A bilateral collaborative control method and system for a wireless charging system

Abstract

This invention provides a bilateral cooperative control method and system for a wireless charging system. During the constant current charging phase, the phase shift angle of the rectifier network is fixed, and the phase shift angle of the inverter network is adjusted to perform constant current charging of the load to maintain the maximum output efficiency. It is determined whether the output current to the load exceeds a set threshold. If not, the constant current charging phase continues; if so, the next step is executed. After the constant current charging state ends, the phase shift angle of the inverter network is fixed, and adaptive adjustment of PID parameters is performed based on a deep learning network. The PID output is used as the phase shift angle of the rectifier network to be adjusted, enabling constant voltage charging control and disturbance response control to maintain the maximum output efficiency. This invention employs a phase-shift control method, changing the phase shift angle to adjust the output and maintain the maximum output efficiency, greatly improving wireless charging efficiency.

Description

Technical Field

[0001] This invention relates to the field of wireless charging technology, and in particular to a bilateral cooperative control method and system for a wireless charging system. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Wireless power transfer technology has become a focus of attention in recent years, with widespread applications in both industrial and consumer sectors. Applications include mobile device charging, biomedical implant circuitry, and electric vehicle battery charging, suitable for various power levels. Compared to wired charging, wireless power transfer is more flexible and avoids mechanical wear due to the absence of physical contact. Existing wireless charging systems are primarily developed to meet the needs of devices requiring unidirectional power transfer, but with the rise of V2G, research into bidirectional wireless charging systems is also increasing.

[0004] The inventors discovered that bidirectional wireless charging systems generally employ a symmetrical compensation topology and control circuit, adjusting the output power by modifying the conduction angle and phase shift angle of the primary and secondary control circuits. Existing wireless power transfer methods include microwave, laser, inductive, and magnetically coupled resonant methods. Magnetically coupled resonant wireless power transfer utilizes an energy transfer coil and compensating inductors and capacitors to form a resonant circuit, generating a strong coupled magnetic field between the primary and secondary resonant circuits to achieve energy transfer. However, existing charging control methods have low charging efficiency and response rate, failing to achieve efficient ineffective charging. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a bilateral cooperative control method and system for a wireless charging system. It employs a phase-shift control approach, changing the phase-shift angle to adjust the output, thereby maintaining the output efficiency at its maximum value and significantly improving the wireless charging efficiency.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] The first aspect of this invention provides a bilateral cooperative control method for a wireless charging system.

[0008] A bilateral cooperative control method for a wireless charging system, wherein the wireless charging system includes at least: an interconnected inverter network and a primary compensation network located on the primary side, and an interconnected secondary compensation network and a rectifier network located on the secondary side, wherein the primary compensation network is connected to the primary energy transmission coil, and the secondary compensation network is connected to the secondary energy receiving coil.

[0009] The process includes the following:

[0010] During the constant current charging stage, the phase shift angle of the rectifier network is fixed, and the phase shift angle of the inverter network is adjusted to perform constant current charging on the load so that the output efficiency is kept at its maximum value. It is determined whether the output current to the load is greater than the set threshold. If not, the constant current charging stage continues; if so, the next step is executed.

[0011] After the constant current charging state ends, the phase shift angle of the inverter network is fixed. The PID parameters are adaptively adjusted based on the deep learning network. The output of the PID is used as the phase shift angle of the rectifier network that needs to be adjusted, so as to perform constant voltage charging control and disturbance response control to keep the output efficiency at its maximum value.

[0012] As a further limitation of the first aspect of the present invention, a BP neural network is used for adaptive adjustment of PID parameters.

[0013] As a further limitation of the first aspect of the present invention, the inputs of the BP neural network are: a set value, a secondary output value, and the deviation between the secondary output value and the set value, and the outputs of the BP neural network are the three adjustment parameters of the PID controller.

[0014] As a further limitation of the first aspect of the present invention, the weighting coefficients of the hidden layer and the output layer of the BP neural network are:

[0015]

[0016]

[0017] Where η is the learning rate and α is the inertia coefficient;

[0018]

[0019]

[0020] As input to the hidden layer, The output of the input layer, y(k) is the output of the hidden layer, e(k) is the deviation between the secondary side output and the set value, u(k) is the output of the PID, y(k) is the secondary side output, k is the current sampling time, k-1 is the previous sampling time, f(·) is the activation function of the hidden layer node, and g(·) is the activation function of the output layer node.

[0021] A second aspect of the present invention provides a bilateral collaborative control system for a wireless charging system.

[0022] A bilateral cooperative control system for a wireless charging system, wherein the wireless charging system includes at least: an interconnected inverter network and a primary compensation network on the primary side, and an interconnected secondary compensation network and a rectifier network on the secondary side, wherein the primary compensation network is connected to the primary energy transmission coil, and the secondary compensation network is connected to the secondary energy receiving coil.

[0023] include:

[0024] The constant current charging module is configured as follows: During the constant current charging stage, the phase shift angle of the rectifier network is fixed, the phase shift angle of the inverter network is adjusted, and the load is charged with constant current to keep the output efficiency at its maximum value. It is determined whether the output current to the load is greater than the set threshold. If not, the constant current charging stage continues. If so, the constant voltage charging module process is executed.

[0025] The constant voltage charging module is configured to: end the constant current charging state, fix the phase shift angle of the inverter network, adaptively adjust the PID parameters based on the deep learning network, use the PID output as the phase shift angle of the rectifier network that needs to be adjusted, and perform constant voltage charging control and disturbance response control to keep the output efficiency at its maximum value.

[0026] As a further limitation of the second aspect of the present invention, a BP neural network is used for adaptive adjustment of PID parameters.

[0027] As a further limitation of the second aspect of the present invention, the inputs of the BP neural network are: a set value, a secondary output value, and the deviation between the secondary output value and the set value, and the outputs of the BP neural network are the three adjustment parameters of the PID.

[0028] As a further limitation of the second aspect of the present invention, the weighting coefficients of the hidden layer and the output layer of the BP neural network are:

[0029]

[0030]

[0031] Where η is the learning rate and α is the inertia coefficient;

[0032]

[0033]

[0034] As input to the hidden layer, The output of the input layer, y(k) is the output of the hidden layer, e(k) is the deviation between the secondary side output and the set value, u(k) is the output of the PID, y(k) is the secondary side output, k is the current sampling time, k-1 is the previous sampling time, f(·) is the activation function of the hidden layer node, and g(·) is the activation function of the output layer node.

[0035] A third aspect of the present invention provides a computer-readable storage medium having a program stored thereon that, when executed by a processor, implements the steps of the bilateral cooperative control method for a wireless charging system as described in the first aspect of the present invention.

[0036] A fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in the bilateral cooperative control method for a wireless charging system as described in the first aspect of the present invention.

[0037] Compared with the prior art, the beneficial effects of the present invention are:

[0038] 1. This invention innovatively proposes a bilateral cooperative control method and system for a wireless charging system. It adopts a phase-shift control method to change the phase-shift angle to adjust the output, so that the output efficiency is kept at the maximum value, which greatly improves the wireless charging efficiency.

[0039] 2. This invention innovatively proposes a bilateral cooperative control method and system for a wireless charging system, which realizes efficient bilateral cooperative control of each charging stage of the wireless charging system, and achieves fast-response closed-loop control based on the BP neural network PID parameter adaptive phase angle control method. Attached Figure Description

[0040] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0041] Figure 1 This is a block diagram of the magnetically coupled resonant wireless charging system provided in Embodiment 1 of the present invention;

[0042] Figure 2 This is a circuit diagram of a wireless charging system provided in Embodiment 1 of the present invention;

[0043] Figure 3 This is a voltage waveform diagram of the bilateral phase-shift control method provided in Embodiment 1 of the present invention;

[0044] Figure 4 This is an efficiency contour plot corresponding to different DC voltage ratios provided in Embodiment 1 of the present invention;

[0045] Figure 5This is a power contour plot corresponding to different DC voltage ratios provided in Embodiment 1 of the present invention;

[0046] Figure 6 The power-efficiency relationship curves corresponding to different phase shift angles are provided in Embodiment 1 of the present invention;

[0047] Figure 7 This is a diagram of the three-layer BP neural network structure provided in Embodiment 1 of the present invention;

[0048] Figure 8 This is a schematic diagram of the weight adjustment process provided in Embodiment 1 of the present invention;

[0049] Figure 9 k provided in Embodiment 1 of the present invention p k i k d Schematic diagram of the adjustment process;

[0050] Figure 10 This is a block diagram of the control process provided in Embodiment 1 of the present invention;

[0051] Figure 11 This is a schematic diagram of the adaptive control result of BP neural network PID parameters provided in Embodiment 1 of the present invention;

[0052] Figure 12 This is a schematic diagram illustrating the relationship between the bilateral phase shift angle value and transmission efficiency provided in Embodiment 1 of the present invention;

[0053] Figure 13 The flowchart of bilateral cooperative control based on BP neural network algorithm is provided in Embodiment 1 of the present invention. Detailed Implementation

[0054] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0055] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0056] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0057] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0058] Example 1:

[0059] Embodiment 1 of this invention provides a bilateral collaborative control method for a wireless charging system. Both the primary and secondary sides adopt a symmetrical circuit structure with a fully controlled bridge and a phase-shift control method. The phase shift angle can be changed to adjust the output. The output efficiency is kept at its maximum value through a control strategy. The bilateral collaborative control of efficient output in each charging stage of the wireless charging system is designed and implemented. The closed-loop control with fast response is achieved based on the BP neural network PID parameter adaptive phase shift angle control method.

[0060] Specifically, it includes the following:

[0061] (1) Wireless charging system structure and bilateral control principle.

[0062] The block diagram of a magnetically coupled resonant wireless charging system is as follows: Figure 1 As shown, the primary and secondary compensation networks of this system adopt a symmetrical structure. The system input is connected to single-phase mains power, which then passes through rectification, filtering, and a high-frequency inverter stage. The high-frequency inverter adopts a fully controlled full-bridge structure. The high-frequency AC power is input to the primary energy transmission coil through the resonant compensation network, generating a high-frequency magnetic field that couples with the secondary energy receiving coil, generating an induced electromotive force. The current passes through the secondary resonant network and then through the fully controlled rectifier bridge and filtering stage to charge the load battery. The primary and secondary sides of the system have a communication device to realize real-time interaction of circuit status and data. The compensation topology adopts a symmetrical double LCC structure to balance reactive power and ensure a large output power and efficiency.

[0063] Figure 2 This circuit structure uses a fully controlled bridge design on both the primary and secondary sides, employing a phase-shift control method. s U is the primary-side equivalent DC voltage source. L U is the load voltage of the DC power supply. in i Lf1 U represents the output voltage and current of the primary-side inverter. out i Lf2 This refers to the input voltage and current of the secondary rectifier. Figure 3 The waveform diagram is for phase-shift control. For the phase shift angle of the inverter circuit, Here, θ represents the phase shift angle of the rectifier circuit, and θ represents the phase difference between the primary and secondary sides. Maximum power output is achieved when θ = -90°. Therefore, by simply changing... Adjust the output.

[0064] Modeling the circuit, without considering line resistance and losses, we have the following formulas for calculating the current in each branch with respect to the power supply voltage and load voltage:

[0065]

[0066] The voltage expressions on both sides are:

[0067]

[0068]

[0069] This leads to the formulas for calculating the AC input and output active power without considering line losses:

[0070]

[0071] (2) Calculation of system power and efficiency considering the losses of the bilateral converter.

[0072] The efficiency of the circuit is calculated, primarily considering the power losses of the rectifier and inverter circuits. The formula for calculating the conduction loss of the diode is:

[0073]

[0074] In the formula, U f For the threshold voltage, r D The equivalent on-state impedance, I is the phase angle. o This represents the effective value of the output current of the power converter, and I corresponds to the primary-side inverter circuit. Lf1 The secondary rectifier circuit corresponds to I. Lf2 .

[0075] The formula for calculating the conduction loss of a MOSFET is:

[0076]

[0077] In the formula, r DS This is the equivalent on-state impedance.

[0078] The full-bridge switching losses are:

[0079]

[0080] In the formula, e SW_ON To enable energy loss, e SW_OFF To shut off energy loss, U R I is the drain-source voltage. R Q is the source current. RR To recover the charge in reverse, I R_D This is the reference current for the anti-parallel diode. From the above equation, the expression for the total inverter loss can be obtained as follows:

[0081]

[0082] The expression for the total rectifier loss is:

[0083]

[0084] In summary, the overall power input of the system is P. s =P in +P loss_p The load output power is P L =P out -P loss_s The formula for calculating the overall system efficiency is:

[0085]

[0086] (3) High-efficiency bilateral collaborative control.

[0087] Dual phase-shift control adjusts the output by modifying the phase shift angles of the primary and secondary sides. The phase shift angle affects the power converter's losses; this is analyzed to achieve a low-loss adjustment method. Based on the above expression, the system efficiency is related to the primary and secondary voltages and the two sets of phase shift angles. Figure 4 for Contour plots showing the efficiency relationship at voltage ratios of 1, 0.6, and 0.2. Figure 5 The two sets of graphs, showing the contour plots of power at different voltage ratios, clearly illustrate the impact of the two phase shift angles on efficiency and power. The ratio of the secondary to the primary DC voltage affects the change in efficiency with the phase shift angle; as the voltage ratio decreases... and The greater the difference in the degree of impact on efficiency, the better. Figure 5 Regarding output power, the smaller the voltage ratio, the lower the overall system output power, but... The effect on power does not differ significantly with changes in voltage ratio. Therefore, to achieve high-efficiency output from the system, U... L with U S When the difference is large, that is, in the initial stage of charging, maintain As a constant value, it is mainly adjusted. The output is adjusted accordingly. Once the voltage rises to a certain value, it enters the constant voltage charging stage. At this point, the difference in the impact of the phase shift angle on the system efficiency and power is small. To achieve rapid adjustment of the system output, a secondary-side control method is used to realize constant voltage control.

[0088] Plot the power and efficiency curves for different values ​​of the primary and secondary phase angles, with each solid line corresponding to a primary phase shift angle. For a constant value, the phase shift angle of the secondary side corresponding to each dashed line is... It is a constant value. For a constant-value adjustment method, the efficiency changes little with the rate of change of power, while for For constant-value regulation, efficiency varies significantly with power. During control adjustment, the communication time between the primary and secondary sides limits the adjustment speed. Therefore, the primary-side inverter is first adjusted to determine the phase shift angle, and then the phase shift angle of the secondary-side rectifier is adjusted to achieve a rapid response to disturbances. Adjustment fixed The adjusted three-stage control strategy.

[0089] (4) Adaptive control of PID parameters based on BP neural network.

[0090] Artificial Neural Networks (ANNs) are empirical models that mimic the functions of biological neural networks. A neural network is a network composed of a large number of interconnected processing units. PID control requires adjusting three control actions. Backpropagation (BP) neural networks have the ability to approximate any nonlinear function. They are multilayer feedforward neural networks trained according to the error backpropagation algorithm. They can achieve optimal combination of PID control by learning the system performance, realizing parameter adaptive control during system operation. Since the dual LCC compensation network itself exhibits constant current characteristics, this control strategy is mainly used in the constant voltage output stage to achieve closed-loop control.

[0091] Using incremental digital PID, the formula is:

[0092] u(k)=u(k-1)+k p [e(k)-e(k-1)]+k i e(k)+k d [e(k)-2e(k-1)+e(k-2)]

[0093] u(k) is a function related to the PID coefficients, input, and error; therefore, the optimal control law can be trained using a BP neural network. A three-layer BP neural network structure is used as follows: Figure 7 As shown, the inputs here are set to a setpoint r, an output value y, and a deviation e, and the output of the output layer corresponds to k. p k i k d Since the three output parameters are non-negative, the hidden function of the output layer should be a non-negative Sigmoid function. For the hidden layer, a positive-negative symmetrical Sigmoid function can be selected. The PID output u(k) is the phase shift angle of the full-bridge rectifier / full-bridge inverter circuit.

[0094] To calculate the structure of a BP neural network, firstly, the output of the input layer of the BP neural network is represented as:

[0095]

[0096] Where j is the number of inputs. The input and output of the hidden layer are:

[0097]

[0098]

[0099] Where q is the number of nodes in the hidden layer. The number of weights between the input layer and the hidden layer is 3·q. The activation function is the hyperbolic tangent function, which is a positive-negative symmetric sigmoid function, and its function expression is:

[0100]

[0101] For the output layer of a neural network, its input and output expressions are as follows:

[0102]

[0103]

[0104] Where l is the number of output variables. The weights from the hidden layer to the output layer are 3·q. The activation function for the output layer nodes is the Sigmoid function, which is non-negative, and its expression is:

[0105]

[0106] Next is the calculation of the updated weights. The performance metric function is the square of the output error.

[0107]

[0108] By correcting the weighting coefficients of the network using gradient descent and adding an inertia term that allows the search to quickly converge to a global minimum, the formula for correcting the weighting coefficients of the output layer is first obtained:

[0109]

[0110] η is the learning rate, and α is the inertia coefficient. We obtain:

[0111]

[0112] Each of its terms can be obtained through calculation. Definition:

[0113]

[0114]

[0115] Then the formula for correcting the weighting coefficients of the hidden layer and the output layer can be determined:

[0116]

[0117]

[0118] This completes the algorithm for correcting the weight coefficients of the hidden layer and the output layer.

[0119] Figure 8 and Figure 9 This describes the adjustment process of weights and PID coefficients after a change in system load, with the disturbance occurring at 0.08s. Figure 10 This is a block diagram of the control circuit of the rectifier circuit. Figure 11 For the output of the neural network parameter adaptive constant voltage 300V control, the voltage value at both ends drops after the load changes by 0.05s. The overshoot under this control algorithm is -49V and the adjustment time is 0.015s. Compared with the traditional PID control, the overshoot is reduced by 15.9V and the adjustment time is shortened by 0.02s.

[0120] The efficiency characteristics of the bilateral coordinated control strategy are verified. Figure 12 That is, the corresponding bilateral phase shift angles when the voltage ratio is 0.2, 0.5, and 1. The relationship between the values ​​and transmission efficiency is discussed, where the nine sets of phase shift angles are (π, π / 4), (π, 3π / 8), (π, 2π / 4), (π, 3π / 4), (π, π), (3π / 4, π), (2π / 4, π), (3π / 8, π), and (π / 4, π). It can be concluded that, referring to the range of sets 5 to 9, the smaller the voltage ratio, the higher the transmission efficiency. This value will effectively improve the system output efficiency. As the voltage ratio increases, and The impact on system transmission efficiency is basically symmetrical, proving the effectiveness of three-stage control in improving system transmission efficiency. Figure 13 A flowchart illustrating the overall control of the dual-side wireless charging system.

[0121] Example 2:

[0122] Embodiment 2 of the present invention provides a bilateral cooperative control system for a wireless charging system. The wireless charging system includes at least: an inverter network and a primary compensation network connected to each other on the primary side, and a secondary compensation network and a rectifier network connected to each other on the secondary side. The primary compensation network is connected to the primary energy transmission coil, and the secondary compensation network is connected to the secondary energy receiving coil.

[0123] include:

[0124] The constant current charging module is configured as follows: During the constant current charging stage, the phase shift angle of the rectifier network is fixed, the phase shift angle of the inverter network is adjusted, and the load is charged with constant current to keep the output efficiency at its maximum value. It is determined whether the output current to the load is greater than the set threshold. If not, the constant current charging stage continues. If so, the constant voltage charging module process is executed.

[0125] The constant voltage charging module is configured to: end the constant current charging state, fix the phase shift angle of the inverter network, adaptively adjust the PID parameters based on the deep learning network, use the PID output as the phase shift angle of the rectifier network that needs to be adjusted, and perform constant voltage charging control and disturbance response control to keep the output efficiency at its maximum value.

[0126] The working methods of each module of the system are the same as the details of the bilateral cooperative control method of the wireless charging system provided in Embodiment 1, and will not be repeated here.

[0127] Example 3:

[0128] Embodiment 3 of the present invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the bilateral cooperative control method of the wireless charging system as described in Embodiment 1 of the present invention.

[0129] Example 4:

[0130] Embodiment 4 of the present invention provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the bilateral cooperative control method of the wireless charging system as described in Embodiment 1 of the present invention.

[0131] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0132] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0133] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0134] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0135] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0136] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A bilateral cooperative control method for a wireless charging system, characterized in that, The wireless charging system includes at least: an interconnected inverter network and a primary compensation network on the primary side, and an interconnected secondary compensation network and a rectifier network on the secondary side. The primary compensation network is connected to the primary energy transmission coil, and the secondary compensation network is connected to the secondary energy receiving coil. Includes the following processes: During the constant current charging stage, the phase shift angle of the rectifier network is fixed, and the phase shift angle of the inverter network is adjusted to perform constant current charging on the load so that the output efficiency is kept at its maximum value. It is determined whether the output current to the load is greater than the set threshold. If not, the constant current charging stage continues; if so, the next step is executed. After the constant current charging state ends, the phase shift angle of the inverter network is fixed. The PID parameters are adaptively adjusted based on the deep learning network. The output of the PID is used as the phase shift angle of the rectifier network that needs to be adjusted, so as to perform constant voltage charging control and disturbance response control to keep the output efficiency at its maximum value. Adaptive adjustment of PID parameters is achieved using a BP neural network. The weighting coefficients for the hidden and output layers of a BP neural network are: ； ； in, η For learning rate, α The inertia coefficient; As input to the hidden layer, The output of the input layer, The output of the hidden layer, This refers to the deviation between the secondary output and the set value. For the output of the PID, For secondary side output, k At the current sampling time, k-1 This refers to the previous sampling time.

2. The bilateral cooperative control method for a wireless charging system as described in claim 1, characterized in that, The inputs to the BP neural network are: the setpoint, the secondary output, and the deviation between the secondary output and the setpoint. The output of the BP neural network are the three adjustment parameters of the PID controller.

3. A bilateral cooperative control system for a wireless charging system, characterized in that, The wireless charging system includes at least: an interconnected inverter network and a primary compensation network on the primary side, and an interconnected secondary compensation network and a rectifier network on the secondary side. The primary compensation network is connected to the primary energy transmission coil, and the secondary compensation network is connected to the secondary energy receiving coil. include: The constant current charging module is configured as follows: During the constant current charging stage, the phase shift angle of the rectifier network is fixed, the phase shift angle of the inverter network is adjusted, and the load is charged with constant current to keep the output efficiency at its maximum value. It is determined whether the output current to the load is greater than the set threshold. If not, the constant current charging stage continues. If so, the constant voltage charging module process is executed. The constant voltage charging module is configured to: end the constant current charging state, fix the phase shift angle of the inverter network, adaptively adjust the PID parameters based on the deep learning network, use the PID output as the phase shift angle of the rectifier network that needs to be adjusted, and perform constant voltage charging control and disturbance response control to keep the output efficiency at its maximum value. Adaptive adjustment of PID parameters is achieved using a BP neural network. The weighting coefficients for the hidden and output layers of a BP neural network are: ； ； in, η For learning rate, α The inertia coefficient; As input to the hidden layer, The output of the input layer, The output of the hidden layer, This refers to the deviation between the secondary output and the set value. For the output of the PID, For secondary side output, k At the current sampling time, k-1 This refers to the previous sampling time.

4. The bilateral cooperative control system for the wireless charging system as described in claim 3, characterized in that, The inputs to the BP neural network are: the setpoint, the secondary output, and the deviation between the secondary output and the setpoint. The output of the BP neural network are the three adjustment parameters of the PID controller.

5. A computer-readable storage medium having stored thereon a program, characterized in that, When the program is executed by the processor, it implements the steps in the bilateral cooperative control method for a wireless charging system as described in claim 1 or 2.

6. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the bilateral cooperative control method for a wireless charging system as described in claim 1 or 2.

Images