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

Abstract

The application discloses a modeling optimization method and device for vehicle-pile cooperative wireless charging and discharging strategy and relates to the technical field of electric vehicle charging. State data of a charging coupling system is acquired; an error value is obtained according to a vehicle-end measured voltage and a target charging voltage; if the error value is greater than a first preset threshold, the state data is input into a pre-trained intelligent agent to obtain a phase-shifting angle reference value on both sides; the phase-shifting angle reference value is substituted into a mathematical model of the charging coupling system for state simulation to obtain second state data; whether the phase-shifting angle reference value is reasonable is judged according to the second state data; if the phase-shifting angle reference value is reasonable, a PWM control signal is generated according to the phase-shifting angle reference value for charging control. By introducing the intelligent agent to cooperatively optimize the vehicle-end and pile-end states, the nonlinear and time-varying interference problems in the wireless charging process are more effectively coped with, the response speed of the system to load mutation is improved, double-end cooperative control is realized, and the overall charging efficiency is significantly improved.

Description

Technical Field

[0001] This invention relates to the technical field of electric vehicle charging, and specifically to a modeling and optimization method and apparatus for vehicle-to-charging-pile cooperative wireless charging and discharging strategies. Background Technology

[0002] Against the backdrop of the rapid development of new energy vehicles, vehicle-to-charging (V2C) wireless charging technology has gradually become a key research direction in the field of electric vehicle charging. Compared with traditional wired charging methods, wireless charging technology has advantages such as convenient operation, high safety, and strong environmental adaptability, making it particularly suitable for future mobility scenarios such as intelligent transportation and automatic parking. However, despite the progress made in 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 typically rely on PI (proportional-integral) controller-based adjustment mechanisms, controlling power transfer by adjusting the phase shift angle or duty cycle in real time. However, these methods have several significant limitations: First, PI controllers are inherently linear control mechanisms, making it difficult to handle the complex dynamic problems arising from nonlinearity, time-varying characteristics, and electromagnetic coupling during wireless charging. This is particularly problematic in scenarios involving sudden load changes or environmental interference, which can easily lead to decreased control accuracy, slow system response, or even instability. Second, traditional control methods mostly operate only at the vehicle or charging station level, lacking a system-level coordinated adjustment mechanism. This hinders the full utilization of vehicle-charging station synergy, thus limiting overall charging efficiency and safety. Summary of the Invention

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

[0005] A first aspect of this invention provides a modeling and optimization method for a vehicle-to-pile cooperative wireless charging and discharging strategy, the method comprising:

[0006] Obtain the first system parameters at the vehicle end and the second system parameters at the charging pile end, and establish a mathematical model of the charging coupling system;

[0007] Acquire the first state data of the charging coupling system; the first state data includes the measured voltage at the vehicle end;

[0008] The error value is obtained based on the measured voltage at the vehicle end and the target charging voltage;

[0009] If the error value is greater than the first preset threshold, the first state data is input into the pre-trained agent to obtain the phase shift angle reference values ​​on both sides.

[0010] Substitute the phase shift angle reference value into the mathematical model to perform state simulation and obtain the second state data;

[0011] Based on the second state data, determine whether the phase shift angle reference value is reasonable; if reasonable, generate a PWM control signal based on the phase shift angle reference value for charging control; otherwise, use a preset PI controller to generate a PWM control signal for charging control.

[0012] Optionally, the charging coupling system includes a vehicle end and a charging pile end, the charging pile end being the primary side and the vehicle end being the secondary side; both the primary side and the secondary side adopt a full-bridge structure and each includes four switching transistors.

[0013] Optionally, the reward function for the agent during training is:

[0014] ;

[0015] in, It is the reward for time step t; It is the charging voltage at time step t; It is the target voltage; It is the primary side shift phase angle at time step t; It is the primary side phase shift angle at time step t-1; It is the secondary side phase shift angle at time step t; It is the secondary side phase shift angle at time step t-1; It is the weighting coefficient.

[0016] Optionally, the phase shift angle reference value includes a primary-side reference value and a secondary-side reference value;

[0017] The step of generating a PWM control signal based on the phase shift angle reference value for charging control includes:

[0018] Step 1: Generate single-step adjustment values ​​based on the target reference value and the current target value.

[0019] ;

[0020] in, It is a single-step adjustment value; It is the target reference value, which is either the primary side reference value or the secondary side reference value; It is the current target value corresponding to the target reference value; It is the preset maximum allowable step size per cycle; clip is the amplitude limiting function;

[0021] Step 2: Generate a PWM control signal based on the single-step adjustment value;

[0022] Step 3: If the single-step adjustment value is less than the target reference value, then the single-step adjustment value is returned to Step 1 as the target current value; otherwise, the current control process ends.

[0023] Optionally, the method further includes:

[0024] If the error value is not greater than the first preset threshold and is greater than the second preset threshold, then the error value is input into the preset first PI controller and the second PI controller respectively to obtain the first correction amount on the secondary side and the second correction amount on the primary side respectively.

[0025] Based on the first correction amount, the secondary side phase shift angle adjustment value is obtained; based on the second correction amount, the primary side phase shift angle adjustment value is obtained.

[0026] Based on the secondary phase shift angle adjustment value and the primary phase shift angle adjustment value, PWM control signals are generated on both sides;

[0027] If the error value is not greater than the second preset threshold, then only the secondary side adjustment is performed.

[0028] A second aspect of this invention provides a modeling and optimization device for a vehicle-to-pile cooperative wireless charging and discharging strategy, the device comprising:

[0029] The system modeling module is used to obtain the first system parameters at the vehicle end and the second system parameters at the charging pile end, and to establish a mathematical model of the charging coupling system.

[0030] The charging data acquisition module is used to acquire the first state data of the charging coupling system; the first state data includes the measured voltage at the vehicle end.

[0031] The error evaluation module is used to obtain the error value based on the measured voltage at the vehicle end and the target charging voltage;

[0032] The first adjustment module is used to input the first state data into the pre-trained agent to obtain the phase shift angle reference values ​​on both sides if the error value is greater than the first preset threshold.

[0033] The state prediction module is used to substitute the phase shift angle reference value into the mathematical model to perform state simulation and obtain second state data.

[0034] The optimization evaluation module is used to determine whether the phase shift angle reference value is reasonable based on the second state data;

[0035] The fault-tolerant control module is used to generate a PWM control signal for charging control based on the phase shift angle reference value if the phase shift angle reference value is reasonable; otherwise, it uses a preset PI controller to generate a PWM control signal for charging control.

[0036] Optionally, the charging coupling system includes a vehicle end and a charging pile end, the charging pile end being the primary side and the vehicle end being the secondary side; both the primary side and the secondary side adopt a full-bridge structure and each includes four switching transistors.

[0037] Optionally, the reward function for the agent during training is:

[0038] ;

[0039] in, It is the reward for time step t; It is the charging voltage at time step t; It is the target voltage; It is the primary side shift phase angle at time step t; It is the primary side phase shift angle at time step t-1; It is the secondary side phase shift angle at time step t; It is the secondary side phase shift angle at time step t-1; It is the weighting coefficient.

[0040] Optionally, the phase shift angle reference value includes a primary-side reference value and a secondary-side reference value;

[0041] The fault-tolerant control module includes:

[0042] The single-step limit module is used to generate single-step adjustment values ​​based on the target reference value and the current target value.

[0043] ;

[0044] in, It is a single-step adjustment value; It is the target reference value, which is either the primary side reference value or the secondary side reference value; It is the current target value corresponding to the target reference value; It is the preset maximum allowable step size per cycle; clip is the amplitude limiting function;

[0045] The signal generation module is used to generate a PWM control signal based on the single-step adjustment value;

[0046] The iterative stepping module is used to return the single-step adjustment value as the target current value to step one if the single-step adjustment value is less than the target reference value; otherwise, the current control flow is terminated.

[0047] Optionally, the device further includes:

[0048] The second adjustment module 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 preset second PI controller respectively to obtain a first correction amount on the secondary side and a second correction amount on the primary side respectively; obtain a secondary side phase shift angle adjustment value based on the first correction amount; obtain a primary side phase shift angle adjustment value based on the second correction amount; and generate PWM control signals on both sides based on the secondary side phase shift angle adjustment value and the primary side phase shift angle adjustment value.

[0049] The third adjustment module is used to adjust only the secondary side if the error value is not greater than the second preset threshold.

[0050] The beneficial effects of this invention are:

[0051] This invention proposes a modeling and optimization method for vehicle-to-pile cooperative wireless charging and discharging strategies. The method includes: acquiring first system parameters at the vehicle end and second system parameters at the pile end, and establishing a mathematical model of the charging coupling system; acquiring 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 phase shift angle reference values ​​on both sides; substituting the phase shift angle reference values ​​into the mathematical model for state simulation to obtain second state data; judging whether the phase shift angle reference values ​​are reasonable based on the second state data; if reasonable, generating a PWM control signal based on the phase shift angle reference values ​​for charging control; otherwise, using a preset PI controller to generate a PWM control signal for charging control.

[0052] By introducing intelligent agents to collaboratively optimize the states of both the vehicle and the charging station, the system can more effectively address nonlinear and time-varying interference issues during wireless charging, improving its response speed and stability to sudden load changes. Simultaneously, it achieves dual-end collaborative control, significantly enhancing overall charging efficiency. When the intelligent control strategy fails, the system can automatically switch to PI control as a backup, ensuring the continuity and reliability of the charging process, thus exhibiting enhanced intelligence, adaptability, and practicality. Attached Figure Description

[0053] Figure 1 A flowchart of a modeling and optimization method for a vehicle-pile cooperative wireless charging and discharging strategy is provided for an embodiment of the present invention;

[0054] Figure 2 A schematic diagram of a charging coupling system is provided for an embodiment of the present invention;

[0055] Figure 3 This invention provides a schematic diagram of a modeling and optimization device for a vehicle-pile cooperative wireless charging and discharging strategy. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] This invention provides a modeling and optimization method for a vehicle-to-pile cooperative wireless charging and discharging strategy. See also... Figure 1 , Figure 1 A flowchart illustrating a modeling and optimization method for a vehicle-to-pile cooperative wireless charging and discharging strategy, provided as an embodiment of the present invention. The method includes the following steps:

[0058] S101, obtain the first system parameters at the vehicle end and the second system parameters at the charging pile end, and establish a mathematical model of the charging coupling system.

[0059] S102, Obtain the first state data of the charging coupling system.

[0060] S103, based on the measured voltage at the vehicle end and the target charging voltage, obtain the error value.

[0061] S104, if the error value is greater than the first preset threshold, the first state data is input into the pre-trained agent to obtain the phase shift angle reference values ​​on both sides.

[0062] S105, substitute the phase shift angle reference value into the mathematical model to perform state simulation and obtain the second state data.

[0063] S106, Based on the second state data, determine whether the phase shift angle reference value is reasonable.

[0064] S107 If the phase shift angle reference value is reasonable, a PWM control signal is generated based on the phase shift angle reference value for charging control; otherwise, a preset PI controller is used to generate a PWM control signal for charging control.

[0065] The first state data includes the measured voltage and current at the vehicle end and the pile end, the current phase shift angle, and the coupling coefficient.

[0066] The modeling and optimization method for vehicle-to-pile coordinated wireless charging and discharging strategies provided in this invention introduces an intelligent agent to collaboratively optimize the states of both the vehicle and the charging pile. This method more effectively addresses nonlinear and time-varying interference issues during wireless charging, improves the system's response speed and stability to sudden load changes, and achieves dual-end collaborative control, significantly improving overall charging efficiency. When the intelligent control strategy fails, the system can automatically switch to PI control as a backup, ensuring the continuity and reliability of the charging process, and exhibiting stronger intelligence, adaptability, and practicality.

[0067] In one embodiment, see Figure 2 , Figure 2 This is a schematic diagram of a charging coupling system provided in an embodiment of the present invention. The charging coupling system includes a vehicle end and a charging pile end, both sides adopting a full-bridge structure and each including four switching transistors (P1-P4, S1-S4). The charging 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.

[0068] In one implementation, the mathematical model of the charge-coupled system describes the dynamic response relationship from the primary-side input voltage to the secondary-side output voltage through a series of formulas. This charge-coupled system is a common double-sided full-bridge structure, and its mathematical model will not be elaborated further.

[0069] 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 primary side phase shift angle reference value and the secondary side phase shift angle reference value. Its reward function during training is:

[0070] ;

[0071] in, It is the reward for time step t; It is the charging voltage at time step t; It is the target voltage; It is the primary side shift phase angle at time step t; It is the primary side phase shift angle at time step t-1; It is the secondary side phase shift angle at time step t; It is the secondary side phase shift angle at time step t-1; It's a weighting coefficient. In one implementation, it can be taken as... The core objective is to ensure output voltage accuracy while avoiding excessive changes in the phase shift angle.

[0072] In one embodiment, the phase shift angle reference value includes a primary-side reference value and a secondary-side reference value. Generating a PWM control signal based on the phase shift angle reference value for charging control includes:

[0073] Step 1: Generate single-step adjustment values ​​based on the target reference value and the current target value.

[0074] ;

[0075] in, It is a single-step adjustment value; It is the target reference value, which can be either the primary side reference value or the secondary side reference value; It is the current target value corresponding to the target reference value; It is the preset maximum allowable step size per cycle; clip is the clipping function, specifically: .

[0076] Step 2: Generate a PWM control signal based on the single-step adjustment value.

[0077] Step 3: If the single-step adjustment value is less than the target reference value, then return the single-step adjustment value as the target current value to Step 1; otherwise, end the current control process.

[0078] This embodiment achieves a smooth transition by adjusting the value step by step, rather than jumping to the target value all at once. This effectively prevents current fluctuations, harmonic interference, or overshoot caused by sudden changes in phase angle. In one implementation, the maximum allowable step size per cycle can be set to 0.05 rad (radians).

[0079] In one embodiment, the second state data includes the vehicle-side predicted voltage. When the absolute difference between the vehicle-side predicted voltage and the target charging voltage is less than a preset error threshold, the phase shift angle reference value provided by the agent is deemed reasonable. Specifically, the error threshold can be set to 1% of the target charging voltage.

[0080] In one implementation, the predicted voltage at the vehicle end serves as a "simulation verification," allowing for a pre-emptive assessment of the strategy's rationality before the actual output, thus preventing losses or anomalies caused by erroneous 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, forming a software-hardware collaborative fault-tolerance mechanism. This design effectively improves the overall availability and safety margin of the system.

[0081] In one embodiment, a case where the error value is greater than a first preset threshold is considered case one. The method further includes:

[0082] In scenario two, if the error value is not greater than the first preset threshold but is greater than the second preset threshold, the error value is input to the preset first PI controller and second PI controller respectively to obtain the first correction amount on the secondary side and the second correction amount on the primary side respectively.

[0083] The secondary side phase shift adjustment value is obtained based on the first correction amount. The primary side phase shift adjustment value is obtained based on the second correction amount.

[0084] Based on the secondary phase shift angle adjustment value and the primary phase shift angle adjustment value, PWM control signals are generated on both sides.

[0085] In scenario three, if the error value is not greater than the second preset threshold, then only the first PI controller is used for secondary side adjustment.

[0086] The first and second preset thresholds are flexibly set by technicians based on 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.

[0087] In one implementation, different control methods are activated in different error ranges. When the error is small, frequent bilateral adjustments are avoided, effectively reducing control fluctuations. When the error is large, a reference value is found through an agent, avoiding a slow response of gradual approximation.

[0088] 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 control.

[0089] This invention provides a modeling and optimization device for a vehicle-to-pile cooperative wireless charging and discharging strategy. See also... Figure 3 , Figure 3 This is a schematic diagram of a modeling and optimization device for a vehicle-to-pile cooperative wireless charging and discharging strategy, provided as an embodiment of the present invention. The device includes:

[0090] The system modeling module is used to obtain the first system parameters at the vehicle end and the second system parameters at the charging pile end, and to establish a mathematical model of the charging coupling system.

[0091] The charging data acquisition module is used to acquire the first state data of the charging coupling system.

[0092] The error evaluation module is used to obtain the error value based on the measured voltage at the vehicle end and the target charging voltage.

[0093] The first adjustment module is used to input the first state data into the pre-trained agent to obtain the phase shift angle reference values ​​on both sides if the error value is greater than the first preset threshold.

[0094] The state prediction module is used to substitute the phase shift angle reference value into the mathematical model to perform state simulation and obtain the second state data.

[0095] The optimization and evaluation module is used to determine whether the phase shift angle reference value is reasonable based on the second state data.

[0096] The fault-tolerant control module is used to generate a PWM control signal for charging control based on the phase shift angle reference value if the phase shift angle reference value is reasonable; otherwise, it uses a preset PI controller to generate a PWM control signal for charging control.

[0097] The first state data includes the measured voltage, current, and current phase shift angle at both the vehicle end and the pile end.

[0098] The modeling and optimization device for vehicle-to-pile coordinated wireless charging and discharging strategies provided in this invention introduces an intelligent agent to collaboratively optimize the states of both the vehicle and the charging pile. This effectively addresses nonlinear and time-varying interference issues during wireless charging, improves the system's response speed and stability to sudden load changes, and achieves dual-end collaborative control, significantly improving overall charging efficiency. When the intelligent control strategy fails, the system can automatically switch to PI control as a backup, ensuring the continuity and reliability of the charging process, thus exhibiting stronger intelligence, adaptability, and practicality.

[0099] In one embodiment, the phase shift angle reference value includes a primary-side reference value and a secondary-side reference value. The fault-tolerant control module includes:

[0100] The single-step limit module is used to generate single-step adjustment values ​​based on the target reference value and the current target value.

[0101] ;

[0102] in, It is a single-step adjustment value; It is the target reference value, which can be either the primary side reference value or the secondary side reference value; It is the current target value corresponding to the target reference value; It is the preset maximum allowable step size per single cycle; clip is the amplitude limiting function.

[0103] The signal generation module is used to generate PWM control signals based on the single-step adjustment value.

[0104] The iterative stepping module is used to return to step one as the target current value if the single-step adjustment value is less than the target reference value; otherwise, the current control flow ends.

[0105] In one embodiment, the apparatus further includes:

[0106] The second adjustment module is used to input the error value into a preset first PI controller and a preset second PI controller respectively if the error value is not greater than a first preset threshold and is greater than a second preset threshold, so as to obtain a first correction amount on the secondary side and a second correction amount on the primary side respectively; obtain the secondary side phase shift angle adjustment value according to the first correction amount; obtain the 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.

[0107] The third adjustment module is used to adjust only the secondary side if the error value is not greater than the second preset threshold.

[0108] It should be noted that, in this document, terms such as “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0109] The embodiments of the present invention have been described in detail above, but the content described is only a preferred embodiment of the present invention and should not be considered as limiting the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the patent coverage of the present invention.

Claims

1. A modeling and optimization method for vehicle-to-pile cooperative wireless charging and discharging strategies, characterized in that, The method includes: Obtain the first system parameters at the vehicle end and the second system parameters at the charging pile end, and establish a mathematical model of the charging coupling system; Acquire the first state data of the charging coupling system; the first state data includes the measured voltage at the vehicle end; The error value is obtained based on the measured voltage at the vehicle end and the target charging voltage; If the error value is greater than the first preset threshold, the first state data is input into the pre-trained agent to obtain the phase shift angle reference values ​​on both sides. Substitute the phase shift angle reference value into the mathematical model to perform state simulation and obtain the second state data; Based on the second state data, determine whether the phase shift angle reference value is reasonable; if reasonable, generate a PWM control signal based on the phase shift angle reference value for charging control; otherwise, use a preset PI controller to generate a PWM control signal for charging control.

2. The modeling and optimization method for a vehicle-to-pile cooperative wireless charging and discharging strategy according to claim 1, characterized in that, The charging coupling system includes a vehicle end and a charging pile end, with the charging pile end being the primary side and the vehicle end being the secondary side; both the primary side and the secondary side adopt a full-bridge structure and each includes four switching transistors.

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

4. The modeling and optimization method for a vehicle-to-pile cooperative wireless charging and discharging strategy according to claim 2, characterized in that, The phase shift angle reference value includes the primary side reference value and the secondary side reference value; The step of generating a PWM control signal based on the phase shift angle reference value for charging control includes: Step 1: Generate single-step adjustment values ​​based on the target reference value and the current target value. i target =θ now +clip(θ ref -θ now ,-ΔSL max ,ΔSL max ); Where, θ target It is a single-step adjustment value; θ ref The target reference value is either the primary side reference value or the secondary side reference value; θ now It is the current target value corresponding to the target reference value; SL max It is the preset maximum allowable step size per cycle; clip is the amplitude limiting function; Step 2: Generate a PWM control signal based on the single-step adjustment value; Step 3: If the single-step adjustment value is less than the target reference value, then the single-step adjustment value is returned to Step 1 as the target current value; otherwise, the current control process ends.

5. The modeling and optimization method for a vehicle-to-pile cooperative wireless charging and discharging strategy according to claim 2, characterized in that, The method further includes: If the error value is not greater than the first preset threshold and is greater than the second preset threshold, then the error value is input into the preset first PI controller and the second PI controller respectively to obtain the first correction amount on the secondary side and the second correction amount on the primary side respectively. Based on the first correction amount, the secondary side phase shift angle adjustment value is obtained; based on the second correction amount, the primary side phase shift angle adjustment value is obtained. Based on the secondary phase shift angle adjustment value and the primary phase shift angle adjustment value, PWM control signals are generated on both sides; If the error value is not greater than the second preset threshold, then only the secondary side adjustment is performed.

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

7. The modeling and optimization device for vehicle-pile cooperative wireless charging and discharging strategy according to claim 6, characterized in that, The charging coupling system includes a vehicle end and a charging pile end, with the charging pile end being the primary side and the vehicle end being the secondary side; both the primary side and the secondary side adopt a full-bridge structure and each includes four switching transistors.

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

9. The modeling and optimization device for vehicle-pile cooperative wireless charging and discharging strategy according to claim 7, characterized in that, The phase shift angle reference value includes the primary side reference value and the secondary side reference value; The fault-tolerant control module includes: The single-step limit module is used to generate single-step adjustment values ​​based on the target reference value and the current target value. i target =θ now +clip(θ ref -θ now ,-ΔSL max ,ΔSL max ); Where, θ target It is a single-step adjustment value; θ ref The target reference value is either the primary side reference value or the secondary side reference value; θ now It is the current target value corresponding to the target reference value; SL max It is the preset maximum allowable step size per cycle; clip is the amplitude limiting function; The signal generation module is used to generate a PWM control signal based on the single-step adjustment value; The iterative stepping module is used to return the single-step adjustment value as the target current value to step one if the single-step adjustment value is less than the target reference value; otherwise, the current control flow is terminated.

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

Images