Electric drive system carrier frequency adjustment method, device, equipment, medium and product

Abstract

The present application discloses a method, device, equipment, medium and product for adjusting the carrier frequency of an electric drive system, the method comprising: obtaining multiple carrier frequency values ​​and corresponding performance parameter values ​​of the electric drive system; constructing a system objective function of a gradient descent algorithm according to the multiple carrier frequency values ​​and corresponding performance parameter values; iteratively searching for the corresponding target carrier frequency value and system index result when the system objective function is minimized according to the gradient descent algorithm; applying the target carrier frequency value and system index result to the electric drive system, and monitoring the performance information of the electric drive system to obtain the monitoring result; when the monitoring result indicates that the system performance information does not meet the preset standard, optimizing the target carrier frequency value until the system performance information meets the preset standard. The scheme can dynamically adjust the carrier frequency to adapt to different driving conditions and load requirements, and improves the adaptability of the system in different working conditions.

Description

Technical Field

[0001] The present application relates to the field of electric drive system control technology, and in particular to a method, device, equipment, medium and product for adjusting the carrier frequency of an electric drive system. Background Art

[0002] With the continuous development of automobile technology, electric drive systems, as the driving force source of vehicles, have been increasingly applied to vehicles. They can convert the electric energy provided by the battery into the driving force of the vehicle, drive the vehicle forward and recover braking energy. Among them, the carrier frequency of the electric drive system, as one of the key parameters for electric vehicle control, affects the frequency and performance of the electric drive system. In order to effectively improve the control accuracy and operating efficiency of the electric drive system and reduce noise and electromagnetic interference, it is particularly important to select a suitable carrier frequency range for the electric drive system.

[0003] At present, the relevant technology usually implements the setting of carrier frequency based on a fixed formula or a preset parameter table. However, this solution is relatively fixed and one-sided, and does not take into account the impact of real-time working conditions on system performance. When dealing with high-load conditions such as high-speed driving or climbing, the use of a fixed carrier frequency can easily lead to a decrease in the efficiency of the electric drive system, thereby increasing electromagnetic interference and making it less adaptable to variable working conditions. Summary of the invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, it is desired to provide a method, device, equipment, medium and product for adjusting the carrier frequency of an electric drive system, which can dynamically adjust the carrier frequency to adapt to different driving conditions and load requirements, thereby improving the adaptability of the system under different working conditions.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present invention provides a method for adjusting the carrier frequency of an electric drive system, the method comprising:

[0007] Acquire multiple carrier frequency values ​​and corresponding performance parameter values ​​of the electric drive system;

[0008] Constructing a system objective function of a gradient descent algorithm according to the multiple carrier frequency values ​​and corresponding performance parameter values; the system objective function is used to characterize the degree of influence of carrier frequency changes on the performance of the electric drive system;

[0009] According to the gradient descent algorithm, iteratively search for the target carrier frequency value and system index result corresponding to the minimization of the system objective function;

[0010] Applying the target carrier frequency value and the system indicator result to the electric drive system, and monitoring the performance information of the electric drive system to obtain a monitoring result;

[0011] When the monitoring result indicates that the system performance information does not meet the preset standard, the target carrier frequency value is optimized until the system performance information meets the preset standard.

[0012] In one embodiment, constructing a system objective function of a gradient descent algorithm according to the multiple carrier frequency values ​​and performance parameter values ​​includes:

[0013] Obtain the initial carrier frequency change rate and the initial objective function gain value;

[0014] Determining an initial objective function based on the initial carrier frequency change rate, the initial objective function gain value, the multiple carrier frequency values ​​and a preset linear function;

[0015] Get the preset iteration step size and preset learning rate of the gradient descent algorithm;

[0016] Based on the preset iteration step size, the preset learning rate, the initial objective function and the performance parameter value, a system objective function of the gradient descent algorithm is constructed.

[0017] In one embodiment, based on the preset iteration step size, the preset learning rate, the initial objective function and the performance parameter value, constructing a system objective function of the gradient descent algorithm includes:

[0018] Based on the initial objective function, a carrier function numerical matrix is ​​constructed, and partial derivatives of the initial objective function and the initial change rate of the carrier frequency are calculated to determine a gradient value;

[0019] Constructing a parameter update numerical matrix based on the carrier function numerical matrix, the preset iteration step size, the preset learning rate and the gradient numerical value;

[0020] Determining a system parameter threshold value according to the performance parameter value;

[0021] A gradient vector of the parameter update numerical matrix is ​​determined, and the system objective function is constructed based on the gradient vector and the system threshold.

[0022] In one of the embodiments, the target carrier frequency value includes a first carrier frequency value and a second carrier frequency value, and the system indicator result includes a first system indicator result and a second system indicator result;

[0023] Iteratively searching for the target carrier frequency value and the system index result corresponding to the minimization of the system objective function according to the gradient descent algorithm, including:

[0024] When the system indicator result includes multiple element types, the gradient descent algorithm is used to iteratively search for the first carrier frequency value and the first system indicator result when the system indicator result of each element type is optimal according to the minimization of the system objective function;

[0025] When the system indicator result includes multiple element types, the gradient descent algorithm is used to iteratively search for the second carrier frequency value and the corresponding second system indicator result when the system indicator results of all element types are optimal according to the minimization of the system objective function.

[0026] In one embodiment, optimizing the target carrier frequency value until the system performance information meets a preset standard includes:

[0027] Determining a system indicator threshold from the monitoring results, and constructing an updated system objective function according to the system indicator threshold;

[0028] According to the gradient descent algorithm, iteratively search for the updated carrier frequency value and the corresponding updated system index result when the updated system objective function is minimized.

[0029] In one embodiment, obtaining multiple carrier frequency values ​​and corresponding performance parameter values ​​of the electric drive system includes:

[0030] According to preset standard operating conditions, a plurality of carrier frequency values ​​of the electric drive system are obtained;

[0031] For each carrier frequency value among the multiple carrier frequency values, the performance parameter of the electric drive system is monitored to obtain the performance parameter value corresponding to each carrier frequency value.

[0032] In a second aspect, an embodiment of the present application provides a carrier frequency adjustment device for an electric drive system, the device comprising:

[0033] An acquisition module, used to acquire multiple carrier frequency values ​​and corresponding performance parameter values ​​of the electric drive system;

[0034] A function construction module, used to construct a system objective function of a gradient descent algorithm according to the multiple carrier frequency values ​​and corresponding performance parameter values; the system objective function is used to characterize the degree of influence of carrier frequency changes on the performance of the electric drive system;

[0035] An iterative search module, used to iteratively search for a target carrier frequency value and a system index result corresponding to when the system objective function is minimized according to the gradient descent algorithm;

[0036] an application module, configured to apply the target carrier frequency value and the system indicator result to the electric drive system, and monitor the performance information of the electric drive system to obtain a monitoring result;

[0037] The optimization module is used to optimize the target carrier frequency value until the system performance information meets the preset standard when the monitoring result indicates that the system performance information does not meet the preset standard.

[0038] In a third aspect, an embodiment of the present application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method provided in the above embodiment.

[0039] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method provided in the above embodiment is implemented.

[0040] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method provided in the above embodiment.

[0041] The embodiment of the present application provides a method for adjusting the carrier frequency of an electric drive system, the method comprising: obtaining multiple carrier frequency values ​​and corresponding performance parameter values ​​of the electric drive system, constructing a system objective function of a gradient descent algorithm according to the multiple carrier frequency values ​​and the corresponding performance parameter values, iteratively searching for a target carrier frequency value and a system index result corresponding to when the system objective function is minimized according to the gradient descent algorithm, then applying the target carrier frequency value and the system index result to the electric drive system, and monitoring the performance information of the electric drive system to obtain a monitoring result, and when the monitoring result indicates that the system performance information does not meet the preset standard, optimizing the target carrier frequency value until the system performance information meets the preset standard. Compared with the prior art, on the one hand, this technical solution can, based on multiple carrier frequency values ​​and performance parameter values ​​of the electric drive system, specifically construct a system objective function for characterizing the degree of influence of carrier frequency changes on the performance of the electric drive system, so that the system objective function can more realistically simulate the correlation between carrier frequency changes and the electric drive system; on the other hand, the target carrier frequency is iteratively searched according to the gradient descent algorithm, thereby realizing dynamic adaptive adjustment of the carrier frequency, and being able to accurately determine the target carrier frequency value, which not only effectively reduces electromagnetic interference and enhances the electromagnetic compatibility and system efficiency of the system, but also can adapt to different driving conditions and load requirements, thereby improving the adaptability of the system under different working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A schematic diagram of the structure of a carrier frequency adjustment system for an electric drive system provided in an embodiment of the present application;

[0044] Figure 2 A schematic diagram of a flow chart of a method for adjusting the carrier frequency of an electric drive system provided in an embodiment of the present application;

[0045] Figure 3 A schematic diagram of a process for constructing a system objective function of a gradient descent algorithm provided in an embodiment of the present application;

[0046] Figure 4 A schematic flow chart of a method for adjusting the carrier frequency of an electric drive system provided in another embodiment of the present application;

[0047] Figure 5 A schematic diagram of the structure of a carrier frequency adjustment device for an electric drive system provided in an embodiment of the present application;

[0048] Figure 6 A schematic diagram of the structure of a processing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0051] It is understood that the carrier frequency of the electric drive system refers to the frequency used when the AC power supply is used to control the three-phase motor in the electric drive system of the electric vehicle, and the power supply frequency is modulated into a high-frequency signal (i.e., the carrier signal) to control the motor's speed, direction, torque and other parameters. The carrier frequency of the electric drive system can not only improve the dynamic response performance of the motor control, but also effectively reduce the motor noise and electromagnetic interference.

[0052] At present, the relevant technology usually implements the setting of carrier frequency based on a fixed formula or a preset parameter table. However, this solution is relatively fixed and one-sided, and does not take into account the impact of real-time working conditions on system performance. When dealing with high-load conditions such as high-speed driving or climbing, the use of a fixed carrier frequency can easily lead to a decrease in the efficiency of the electric drive system, thereby increasing electromagnetic interference and making it less adaptable to variable working conditions.

[0053] Based on the above-mentioned defects, the present application provides a method, device, equipment, medium and product for adjusting the carrier frequency of an electric drive system. Compared with the prior art, on the one hand, the technical solution can, based on multiple carrier frequency values ​​and performance parameter values ​​of the electric drive system, specifically construct a system objective function for characterizing the degree of influence of carrier frequency changes on the performance of the electric drive system, so that the system objective function can more realistically simulate the correlation between the carrier frequency change and the electric drive system; on the other hand, the target carrier frequency is iteratively searched according to the gradient descent algorithm, thereby realizing dynamic adaptive adjustment of the carrier frequency, and being able to accurately determine the target carrier frequency value, which not only effectively reduces electromagnetic interference and enhances the electromagnetic compatibility and system efficiency of the system, but also can adapt to different driving conditions and load requirements, thereby improving the adaptability of the system under different working conditions.

[0054] See also Figure 1 As shown, Figure 1 Schematic diagram of the structure of the carrier frequency adjustment system of the electric drive system. The system can be located in the vehicle or outside the vehicle. The system may include: an electric drive system 10 and a processing device 20, and the electric drive system 10 may establish a communication connection with the processing device 20. Optionally, the processing device 20 may include a display unit, a processing unit, a storage unit, etc., and the processing unit establishes a communication connection with the display unit and the storage unit respectively.

[0055] It should be noted that the processing unit may be provided with a microprocessor (MCU), a memory (ROM, RAM), an input / output interface (I / O), an analog-to-digital converter (A / D), and large-scale integrated circuits such as shaping and driving, and has the function of processing data. The display unit may be, for example, a display screen, capable of displaying data, for example, displaying system indicator results. The storage unit is used to store data, for example, system data may be stored.

[0056] Optionally, the above system may further include: a sensor component 30 , which may establish a communication connection with the processing device 20 .

[0057] The sensor assembly 30 may include sensors with different functions, such as a voltage sensor for detecting the voltage of the electric drive system, a vibration detection sensor for detecting the vibration parameters of the electric drive system, a noise detection sensor for detecting the noise parameters of the electric drive system, a load antenna for obtaining the radiation field strength, etc.

[0058] The sensor assembly 30 is used to obtain the performance parameter value of the electric drive system 10 and send it to the processing device 20. The processing device 20 is used to obtain multiple carrier frequency values ​​of the electric drive system 10. Based on the multiple carrier frequency values ​​and performance parameter values, a gradient descent algorithm is used for iterative optimization to obtain the target carrier frequency value.

[0059] In order to better understand and illustrate the carrier frequency adjustment method of the electric drive system provided in the embodiment of the present application, Figures 2 to 6 Detailed explanation.

[0060] Figure 2 A flow chart of a method for adjusting the carrier frequency of an electric drive system provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the method is executed by a processing device, and the processing device can be implemented as part or all of the processing device by software, hardware, or a combination of software and hardware. The method includes:

[0061] S101. Acquire multiple carrier frequency values ​​and corresponding performance parameter values ​​of an electric drive system.

[0062] It should be noted that the multiple carrier frequency values ​​of the above-mentioned electric drive system refer to the initial carrier frequency values ​​defined when optimizing using the gradient descent algorithm, and the performance parameter value refers to the performance parameter information of the system in the electric drive system, which may include, for example, current parameters, voltage parameters, vibration parameters, noise parameters and radiation parameters of the electric drive system.

[0063] The multiple carrier frequency values ​​of the electric drive system may be determined by user experience, randomly acquired from a database, or imported from an external device. The embodiment of the present application does not impose any limitation on the acquisition method of the multiple carrier frequency values. The performance parameter values ​​may be acquired by different sensors in the sensor assembly.

[0064] Specifically, in the process of obtaining multiple carrier frequency values ​​and corresponding performance parameter values ​​of the electric drive system, it is possible to first obtain multiple carrier frequency values ​​of the electric drive system according to preset standard operating conditions, monitor the performance parameters of the electric drive system at each carrier frequency value of the multiple carrier frequency values, and obtain the performance parameter value corresponding to each carrier frequency value.

[0065] It is understandable that, for the processing device, different processing devices have different operation interfaces, and the operation steps performed when obtaining multiple carrier frequency values ​​are also different. Different processing devices correspond to different standard operating conditions. Multiple carrier frequency values ​​can be initially set at a preset frequency interval, and then according to the preset standard operating conditions of the electric drive system, the processing device obtains multiple carrier frequency values, for example, 8000MHZ, 8100MHZ, 8200MHZ, ..., 12000MHZ.

[0066] The electric drive system may be provided with a plurality of sensor components, which include a plurality of sensors with different functions. After obtaining a plurality of carrier frequency values, at each carrier frequency, the performance parameters of the electric drive system are monitored in real time through the sensor components provided in the electric drive system and sent to the data acquisition module, so that the performance parameter values ​​are collected through the data acquisition module, so that the processing device obtains the performance parameter values ​​corresponding to each carrier frequency value.

[0067] S102. Constructing a system objective function of a gradient descent algorithm according to a plurality of carrier frequency values ​​and corresponding performance parameter values; the system objective function is used to characterize the influence of carrier frequency changes on the performance of the electric drive system.

[0068] Specifically, after obtaining multiple carrier frequency values ​​and corresponding performance parameter values, the initial elements of the gradient descent algorithm can be initially set. The initial elements may include parameters such as iteration step size, learning rate, gradient value and system threshold. After setting the initial elements, the initial objective function can be constructed first, and then the initial objective function can be updated to construct the system objective function of the gradient descent algorithm.

[0069] In one embodiment, the present application embodiment provides a specific implementation method for constructing a system objective function of a gradient descent algorithm. Figure 3 As shown, the method includes:

[0070] S201. Obtain an initial carrier frequency change rate and an initial objective function gain value.

[0071] S202: Determine an initial objective function based on an initial carrier frequency change rate, an initial objective function gain value, a plurality of carrier frequency values ​​and a preset linear function.

[0072] S203: Obtain a preset iteration step size and a preset learning rate of the gradient descent algorithm.

[0073] S204: Construct a system objective function of the gradient descent algorithm based on a preset iteration step size, a preset learning rate, an initial objective function and a performance parameter value.

[0074] Specifically, the above-mentioned carrier frequency initial change rate and initial objective function gain value can be customized based on actual experience, or the initial change rate and initial objective function gain value can be set according to multiple carrier frequency values ​​obtained. For example, when the frequency interval between each two adjacent carrier frequency values ​​in the multiple carrier frequency values ​​is 100, the set carrier frequency initial change rate can be 100, and the initial objective function gain value can be set to 8000.

[0075] After obtaining multiple carrier frequency values, a preset linearization function of the multiple carrier frequency values ​​can be established through a formula. The formula of the linearization function is as follows:

[0076] ;

[0077] in, is the initial objective function of the carrier frequency, f 1 is the first carrier frequency value obtained, f i is the carrier frequency value obtained for the ith time, i>1, The initialization change rate set for the carrier frequency, a is the initial objective function gain value of the carrier frequency.

[0078] After setting the initial change rate of the carrier frequency setting and the initial objective function gain value, multiple carrier frequency values, the initial change rate of the carrier frequency setting, and the initial objective function gain value can be substituted into the above preset linear function formula to obtain The value of is, for example, 40, and then the initial objective function is obtained, which can be expressed by the following formula:

[0079] ;

[0080] in, is the initial rate of change set for the carrier frequency, is the initial objective function of the carrier frequency.

[0081] It is understandable that the basic idea of ​​gradient descent is to iterate along the negative gradient direction of the objective function to find the local minimum of the function. Specifically, for a multidimensional function, gradient descent calculates the gradient (i.e., partial derivative) of the objective function at the current parameter position, and then updates the parameters in the opposite direction of the gradient, so that the function value continues to decrease. This process is repeated until a certain stopping condition is reached, such as reaching a specified number of iterations or the change in the objective function is less than a certain threshold.

[0082] The preset iteration step size and learning rate of the gradient descent algorithm can be obtained based on actual experience. They can be customized according to the size of the iteration change and the convergence state. Among them, the iteration step size represents the size of each iteration change of the independent variable. The learning rate affects the convergence speed of the model during the training process and the final convergence state, and determines the step size of each parameter update. A larger learning rate can speed up the convergence speed, and it may also cause the algorithm to cross the minimum value; on the contrary, a smaller learning rate may lead to a slower convergence speed, but it helps to find a more accurate minimum value.

[0083] In the process of constructing the system objective function of the gradient descent algorithm based on the preset iteration step, the preset learning rate, the initial objective function and the performance parameter value, the carrier function numerical matrix can be determined based on the initial objective function, the partial derivative of the initial objective function and the initial change rate of the carrier frequency can be calculated, and the gradient value can be determined. Then, based on the carrier function numerical matrix, the preset iteration step, the preset learning rate and the gradient value, the parameter update numerical matrix can be constructed, based on the performance parameter value, the system parameter threshold can be determined, the gradient vector of the parameter update numerical matrix can be determined, and based on the gradient vector and the system threshold, the parameter update numerical matrix can be constructed. The obtained parameter update numerical matrix can be expressed by the following formula:

[0084] ;

[0085] in, Update the numerical matrix for the carrier frequency parameters, is the carrier function numerical matrix corresponding to the initial target function of the carrier frequency. The number of elements in the matrix can be determined by the iteration step size. α is the learning rate, and the gradient value is and The partial derivative of is the initial rate of change set for the carrier frequency, is the initial objective function of the carrier frequency.

[0086] After constructing the parameter update value matrix, the system parameter threshold can be determined. The system parameter threshold is the reference value corresponding to the iterative optimization process.

[0087] As an implementable manner, the system parameter threshold may be determined by performance parameter values ​​corresponding to multiple carrier frequency values, for example, by using a preset algorithm to determine the performance parameter value, and the preset algorithm may be obtained by averaging multiple performance parameter values; as another implementable manner, the system parameter threshold may be custom set based on historical experience, and the historical experience may be manually determined based on historical data.

[0088] The above-mentioned system parameter thresholds correspond one-to-one to the element types of the performance parameter values. For example, when the performance parameter values ​​include first element values ​​corresponding to four types of elements, and the first element values ​​are voltage parameters, vibration parameters, noise parameters and radiation parameters respectively, then the system parameter thresholds also include second element values ​​corresponding to the four types of elements, and the second element values ​​are voltage parameters, vibration parameters, noise parameters and radiation parameters respectively, wherein the first element value and the second element value corresponding to each element type are different.

[0089] Further, after determining the system parameter thresholds, which are, for example, the voltage spectrum threshold, the vibration spectrum threshold, and the electromagnetic interference spectrum threshold of the electric drive system, the gradient vector of the parameter update numerical matrix can be determined first, and the system objective function can be constructed based on the gradient vector and the system threshold. The system objective function is used to quantify the impact of carrier frequency changes on the performance of the electric drive system, which can be used as the overall system update formula for the gradient descent algorithm and can be expressed by the following formula:

[0090]

[0091] in, θ update is the system update parameter vector, is the voltage spectrum threshold, v system is the vibration spectrum threshold, E system is the electromagnetic interference spectrum threshold, the optimized matrix is ​​the optimal solution after the system objective function is optimized, and the set matrix is ​​the initial setting value before the system objective function is optimized. The elements in this matrix include the system threshold, ∇ f ( · ) is the gradient vector of the parameter update matrix.

[0092] S103. According to the gradient descent algorithm, iteratively search for the target carrier frequency value and system index result corresponding to the minimization of the system objective function.

[0093] It should be noted that the above-mentioned target carrier frequency value refers to the target function determined after optimizing the system target function. The target carrier frequency value includes a first carrier frequency value and a second carrier frequency value. The first carrier frequency value refers to the carrier frequency value corresponding to the optimal system indicator result of a single element type, and the second carrier frequency value refers to the carrier frequency value corresponding to the optimal system indicator result of all element types.

[0094] The above-mentioned system indicator results include a first system indicator result and a second system indicator result. The first system indicator result may include multiple results, and each first system indicator result may be the minimum performance parameter value determined from all performance parameter values. For example, when the performance parameter value is a voltage parameter, the first system indicator result is the minimum value of all voltage parameters. When the performance parameter value is a vibration parameter, the first system indicator result is the minimum value of all vibration parameters. The second system indicator result may include all element types in the performance parameter value. When the performance parameter value includes a current parameter, a voltage parameter, a vibration parameter, a noise parameter, and a radiation parameter, the second system indicator result also includes a current parameter, a voltage parameter, a vibration parameter, a noise parameter, and a radiation parameter.

[0095] After constructing the system objective function, the gradient descent algorithm can be used to update the carrier frequency value, and iteratively adjust and optimize in the direction of the minimum value of the system objective function to find the minimum value of the objective function.

[0096] In one of the embodiments, a flowchart of a method for iteratively searching for the target carrier frequency value and system index result corresponding to the minimization of the system objective function according to the gradient descent algorithm is also provided. Figure 4 As shown, the method includes:

[0097] S301. When the system indicator result includes multiple element types, a gradient descent algorithm is used to iteratively search for the first carrier frequency value and the corresponding first system indicator result when the system indicator result of each element type is optimal according to the minimization of the system objective function.

[0098] As an implementable method, when the system indicator result includes multiple element types, a gradient descent algorithm is used to input multiple carrier frequency values ​​and corresponding performance parameter values ​​into the system objective function. In the direction of minimizing the system objective function, the first carrier frequency value and the corresponding first system indicator result when the system indicator result of each element type is optimal are iteratively searched. When the function value of the objective function changes very little or the maximum number of iterations is reached, the loop is ended to determine the first carrier frequency value and the corresponding first system indicator result.

[0099] S302. When the system indicator result includes multiple element types, a gradient descent algorithm is used to iteratively search for the second carrier frequency value and the corresponding second system indicator result when the system indicator results of all element types are optimal according to the system objective function minimization.

[0100] As another feasible method, when the system index result includes multiple element types, a gradient descent algorithm is used to input multiple carrier frequency values ​​and corresponding performance parameter values ​​into the system objective function, and in the direction of minimizing the system objective function, the second carrier frequency value and the corresponding second system index result when the system index results of all element types are optimal are iteratively searched. When the function value of the objective function changes very little or the maximum number of iterations is reached, the loop is ended to determine the second carrier frequency value and the corresponding second system index result.

[0101] In this step, by iteratively checking the target carrier frequency value and system index results corresponding to the minimization of the system objective function according to the gradient descent algorithm, dynamic adaptive adjustment of the carrier frequency can be achieved, thereby improving the responsiveness of the electric drive system under different working conditions. While optimizing the overall performance, it also increases the electromagnetic compatibility and system efficiency of the system.

[0102] S104: Apply the target carrier frequency value and the system indicator result to the electric drive system, monitor the performance information of the electric drive system, and obtain a monitoring result.

[0103] Specifically, after determining the target carrier frequency value and the system index result, the target carrier frequency value and the system index result can be applied to the electric drive system, and the performance parameters of the electric drive system can be monitored by the sensor component to obtain a monitoring result, which is used to characterize whether the system performance information of the electric drive system meets the preset standard. The preset standard is custom set based on actual experience.

[0104] Exemplarily, in the process of determining whether the system performance information meets the preset standard, the processing device may compare the system performance information of the electric drive system with the preset standard. When the comparison is consistent, it indicates that the system performance information of the electric drive system meets the preset standard; when the comparison is inconsistent, it indicates that the system performance information of the electric drive system does not meet the preset standard.

[0105] S105. When the monitoring result indicates that the system performance information does not meet the preset standard, the target carrier frequency value is optimized until the system performance information meets the preset standard.

[0106] When the monitoring results indicate that the system performance information does not meet the preset standard, the target carrier frequency value is optimized, which can be to determine the system index threshold from the monitoring results, construct an updated system objective function according to the system index threshold, and then iteratively search for the corresponding updated carrier frequency value and the corresponding updated system index result when the updated system objective function is minimized according to the gradient descent algorithm. The preset standard can be a predetermined performance target value or an optimization threshold.

[0107] It can be understood that different electric drive systems have different carrier frequency values ​​and different carrier frequency values ​​correspond to performance parameter values. Therefore, the processing device can obtain multiple carrier frequency values ​​and corresponding performance parameter values ​​of different electric drive systems, and then construct an updated system objective function based on the multiple carrier frequency values ​​and the corresponding performance parameter values. According to the gradient descent algorithm, iteratively search for the corresponding updated target carrier frequency value and the updated system indicator result when the updated system objective function is minimized.

[0108] In this step, the system objective function can be continuously updated, the carrier frequency adjustment optimization is achieved, the noise and vibration in the operation of electric vehicles are reduced, and the driving experience is improved. At the same time, the system's adaptability to various driving conditions is adaptively adjusted, thereby enhancing the reliability and durability of the electric drive system.

[0109] An embodiment of the present application provides a method for adjusting the carrier frequency of an electric drive system, the method comprising: obtaining multiple carrier frequency values ​​and corresponding performance parameter values ​​of the electric drive system, constructing a system objective function of a gradient descent algorithm according to the multiple carrier frequency values ​​and the corresponding performance parameter values, iteratively searching for a target carrier frequency value and a system index result corresponding to when the system objective function is minimized according to the gradient descent algorithm, then applying the target carrier frequency value and the system index result to the electric drive system, and monitoring the performance information of the electric drive system to obtain a monitoring result. However, when the monitoring result indicates that the system performance information does not meet a preset standard, the target carrier frequency value is optimized until the system performance information meets the preset standard. Compared with the prior art, on the one hand, this technical solution can, based on multiple carrier frequency values ​​and performance parameter values ​​of the electric drive system, specifically construct a system objective function for characterizing the degree of influence of carrier frequency changes on the performance of the electric drive system, so that the system objective function can more realistically simulate the correlation between carrier frequency changes and the electric drive system; on the other hand, the target carrier frequency is iteratively searched according to the gradient descent algorithm, thereby realizing dynamic adaptive adjustment of the carrier frequency, and being able to accurately determine the target carrier frequency value, which not only effectively reduces electromagnetic interference and enhances the electromagnetic compatibility and system efficiency of the system, but also can adapt to different driving conditions and load requirements, thereby improving the adaptability of the system under different working conditions.

[0110] Exemplarily, multiple carrier frequency values ​​of the electric drive system are initially set according to historical experience, and uploaded to the processing device according to preset standard operating conditions, so that the processing device obtains multiple carrier frequency values, for example, including 41 carrier frequency values, namely 8000MHZ, 8100MHZ, 8200MHZ, ..., 12000MHZ. And at each carrier frequency, the performance parameters of the electric drive system are monitored in real time through the sensor components set in the electric drive system and sent to the data acquisition module, so that the performance parameter values ​​are collected through the data acquisition module, so that the processing device obtains the performance parameter values ​​corresponding to each carrier frequency value, and the performance parameter values ​​include voltage value, vibration acceleration, A-weighted sound pressure level, radiation field strength, etc.

[0111] After obtaining multiple carrier frequency values ​​and performance parameter values, the system objective function of the gradient descent algorithm is constructed. Specifically, the initial elements of the gradient descent algorithm are set first. The initial elements include iteration step size, learning rate, gradient value, system threshold, etc., and then the initial objective function is constructed. The preset linearization function of multiple carrier frequency values ​​can be established first. The linearization function is as follows:

[0112] ;

[0113] in, is the initial objective function of the carrier frequency, f 1 is the first carrier frequency value obtained, f i is the carrier frequency value obtained for the ith time, i>1, The rate of change set for the carrier frequency initialization, a is the initial objective function gain value of the carrier frequency.

[0114] The performance parameter values ​​within the above carrier frequency band can be found in the following table:

[0115]

[0116] Furthermore, the initial change rate of the carrier frequency setting is set to 100, and the initial objective function gain value is set to 8000. The multiple carrier frequency values, the initial change rate, and the initial objective function gain value are substituted into the above preset linear function to obtain the following formula:

[0117] ;

[0118] in, is the initial objective function of the carrier frequency, Initializes the rate of change set for the carrier frequency.

[0119] The iteration step size is set to 10, the learning rate is set to 0.01, and the gradient value is set to and The partial derivative of is 40, and then the system carrier frequency parameter update numerical matrix is ​​determined. The number of elements of the matrix is ​​determined by the iteration step size. The update formula is obtained based on the initial objective function of the carrier frequency, the gradient value and the learning rate. The update formula is as follows:

[0120]

[0121] in, Update the numerical matrix for the system carrier frequency parameters, The rate of change set for the carrier frequency initialization, is the numerical matrix of the carrier function corresponding to the initial objective function.

[0122] After constructing the parameter update numerical matrix, the system parameter thresholds can be determined. The system thresholds include the voltage value, vibration acceleration value, A-weighted sound pressure level, and radiation field strength value of the electric drive system. The system parameter thresholds can be shown in the following table:

[0123]

[0124] After the system threshold is determined, the system objective function can be determined according to the system threshold and the update formula. The system objective function can be shown as follows:

[0125]

[0126]

[0127] in, θ update is the system update parameter vector, U system is the voltage spectrum threshold, v system is the vibration spectrum threshold, E system is the electromagnetic interference spectrum threshold, the optimized matrix is ​​the optimal solution after the system objective function is optimized, and the set matrix is ​​the initial setting value before the system objective function is optimized. The elements in this matrix include the system threshold, ∇ f ( · ) is the gradient vector of the parameter update matrix.

[0128] After determining the system objective function, the gradient information of the system objective function with respect to the carrier frequency value is calculated. According to the gradient descent algorithm, the first carrier frequency value and the corresponding first system indicator result when the system indicator result of each element type is optimal are iteratively searched, including four optimization results, which are the minimum values ​​within the carrier frequency; at the same time, in all iterative learning processes, the second carrier frequency value and the corresponding second system indicator result are determined. The first system indicator result and the second system indicator result can be shown in the following table:

[0129]

[0130] Furthermore, after determining the target carrier frequency value and the system index result, the target carrier frequency value and the system index result can be applied to the electric drive system, and the performance parameters of the electric drive system can be monitored through the sensor component to verify whether the electric drive system matches the iterative learning results at different carrier frequencies, so that the system can ensure optimal performance.

[0131] Optionally, different electric drive systems have different carrier frequency values ​​and performance parameter values, and then according to multiple carrier frequency values ​​and corresponding performance parameter values, a new system objective function is constructed, and according to the gradient descent algorithm, a new target carrier frequency value and a new system indicator result corresponding to the minimization of the new system objective function are iteratively searched. In the updating process, the performance parameter value can be obtained according to a preset period to update the corresponding system objective function, so as to adapt to the long-term changes in the corresponding performance requirements of different electric drive systems.

[0132] The electric drive system carrier frequency adjustment method based on the gradient descent algorithm in the embodiment of the present application can realize adaptive adjustment of the carrier frequency in the electric drive system, reduce electromagnetic interference, and reduce system losses. Compared with the traditional inherent carrier frequency setting method, it can dynamically adjust the carrier frequency to adapt to different driving conditions and load requirements, thereby improving the system's adaptability to variable working conditions.

[0133] On the other hand, the present application embodiment provides a carrier frequency adjustment device for an electric drive system, see Figure 5 As shown, Figure 5 A schematic diagram of the structure of a carrier frequency adjustment device for an electric drive system provided in an embodiment of the present application, the device comprising:

[0134] An acquisition module 310 is used to acquire multiple carrier frequency values ​​and corresponding performance parameter values ​​of the electric drive system;

[0135] A function construction module 320 is used to construct a system objective function of a gradient descent algorithm according to a plurality of carrier frequency values ​​and corresponding performance parameter values; the system objective function is used to characterize the degree of influence of carrier frequency changes on the performance of the electric drive system;

[0136] An iterative search module 330 is used to iteratively search for a target carrier frequency value and a system index result corresponding to minimization of a system objective function according to a gradient descent algorithm;

[0137] An application module 340 is used to apply the target carrier frequency value and the system indicator result to the electric drive system, and monitor the performance information of the electric drive system to obtain a monitoring result;

[0138] The optimization module 350 is used to optimize the target carrier frequency value until the system performance information meets the preset standard when the monitoring result indicates that the system performance information does not meet the preset standard.

[0139] In one embodiment, the function building module 320 is specifically used to:

[0140] Obtain the initial carrier frequency change rate and the initial objective function gain value;

[0141] Determining an initial objective function based on an initial carrier frequency change rate, an initial objective function gain value, a plurality of carrier frequency values ​​and a preset linear function;

[0142] Get the preset iteration step size and preset learning rate of the gradient descent algorithm;

[0143] Based on the preset iteration step size, preset learning rate, initial objective function and performance parameter value, the system objective function of the gradient descent algorithm is constructed.

[0144] In one embodiment, the function building module 320 is further used to:

[0145] Based on the initial objective function, a carrier function numerical matrix is ​​constructed, and partial derivatives of the initial objective function and the initial change rate of the carrier frequency are calculated to determine the gradient value;

[0146] Constructing a parameter update numerical matrix based on a carrier function numerical matrix, a preset iteration step size, a preset learning rate and a gradient numerical value;

[0147] Determine the system parameter threshold value according to the performance parameter value;

[0148] Determine the gradient vector of the parameter update numerical matrix, and construct the system objective function based on the gradient vector and the system threshold.

[0149] In one embodiment, the iterative search module 330 is specifically used to:

[0150] When the system index result includes multiple element types, a gradient descent algorithm is used to iteratively search for the first carrier frequency value and the first system index result when the system index result of each element type is optimal according to the minimization of the system objective function;

[0151] When the system indicator result includes multiple element types, a gradient descent algorithm is used to iteratively search for the second carrier frequency value and the corresponding second system indicator result when the system indicator results of all element types are optimal according to the system objective function minimization.

[0152] In one embodiment, the optimization module 350 is specifically used to:

[0153] Determine the system indicator threshold from the monitoring results, and construct an updated system objective function based on the system indicator threshold;

[0154] According to the gradient descent algorithm, the updated carrier frequency value and the corresponding updated system index result are iteratively searched when the updated system objective function is minimized.

[0155] In one embodiment, the acquisition module 310 is specifically used to:

[0156] According to preset standard operating conditions, a plurality of carrier frequency values ​​of the electric drive system are obtained;

[0157] For each carrier frequency value among the multiple carrier frequency values, the performance parameter of the electric drive system is monitored to obtain the performance parameter value corresponding to each carrier frequency value.

[0158] Compared with the prior art, the electric drive system carrier frequency regulation device provided in the embodiment of the present application can, on the one hand, construct a system objective function for characterizing the degree of influence of carrier frequency changes on the performance of the electric drive system in a targeted manner based on multiple carrier frequency values ​​and performance parameter values ​​of the electric drive system, so that the system objective function can more realistically simulate the correlation between the carrier frequency change and the electric drive system; on the other hand, it iteratively searches for the target carrier frequency according to the gradient descent algorithm, thereby realizing dynamic adaptive adjustment of the carrier frequency and being able to accurately determine the target carrier frequency value, which not only effectively reduces electromagnetic interference and enhances the electromagnetic compatibility and system efficiency of the system, but also can adapt to different driving conditions and load requirements, thereby improving the adaptability of the system under different working conditions.

[0159] Figure 6 FIG. 2 is a schematic diagram of a processing device 20 provided in an embodiment of the present invention. Figure 6 As shown, it shows a structural schematic diagram of a processing device 20 suitable for implementing an embodiment of the present application.

[0160] like Figure 6As shown, the processing device 20 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage part 408 to a random access memory (RAM) 403. Various programs and data required for system operation are also stored in the RAM 403. The CPU 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 406 is also connected to the bus 404.

[0161] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 406 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed, so that a computer program read therefrom is installed into the storage section 408 as needed.

[0162] In particular, according to the embodiments of the present disclosure, the above reference Figure 3 The described processes may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising a computer program for executing Figure 3 In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 409 and / or installed from the removable medium 411.

[0163] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of the code, and the aforementioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0164] The units or modules involved in the embodiments described in this application may be implemented by software or hardware, and the units or modules described may also be set in a processor.

[0165] As another aspect, the present application also provides a computer-readable medium, which may be included in the processing device described in the above embodiment; or may exist independently without being assembled into the processing device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a processing device, the processing device implements the electric drive system carrier frequency adjustment method as in the above embodiment.

[0166] As another aspect, the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the carrier frequency adjustment method of the electric drive system provided in the above embodiment.

[0167] For example, the processing device may implement Figure 2As shown in: Step S101, obtaining multiple carrier frequency values ​​and corresponding performance parameter values ​​of the electric drive system; Step S102, constructing a system objective function of the gradient descent algorithm based on multiple carrier frequency values ​​and corresponding performance parameter values; the system objective function is used to characterize the degree of influence of carrier frequency changes on the performance of the electric drive system; Step S103, iteratively searching for the target carrier frequency value and system index result corresponding to the minimization of the system objective function according to the gradient descent algorithm; Step S104, applying the target carrier frequency value and system index result to the electric drive system, and monitoring the performance information of the electric drive system to obtain monitoring results; Step S105, when the monitoring result indicates that the system performance information does not meet the preset standard, optimizing the target carrier frequency value until the system performance information meets the preset standard. For another example, the processing device can be implemented as follows Figure 3 The steps shown in .

[0168] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0169] In addition, although the steps of the method in the present disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc. Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware.

[0170] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the present application.

Claims

1. A method for adjusting the carrier frequency of an electric drive system, It is characterized in that The carrier frequency adjustment method of the electric drive system includes: Acquire multiple carrier frequency values ​​and corresponding performance parameter values ​​of the electric drive system; According to the multiple carrier frequency values ​​and the corresponding performance parameter values, a system objective function of a gradient descent algorithm is constructed; the system objective function is used to characterize the influence of the carrier frequency change on the performance of the electric drive system; According to the gradient descent algorithm, iteratively search for the target carrier frequency value and system index result corresponding to the minimization of the system objective function; Applying the target carrier frequency value and the system indicator result to the electric drive system, and monitoring the performance information of the electric drive system to obtain a monitoring result; When the monitoring result indicates that the system performance information does not meet the preset standard, optimizing the target carrier frequency value until the system performance information meets the preset standard; Wherein, according to the multiple carrier frequency values ​​and performance parameter values, a system objective function of the gradient descent algorithm is constructed, including: Obtain the initial carrier frequency change rate and the initial objective function gain value; Determining an initial objective function based on the initial carrier frequency change rate, the initial objective function gain value, the multiple carrier frequency values ​​and a preset linear function; Get the preset iteration step size and preset learning rate of the gradient descent algorithm; Based on the preset iteration step size, the preset learning rate, the initial objective function and the performance parameter value, a system objective function of the gradient descent algorithm is constructed.

2. The method for adjusting the carrier frequency of the electric drive system according to claim 1, It is characterized in that Based on the preset iteration step size, the preset learning rate, the initial objective function and the performance parameter value, a system objective function of the gradient descent algorithm is constructed, including: Based on the initial objective function, a carrier function numerical matrix is ​​constructed, and partial derivatives of the initial objective function and the initial change rate of the carrier frequency are calculated to determine a gradient value; Constructing a parameter update numerical matrix based on the carrier function numerical matrix, the preset iteration step size, the preset learning rate and the gradient numerical value; Determining a system parameter threshold value according to the performance parameter value; A gradient vector of the parameter update numerical matrix is ​​determined, and the system objective function is constructed based on the gradient vector and the system threshold.

3. The method for adjusting the carrier frequency of the electric drive system according to claim 1, It is characterized in that The target carrier frequency value includes a first carrier frequency value and a second carrier frequency value, and the system indicator result includes a first system indicator result and a second system indicator result; Iteratively searching for the target carrier frequency value and the system index result corresponding to the minimization of the system objective function according to the gradient descent algorithm, including: When the system indicator result includes multiple element types, the gradient descent algorithm is used to iteratively search for the first carrier frequency value and the first system indicator result when the system indicator result of each element type is optimal according to the minimization of the system objective function; When the system indicator result includes multiple element types, the gradient descent algorithm is used to iteratively search for the second carrier frequency value and the corresponding second system indicator result when the system indicator results of all element types are optimal according to the minimization of the system objective function.

4. The method for adjusting the carrier frequency of an electric drive system according to claim 1, It is characterized in that Optimizing the target carrier frequency value until the system performance information meets a preset standard includes: Determining a system indicator threshold from the monitoring results, and constructing an updated system objective function according to the system indicator threshold; According to the gradient descent algorithm, iteratively search for the updated carrier frequency value and the corresponding updated system index result when the updated system objective function is minimized.

5. The method for adjusting the carrier frequency of an electric drive system according to claim 1, It is characterized in that Obtain multiple carrier frequency values ​​and corresponding performance parameter values ​​of the electric drive system, including: According to preset standard operating conditions, a plurality of carrier frequency values ​​of the electric drive system are obtained; For each carrier frequency value among the multiple carrier frequency values, the performance parameter of the electric drive system is monitored to obtain the performance parameter value corresponding to each carrier frequency value.

6. A carrier frequency adjustment device for an electric drive system, It is characterized in that The electric drive system carrier frequency adjustment device comprises: An acquisition module, used to acquire multiple carrier frequency values ​​and corresponding performance parameter values ​​of the electric drive system; A function construction module, used to construct a system objective function of a gradient descent algorithm according to the multiple carrier frequency values ​​and corresponding performance parameter values; the system objective function is used to characterize the degree of influence of carrier frequency changes on the performance of the electric drive system; An iterative search module, used to iteratively search for a target carrier frequency value and a system index result corresponding to when the system objective function is minimized according to the gradient descent algorithm; an application module, configured to apply the target carrier frequency value and the system indicator result to the electric drive system, and monitor the performance information of the electric drive system to obtain a monitoring result; An optimization module, configured to optimize the target carrier frequency value until the system performance information meets the preset standard when the monitoring result indicates that the system performance information does not meet the preset standard; Wherein, the function building module is specifically used for: Obtain the initial carrier frequency change rate and the initial objective function gain value; Determining an initial objective function based on the initial carrier frequency change rate, the initial objective function gain value, the multiple carrier frequency values ​​and a preset linear function; Get the preset iteration step size and preset learning rate of the gradient descent algorithm; Based on the preset iteration step size, the preset learning rate, the initial objective function and the performance parameter value, a system objective function of the gradient descent algorithm is constructed.

7. A computer device, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for adjusting the carrier frequency of the electric drive system described in any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method for adjusting the carrier frequency of an electric drive system according to any one of claims 1 to 5 are implemented.

9. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the steps of the method for adjusting the carrier frequency of an electric drive system according to any one of claims 1 to 5 are implemented.

Images