Wireless charging power adaptive matching method based on multi-objective optimization

Abstract

The invention discloses a wireless charging power adaptive matching method based on multi-objective optimization, and particularly relates to the technical field of wireless charging. By introducing two complexity evaluation features of Pareto conflict density and local dominant index, a sorting complexity index model is constructed, sorting load is dynamically judged, a complexity reduction mechanism is triggered under the condition of high load, and non-dominant sorting overhead is effectively reduced; on the premise that the solution quality and diversity are guaranteed, the real-time performance and deployment feasibility of the algorithm in the embedded wireless charging system are improved, and finally efficient self-adaptive power matching control over different devices and environments is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of wireless charging, and in particular to a wireless charging power adaptive matching method based on multi-objective optimization. Background Art

[0002] Wireless charging adaptive power matching means that during the wireless charging process, the charging device (such as a charger) can automatically adjust the output power based on the power requirements and operating status of the charged device (such as a mobile phone or headphones) to achieve optimal charging efficiency and safety. This technology can avoid energy waste, device overheating, or slow charging caused by power mismatch, thereby improving the overall user experience.

[0003] The existing technology has the following shortcomings: In the existing technology, in high-dimensional optimization scenarios (such as involving four or more objectives such as efficiency, temperature, life, and harmonics), the non-dominated sorting step of the NSGA-II algorithm faces the problem of a sharp increase in computational complexity, and its time complexity is , where M is the number of targets and N is the population size. This computational explosion is particularly severe in embedded or real-time wireless charging systems, causing the optimization algorithm’s response time to be unable to meet millisecond-level control requirements, thus limiting its deployment and application in practical systems. Summary of the Invention

[0004] The purpose of the present invention is to provide a wireless charging power adaptive matching method based on multi-objective optimization to address the shortcomings of the background technology.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a wireless charging power adaptive matching method based on multi-objective optimization, comprising: Collect various key performance parameters of the wireless charging system and build a multi-objective optimization model; Construct the initial population based on the non-dominated sorting genetic algorithm and calculate the fitness value of each individual in the multi-objective space; Extract characteristic parameters for complexity evaluation from the current population, including Pareto conflict density and local dominance index; The Pareto conflict density and local dominance index are comprehensively calculated based on the preset complexity evaluation model to obtain the sorting complexity index value. This value is then compared with the preset threshold to determine whether there is a risk of a surge in sorting complexity. If the sorting complexity index value exceeds the preset threshold, the complexity reduction mechanism is triggered, including performing local non-dominated sorting on the high local dominance index area and adopting a fast pre-screening strategy for the low local dominance index area; Based on the improved ranking results, tournament selection, crossover, and mutation operations are performed to generate a new generation of individuals, and the optimization process is iteratively performed; The Pareto optimal solution set after dynamic adjustment and optimization is output, and the selected power matching parameters are configured into the wireless charging system to achieve adaptive charging strategies for different devices and environments.

[0006] Preferably, the acquisition of multiple key performance parameters of the wireless charging system includes: obtaining the transmitter input power and the receiver output power in real time through a dual-channel voltage / current sampler to calculate the charging efficiency parameters; monitoring the energy loss of key components in the system through thermistors and power sensors; placing temperature sensors at heating parts to obtain temperature rise data; and using a high-speed ADC combined with an FFT module to perform frequency domain analysis on the current signal to obtain harmonic interference indicators.

[0007] Preferably, the optimization objectives in the multi-objective optimization model include: maximizing charging efficiency, minimizing energy loss, minimizing temperature rise level, and minimizing harmonic interference index.

[0008] Preferably, individual The fitness of is a collection of multiple objective function values: ;in: is the i-th individual, corresponding to a wireless charging parameter combination, M is the number of objective functions in the multi-objective optimization, is the jth objective function in individual The value of and , if it satisfies all objective functions ; and there is at least one target ; then it is believed non-dominance .

[0009] Preferably, the Pareto conflict density extraction method is: set the current population to , each individual has a corresponding function value on M targets For any pair of targets , calculate the conflict density: Where, is the index of the degree of conflict between the pth objective function and the qth objective function in the current population; R is the number of individuals in the current population; For individuals The function value on the objective function p, For individuals Function value on the objective function q; For individuals Relative to the changing trend of its neighboring individuals on the target p, sign is the sign function, and the average of all target pairs is obtained to obtain the Pareto conflict density PCD, which is expressed as: .

[0010] Preferably, the local dominant index extraction method is: for each individual , calculate its nearest k neighbors in the target space; count how many neighbors there are in the neighborhood satisfy non-dominance ; Define the local dominance index of an individual The calculation expression is: ; Average the entire population to obtain the overall local dominance index LDI, which is expressed as: ; Where S is the total number of individuals.

[0011] Preferably, the Pareto conflict density and the local dominance index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as inputs of the machine learning model. The machine learning model uses the prediction target of the sorting complexity index value label of each group of comprehensive feature vectors, and uses minimizing the sum of the prediction errors of all sorting complexity index value labels as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence, and the model training is stopped. The sorting complexity index value is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0012] Preferably, the obtained sorting complexity index value is compared with a preset threshold. If the sorting complexity index value is greater than or equal to the preset threshold, it is considered that the current population has a risk of a surge in sorting complexity, and the corresponding complexity reduction processing mechanism is triggered; if the sorting complexity index value is less than the preset threshold, it is considered that the current sorting load is within a controllable range, and the standard global non-dominated sorting process continues to be executed.

[0013] Preferably, if it is determined that there is a risk of a surge in sorting complexity, the complexity reduction mechanism includes: The current population is divided into high local dominance index area and low local dominance index area according to the local dominance index; Perform an exact non-dominated sort on regions with high local dominance index; A fast heuristic pre-ranking strategy is adopted for low local dominance index areas, including single-target mapping ranking or weighted scoring ranking; The sequencing results of the two regions were combined for subsequent genetic operations.

[0014] Preferably, the performing of genetic operations includes: performing tournament selection according to the sorting results, selecting individuals with high fitness as parents; performing a crossover operation on the selected parent individuals according to a preset probability to generate offspring individuals; performing parameter perturbations on the offspring individuals according to a preset probability to complete a mutation operation; and merging the offspring with the selected parent individuals to form the next generation population.

[0015] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. This invention effectively quantifies the computational burden of non-dominated sorting by introducing Pareto conflict density and local dominance index as complexity assessment features. It also combines machine learning models to predict sorting complexity, enabling dynamic assessment and management of sorting workloads. When excessive computational workloads are detected, the invention further employs local precise sorting and rapid pre-screening through a partitioning strategy to reduce overall computational complexity, thereby resolving the issue of slow computational response associated with the traditional NSGA-II algorithm in embedded or real-time systems.

[0016] 2. This invention also performs genetic operations and iterative updates based on the optimized population results, ultimately outputting a Pareto-optimal solution set suitable for practical application scenarios. The selected power matching parameters are then configured in the wireless charging system, enabling efficient and adaptive charging control for multiple types of devices and complex environments. This integrated approach not only improves optimization efficiency and system real-time performance, but also offers robust engineering deployment capabilities, making it suitable for practical scenarios requiring high-precision, low-latency, and multi-objective coordination in wireless charging systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0018] Figure 1 This is a mind map of the method of the present invention. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0020] For examples, see Figure 1 As shown, the wireless charging power adaptive matching method based on multi-objective optimization described in this embodiment includes: Collect various key performance parameters of the wireless charging system and build a multi-objective optimization model; Construct the initial population based on the non-dominated sorting genetic algorithm and calculate the fitness value of each individual in the multi-objective space; Extract characteristic parameters for complexity evaluation from the current population, including Pareto conflict density and local dominance index; The Pareto conflict density and local dominance index are comprehensively calculated based on the preset complexity evaluation model to obtain the sorting complexity index value. This value is then compared with the preset threshold to determine whether there is a risk of a surge in sorting complexity. If the sorting complexity index value exceeds the preset threshold, the complexity reduction mechanism is triggered, including performing local non-dominated sorting on the high local dominance index area and adopting a fast pre-screening strategy for the low local dominance index area; Based on the improved ranking results, tournament selection, crossover, and mutation operations are performed to generate a new generation of individuals, and the optimization process is iteratively performed; The Pareto optimal solution set after dynamic adjustment and optimization is output, and the selected power matching parameters are configured into the wireless charging system to achieve adaptive charging strategies for different devices and environments.

[0021] In this embodiment, the wireless charging system includes a transmitter and a receiver, and the system structure includes a power transmitter module, a magnetic coupling resonant circuit, a rectifier and filter module, and a system controller.

[0022] Charging efficiency parameter η, using dual-channel voltage / current samplers to measure the transmitter input power and the receiving end output power , calculate charging efficiency in real time: The sampling period is set to every 10 ms, and the average efficiency and instantaneous fluctuation are calculated using a continuous sliding window.

[0023] Energy loss parameters , through precision thermistors and resistor power sensors to monitor the power loss of each component (coil, inductor, capacitor, MOSFET) in real time: ;in is the equivalent series resistance of the component, is the voltage drop of the switching device, is the current flowing through.

[0024] Temperature rise control parameter ΔT, arrange NTC thermistors or DS18B20 temperature sensors at key locations (transformer, MOS tube, coil center) on the transmitter and receiver ends. Set the reference temperature , real-time collection of current working temperature , the temperature rise is obtained: ; and evaluate the temperature rise trend in combination with the time function to reflect the effect of continuous heat accumulation.

[0025] The harmonic interference parameter THD uses a high-speed ADC with a fast Fourier transform (FFT) module to sample the AC current signal on the transmitting side. Calculate the total harmonic distortion rate: ;in is the nth harmonic current, is the fundamental component, usually in the range of 2kHz to 200kHz, and N is the upper limit of the harmonic order (such as 20).

[0026] Combining the above key performance indicators, the following multi-objective function set is established: Maximize charging efficiency: ; Minimize energy loss: ; Minimize temperature rise levels: ; Minimize harmonic distortion: ; The variable x represents the optimized system parameter vector, including but not limited to power output level, switching frequency, matching capacitance value, coil spacing, modulation duty cycle, etc.

[0027] The system controller uses an STM32H7 or higher-performance embedded chip. All acquired signals are input through an isolated ADC (such as the ADS131M04) and transmitted to the embedded main controller via DMA. FPGA coprocessing is used for FFT acceleration calculation. All parameters are normalized to 32-bit floating-point format to facilitate interface with the NSGA-II algorithm.

[0028] Through this implementation, we can systematically collect multi-dimensional key parameters reflecting wireless charging performance, build an accurate, adjustable, and real-time iterative multi-objective optimization model, and provide complete input support for subsequent adaptive power matching based on NSGA-II.

[0029] In NSGA-II, each individual The fitness of is not a single value, but a collection of multiple objective function values: ;in: is the i-th individual, corresponding to a wireless charging parameter combination, M is the number of objective functions in the multi-objective optimization, is the jth objective function in individual The fitness evaluation does not directly synthesize a single value, but is sorted and screened through two key processes: non-dominated sorting and crowding distance calculation.

[0030] For two individuals and , if: On all objective functions ; and there is at least one target ; then it is believed non-dominance .

[0031] The expression for calculating the crowding distance is: ; Where: M is the total number of targets, 、 For individuals The adjacent sorted individual values ​​on the j-th target, is the maximum / minimum value of the j-th objective (used for normalization); The larger the crowding distance, the more "sparse" the solution is in the solution space, which helps to preserve diversity.

[0032] Pareto conflict density is used to quantify the degree of conflict between multiple objectives in the current population, that is, whether the improvement of a certain objective function is often accompanied by the deterioration of other objectives, reflecting the non-cooperation of the optimization space.

[0033] The extraction method is: set the current population to , each individual has a corresponding function value on M targets ; For any pair of targets , calculate the conflict density: Where, is the conflict degree index (conflict density) between the p-th objective function and the q-th objective function in the current population; R is the number of individuals in the current population; For individuals The function value on the objective function p, For individuals Function value on the objective function q; For individuals Relative to the changing trend of its neighboring individuals on the target p, it can be approximated as , that is, the first-order difference; sign is the sign function, defined as: ; Average all target pairs to obtain the Pareto conflict density PCD, which is expressed as: ; In the formula, PCD∈[0,1], close to 1 indicates high conflict and high pressure of multi-objective optimization; close to 0 indicates coordination between objectives, which is suitable for conventional non-dominated sorting processing.

[0034] The local dominance index is used to measure the degree to which a solution is non-dominated by other individuals in its neighborhood and to identify the spatial distribution of non-dominated sorting pressure in the population.

[0035] The local dominant index extraction method is: For each individual , calculate its nearest k neighbors in the target space (usually k=10); Count how many neighbors there are in the neighborhood satisfy non-dominance ; Define the local dominance index of an individual The calculation expression is: ; Average the entire population to obtain the overall local dominance index LDI, which is expressed as: ; Where S is the total number of individuals.

[0036] The obtained overall local dominance index LDI is compared with the preset local dominance index reference threshold. If the local dominance index LDI is greater than or equal to the local dominance index reference threshold, it means that the non-dominated sorting operation is mainly concentrated in the local subspace in the population, and there is a problem of local excessive computational load. It is suitable to trigger a sorting substitution strategy based on local areas to reduce the overall computational complexity. If the local dominance index LDI is less than the reference threshold, it means that the non-dominated relationship is relatively evenly distributed in the population, the sorting operation load is dispersed, and the standard global non-dominated sorting operation can continue to be performed to maintain the comprehensive exploration and diversity of the solution.

[0037] The Pareto conflict density and local dominance index are converted into comprehensive feature vectors, which are used as inputs of the machine learning model. The machine learning model uses the sorting complexity index value label predicted by each set of comprehensive feature vectors as the prediction target, and minimizes the sum of prediction errors of all sorting complexity index value labels as the training target. The machine learning model is trained until the sum of prediction errors reaches convergence, and the model training is stopped. The sorting complexity index value is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0038] The obtained sorting complexity index value is compared with the preset threshold. If the sorting complexity index value is greater than or equal to the preset threshold, it is considered that the current population is at risk of a surge in sorting complexity, and the corresponding complexity reduction processing mechanism (such as local sorting, target compression, etc.) is triggered; if the sorting complexity index value is less than the preset threshold, it is considered that the current sorting load is within a controllable range, and the standard global non-dominated sorting process continues.

[0039] When the sorting complexity index value is greater than or equal to the preset threshold, the complexity reduction mechanism is triggered, including performing local non-dominated sorting on the high local dominance index area and adopting a fast pre-screening strategy for the low local dominance index area. Specifically: If the local dominant index LDI is greater than or equal to the local dominant index reference threshold, it is marked as a high local dominant index area; if the local dominant index LDI is less than the reference threshold, it is marked as a low local dominant index area.

[0040] For individuals in high LDI areas, accurate NSGA-II non-dominated sorting is performed separately to ensure that the optimal solutions in local dense areas can be accurately identified to prevent degradation or misscreening.

[0041] For individuals in low LDI areas, the complete non-dominated sorting process is skipped; instead, a fast heuristic pre-sorting strategy (such as single target projection, weighted scoring method) is used to screen the top-ranked individuals; redundant sorting calculations are reduced to improve overall operation efficiency.

[0042] Merge the sorting results of high LDI areas and the pre-sorting results of low LDI areas; Perform subsequent genetic operations (crossover, mutation, etc.) such as tournament selection; generate the next generation population and continue to enter the NSGA-II iterative cycle.

[0043] From the improved sorting results, multiple candidate individuals are randomly selected according to their non-dominated rank and crowding information. In each group of candidate individuals, individuals with higher fitness are retained first based on ranking priority and distribution diversity evaluation; The selected individuals are formed into the parent population to provide a genetic basis for subsequent operations.

[0044] Select several pairs of individuals from the parent population and perform crossover operations according to the set probability; Combining the parameter information of two individuals to generate a new individual, thus forming a new parameter area exploration in the solution space; Ensure that the crossover operation does not destroy the diversity of the population while enhancing the ability to search for the global optimal solution.

[0045] In the newly generated individuals, a small range of perturbations is performed on certain parameters with a certain probability; Mutation operations help to escape local optima and improve the overall search capability of the population; Ensure that the variation range is within the system safety range to avoid unreasonable parameters causing abnormalities in subsequent simulations or system operations.

[0046] Merge the offspring individuals generated through crossover and mutation with some of the elite individuals of the parent generation to form the next generation population; Repeated optimization process, including multi-objective function evaluation, sorting complexity judgment, complexity reduction processing, selection and update; The process is iterated until the termination condition is met, such as the number of iterations reaches a set upper limit or the population convergence meets the set criteria.

[0047] In the final generation of population, the solutions on the non-dominated frontier are screened out to form a Pareto optimal solution set; This solution set reflects the optimal trade-off relationship between multiple objectives, covering different optimization directions such as high efficiency, low loss, low temperature rise, and low harmonics.

[0048] Based on actual application requirements (such as device type, ambient temperature, power supply conditions, etc.), a set of power matching parameters that best matches the current strategy is selected from the Pareto optimal solution set; Send the selected parameters to the wireless charging system control module to dynamically configure output power, modulation frequency, matching network parameters, etc. Realize adaptive and efficient wireless charging control for different devices and different operating environments.

[0049] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0050] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0051] It should be understood that the term "and / or" herein is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone, where A and B may be singular or plural. In addition, the character " / " herein generally indicates that the objects associated with each other are in an "or" relationship, but it may also indicate an "and / or" relationship, which can be understood by referring to the context. A person of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0052] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A wireless charging power adaptive matching method based on multi-objective optimization, characterized by: include: Collect various key performance parameters of the wireless charging system and build a multi-objective optimization model; Construct the initial population based on the non-dominated sorting genetic algorithm and calculate the fitness value of each individual in the multi-objective space; Extract characteristic parameters for complexity evaluation from the current population, including Pareto conflict density and local dominance index; The Pareto conflict density and local dominance index are comprehensively calculated based on the preset complexity evaluation model to obtain the sorting complexity index value. This value is then compared with the preset threshold to determine whether there is a risk of a surge in sorting complexity. If the sorting complexity index value exceeds the preset threshold, the complexity reduction mechanism is triggered, including performing local non-dominated sorting on the high local dominance index area and adopting a fast pre-screening strategy for the low local dominance index area; Based on the improved ranking results, tournament selection, crossover, and mutation operations are performed to generate a new generation of individuals, and the optimization process is iteratively performed; The Pareto optimal solution set after dynamic adjustment and optimization is output, and the selected power matching parameters are configured into the wireless charging system to achieve adaptive charging strategies for different devices and environments.

2. The wireless charging power adaptive matching method based on multi-objective optimization according to claim 1, characterized in that: The method for collecting various key performance parameters of the wireless charging system includes: obtaining the transmitter input power and the receiver output power in real time through a dual-channel voltage / current sampler to calculate the charging efficiency parameters; monitoring the energy loss of key components in the system through thermistors and power sensors; placing temperature sensors at heating parts to obtain temperature rise data; and using a high-speed ADC combined with an FFT module to perform frequency domain analysis on the current signal to obtain harmonic interference indicators.

3. The wireless charging power adaptive matching method based on multi-objective optimization according to claim 2, characterized in that: The optimization objectives in the multi-objective optimization model include: maximizing charging efficiency, minimizing energy loss, minimizing temperature rise level, and minimizing harmonic interference index.

4. The wireless charging power adaptive matching method based on multi-objective optimization according to claim 1, characterized in that: individual The fitness of is a collection of multiple objective function values: ;in: is the i-th individual, corresponding to a wireless charging parameter combination, M is the number of objective functions in the multi-objective optimization, is the jth objective function in individual The value of and , if it satisfies all objective functions ; and there is at least one target ; then it is believed non-dominance .

5. The wireless charging power adaptive matching method based on multi-objective optimization according to claim 4, characterized in that: The Pareto conflict density extraction method is: set the current population to be , each individual has a corresponding function value on M targets For any pair of targets , calculate the conflict density: Where, is the index of the degree of conflict between the pth objective function and the qth objective function in the current population; R is the number of individuals in the current population; For individuals The function value on the objective function p, For individuals Function value on the objective function q; For individuals Relative to the changing trend of its neighboring individuals on the target p, sign is the sign function, and the average of all target pairs is obtained to obtain the Pareto conflict density PCD, which is expressed as: .

6. The wireless charging power adaptive matching method based on multi-objective optimization according to claim 5, characterized in that: The local dominant index extraction method is: for each individual , calculate its nearest k neighbors in the target space; count how many neighbors there are in the neighborhood satisfy non-dominance ; Define the local dominance index of an individual The calculation expression is: ; Average the entire population to obtain the overall local dominance index LDI, which is expressed as: ; Where S is the total number of individuals.

7. The wireless charging power adaptive matching method based on multi-objective optimization according to claim 6, characterized in that: The Pareto conflict density and local dominance index are converted into comprehensive feature vectors, which are used as inputs of the machine learning model. The machine learning model uses the sorting complexity index value label predicted by each set of comprehensive feature vectors as the prediction target, and minimizes the sum of prediction errors of all sorting complexity index value labels as the training target. The machine learning model is trained until the sum of prediction errors reaches convergence, and the model training is stopped. The sorting complexity index value is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

8. The wireless charging power adaptive matching method based on multi-objective optimization according to claim 7, characterized in that: The obtained sorting complexity index value is compared with the preset threshold. If the sorting complexity index value is greater than or equal to the preset threshold, it is considered that the current population is at risk of a surge in sorting complexity, and the corresponding complexity reduction processing mechanism is triggered; if the sorting complexity index value is less than the preset threshold, it is considered that the current sorting load is within a controllable range, and the standard global non-dominated sorting process continues.

9. The wireless charging power adaptive matching method based on multi-objective optimization according to claim 8, characterized in that: If it is determined that there is a risk of a surge in sorting complexity, the complexity reduction mechanism includes: The current population is divided into high local dominance index area and low local dominance index area according to the local dominance index; Perform an exact non-dominated sort on regions with high local dominance index; A fast heuristic pre-ranking strategy is adopted for low local dominance index areas, including single-target mapping ranking or weighted scoring ranking; The sequencing results of the two regions were combined for subsequent genetic operations.

10. The wireless charging power adaptive matching method based on multi-objective optimization according to claim 9, characterized in that: The genetic operation includes: performing tournament selection according to the sorting results to select individuals with high fitness as parents; performing a crossover operation on the selected parent individuals according to a preset probability to generate offspring individuals; performing parameter perturbations on the offspring individuals according to a preset probability to complete a mutation operation; and merging the offspring with the selected parent individuals to form the next generation population.

Images