Modeling optimization method and device for vehicle-pile cooperative wireless charging and discharging strategy

Abstract

The invention discloses a modeling optimization method and device for a vehicle pile cooperative wireless charging and discharging strategy, and relates to the technical field of electric vehicle charging. The method comprises: acquiring state data of a charging coupling system; obtaining an error value according to the vehicle end actually-measured voltage and the target charging voltage; if the error value is greater than a first preset threshold value, inputting the state data into a pre-trained agent to obtain phase shift angle reference values on two sides; substituting the phase shift angle reference value into a mathematical model of the charging coupling system for state simulation to obtain second state data; judging whether the phase shift angle reference value is reasonable or not according to the second state data; and if so, generating a PWM control signal according to the phase shift angle reference value to perform charging control. The intelligent agent is introduced to carry out collaborative optimization on the states of the vehicle end and the pile end, the nonlinear and time-varying interference problem in the wireless charging process is more effectively solved, the response speed of the system to the sudden change of the load is improved, double-end collaborative control is achieved, and the overall charging efficiency is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric vehicle charging, and particularly to a modeling optimization method and device for vehicle-pile collaborative wireless charging and discharging strategies. Background Art

[0002] Under the background of the rapid development of new energy vehicles at present, vehicle-pile collaborative wireless charging technology has gradually become a key research direction in the field of electric vehicle energy replenishment. Compared with the traditional wired charging method, wireless charging technology has the advantages of convenient operation, high safety, strong environmental adaptability, etc., and is especially suitable for future travel scenarios such as intelligent transportation and automatic parking. However, despite the certain progress of wireless charging technology, it still faces many challenges in practical applications, especially in terms of control strategies and system coordination.

[0003] Traditional wireless charging control methods usually rely on an adjustment mechanism based on a PI (Proportional-Integral) controller to control power transmission by adjusting the phase shift angle or duty cycle in real time. However, such methods have the following obvious limitations: First, the PI controller is essentially a linear control means and is difficult to cope with the complex dynamic problems brought by nonlinearity, time-variation, and electromagnetic coupling during the wireless charging process. Especially in scenarios such as sudden load changes or environmental interference, it is easy to cause a decrease in control accuracy, slow system response, or even instability. Second, most traditional control methods only control the vehicle side or the pile side separately, lacking a system-level collaborative adjustment mechanism, and it is difficult to fully utilize the advantages of vehicle-pile collaboration, thus restricting the overall charging efficiency and safety. Summary of the Invention

[0004] The purpose of the present invention is to solve the problem of slow system response mentioned in the above background art, and to propose a modeling optimization method and device for vehicle-pile collaborative wireless charging and discharging strategies.

[0005] In the first aspect of the implementation of the present invention, a modeling optimization method for vehicle-pile collaborative wireless charging and discharging strategies is provided. The method includes: Obtain the first system parameters of the vehicle side and the second system parameters of the pile side, and establish a mathematical model of the charging coupling system; Obtain the first state data of the charging coupling system; the first state data includes the actually measured voltage of the vehicle side; Obtain an error value according to the actually measured voltage of the vehicle side and the target charging voltage; If the error value is greater than the first preset threshold, input the first state data into a pre-trained intelligent agent to obtain the reference phase shift angle values on both sides; Substitute the reference phase shift angle values into the mathematical model for state simulation to obtain the second state data; Based on the second state data, determine whether the phase-shift angle reference value is reasonable; if it is reasonable, generate a PWM control signal according to the phase-shift angle reference value for charging control; otherwise, use a preset PI controller to generate a PWM control signal for charging control.

[0006] Optionally, the charging coupling system includes a vehicle end and a pile end, the pile end is the primary side, and the vehicle end is the secondary side; both the primary side and the secondary side adopt a full-bridge structure and each includes four switching tubes.

[0007] Optionally, the reward function during the training of the agent is: ; where is the reward at time step t; is the charging voltage at time step t; is the target voltage; is the primary side phase-shift angle at time step t; is the primary side phase-shift angle at time step t-1; is the secondary side phase-shift angle at time step t; is the secondary side phase-shift angle at time step t-1; is the weight coefficient.

[0008] Optionally, the phase-shift angle reference value includes a primary side reference value and a secondary side reference value; The generating a PWM control signal for charging control according to the phase-shift angle reference value includes: Step 1, generate a single-step adjustment value according to the target reference value and the target current value: ; where is the single-step adjustment value; is the target reference value, which is either the primary side reference value or the secondary side reference value; is the target current value corresponding to the target reference value; is the preset maximum allowable step size per cycle; clip is a clipping function; Step 2, generate a PWM control signal according to the single-step adjustment value; Step 3, if the single-step adjustment value is less than the target reference value, return the single-step adjustment value as the target current value to Step 1; otherwise, end this control process.

[0009] Optionally, the method further includes: If the error value is not greater than the first preset threshold and greater than the second preset threshold, the error value is respectively input into a preset first PI controller and a second PI controller to obtain a first correction amount on the secondary side and a second correction amount on the primary side; According to the first correction amount, a secondary side phase shift angle adjustment value is obtained; according to the second correction amount, a primary side phase shift angle adjustment value is obtained; According to the secondary side phase shift angle adjustment value and the primary side phase shift angle adjustment value, PWM control signals on both sides are generated; If the error value is not greater than the second preset threshold, only the secondary side adjustment is performed.

[0010] In the second aspect of the implementation of the present invention, a modeling optimization device for vehicle-pile collaborative wireless charging and discharging strategy is provided. The device includes: A system modeling module for obtaining first system parameters of the vehicle side and second system parameters of the pile side, and establishing a mathematical model of the charging coupling system; A charging data acquisition module for acquiring first state data of the charging coupling system; the first state data includes the actually measured voltage of the vehicle side; An error evaluation module for obtaining an error value according to the actually measured voltage of the vehicle side and the target charging voltage; A first adjustment module for, if the error value is greater than the first preset threshold, inputting the first state data into a pre-trained intelligent body to obtain phase shift angle reference values on both sides; A state prediction module for substituting the phase shift angle reference values into the mathematical model for state simulation to obtain second state data; An optimization evaluation module for judging whether the phase shift angle reference values are reasonable according to the second state data; A fault tolerance control module for, if the phase shift angle reference values are reasonable, generating PWM control signals according to the phase shift angle reference values for charging control; otherwise, generating PWM control signals by using a preset PI controller for charging control.

[0011] Optionally, the charging coupling system includes a vehicle side and a pile side. The pile side is the primary side, and the vehicle side is the secondary side; both the primary side and the secondary side adopt a full-bridge structure and both include four switching tubes.

[0012] Optionally, the reward function during the training process of the intelligent body is: ; Wherein, is the reward at time step t; is the charging voltage at time step t; is the target voltage; is the primary side phase shift angle at time step t; is the original side phase shift angle at time step t-1; is the secondary side phase shift angle at time step t; is the secondary side phase shift angle at time step t-1; is the weight coefficient.

[0013] Optionally, the phase shift angle reference value includes an original side reference value and a secondary side reference value; The fault tolerance control module includes: A single-step limit module, configured to generate a single-step adjustment value according to a target reference value and a target current value: ; wherein, is the single-step adjustment value; is the target reference value, which is any one of the original side reference value and the secondary side reference value; is the target current value corresponding to the target reference value; is a preset maximum allowable step length for a single period; clip is a clipping function; A signal generation module, configured to generate a PWM control signal according to the single-step adjustment value; An iterative stepping module, configured to, if the single-step adjustment value is less than the target reference value, return the single-step adjustment value as the target current value to step one; otherwise, end the current control process.

[0014] Optionally, the device further includes: A second adjustment module, configured to, if the error value is not greater than a first preset threshold and greater than a second preset threshold, input the error value into a preset first PI controller and a second PI controller respectively to obtain a first correction amount for the secondary side and a second correction amount for the original side; obtain a secondary side phase shift angle adjustment value according to the first correction amount; obtain an original side phase shift angle adjustment value according to the second correction amount; generate PWM control signals for both sides according to the secondary side phase shift angle adjustment value and the original side phase shift angle adjustment value; A third adjustment module, configured to, if the error value is not greater than the second preset threshold, only perform secondary side adjustment.

[0015] Advantages of the present invention: The present invention proposes a modeling optimization method for vehicle-pile collaborative wireless charging and discharging strategies. The method includes: obtaining first system parameters of the vehicle side and second system parameters of the pile side, and establishing a mathematical model of the charging coupling system; obtaining first state data of the charging coupling system; the first state data includes the actually measured voltage of the vehicle side; obtaining an error value according to the actually measured voltage of the vehicle side and the target charging voltage; if the error value is greater than a first preset threshold, inputting the first state data into a pre-trained intelligent agent to obtain reference phase-shift angle values on both sides; substituting the reference phase-shift angle values into the mathematical model for state simulation to obtain second state data; judging whether the reference phase-shift angle values are reasonable according to the second state data; if reasonable, generating a PWM control signal according to the reference phase-shift angle values for charging control; otherwise, using a preset PI controller to generate a PWM control signal for charging control.

[0016] By introducing an intelligent agent to collaboratively optimize the states of the vehicle side and the pile side, it is possible to more effectively cope with the non-linear and time-varying interference problems during wireless charging, improve the response speed and stability of the system to sudden load changes, and at the same time achieve dual-end collaborative control, significantly improving the overall charging efficiency. When the intelligent control strategy fails, the system can automatically switch to PI control as a backup to ensure the continuity and reliability of the charging process, and has stronger intelligence, self-adaptability and practicability. Description of the Drawings

[0017] Figure 1 The flowchart of a modeling optimization method for vehicle-pile collaborative wireless charging and discharging strategies provided by an embodiment of the present invention; Figure 2 The structural schematic diagram of a charging coupling system provided by an embodiment of the present invention; Figure 3 The structural schematic diagram of a modeling optimization device for vehicle-pile collaborative wireless charging and discharging strategies provided by an embodiment of the present invention. Detailed Embodiments

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0019] An embodiment of the present invention provides a modeling optimization method for vehicle-pile collaborative wireless charging and discharging strategies. Refer to Figure 1 , Figure 1 The flowchart of a modeling optimization method for vehicle-pile collaborative wireless charging and discharging strategies provided by an embodiment of the present invention. The method includes the following steps: S101. Obtain the first system parameters of the vehicle end and the second system parameters of the pile end, and establish a mathematical model of the charging coupling system.

[0020] S102. Obtain the first state data of the charging coupling system.

[0021] S103. Obtain an error value based on the measured voltage at the vehicle end and the target charging voltage.

[0022] S104. If the error value is greater than the first preset threshold, input the first state data into a pre-trained agent to obtain the reference phase-shift angle values on both sides.

[0023] S105. Substitute the reference phase-shift angle values into the mathematical model for state simulation to obtain the second state data.

[0024] S106. Determine whether the reference phase-shift angle values are reasonable according to the second state data.

[0025] S107. If the reference phase-shift angle values are reasonable, generate a PWM control signal according to the reference phase-shift angle values for charging control; otherwise, use a preset PI controller to generate a PWM control signal for charging control.

[0026] Among them, the first state data includes the measured voltage, current, current phase-shift angle, and coupling coefficient at the vehicle end and the pile end.

[0027] Based on a modeling optimization method for vehicle-pile collaborative wireless charging and discharging strategy provided by an embodiment of the present invention, by introducing an agent to collaboratively optimize the states of the vehicle end and the pile end, it can more effectively cope with the non-linear and time-varying interference problems in the wireless charging process, improve the response speed and stability of the system to load mutations, and at the same time achieve dual-end collaborative control, significantly improving the overall charging efficiency. When the intelligent control strategy fails, the system can automatically switch to PI control as a backup to ensure the continuity and reliability of the charging process, and has stronger intelligence, self-adaptability, and practicability.

[0028] In one embodiment, refer to Figure 2 , Figure 2 is a schematic structural diagram of a charging coupling system provided by an embodiment of the present invention. The charging coupling system includes a vehicle end and a pile end. Both sides adopt a full-bridge structure and each includes four switching tubes (P1 - P4, S1 - S4). The pile end is the primary side, and the vehicle end is the secondary side. The first system parameters include the coil self-inductance, coil internal resistance, series capacitor Cs, parallel capacitor Cf2, compensation inductor Lf2, and filter capacitor Co on the secondary side; the second system parameters include the coil self-inductance, coil internal resistance, series capacitor Cp, parallel capacitor Cf1, and compensation inductor Lf1 on the primary side.

[0029] In one implementation, the mathematical model of the charging coupling system describes the dynamic response relationship from the input voltage on the primary side to the output voltage on the secondary side through a series of formulas. The charging coupling system is a common bilateral full-bridge structure, and its mathematical model will not be elaborated here.

[0030] In one embodiment, the agent is a reinforcement learning agent. Its environmental state includes the voltage and current on the primary and secondary sides, the current phase shift angle, the coupling coefficient, and the error value. Its action space includes the reference value of the primary side phase shift angle and the reference value of the secondary side phase shift angle. Its reward function during the training process is: ; where is the reward at time step t; is the charging voltage at time step t; is the target voltage; is the primary side phase shift angle at time step t; is the primary side phase shift angle at time step t-1; is the secondary side phase shift angle at time step t; is the secondary side phase shift angle at time step t-1; is the weight coefficient. In one implementation, can be taken. With the output voltage accuracy as the core goal, while avoiding excessive changes in the phase shift angle.

[0031] In one embodiment, the phase shift angle reference value includes the primary side reference value and the secondary side reference value. Generating a PWM control signal according to the phase shift angle reference value for charging control includes: Step 1, generate a single-step adjustment value according to the target reference value and the target current value: ; where is the single-step adjustment value; is the target reference value, which is either the primary side reference value or the secondary side reference value; is the target current value corresponding to the target reference value; is the preset maximum allowable step size per cycle; clip is a clipping function, specifically: .

[0032] Step 2, generate a PWM control signal according to the single-step adjustment value.

[0033] Step 3, if the single-step adjustment value is less than the target reference value, return the single-step adjustment value as the target current value to Step 1; otherwise, end this control process.

[0034] In this embodiment, smooth transition is achieved through single-step adjustment values instead of jumping directly to the target value at once, which can effectively prevent current fluctuations, harmonic interference, or overshoot phenomena caused by sudden changes in the phase-shifting angle in the system. In one implementation, the maximum allowable step size per cycle can be set to 0.05 rad (in radians).

[0035] In one embodiment, the second state data includes the predicted voltage at the vehicle end. When the absolute difference between the predicted voltage at the vehicle end and the target charging voltage is less than a preset error threshold, it is determined that the phase-shifting angle reference value given by the agent is reasonable. Specifically, the error threshold can be set to 1% of the target charging voltage.

[0036] In one implementation, using the predicted voltage at the vehicle end as a kind of "simulation verification" can pre-judge whether the strategy is reasonable before the actual output, avoiding losses or abnormalities caused by incorrect control. If the prediction error is small, the agent strategy is executed; otherwise, it can switch back to traditional PI control or other conservative strategies to form a soft-hard collaborative fault-tolerant mechanism. This design effectively improves the overall usability and safety margin of the system.

[0037] In one embodiment, the situation where the error value is greater than the first preset threshold is regarded as Case One. The method further includes: Case Two, if the error value is not greater than the first preset threshold and is greater than the second preset threshold, the error value is respectively input into a preset first PI controller and a second PI controller to obtain a first correction amount on the secondary side and a second correction amount on the primary side respectively.

[0038] According to the first correction amount, the secondary side phase-shifting angle adjustment value is obtained. According to the second correction amount, the primary side phase-shifting angle adjustment value is obtained.

[0039] According to the secondary side phase-shifting angle adjustment value and the primary side phase-shifting angle adjustment value, PWM control signals for both sides are generated.

[0040] Case Three, if the error value is not greater than the second preset threshold, only the first PI controller is used for secondary side adjustment.

[0041] Among them, the first preset threshold and the second preset threshold are flexibly set by technicians according to the actual accuracy of the PI controller. For example, the first preset threshold can be set to 5% of the target charging voltage, and the second preset threshold can be set to 1% of the target charging voltage.

[0042] In one implementation, different control means are enabled in different error intervals, avoiding frequent bilateral adjustment when the error is small, and effectively reducing the fluctuation of the control amount. When the error is large, the reference value is found through the agent, avoiding the slow response of gradual approximation.

[0043] In one implementation, when the error value is greater than the first preset threshold and the phase shift angle reference value given by the agent is unreasonable, the scheme of Case 2 can be used for bilateral regulation.

[0044] An embodiment of the present invention provides a modeling optimization device for vehicle-pile collaborative wireless charging and discharging strategies. Refer to Figure 3 , Figure 3 which is a schematic structural diagram of a modeling optimization device for vehicle-pile collaborative wireless charging and discharging strategies provided by an embodiment of the present invention. The device includes: A system modeling module, configured to obtain the first system parameters of the vehicle side and the second system parameters of the pile side, and establish a mathematical model of the charging coupling system.

[0045] A charging data acquisition module, configured to acquire the first state data of the charging coupling system.

[0046] An error evaluation module, configured to obtain an error value according to the measured voltage at the vehicle side and the target charging voltage.

[0047] A first adjustment module, configured to input the first state data into a pre-trained agent if the error value is greater than the first preset threshold, and obtain the phase shift angle reference values on both sides.

[0048] A state prediction module, configured to substitute the phase shift angle reference values into the mathematical model for state simulation, and obtain the second state data.

[0049] An optimization evaluation module, configured to determine whether the phase shift angle reference values are reasonable according to the second state data.

[0050] A fault tolerance control module, configured to generate a PWM control signal for charging control according to the phase shift angle reference values if the phase shift angle reference values are reasonable; otherwise, generate a PWM control signal for charging control by using a preset PI controller.

[0051] Wherein, the first state data includes the measured voltage, current, and current phase shift angle at the vehicle side and the pile side.

[0052] Based on the modeling optimization device for vehicle-pile collaborative wireless charging and discharging strategies provided by the embodiment of the present invention, by introducing an agent to collaboratively optimize the states of the vehicle side and the pile side, it can more effectively cope with the non-linear and time-varying interference problems in the wireless charging process, improve the response speed and stability of the system to load mutations, and at the same time achieve dual-end collaborative control, significantly improving the overall charging efficiency. When the intelligent control strategy fails, the system can automatically switch to PI control as a backup to ensure the continuity and reliability of the charging process, and has stronger intelligence, self-adaptability, and practicability.

[0053] In one embodiment, the phase shift angle reference values include the primary side reference value and the secondary side reference value. The fault tolerance control module includes: A single-step limit module, configured to generate a single-step adjustment value according to a target reference value and a target current value: ; Wherein, is the single-step adjustment value; is the target reference value, which is either the primary-side reference value or the secondary-side reference value; is the target current value corresponding to the target reference value; is a preset maximum allowable step size per cycle; clip is a clipping function.

[0054] A signal generation module, configured to generate a PWM control signal according to the single-step adjustment value.

[0055] An iterative stepping module, configured to, if the single-step adjustment value is less than the target reference value, return the single-step adjustment value as the target current value to step one; otherwise, end the current control process.

[0056] In one embodiment, the device further includes: A second adjustment module, configured to, if the error value is not greater than a first preset threshold and greater than a second preset threshold, input the error value into a preset first PI controller and a second PI controller respectively, to obtain a first correction amount on the secondary side and a second correction amount on the primary side; obtain a secondary-side phase-shift angle adjustment value according to the first correction amount; obtain a primary-side phase-shift angle adjustment value according to the second correction amount; and generate PWM control signals on both sides according to the secondary-side phase-shift angle adjustment value and the primary-side phase-shift angle adjustment value.

[0057] A third adjustment module, configured to, if the error value is not greater than the second preset threshold, only perform secondary-side adjustment.

[0058] It should be noted that in this article, terms such as "including", "comprising" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0059] The above has described the embodiments of the present invention in detail, but the described content is only the preferred embodiments of the present invention and cannot be considered as limiting the scope of implementation of the present invention. Any equivalent changes and improvements made within the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A modeling optimization method for vehicle-pile collaborative wireless charging and discharging strategies, characterized in that, The method includes: Obtaining the first system parameters of the vehicle end and the second system parameters of the pile end, and establishing a mathematical model of the charging coupling system; Obtaining the first state data of the charging coupling system; the first state data includes the measured voltage at the vehicle end; Obtaining an error value based on the measured voltage at the vehicle end and the target charging voltage; If the error value is greater than a first preset threshold, inputting the first state data into a pre-trained agent to obtain the reference phase shift angle values on both sides; Substituting the reference phase shift angle values into the mathematical model for state simulation to obtain second state data; Judging whether the reference phase shift angle values are reasonable according to the second state data; if reasonable, generating a PWM control signal according to the reference phase shift angle values for charging control; otherwise, using a preset PI controller to generate a PWM control signal for charging control.

2. The modeling optimization method for the vehicle-pile collaborative wireless charging and discharging strategy according to claim 1, wherein, The charging coupling system includes a vehicle end and a pile end, the pile end is the primary side, and the vehicle end is the secondary side; both the primary side and the secondary side adopt a full-bridge structure and both include four switching tubes.

3. The modeling optimization method for vehicle-pile collaborative wireless charging and discharging strategy according to claim 1, wherein, The reward function of the agent during training is: where, R(t) is the reward at time step t; U t is the charging voltage at time step t; U0 is the target voltage; OPA t is the primary side phase shift angle at time step t; OPA t-1 is the primary side phase shift angle at time step t - 1; SPA t is the secondary side phase shift angle at time step t; SPA t-1 is the secondary side phase shift angle at time step t - 1; w1, w2, and w3 are weight coefficients.

4. A modeling optimization method for vehicle-pile collaborative wireless charging and discharging strategy according to claim 2, characterized in that, The reference phase shift angle values include a primary side reference value and a secondary side reference value; The generating a PWM control signal according to the reference phase shift angle values for charging control includes: Step 1, generating a single-step adjustment value according to a target reference value and a target current value: θ target = θ now + clip(θ ref - θ now , -ΔSL max , ΔSL max ); Among them, θ target is the single-step adjustment value; θ ref is the target reference value, which is either the primary-side reference value or the secondary-side reference value; θ now is the target current value corresponding to the target reference value; SL max is the preset maximum allowable step length per cycle; clip is the clipping function; Step 2, generating a PWM control signal according to the single-step adjustment value; Step 3, if the single-step adjustment value is less than the target reference value, using the single-step adjustment value as the target current value and returning to Step 1; otherwise, ending the current control process.

5. The modeling optimization method for the vehicle-pile collaborative wireless charging and discharging strategy according to claim 2, wherein The method further includes: If the error value is not greater than the first preset threshold and is greater than a second preset threshold, inputting the error value into a preset first PI controller and a second PI controller respectively to obtain a first correction amount for the secondary side and a second correction amount for the primary side; Obtaining a secondary side phase shift angle adjustment value according to the first correction amount; obtaining a primary side phase shift angle adjustment value according to the second correction amount; Generating PWM control signals on both sides according to the secondary side phase shift angle adjustment value and the primary side phase shift angle adjustment value; If the error value is not greater than the second preset threshold, only performing secondary side adjustment.

6. A modeling and optimization device for vehicle-pile collaborative wireless charging and discharging strategies, characterized in that, The device includes: A system modeling module, configured to obtain the first system parameters of the vehicle end and the second system parameters of the pile end, and establish a mathematical model of the charging coupling system; A charging data acquisition module, configured to obtain the first state data of the charging coupling system; the first state data includes the measured voltage at the vehicle end; An error evaluation module, configured to obtain an error value according to the measured voltage at the vehicle end and the target charging voltage; A first adjustment module, configured to, if the error value is greater than a first preset threshold, input the first state data into a pre-trained agent to obtain the reference phase shift angle values on both sides; A state prediction module, configured to substitute the reference phase shift angle values into the mathematical model for state simulation to obtain second state data; An optimization evaluation module, configured to judge whether the reference phase shift angle values are reasonable according to the second state data; The fault-tolerant control module is used to generate a PWM control signal for charging control according to the phase-shift angle reference value if the phase-shift angle reference value is reasonable; otherwise, a preset PI controller is used to generate a PWM control signal for charging control.

7. The modeling and optimization device for the vehicle-pile collaborative wireless charging and discharging strategy according to claim 6, characterized in that, The charging coupling system includes a vehicle end and a pile end. The pile end is the primary side, and the vehicle end is the secondary side. Both the primary side and the secondary side adopt a full-bridge structure and each includes four switching tubes.

8. The modeling and optimization device for the vehicle-pile collaborative wireless charging and discharging strategy according to claim 6, characterized in that, The reward function of the agent during the training process is: Among them, R(t) is the reward at time step t; U t is the charging voltage at time step t; U0 is the target voltage; OPA t is the primary side phase-shift angle at time step t; OPA t-1 is the primary side phase-shift angle at time step t-1; SPA t is the secondary side phase-shift angle at time step t; SPA t-1 is the secondary side phase-shift angle at time step t-1; w1, w2, and w3 are weight coefficients.

9. The modeling and optimization device for the vehicle-pile collaborative wireless charging and discharging strategy according to claim 7, characterized in that, The phase-shift angle reference value includes a primary side reference value and a secondary side reference value; The fault-tolerant control module includes: A single-step limit module, which is used to generate a single-step adjustment value according to a target reference value and a target current value: θ target = θ now + clip(θ ref - θ now , -ΔSL max , ΔSL max ); Among them, θ target is the single-step adjustment value; θ ref is the target reference value, which is either the primary-side reference value or the secondary-side reference value; θ now is the target current value corresponding to the target reference value; SL max is the preset maximum allowable step length per cycle; clip is the clipping function; A signal generation module, which is used to generate a PWM control signal according to the single-step adjustment value; An iterative stepping module, which is used to, if the single-step adjustment value is less than the target reference value, return the single-step adjustment value as the target current value to step one; otherwise, end the current control process.

10. A modeling and optimization device for vehicle-pile collaborative wireless charging and discharging strategy according to claim 7, characterized in that, The device further includes: A second adjustment module, which is used to, if the error value is not greater than a first preset threshold and is greater than a second preset threshold, input the error value into a preset first PI controller and a second PI controller respectively to obtain a first correction amount for the secondary side and a second correction amount for the primary side; obtain a secondary side phase-shift angle adjustment value according to the first correction amount; obtain a primary side phase-shift angle adjustment value according to the second correction amount; and generate PWM control signals for both sides according to the secondary side phase-shift angle adjustment value and the primary side phase-shift angle adjustment value; A third adjustment module, which is used to, if the error value is not greater than the second preset threshold, only perform secondary side adjustment.

Images