model to obtain the variable relationship between the independent variable and the dependent variable.

[0105] Specifically, by establishing a multiple linear regression model, the variable relationship between the independent variable and the dependent variable can be analyzed, and this variable relationship is visually represented as the analysis result and sent to the information display system for display, so as to intuitively reflect the change relationship and change degree between the data.

[0106] In step S23 of this embodiment, the multiple linear regression model is expressed as:

[0107] y1 = β0 + β1x t1 + β2x t2 +... + β p x tp + ε t ;

[0108] Among them, β0 is the constant term; β1, β2,..., β p are the regression coefficients; ε t represents the random error; y1 represents the dependent variable; x t1 、x t2 、...、x tp are the independent variables.

[0109] In this embodiment, the data of the above-mentioned dependent variable and independent variable collected are fitted through modeling, and parameter estimation is carried out after the collected data is fitted; the purpose of parameter estimation is mainly to estimate the values of the partial regression coefficients of the model, so as to use the estimated values to collect new data of the independent variable for prediction, which is also called the sample size.

[0110] Furthermore, in this embodiment, the least squares method is used for parameter estimation, that is: estimating the coefficient β of the independent variable X, which is expressed by the formula: where β includes β1, β2,..., β p .

[0111] In practical applications, the relationship between the dependent variable and the independent variable is not obvious, so certain significance tests and verifications are required to determine whether there is a good significant relationship between the two; therefore, in this embodiment, the statistic F is cited as a constraint condition of the model to test the significance of the regression equation.

[0112] In step S24 of this embodiment, the multiple linear regression model is evaluated and optimized, which specifically includes the following steps:

[0113] S241, performing significance tests on the multiple linear regression model and each coefficient of the independent variable;

[0114] Specifically: the overall significance of the multiple linear regression model can be tested using the F statistic, and the significance of the independent variable can be tested using the t statistic.

[0115] S242, performing diagnostic analysis on the residuals of the multiple linear regression model to obtain the residual analysis results;

[0116] Specifically: the fitting situation of the model and the rationality of the residuals are evaluated by performing diagnostic analysis on the residuals of the model. The residual analysis adopted in this embodiment includes: checking the normality, heteroscedasticity and autocorrelation of the residuals.

[0117] S243, optimizing the multiple linear regression model according to the residual analysis results;

[0118] Model optimization can be carried out by means of transforming variables, introducing interaction terms, removing outliers, etc.

[0119] S244, evaluating the optimized multiple linear regression model according to the data to be analyzed.

[0120] In this embodiment, the data to be analyzed is used as an independent test data set to evaluate the performance of the optimized model, and various indicators (such as mean square error, R-squared, etc.) are used to evaluate the accuracy and prediction ability of the model.

[0121] In this embodiment, by analyzing and processing data, and by constructing and optimizing a multiple linear regression model, the adaptability of the model is improved, enabling it to better describe the relationship between independent variables and dependent variables; by analyzing and optimizing the residuals of the model, the errors and biases of the model are reduced, and the prediction accuracy and generalization ability of the model are improved; through the significance test of the model, it can be determined whether there is a significant relationship between independent variables and dependent variables, thus avoiding the occurrence of selecting invalid independent variables or overfitting phenomena; it helps to ensure that the constructed multiple linear regression model is accurate, reliable and reasonable in prediction and interpretation, and improves the adaptability and prediction accuracy of the model.

[0122] Regarding the data storage module, this module stores the analysis results output by the data analysis module and establishes a decision-making model based on them. This decision-making model is used to combine the actual parameters of the test motor and formulate test decisions; through the explanation of the multiple linear regression model for the relationship between independent variables and dependent variables, accurate decisions are provided for the routine test bench, and then the tester can dynamically adjust the test method of the test motor according to the decisions, further ensuring the accuracy and reliability of the test motor during the test process.

[0123] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above-mentioned functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be described in detail here.

[0124] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0125] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0126] As described above, the above are only the preferred embodiments of the present invention, and there is no any form of limitation to the present invention. Although the present invention has been disclosed as above with the preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the equivalent embodiments by using the technical content disclosed above within the scope of the technical solution of the present invention. However, as long as it does not depart from the content of the technical solution of the present invention, any brief modifications, equivalent changes and modifications made to the above embodiments according to the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A detection data analysis system for a permanent magnet motor routine test bench, characterized in that: It includes a data acquisition module, a data processing module, a data analysis module, and a data storage module that are communicatively connected in sequence; The data acquisition module is used to obtain the detection data of the test motor in the routine test bench; The data processing module is used to process the detection data to obtain the data to be analyzed; The data analysis module is used to analyze the data to be analyzed, obtain the analysis result and visually represent it; The data storage module is used to store the analysis result and establish a decision-making model; Among them, the decision-making model is used to combine the actual parameters of the test motor and formulate a test decision; the test decision is applied to the routine test bench; Among them, the data acquisition module uses a distributed data acquisition method to collect data; A data synchronization algorithm is adopted during the distributed data acquisition process; Among them, the data analysis module uses the multiple linear regression method to establish a multiple linear regression model and conducts data analysis through it; To establish the multiple linear regression model, the following steps are included: S21, determine the dependent variable of the test motor; S22, select independent variables from the data to be analyzed to generate an independent variable set; the independent variables are associated with the dependent variable; S23, analyze the independent variable set and use the multiple linear regression method to establish a model to generate the multiple linear regression model; S24, evaluate and optimize the multiple linear regression model to obtain the variable relationship between the independent variable and the dependent variable.

2. The detection data analysis system for a permanent magnet motor routine test bench according to claim 1, wherein: The data acquisition module includes a data test cabinet, data acquisition instruments, and several sensors.

3. The detection data analysis system for a permanent magnet motor routine test bench according to claim 2, wherein: The detection data includes: voltage, current, power, temperature, vibration, rotational speed, and power factor.

4. The detection data analysis system for a permanent magnet motor routine test bench according to claim 3, wherein: Regarding the data synchronization algorithm, it specifically includes the following steps: S11, select a data source and collect the detection data; S12, select a data synchronization protocol and communicate and synchronize between the data sources; S13, determine the synchronization period and synchronization strategy; S14, perform data transmission and reception and resolve data conflicts; S15, record the data transmission log and process abnormal data.

5. The detection data analysis system for a permanent magnet motor routine test bench according to claim 1, wherein: The data processing module uses the TSNN algorithm to process the missing data in the detection data.

6. The detection data analysis system for a permanent magnet motor routine test bench according to claim 5, characterized in that: According to the final calculation formula of the data missing estimate value obtained by the TSNN algorithm, it is expressed as: Among them, represents the spatio-temporal estimated value; s i represents the sensor node; u miss represents the time; represents the spatial estimated value of the data missing value calculated using two spatial nearest neighbor values; represents the temporal estimated value of the data missing value calculated using two temporal nearest neighbor values; λ represents the spatio-temporal coefficient; NA represents the missing value.

7. A detection data analysis system for a permanent magnet motor routine test bench according to claim 6, characterized in that: The spatio-temporal coefficient is used to represent the contribution ratio of the spatio-temporal estimate value, and its calculation formula is expressed as: Among them, N(S, V i ) represents the spatial missing value, and N(T, V i ) represents the temporal missing value; VG represents the auxiliary window group, W is the observation window; V i represents the auxiliary window, V i = {v1, v2,..., v m-1 , v m}, U miss is the missing data set; Among them, the spatial missing value is expressed as: The missing value of the time is represented as: RMSE(S, V i ) represents the spatial accuracy, and RMSE(T, V i ) represents the temporal accuracy.

8. The detection data analysis system for a permanent magnet motor routine test bench according to claim 7, characterized in that: Use RMSE as the evaluation index for continuous data, which is expressed as: Among them, N MV represents the total number of missing data; V a represents the actual value of the missing data; V e represents the estimated value of the missing data.

9. A detection data analysis system for a permanent magnet motor routine test bench according to claim 1, characterized in that: In step S23, the multiple linear regression model is expressed as: y1 = β0 + βx t1 + β2x t2 +... + β p x tp + ε t ; Among them, β0 is the constant term; β1, β2, …, β p are regression coefficients; ε t represents the random error; y1 represents the dependent variable; x t1 、x t2 、…、x tp are independent variables.

10. The detection data analysis system for a permanent magnet motor routine test bench according to claim 1, characterized in that: In step S24, to evaluate and optimize the multiple linear regression model, it specifically includes the following steps: S241, conduct a significance test on the multiple linear regression model and each coefficient of the independent variable; S242, conduct a diagnostic analysis on the residuals of the multiple linear regression model to obtain the residual analysis result; S243, optimize the multiple linear regression model according to the residual analysis result; S244, evaluate the optimized multiple linear regression model according to the data to be analyzed.

Images