Motor Current Acquisition Method, Device, Storage Medium and Electronic Device

Abstract

The present invention provides a method, device, storage medium and electronic device for obtaining motor current, relating to the technical field of rail transit. The method is applied to a train traction system, and the train traction system includes the motor. The method includes: obtaining the current torque, current speed and current theoretical estimated value of the motor; obtaining the current operating condition information of the train; inputting the current torque, the current speed, the current theoretical estimated value of the current and the current operating condition information into a pre-trained current prediction model, so that the current prediction model outputs the current prediction value of the motor under the current operating condition. The technical solution provided by the present invention can obtain the motor current value in real time and accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of rail transit, and particularly to a method, device, storage medium and electronic device for obtaining motor current. Background Art

[0002] The motor current signal is a key signal for the closed-loop control and fault diagnosis of the train traction system. Therefore, accurately obtaining the motor current values under different operating conditions of the train traction system in the normal operating state has positive significance for subsequent train fault diagnosis.

[0003] Currently, only a rough estimation method is used to obtain the above-mentioned motor current value, and the actual operating conditions of the train are not considered during the estimation process. That is, the motor current value obtained by the existing technology is not accurate, and further, the subsequent diagnosis result of the train fault based on this motor current value is also inaccurate. In addition, the existing estimation method needs to be carried out after collecting relevant data and cannot achieve real-time estimation. Summary of the Invention

[0004] In view of the above problems in the prior art, the present application proposes a method, device, storage medium and electronic device for obtaining motor current, which can obtain the motor current value in real time and accurately.

[0005] To achieve the above object, the technical solution of the present invention is implemented as follows:

[0006] In a first aspect, an embodiment of the present invention provides a method for obtaining motor current. The method is applied to a train traction system, and the train traction system includes the motor. The method includes:

[0007] Obtain the current torque, current speed and current theoretical estimated value of the motor;

[0008] Obtain the current operating condition information of the train;

[0009] Input the current torque, the current speed, the current theoretical estimated value of the current and the current operating condition information into a pre-trained current prediction model, so that the current prediction model outputs the current prediction value of the motor under the current operating condition.

[0010] In some embodiments, the method further includes:

[0011] Obtain the actual current value of the motor;

[0012] Based on the actual current value of the current and the current prediction value, calculate the residual between the actual current value of the current and the current prediction value;

[0013] Based on the residual between the actual current value and the predicted current value, determine whether the train traction system is abnormal.

[0014] In some embodiments, the determining whether the train traction system is abnormal based on the residual between the actual current value and the predicted current value includes:

[0015] Based on the residual between the actual current value and the predicted current value, use the CUSUM algorithm to determine whether the current of the motor is abnormal;

[0016] When the current of the motor is abnormal, determine that the train traction system is abnormal.

[0017] In some embodiments, the method further includes:

[0018] When it is determined that the train traction system is abnormal, an alarm is issued.

[0019] In some embodiments, the following expression is used to obtain the theoretical estimated value of the current of the motor:

[0020]

[0021]

[0022]

[0023] Wherein, is the theoretical estimated value of the current of the motor; s is the slip ratio of the motor; k is a preset coefficient; T e is the torque of the motor; N p is the number of pole pairs of the motor; n is the speed of the motor; ψ s is the given value of the stator flux of the motor; ω sl is the slip angular frequency of the motor; R r is the rotor resistance of the motor; L m is the rotor mutual inductance of the motor; L r is the rotor equivalent self-inductance of the motor.

[0024] In some embodiments, the train traction system further includes: an inverter and a control handle; the obtaining the current operating condition information of the train includes:

[0025] Obtain the operating state of the inverter;

[0026] Obtain the position information of the control handle;

[0027] Based on the operating state of the inverter, the position information of the control handle, and the current speed of the motor, obtain the current operating condition information of the train.

[0028] In some embodiments, the current prediction model is an LSSVM prediction model.

[0029] In a second aspect, an embodiment of the present invention provides a device for obtaining motor current. The device is applied to a train traction system, and the train traction system includes the motor. The device includes:

[0030] A first acquisition unit, configured to acquire the current torque, current speed, and current theoretical estimated value of the motor;

[0031] A second acquisition unit, configured to acquire the current operating condition information of the train;

[0032] An input unit, configured to input the current torque, the current speed, the current theoretical estimated value of the current, and the current operating condition information into a pre-trained current prediction model, so that the current prediction model outputs a current prediction value of the motor under the current operating condition.

[0033] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which program code is stored. When the program code is executed by a processor, the method for obtaining motor current according to any one of the above embodiments is implemented.

[0034] In a fourth aspect, an embodiment of the present invention provides an electronic device, which includes a memory and a processor. Program code that can run on the processor is stored on the memory. When the program code is executed by the processor, the method for obtaining motor current according to any one of the above embodiments is implemented.

[0035] The method, device, storage medium, and electronic device for obtaining motor current provided by the embodiments of the present invention obtain the current torque, current speed, current theoretical estimated value of the motor, and the current operating condition information of the train, and input the above current torque, current speed, current theoretical estimated value of the current, and current operating condition information into a pre-trained current prediction model, so that the current prediction model outputs a current prediction value of the motor under the above current operating condition, enabling the acquisition of the motor current value (i.e., the current prediction value of the above motor) to be performed in real time based on the pre-trained current prediction model, realizing real-time prediction of the motor current. And the current prediction model uses the current operating condition information of the train as one of the input information, that is, the embodiments of the present invention fully consider the actual operating condition of the train, making the prediction result more accurate. It can be seen that the technical solution provided by the embodiments of the present invention can obtain the motor current value in real time and accurately. Description of the Drawings

[0036] The scope of the disclosure of the present invention can be better understood by reading the following detailed description of exemplary embodiments in conjunction with the accompanying drawings. The accompanying drawings included are:

[0037] Figure 1 is the method flow of the embodiment of the present invention Figure 1 ;

[0038] Figure 2 is the method flow of the embodiment of the present invention Figure 2 ;

[0039] Figure 3 is the overall flow schematic diagram of the embodiment of the present invention;

[0040] Figure 4 is the diagram of the operating condition change of the train in the embodiment of the present invention;

[0041] Figure 5 is the diagram of the change of the torque and speed of the motor in the embodiment of the present invention;

[0042] Figure 6 is the comparison diagram of the current prediction effect of a certain actual data on site in the embodiment of the present invention;

[0043] Figure 7 is the device structure of the embodiment of the present invention Figure 1 ;

[0044] Figure 8 is the device structure of the embodiment of the present invention Figure 2 . Detailed implementation manners

[0045] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the following will describe in detail the implementation method of the present invention in conjunction with the accompanying drawings and embodiments, so as to fully understand how the present invention uses technical means to solve technical problems and achieve the implementation process of technical effects and implement accordingly.

[0046] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0047] Example 1

[0048] An embodiment of the present invention provides a method for obtaining motor current. The method is applied to a train traction system, and the train traction system includes the motor. As Figure 1 shown, the method described in this embodiment includes step S101, step S102, and step S103. The specific contents of these steps are described in detail below:

[0049] Step S101, obtain the current torque, current speed, and current theoretical estimated value of the motor;

[0050] In this embodiment, the following expression is used to obtain the current theoretical estimated value of the motor current:

[0051]

[0052]

[0053]

[0054] Wherein, is the current theoretical estimated value of the motor current; s is the slip ratio of the motor; k is a preset coefficient; T e is the torque of the motor; N p is the number of pole pairs of the motor; n is the speed of the motor; ψ s is the stator flux reference value of the motor; ω sl is the slip angular frequency of the motor; R r is the rotor resistance of the motor; L m is the rotor mutual inductance of the motor; L r is the rotor equivalent self-inductance of the motor.

[0055] Wherein, the stator flux reference value ψ s of the motor is strongly correlated with the motor speed, and its functional relationship ψ s = f(n) can be obtained by fitting experimental data; the rotor equivalent self-inductance L r of the motor is the sum of the rotor mutual inductance L m and the rotor leakage inductance L lr of the motor.

[0056] Substituting the above formulas (1) and (2) into formula (3), it can be seen that the current theoretical estimated value of the motor current is only related to the torque T e of the motor, the speed n of the motor, and the basic parameters of the motor. Therefore, the current theoretical estimated value of the motor current can be calculated by integrating the above formulas (1), (2), and (3)

[0057] Step S102, obtain the current operating condition information of the train;

[0058] In order to obtain the motor current value more accurately, the current operating condition of the train is considered in this embodiment.

[0059] In this embodiment, the train traction system further includes: an inverter and a driver's control handle; obtaining the current operating condition information of the train includes: obtaining the operating state of the inverter; obtaining the position information of the driver's control handle; and obtaining the current operating condition information of the train based on the operating state of the inverter, the position information of the driver's control handle, and the current rotational speed of the motor.

[0060] Specifically, according to the train operation law, the above operating conditions can be divided into multiple categories in this embodiment. Based on the position information of the driver's control handle, the operating state of the inverter, and the current rotational speed of the motor, it is divided into 7 operating conditions according to the train operation law, as shown in Table 1 below:

[0061] Table 1 Explanation of Operating Condition Division

[0062]

[0063]

[0064] In Table 1, when in operating condition W0, since the inverter is in the blocked state, the magnitude of the motor current has nothing to do with the position of the driver's control handle and the rotational speed of the motor, and its value is constantly 0; when in operating condition W5, since the rotational speed of the motor is 0, the traction motor cannot exert braking force, and the motor current at this time is equivalent to the motor current in operating condition W6.

[0065] Step S103, input the current torque, the current rotational speed, the theoretical estimated value of the current current, and the current operating condition information into a pre-trained current prediction model, so that the current prediction model outputs the predicted value of the motor current under the current operating condition.

[0066] In this embodiment, the current prediction model is an LSSVM (Least Square Support Vector Machine) prediction model. That is, in this embodiment, the LSSVM algorithm is used to perform real-time prediction of the motor current. Of course, in practical applications, other data-driven prediction algorithms can also be used according to actual needs, and this embodiment does not make specific limitations on this.

[0067] The overall flow diagram of the real-time prediction of the motor current and the real-time diagnosis of current anomalies proposed in this embodiment is as Figure 3 shown. The entire algorithm is divided into two parts: offline modeling and online implementation.

[0068] Specifically, in the offline modeling stage, an LSSVM prediction model is first established, and then the LSSVM prediction model is trained based on relevant variables of historical operation data under each train operation condition. That is, the motor torque, motor speed, theoretical estimated value of motor current, and operation condition information are used as the input of the LSSVM prediction model, and the motor current value under this operation condition is used as the output of the LSSVM prediction model to train the LSSVM prediction model, and a trained current prediction model is obtained. Through this current prediction model, the motor current value under various operation conditions can be predicted, that is, the current prediction value of the above motor is obtained. Since the training samples of the train traction system in the normal operation state are used when training the LSSVM prediction model, when the above trained current prediction model is used for prediction, the motor current prediction values under different operation conditions of the train traction system in the normal operation state are also obtained.

[0069] In the online implementation stage, as Figure 3 shown, after the current torque of the motor, the current speed of the motor, the current theoretical estimated value of the motor current, and the current operation condition information of the train are obtained in real time by using the above steps S101 and S102, they can be input into the above trained current prediction model, so that the current prediction model outputs the current prediction value of the motor current under the current operation condition, that is, the motor current value can be predicted online and in real time through this current prediction model.

[0070] The motor current signal is a key signal for the closed-loop control and fault diagnosis of the train traction drive system. When there are abnormalities in the inverter power supply, motor body or control of the traction drive system, the current value of the traction motor will deviate to varying degrees from the normal situation. At present, for the diagnosis of abnormal motor current, generally only a current threshold with a certain overload coefficient is set according to its rated current value. When the current exceeds the set threshold during the train operation, an overcurrent fault will be reported and relevant protection actions will be executed to avoid the expansion of the fault. Through the above steps S101 - S103 of this embodiment, the theoretical value of the traction motor current under various train operation conditions can be effectively estimated. If an adaptive current threshold can be set according to the train operating condition and the current motor current is monitored in real time to determine whether it is within the normal threshold range, and the system protection is performed in a timely manner when an abnormality occurs, the train operation safety can be effectively improved. Therefore, the research on the real-time prediction of traction motor current and the real-time diagnosis method of current abnormality is of great significance for improving the reliability of the traction drive system.

[0071] Based on the above ideas, as Figure 2 shown, the method described in this embodiment further includes:

[0072] Step S104, obtaining the actual current value of the motor;

[0073] Step S105: Calculate the residual between the actual current value and the predicted current value based on the actual current value and the predicted current value of the motor.

[0074] Step S106: Determine whether the train traction system is abnormal based on the residual between the actual current value and the predicted current value of the motor.

[0075] In this embodiment, since the predicted current value of the motor is the effective value in practical applications, for the convenience of calculation, the actual current value of the motor also uses the effective value. Then, obtaining the actual current value of the motor includes: obtaining the instantaneous current value of the motor; performing effective value calculation on the instantaneous current value of the motor to obtain the effective current value of the motor, and using this effective current value as the actual current value of the motor.

[0076] In this embodiment, a current acquisition device can be used to collect the instantaneous current value of the motor in real time.

[0077] In this embodiment, determining whether the train traction system is abnormal based on the residual between the actual current value and the predicted current value of the motor includes: determining whether the current of the motor is abnormal by using the CUSUM algorithm based on the residual between the actual current value and the predicted current value of the motor; when the current of the motor is abnormal, determining that the train traction system is abnormal.

[0078] Furthermore, to effectively remind train technicians, the method described in this embodiment further includes: when it is determined that the train traction system is abnormal, an alarm is issued.

[0079] It should be noted that there is no sequential execution order between step S104 and step S103, and step S104 and step S103 can also be executed simultaneously. Figure 2 It is only a flow schematic diagram of one implementation manner.

[0080] Specifically, as Figure 3 shown, perform effective value calculation on the collected instantaneous current value i s of the motor to obtain the effective current value I s of the motor, and then calculate the predicted current value I s P of the motor and the residual ε between the effective current value I s of the motor. Then, use the CUSUM (Cumulative Sum) algorithm for diagnostic decision-making to obtain the diagnostic result of whether the motor current is abnormal, and further determine whether the train traction system is abnormal based on this diagnostic result. Of course, in practical applications, other residual detection methods can also be used for the above diagnostic decision-making according to actual needs, not limited to the above CUSUM algorithm.

[0081] The technical effects of this embodiment are demonstrated by the following practical application:

[0082] A section of actual continuous data that experiences multiple operating conditions during the on-site operation of a certain type of EMU is randomly selected, and comparative tests are respectively carried out using the existing mechanism model-based method, the LS (Least Square) method, and the LSSVM prediction model described in this embodiment.

[0083] From Figure 4 it can be seen that the train has experienced all operating conditions except W5, and the torque and speed change ranges are as Figure 5 shown, reaching 0 - 8200 N·m and 0 - 3000 r·min respectively -1 , with good data coverage and meeting the verification requirements. From Figure 6 the current prediction effects of various algorithms in it, it can be seen that within the entire time range, the LSSVM algorithm is significantly better than the LS method and the mechanism model-based prediction method. The RMSE (Root Mean Squared Error) indexes of the motor current predictions of different algorithms within the entire time range are statistically analyzed according to operating conditions, and the results are shown in Table 2.

[0084] Table 2 Test effects of on-site data (RMSE index) Unit: (A)

[0085]

[0086] As can be seen from Table 2, when the operating conditions are W1 - W3, the LSSVM algorithm is better than other methods, and the maximum RMSE value is about 10 A, which is much smaller than the LS method and the method based on the mechanism model (MM in the table). When the operating condition is W4, its RMSE value is comparable to that of the LS method, both less than 5 A. When the operating condition is W6, the errors of several methods are relatively large, but the LSSVM algorithm is still better than the LS method and the method based on the mechanism model, meeting the requirements of practical applications.

[0087] The method for obtaining the motor current provided by the embodiment of the present invention obtains the current torque, current speed, current theoretical estimated value of the motor, and the current operating condition information of the train, and inputs the above current torque, current speed, current theoretical estimated value, and current operating condition information into a pre-trained current prediction model, so that the current prediction model outputs the current prediction value of the motor under the above current operating condition, enabling the acquisition of the motor current value (i.e., the current prediction value of the above motor) to be carried out in real time based on the pre-trained current prediction model, realizing the real-time prediction of the motor current. And the current prediction model takes the current operating condition information of the train as one of the input information, that is, the embodiment of the present invention fully considers the actual operating condition of the train, making the prediction result more accurate. It can be seen that the technical solution provided by the embodiment of the present invention can obtain the motor current value in real time and accurately.

[0088] In addition, the embodiment of the present invention also provides a method for diagnosing the abnormality of the traction system, which can realize the real-time diagnosis of whether the traction system is abnormal based on the actual current value of the motor and the current prediction value of the motor, thereby improving the reliability and operation safety of the traction system.

[0089] Example 2

[0090] Corresponding to the above method embodiment, the present invention also provides a device for obtaining the motor current. The device is applied to the train traction system, and the train traction system includes the motor; as Figure 7 shown, the device includes:

[0091] A first acquisition unit 201 for acquiring the current torque, current speed, and current theoretical estimated value of the motor;

[0092] A second acquisition unit 202 for acquiring the current operating condition information of the train;

[0093] An input unit 203 for inputting the current torque, the current speed, the current theoretical estimated value, and the current operating condition information into a pre-trained current prediction model, so that the current prediction model outputs the current prediction value of the motor under the current operating condition.

[0094] Further, as Figure 8 shown, the device in this embodiment further includes:

[0095] A third acquisition unit 204 for acquiring the actual current value of the motor;

[0096] A residual calculation unit 205 for calculating the residual between the actual current value and the current prediction value based on the actual current value of the motor and the current prediction value;

[0097] A judgment unit 206, configured to judge whether the train traction system is abnormal based on the residual between the actual current value and the predicted current value.

[0098] In this embodiment, the judgment unit 206 judges whether the train traction system is abnormal in the following manner:

[0099] Based on the residual between the actual current value and the predicted current value, the CUSUM algorithm is used to judge whether the current of the motor is abnormal;

[0100] When the current of the motor is abnormal, it is determined that the train traction system is abnormal.

[0101] Further, in order to effectively remind train technicians, as Figure 8 shown, the device described in this embodiment further includes:

[0102] An alarm unit 207, configured to give an alarm when it is determined that the train traction system is abnormal.

[0103] In this embodiment, the first acquisition unit 201 acquires the theoretical estimated value of the current of the motor by using the following expression:

[0104]

[0105]

[0106]

[0107] where is the theoretical estimated value of the current of the motor; s is the slip ratio of the motor; k is a preset coefficient; T e is the torque of the motor; N p is the number of pole pairs of the motor; n is the rotational speed of the motor; ψ s is the stator flux reference value of the motor; ω sl is the slip angular frequency of the motor; R r is the rotor resistance of the motor; L m is the rotor mutual inductance of the motor; L r is the rotor equivalent self-inductance of the motor.

[0108] In this embodiment, the train traction system further includes: an inverter and a control handle; the second acquisition unit 202 acquires the current operating condition information of the train in the following manner:

[0109] Acquire the operating state of the inverter;

[0110] Acquire the position information of the control handle;

[0111] Obtain the current operating condition information of the train based on the operating state of the inverter, the position information of the driver's control handle, and the current speed of the motor.

[0112] In this embodiment, the current prediction model is an LSSVM prediction model.

[0113] For the working principle, working process and other content related to the specific implementation manner of the above device, reference can be made to the specific implementation manner of the motor current acquisition method provided by the present invention, and the same technical content will not be described in detail here.

[0114] The motor current acquisition device provided by the embodiment of the present invention obtains the current torque, current speed, current theoretical estimated value of the current, and the current operating condition information of the train, and inputs the above current torque, current speed, current theoretical estimated value of the current, and current operating condition information into a pre-trained current prediction model, so that the current prediction model outputs the current prediction value of the motor under the above current operating condition, enabling the acquisition of the motor current value (i.e., the above current prediction value of the motor) to be carried out in real time based on the pre-trained current prediction model, realizing the real-time prediction of the motor current. And the current prediction model takes the current operating condition information of the train as one of the input information, that is, the embodiment of the present invention fully considers the actual operating condition of the train, making the prediction result more accurate. It can be seen that the technical solution provided by the embodiment of the present invention can obtain the motor current value in real time and accurately.

[0115] In addition, the embodiment of the present invention also has a traction system abnormal diagnosis function, which can realize the real-time diagnosis of whether the traction system is abnormal based on the actual value of the current of the motor and the current prediction value of the motor, thereby improving the reliability and operation safety of the traction system.

[0116] Example 3

[0117] According to an embodiment of the present invention, there is also provided a computer-readable storage medium, on which program code is stored, and when the program code is executed by a processor, the motor current acquisition method as described in any one of the above embodiments is implemented.

[0118] Example 4

[0119] According to an embodiment of the present invention, there is also provided an electronic device, the electronic device includes a memory and a processor, and program code that can run on the processor is stored on the memory, and when the program code is executed by the processor, the motor current acquisition method as described in any one of the above embodiments is implemented.

[0120] The method, device, storage medium and electronic device for obtaining motor current provided by the embodiments of the present invention obtain the current torque, current speed, current theoretical estimated value of the motor and the current operating condition information of the train, and input the above current torque, current speed, current theoretical estimated value of the motor and current operating condition information into a pre-trained current prediction model, so that the current prediction model outputs the current prediction value of the motor under the above current operating condition, enabling the acquisition of the motor current value (i.e., the current prediction value of the above motor) to be carried out in real time based on the pre-trained current prediction model, and realizing the real-time prediction of the motor current. Moreover, the current prediction model takes the current operating condition information of the train as one of the input information, that is, the embodiments of the present invention fully consider the actual operating conditions of the train, making the prediction result more accurate. It can be seen that the technical solution provided by the embodiments of the present invention can obtain the motor current value in real time and accurately.

[0121] In addition, the embodiments of the present invention also provide a method for diagnosing abnormal traction system, which can realize the real-time diagnosis of whether the traction system is abnormal based on the actual current value of the motor and the current prediction value of the motor, thereby improving the reliability and operation safety of the traction system.

[0122] The present invention can realize the real-time prediction of motor current and the real-time and effective diagnosis of abnormal motor current, effectively improving the reliability and safety of the traction system. And it does not need to change the existing hardware, and the engineering implementation is simple.

[0123] In several embodiments provided by the present application, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0124] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present invention.

[0125] In addition, each functional unit in the embodiments of the present invention can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0126] When an integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing an electronic device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0127] Although the embodiments disclosed in the present invention are as described above, the content described is only an embodiment adopted for the convenience of understanding the present invention and is not intended to limit the present invention. Any person skilled in the art within the technical field to which the present invention pertains, without departing from the spirit and scope disclosed by the present invention, can make any modifications and changes in the form of implementation and details, but the protection scope of the present invention shall still be subject to the scope defined by the appended claims.

Claims

1. A method for obtaining motor current, characterized in that, The method is applied to a train traction system, and the train traction system includes the motor; the method includes: Obtain the current torque, current speed and theoretical estimated value of the current of the motor; Obtain the theoretical estimated value of the current of the motor by using the following expression: Among them, is the current theoretical estimated value of the motor; s is the slip ratio of the motor; k is a preset coefficient; T e is the torque of the motor; N p is the number of pole pairs of the motor; n is the rotational speed of the motor; ψ s is the given value of the stator flux linkage of the motor; ω sl is the slip angular frequency of the motor; R r is the rotor resistance of the motor; L m is the rotor mutual inductance of the motor; L r is the equivalent self-inductance of the rotor of the motor; Obtain the current operating condition information of the train; Input the current torque, the current speed, the theoretical estimated value of the current and the current operating condition information into a pre-trained current prediction model, so that the current prediction model outputs the current prediction value of the motor under the current operating condition.

2. The method for obtaining motor current according to claim 1, characterized in that, The method further includes: Obtain the actual value of the current of the motor; Based on the actual value of the current and the current prediction value, calculate the residual between the actual value of the current and the current prediction value; Based on the residual between the actual value of the current and the current prediction value, determine whether the train traction system is abnormal.

3. The method for obtaining motor current according to claim 2, characterized in that, The determining whether the train traction system is abnormal based on the residual between the actual value of the current and the current prediction value includes: Based on the residual between the actual value of the current and the current prediction value, use the CUSUM algorithm to determine whether the current of the motor is abnormal; When the current of the motor is abnormal, determine that the train traction system is abnormal.

4. The method for obtaining motor current according to claim 2, wherein The method further includes: When it is determined that the train traction system is abnormal, give an alarm.

5. The method for obtaining motor current according to claim 1, wherein, The train traction system further includes: an inverter and a driver's control handle; the obtaining the current operating condition information of the train includes: Obtain the operating state of the inverter; Obtain the position information of the driver's control handle; Based on the operating state of the inverter, the position information of the driver's control handle and the current speed of the motor, obtain the current operating condition information of the train.

6. The method for obtaining motor current according to claim 1, characterized in that, The current prediction model is an LSSVM prediction model.

7. A device for obtaining motor current, characterized in that, The device is applied to a train traction system, and the train traction system includes the motor; the device includes: A first obtaining unit, configured to obtain the current torque, current speed and theoretical estimated value of the current of the motor; Obtain the theoretical estimated value of the current of the motor by using the following expression: Among them, is the current theoretical estimated value of the motor; s is the slip ratio of the motor; k is a preset coefficient; T e is the torque of the motor; N p is the number of pole pairs of the motor; n is the rotational speed of the motor; ψ s is the stator flux reference value of the motor; ω sl is the slip angular frequency of the motor; R r is the rotor resistance of the motor; L m is the rotor mutual inductance of the motor; L r is the rotor equivalent self-inductance of the motor; A second obtaining unit, configured to obtain the current operating condition information of the train; An input unit, configured to input the current torque, the current speed, the theoretical estimated value of the current and the current operating condition information into a pre-trained current prediction model, so that the current prediction model outputs the current prediction value of the motor under the current operating condition.

8. A computer-readable storage medium having program code stored thereon, characterized in that, When the program code is executed by a processor, it implements the method for obtaining the motor current according to any one of claims 1 to 6.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, and a program code that can run on the processor is stored on the memory. When the program code is executed by the processor, it implements the method for obtaining the motor current according to any one of claims 1 to 6.

Images