Portable wireless charging electronic system and method

Abstract

The invention relates to the field of wireless charging, and discloses a portable wireless charging electronic system and method, and the method comprises the steps: obtaining the electric quantity of a battery and the inclination or movement state data of equipment through an input system of the wireless charging equipment, and carrying out the analysis through combining with an electromagnetic field intensity algorithm, and constructing a battery charging environment data set of the equipment; performing dynamic feature extraction on the battery charging environment data set, and constructing an equipment charging state model based on a real-time electromagnetic field simulation algorithm; whether the charging process is stable or not is judged based on the charging efficiency change condition, if yes, the periodic change result of the charging efficiency is recorded, dynamic adjustment is conducted in combination with equipment position information, and the electromagnetic field coupling effect is optimized; according to the adjusted electromagnetic field coupling effect, applying a multi-dimensional real-time feedback algorithm to carry out environmental adaptability correction on the charging efficiency; and on the basis of the optimized charging strategy, the charging process is monitored in real time in combination with an equipment state detection system. The method has the advantage of improving the charging efficiency.

Description

Technical Field

[0001] The present invention relates to the field of wireless charging, and specifically to a portable wireless charging electronic system and method. Background Art

[0002] In mobile usage scenarios, the negative impact of the angle change of portable wireless charging devices on the charging effect is an important technical challenge. Traditional wireless charging systems are usually based on the principles of electromagnetic induction or electromagnetic resonance, which require a relatively precise alignment between the charger and the device. When the device undergoes an angle change during use, the energy transfer efficiency between the charger and the device is significantly reduced. Especially when the device is tilted or moving, the coupling efficiency of the electromagnetic field changes, resulting in power loss or a significant slowdown in the charging speed, or even a complete interruption of the charging process. Users often need to manually adjust the position when using the device, increasing the inconvenience of operation. Therefore, it is necessary to design a portable wireless charging electronic system and method that can improve the charging efficiency. Summary of the Invention

[0003] Aiming at the deficiencies of the prior art, the present invention provides a portable wireless charging electronic system and method, which has the advantage of improving the charging efficiency and solves the problems in the above background art.

[0004] To achieve the above object of improving the charging efficiency, the present invention provides the following technical solution: A portable wireless charging electronic method, comprising the following steps:

[0005] Obtain the battery power and the data of the device tilt or movement state through the input system of the wireless charging device, and construct a battery charging environment data set of the device by combining the electromagnetic field strength algorithm analysis;

[0006] Perform dynamic feature extraction on the battery charging environment data set, construct a device charging state model based on the real-time electromagnetic field simulation algorithm, introduce an adaptive compensation mechanism to optimize and train the charging state model, and monitor the change of the charging efficiency in real time during the optimization training process;

[0007] Based on the change of the charging efficiency, judge whether the charging process is stable. If it is stable, record the phased change result of the charging efficiency, and perform dynamic adjustment in combination with the device position information to optimize the electromagnetic field coupling effect;

[0008] According to the adjusted electromagnetic field coupling effect, apply a multi-dimensional real-time feedback algorithm to correct the charging efficiency for environmental adaptability, extract correction parameters, and dynamically adjust the charging strategy to optimize the charging process;

[0009] Based on the optimized charging strategy, in combination with the device state detection system, monitor the charging process in real time and automatically adjust the charging method.

[0010] Preferably, the process of constructing the battery charging environment dataset of the device is as follows:

[0011] Collect multi-source raw charging data through a wireless charging device;

[0012] Obtain the tilt angle and acceleration parameters of the device;

[0013] Construct a multi-dimensional data vector, analyze it in combination with the electromagnetic field strength algorithm, and dynamically calculate the electromagnetic coupling strength index according to the position change of the device relative to the charging coil;

[0014] Fuse the time series information and integrate the charging status records of different time segments into the charging environment dataset.

[0015] Preferably, the process of dynamically extracting features from the battery charging environment dataset is as follows:

[0016] Use the sliding time window method to segment the battery charging environment dataset, and extract the charging voltage, current fluctuation trend, and electromagnetic field strength change rate within each time segment;

[0017] Construct a feature vector for each time segment and calculate the statistical features;

[0018] Based on the anomaly detection mechanism based on the change rate, identify short-term mutation signals and mark them as feature mutation events;

[0019] Merge the features of all time segments to construct a multi-dimensional dynamic feature matrix.

[0020] Preferably, the process of constructing the device charging status model based on the real-time electromagnetic field simulation algorithm is as follows:

[0021] Use the physical modeling framework, combine the numerical information in the dynamic feature matrix, and simulate the current induction charging process;

[0022] During the electromagnetic simulation process, establish the mapping relationship between the charging input and the efficiency output;

[0023] Train and optimize the simulation model through historical data samples to form a device charging status model based on real-time input data output.

[0024] Preferably, the process of optimizing and training the charging status model by introducing an adaptive compensation mechanism is as follows:

[0025] Compare the real-time observed charging efficiency with the predicted value of the status model, calculate the error residual and define it as the performance deviation function;

[0026] Introduce an adaptive compensation mechanism and automatically adjust the parameters based on the performance deviation function;

[0027] Using a regulator based on reinforcement learning, a reward function is dynamically generated according to the feedback of historical charging effects to adjust the model optimization path.

[0028] Preferably, the process of judging whether the charging process is stable is as follows:

[0029] Real-time monitor the power output, efficiency curve, battery temperature rise rate, and attitude change amplitude during the charging process;

[0030] Calculate the change rate of charging efficiency within a continuous time window and compare it with a set threshold;

[0031] If the change rate of charging efficiency within the continuous time window is less than the set threshold, it is determined that the current charging process is stable;

[0032] If the change rate of charging efficiency within the continuous time window is greater than or equal to the set threshold, it is determined that the current charging process is unstable.

[0033] Preferably, the process of applying a multi-dimensional real-time feedback algorithm to correct the charging efficiency for environmental adaptability is as follows:

[0034] Obtain external environmental variable information and construct a mapping function between environmental variables and charging efficiency based on a deep neural network model;

[0035] Input the current environmental state into the mapping function and output a correction parameter vector.

[0036] Preferably, the process of dynamically adjusting the charging strategy is as follows:

[0037] Based on the correction parameters and the stability judgment result, determine and switch the currently adopted charging mode;

[0038] Control the output power amplitude and frequency range of the transmitting end;

[0039] When detecting the movement or attitude adjustment of the device, dynamically adjust the coil excitation mode and time series waveform to maintain a stable coupling state.

[0040] Preferably, the process of real-time monitoring the charging process and automatically adjusting the charging method is as follows:

[0041] Through the central control unit, perform multi-channel data fusion analysis to judge whether there is a risk in the current charging method;

[0042] If it is detected that the risk factor exceeds the safety threshold, immediately call the most suitable charging method for the current state to replace the original mode.

[0043] A portable wireless charging electronic system includes:

[0044] Environmental data acquisition module: used to obtain perception data, and combined with the electromagnetic field strength parameters, construct a battery charging environment dataset for the device;

[0045] Charging state modeling module: used to extract dynamic features from environmental data, construct a charging state model based on real-time electromagnetic field simulation, and introduce an adaptive compensation mechanism to optimize the model training process;

[0046] Charging stability evaluation module: used to monitor the change of charging efficiency, judge whether the charging process is stable, and record stage efficiency data and dynamically adjust position information under stable conditions;

[0047] Charging strategy optimization module: used to apply a multi-dimensional real-time feedback algorithm according to the electromagnetic field coupling effect, correct the environmental adaptability of the charging efficiency, and generate correction parameters;

[0048] Charging control module: used to perform real-time monitoring and automatic charging method adjustment of the charging process based on the optimized charging strategy and combined with device status detection.

[0049] Compared with the prior art, the present invention provides a portable wireless charging electronic system and method, which has the following beneficial effects:

[0050] The present invention obtains the battery power and the tilt or movement state data of the device through the input system of the wireless charging device, and combined with the electromagnetic field strength algorithm analysis, can comprehensively collect the environmental information during the charging process, construct an accurate battery charging environment dataset, and provide a basis for the subsequent establishment of the charging state model. Based on the battery charging environment dataset, combined with real-time electromagnetic field simulation and adaptive compensation mechanism, the system can dynamically optimize the charging state model, improve the charging efficiency and stability. By real-time monitoring and analysis of the charging efficiency, judge the stability of the charging process, and perform electromagnetic field coupling optimization when stable, adjust the charging strategy to adapt to environmental changes, and ensure the charging process is efficient, stable and safe. Based on the optimized charging strategy and real-time device status monitoring, the system can intelligently adjust the charging method, improve the overall performance and user experience of the charging process. Brief Description of the Drawings

[0051] Figure 1 It is a schematic diagram of the method of the present invention;

[0052] Figure 2 It is a schematic diagram of the structure of the present invention. Detailed Embodiment

[0053] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0054] Embodiment 1

[0055] Please refer to Figure 1 As shown, a portable wireless charging electronic method according to an embodiment of the present invention includes the following steps:

[0056] S1: Through the input system of the wireless charging device, obtain battery power and device tilt or movement status data, and construct a battery charging environment data set for the device by combining electromagnetic field strength algorithm analysis.

[0057] The process of constructing the battery charging environment data set in S1 is as follows:

[0058] Collect multi-source raw charging data including remaining battery power, voltage, current, temperature, charging frequency, and spatial attitude data through the wireless charging device;

[0059] Obtain the tilt angle and acceleration parameters of the device; perform denoising and stabilization processing on the sensor output signal by combining the attitude fusion algorithm, and calculate the tilt angle corresponding to the current attitude of the device; use the tilt angle and acceleration parameters as spatial dynamic state quantities.

[0060] Construct a multi-dimensional data vector for characterizing the charging environment characteristics, combine electromagnetic field strength algorithm analysis, and dynamically calculate the electromagnetic coupling strength index according to the position change of the device relative to the charging coil; after standardizing various collected charging-related parameters, combine and construct a multi-dimensional data vector including dimensions such as voltage, current, power, temperature, charging frequency, tilt angle, and acceleration; based on the electromagnetic field strength analysis algorithm, combine the device's spatial attitude and its position information such as distance and angle relative to the charging coil, and dynamically calculate the electromagnetic coupling strength between it and the charging transmitting coil; record the change trend of the coupling strength index in different spatial states to evaluate the energy transmission efficiency and position matching degree during wireless charging.

[0061] Fuse the timing information, integrate the charging status records of different time segments into a charging environment data set; record a complete multi-dimensional vector state for each time segment, and attach a time stamp and device position information; through methods such as window sliding, feature smoothing, or key frame extraction, integrate and summarize the multi-period state information during the entire charging process to form a charging environment data set representing the current device charging environment state.

[0062] The battery power and the tilt or movement state data of the device are obtained through the input system of the wireless charging device, and analyzed in combination with the electromagnetic field strength algorithm, so as to comprehensively understand the charging physical environment of the device during actual use. This step provides a reliable multi-source data basis for the accurate construction of subsequent models and the dynamic adaptation of charging strategies by constructing a battery charging environment data set including information such as position, attitude, power, and electromagnetic characteristics, significantly improving the system's perception ability of complex charging states.

[0063] S2: Dynamically extract features from the battery charging environment data set, construct a device charging state model based on the real-time electromagnetic field simulation algorithm, introduce an adaptive compensation mechanism to optimize and train the charging state model, and monitor the change of charging efficiency in real time during the optimization training process.

[0064] The process of dynamically extracting features from the battery charging environment data set in S2 is as follows:

[0065] The sliding time window method is used to segment the battery charging environment data set, and the charging voltage, current fluctuation trend, and electromagnetic field strength change rate within each time period are extracted; set the sliding time window parameters with a fixed length, and define the window sliding step size to achieve continuous coverage of the data; the original charging environment data set is sliced along the time axis so that each window segment contains a certain number of continuous data points; ensure that the sliding window covers the entire charging process data to form multiple time period segments for subsequent dynamic feature extraction; perform trend analysis on the charging voltage and current data within each window segment, including the judgment of rising, falling, or stable states; calculate the change rate of the electromagnetic field strength within each time period, and use the difference method or the method of fitting the derivative to obtain the change value per unit time; at the same time, record the fluctuation amplitude and frequency of the voltage and current to provide support for the evaluation of charging stability.

[0066] Construct a feature vector for each time segment, and calculate statistical features such as mean, variance, maximum / minimum value, and change slope; calculate the mean, standard deviation, maximum value, minimum value, and linear fitting slope of each key parameter within the sliding window respectively; use normalization or standardization processing to improve the stability of the features in the subsequent model; arrange the above statistical features in sequence to form a complete time segment feature vector, representing the charging behavior characteristics within that time period.

[0067] Based on the anomaly detection mechanism based on the change rate identification, identify short-term mutation signals and mark them as feature mutation events; establish a change rate threshold model, and when the change rate of voltage, current, or electromagnetic field strength per unit time exceeds the preset threshold, it is determined as a mutation behavior; mark the time point and related parameters of the mutation, and record the mutation type; mark this time period as a "feature mutation event" for anomaly state identification or special working condition analysis in the model.

[0068] Merge all time - period features to construct a multi - dimensional dynamic feature matrix, providing a dynamic input basis for the charging state model; arrange the feature vectors extracted in each time period in chronological order to form a multi - dimensional dynamic feature matrix; each row of the matrix corresponds to the state features of a time window, and each column corresponds to a statistical feature index, constituting a time - series continuous feature description structure; finally, use the dynamic feature matrix as input data and send it to the subsequent charging state modeling module to describe the dynamic evolution law during the charging process.

[0069] The process of constructing the device charging state model based on the real - time electromagnetic field simulation algorithm in S2 is as follows:

[0070] Use a physical modeling framework that includes the law of electromagnetic field induction, combined with the numerical information about the device attitude and electromagnetic coupling in the dynamic feature matrix, to simulate the inductive charging process at the current moment; construct an electromagnetic field simulation model based on Maxwell's equations, and establish a physical scenario that includes the charging coil structure, device position, relative attitude, and electromagnetic coupling factor; input the key variables such as the real - time attitude parameters of the device, electromagnetic field intensity, distance between coils, and angle deviation extracted from the dynamic feature matrix; call finite - element simulation (such as FEM) or equivalent - circuit modeling methods to simulate and deduce the charging process at a given moment, and output results such as induced current, voltage, and electromagnetic coupling efficiency; the simulation process can be carried out cyclically, supporting the dynamic simulation of the charging state for each time segment to achieve continuous - time modeling.

[0071] During the electromagnetic simulation process, consider parameters such as the position error between coils, magnetic field intensity distribution, and magnetic flux density change, and establish a mapping relationship between charging input and efficiency output; introduce spatial error parameters such as horizontal offset, vertical displacement, and rotation angle between coils in the electromagnetic simulation model to simulate the pose instability factors in the actual use process; conduct grid analysis on the magnetic field intensity distribution map generated during the simulation process, and calculate the magnetic flux density, magnetic field leakage range, and induced energy concentration area at each position; extract the corresponding relationship between charging input power, magnetic field action intensity, coil voltage / current, and output efficiency according to the changes in various parameters.

[0072] The simulation model is trained and optimized using historical data samples to form a device charging status model that outputs based on real-time input data; historical charging data samples are called, including attitude parameters, electromagnetic environment data, input power, and final charging efficiency records during the actual device charging process; the above samples are compared with the output of the simulation model, and the model parameters are finely tuned using supervised learning methods to reduce simulation errors; machine learning algorithms are introduced to iteratively train the simulation model to improve the generalization ability of the model under complex working conditions; finally, a device charging status model that quickly predicts the current charging status based on real-time input is formed, providing a basis for subsequent adaptive compensation and strategy adjustment.

[0073] The process of optimizing and training the charging status model by introducing an adaptive compensation mechanism in S2 is as follows:

[0074] Compare the real-time observed charging efficiency with the predicted value of the status model, calculate the error residual, and define it as the performance deviation function; during the charging process, the system will collect the current actual charging efficiency in real time; according to the previously trained charging status model, input the environmental characteristics such as the attitude and electromagnetic field at the current moment to obtain the corresponding predicted charging efficiency value; compare the real-time observed value η real (t) with the model predicted value η pred (t), calculate the residual value, that is, the error term: Δη(t) = η real (t) - η pred (t); construct a performance deviation function based on this error value, such as using a squared loss function or a weighted error evaluation function, to measure the deviation between the current model and the actual environment; the performance deviation function will be used as the adjustment basis for the subsequent compensation mechanism.

[0075] Introduce an adaptive compensation mechanism to automatically adjust parameters based on the performance deviation function, including the magnetic field strength weight, attitude compensation factor, etc.; the system will analyze the main error sources based on the output of the current performance deviation function, such as the reduction of magnetic field coupling caused by attitude changes; dynamically adjust the key influencing factors, for example: increase or decrease the magnetic field strength weight coefficient, adjust the influence ratio of electromagnetic induction on efficiency estimation in the model; add an attitude compensation factor to the device tilt angle parameter to correct the non-linear influence of attitude changes on charging performance; the adjusted parameters will act on the model again in the next charging status prediction cycle to form an adaptive feedback closed loop of charging and adjustment.

[0076] Utilize a regulator based on reinforcement learning to dynamically generate a reward function according to the feedback of historical charging effects, and adjust the model optimization path; construct an optimizer based on reinforcement learning, and use the model prediction error, the improvement amplitude of charging efficiency, etc. as state inputs; construct a reward function with goals such as improving charging efficiency and enhancing charging stability: R(t) = f(Δη(t), power consumption, volatility); according to the policy optimization process of reinforcement learning, update the model parameters or select appropriate adjustment actions to improve the accuracy of future predictions and charging effects.

[0077] Ensure that the model can still maintain high prediction accuracy and stability under different device usage scenarios, charging angles, and temperature conditions; during the training and optimization process, the system introduces historical samples of multiple typical charging scenarios for multi-scenario adaptation training; through parameter regularization and environmental normalization processing, the model has good generalization ability for diverse charging environments; during actual operation, the model switches according to scenario labels or adjusts adaptive weights to adapt to the charging state evaluation under different environments; at the same time, monitor the prediction variance and residual fluctuation range of the model, and trigger the model retraining mechanism if it exceeds the set threshold to ensure long-term stability and high accuracy.

[0078] By introducing an adaptive compensation mechanism to continuously optimize and train the model, and monitoring the change of charging efficiency in real time during the process, it not only improves the model's adaptability to non-ideal states, but also realizes the dynamic control and prediction of wireless energy transfer efficiency, effectively improving the stability and efficiency of overall charging.

[0079] Embodiment 2

[0080] As Figure 1 shown, a portable wireless charging electronic method further includes the following steps:

[0081] S3: Based on the change of charging efficiency, judge whether the charging process is stable. If it is stable, record the phased change result of the charging efficiency, and perform dynamic adjustment in combination with the device location information to optimize the electromagnetic field coupling effect.

[0082] The process of judging whether the charging process is stable in S3 is as follows:

[0083] Real-time monitor the power output, efficiency curve, battery temperature rise rate, and attitude change amplitude during the charging process;

[0084] Calculate the change rate of charging efficiency within a continuous time window and compare it with a set threshold; process the efficiency data within a set time window and calculate the change rate of charging efficiency during this period: In the formula, η start and η end are the charging efficiencies at the start and end times of the time window respectively;

[0085] If the change rate of the charging efficiency within a continuous time window is less than the set threshold, it is determined that the current charging process is stable;

[0086] If the change rate of the charging efficiency within a continuous time window is greater than or equal to the set threshold, it is determined that the current charging process is unstable.

[0087] By continuously analyzing the change of the charging efficiency, it is judged whether the current charging process is stable. If it is judged to be stable, the device location information is further combined for dynamic adjustment, so as to optimize the coupling effect of the electromagnetic field. This process significantly enhances the system's ability to cope with the charging state fluctuations in the scenario of charging while using. Through active coupling optimization, the stability and effectiveness of the power transmission path are improved, and the energy loss caused by slight movement or rotation of the device is reduced.

[0088] S4: According to the adjusted electromagnetic field coupling effect, apply a multi-dimensional real-time feedback algorithm to perform environmental adaptability correction on the charging efficiency, extract correction parameters, and dynamically adjust the charging strategy to optimize the charging process.

[0089] The process of performing environmental adaptability correction on the charging efficiency in S4 is as follows:

[0090] Obtain external environmental variable information, including environmental temperature, humidity, electromagnetic interference source, device material and magnetic permeability parameters of the shell, etc.;

[0091] Based on a deep neural network model, construct a mapping function between environmental variables and charging efficiency; in the offline training stage of the system, based on a large number of historical charging data samples under different environmental conditions, construct a deep learning model with multiple inputs and a single output: the input dimensions include: temperature, humidity, electromagnetic interference intensity, magnetic permeability of the shell, device posture, etc.; the output dimension is: the charging efficiency under the corresponding conditions; the network training goal is to minimize the error between the real efficiency and the model prediction efficiency, so that the network can accurately fit the influence relationship of environmental variables on efficiency; after the model is trained, it is solidified and deployed in the device-side embedded system as the core of the environmental perception adaptive algorithm.

[0092] Input the mapping function for the current environmental state, and output a correction parameter vector, which reflects the direction of compensation adjustment required under the current conditions; when the device is wirelessly charged, the environmental variable data vector obtained in real time is input into the trained neural network model; the model outputs a set of correction parameter vectors, which are used to indicate how the system should be adjusted under the current environmental conditions to optimize the charging performance; for example: the magnetic field strength adjustment coefficient: appropriately increase the emission intensity of the main coil when the electromagnetic interference is strong; the attitude compensation direction factor: fine-tune the attitude angle when the magnetic permeability of the device shell is high to obtain a higher coupling rate; the voltage / frequency fine-tuning suggestion: adjust the operating frequency or power level in high-temperature or high-humidity environments to avoid overheating or energy loss; the correction parameter vector is passed to the downstream charging strategy dynamic adjustment module, and the charging process is fine-tuned in combination with the real-time state.

[0093] The process of dynamically adjusting the charging strategy in S4 is as follows:

[0094] Based on the correction parameters and the stability judgment result, determine and switch the currently adopted charging mode; the system obtains: the correction parameter vector output from the environmental adaptability model, including the magnetic field strength adjustment coefficient, the attitude compensation direction factor, etc.; the stability status flag from the charging stability detection module, that is, whether there is a situation where the continuous efficiency fluctuation exceeds the threshold; according to the above information, the system evaluates whether the current charging mode is still suitable for the current conditions, including but not limited to:

[0095] Whether the fast charging mode will cause overheating or a sharp drop in efficiency;

[0096] Whether the current frequency range conflicts with the electromagnetic environment interference frequency band;

[0097] Whether the attitude change has affected the alignment degree of the coupling center area;

[0098] If there are non-conforming items, the system automatically switches to another preset adaptive charging mode, including: the standard constant voltage charging mode; the environmentally friendly low-frequency steady state mode; the dynamic adaptive pulse power mode, etc.; the mode switching process is carried out smoothly, and the system ensures that the charging is not interrupted, and at the same time records the efficiency comparison results before and after the mode switching for subsequent strategy optimization.

[0099] Control the output power amplitude and frequency range of the transmitting end to achieve matching with the power requirements of the receiving end; the system dynamically adjusts the output characteristics of the wireless transmitting end according to the current battery state and correction parameters of the device: Output power amplitude control: If it is detected that the current coupling is good and the battery can accept a higher current, the power amplitude is appropriately increased; if it is in a high-temperature environment or the device enters the protection mechanism, the output amplitude is reduced to prevent overload; Frequency range adjustment: According to the electromagnetic field interference spectrum information and the change trend of the resonant frequency of the device receiving coil, the transmission frequency is adjusted in real time; ensure that the transmission frequency forms a good match with the resonant frequency of the receiving end, thereby improving the power transmission efficiency; The matching goal is to achieve maximum power point tracking: maintain the maximum transmission efficiency at all times under different postures and environmental conditions; all adjustment parameters are closed-loop controlled by the regulator and the feedback controller, and the output value is sent to the transmitting end power control circuit through the radio frequency modulation module.

[0100] When detecting the movement or posture adjustment of the device, dynamically adjust the coil excitation mode and time series waveform to maintain a stable coupling state; the system continuously monitors the data of the device's three-axis accelerometer and gyroscope, and judges in real time whether there is movement, rotation or tilt; if the posture change exceeds the set threshold, the system performs the following adjustments: Dynamic switching of coil excitation mode: For example, switch the excitation method from continuous wave excitation to time-division multi-frequency excitation to adapt to the offset of the coupling area; Turn on the standby or auxiliary transmitting coil for dynamic compensation to improve the uniformity of magnetic field coverage; Reconstruction of excitation waveform: Modify the time series characteristics of the excitation signal; Improve the response speed of the electromagnetic field when adapting to the device posture change; During the adjustment process, the system monitors the change of magnetic flux and the voltage response of the receiving end to form a feedback closed loop to ensure that effective energy coupling is still maintained during movement.

[0101] By applying a multi-dimensional real-time feedback algorithm, according to the current environmental conditions and charging response, extract the correction parameters reflecting the actual state, perform environmental adaptability correction on the charging efficiency, and dynamically adjust the current charging strategy adopted. This step enables the system to have a high degree of adaptability to complex and dynamic environments, ensures that the charging efficiency can still be maintained at a high level under non-ideal conditions, and realizes the intelligent self-adjustment of the wireless charging strategy.

[0102] S5: Based on the optimized charging strategy, combined with the device status detection system, monitor the charging process in real time and automatically adjust the charging method.

[0103] The process of automatically adjusting the charging method in the above S5 is as follows:

[0104] Integrate a multi-source sensor system, including temperature, voltage, current, electromagnetic field strength and attitude sensors, to achieve high-frequency sampling and monitoring of the entire charging process;

[0105] Perform multi-channel data fusion analysis through the central control unit to determine whether there are risks in the current charging method; synchronously transmit data from multiple sensors to the central control unit and perform the following operations: Multi-channel data fusion: uniformly perform normalization and synchronization processing on different physical quantities to construct a complete charging state description vector at the current moment; Feature extraction and analysis: evaluate whether the current and voltage fluctuations exceed the normal range; monitor whether the temperature rises too fast; analyze whether the attitude change will cause coupling offset; check whether the change in electromagnetic field strength is abnormal, which may cause energy loss or interference; Risk determination logic: compare each index with the preset safety threshold in real time; if abnormal fluctuations or unstable modes are detected, trigger a safety warning; The risk types are divided into multiple levels, which are used to trigger different levels of regulation strategies.

[0106] If it is detected that a risk factor exceeds the safety threshold, immediately call the charging method most suitable for the current state to replace the original mode; when one or more indicators exceed the corresponding safety threshold, the system performs the following operations: determine the current risk type; according to the risk type, call the predefined safe charging strategy library and select the alternative charging mode most suitable for the current state:

[0107] Abnormal attitude → switch to the adaptive low-frequency coupling mode;

[0108] Abnormal temperature → enable the constant voltage cooling protection mode;

[0109] Electromagnetic interference → switch to the charging mode in the interference avoidance frequency band.

[0110] Through the high-frequency sampling and risk identification mechanism, it is possible to dynamically sense abnormal factors that may cause a decrease in charging efficiency or safety hazards, and automatically call the charging method most suitable for the current conditions for replacement. This step greatly improves the intelligence and safety reliability of the charging system, enabling the charging method to be intelligently switched according to the real-time state, thereby realizing a stable, continuous and efficient wireless charging process.

[0111] Embodiment 3

[0112] Please refer to Figure 2 As shown, a portable wireless charging electronic system described in an embodiment of the present invention includes:

[0113] Environmental data acquisition module: used to obtain perception data and construct a battery charging environment data set of the device in combination with electromagnetic field strength parameters;

[0114] Charging state modeling module: used to perform dynamic feature extraction on environmental data, construct a charging state model based on real-time electromagnetic field simulation, and introduce an adaptive compensation mechanism to optimize the model training process;

[0115] Charging stability evaluation module: used to monitor the change of charging efficiency, judge whether the charging process is stable, and record the stage efficiency data and dynamically adjust the position information under stable conditions;

[0116] Charging strategy optimization module: used to perform environmental adaptability correction on the charging efficiency according to the electromagnetic field coupling effect, apply a multi-dimensional real-time feedback algorithm, and generate correction parameters;

[0117] Charging control module: used to perform real-time monitoring of the charging process and automatic adjustment of the charging method based on the optimized charging strategy in combination with device status detection.

[0118] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0119] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A portable wireless charging electronic method, characterized in that, It includes the following steps: Through the input system of the wireless charging device, obtain the battery power and device tilt or movement status data, and combine electromagnetic field strength algorithm analysis to construct a battery charging environment dataset for the device; Perform dynamic feature extraction on the battery charging environment dataset, construct a device charging status model based on the real-time electromagnetic field simulation algorithm, introduce an adaptive compensation mechanism to optimize and train the charging status model, and monitor the change of charging efficiency in real time during the optimization training process; Based on the change of charging efficiency, judge whether the charging process is stable. If it is stable, record the phased change result of the charging efficiency, and combine the device position information for dynamic adjustment to optimize the electromagnetic field coupling effect; According to the adjusted electromagnetic field coupling effect, apply a multi-dimensional real-time feedback algorithm to correct the charging efficiency for environmental adaptability, extract correction parameters, and dynamically adjust the charging strategy to optimize the charging process; Based on the optimized charging strategy, combine the device status detection system to monitor the charging process in real time and automatically adjust the charging method.

2. The portable wireless charging electronic method according to claim 1, wherein The process of constructing a battery charging environment dataset for the device by combining electromagnetic field strength algorithm analysis is as follows: Collect multi-source original charging data through the wireless charging device; Obtain the tilt angle and acceleration parameters of the device; Construct a multi-dimensional data vector, combine electromagnetic field strength algorithm analysis, and dynamically calculate the electromagnetic coupling strength index according to the position change of the device relative to the charging coil; Fuse the timing information and integrate the charging status records of different time segments into a charging environment dataset.

3. A portable wireless charging electronic method according to claim 1, wherein The process of performing dynamic feature extraction on the battery charging environment dataset is as follows: Adopt the sliding time window method to segment the battery charging environment dataset, and extract the charging voltage, current fluctuation trend, and electromagnetic field strength change rate within each time period; Construct a feature vector for each time segment and calculate the statistical features; Based on the anomaly detection mechanism based on the change rate recognition, identify short-term mutation signals and mark them as feature mutation events; Merge all time segment features to construct a multi-dimensional dynamic feature matrix.

4. A portable wireless charging electronic method according to claim 1, characterized in that The process of constructing a device charging status model based on the real-time electromagnetic field simulation algorithm is as follows: Use the physical modeling framework, combine the numerical information in the dynamic feature matrix, and simulate the current induction charging process; During the electromagnetic simulation process, establish the mapping relationship between the charging input and the efficiency output; Train and optimize the simulation model through historical data samples to form a device charging status model based on real-time input data output.

5. A portable wireless charging electronic method according to claim 1, characterized in that, The process of introducing an adaptive compensation mechanism to optimize and train the charging status model is as follows: Compare the real-time observed charging efficiency with the predicted value of the status model, calculate the error residual and define it as the performance deviation function; Introduce an adaptive compensation mechanism and automatically adjust the parameters based on the performance deviation function; Use a regulator based on reinforcement learning to dynamically generate a reward function according to the historical charging effect feedback and adjust the model optimization path.

6. A portable wireless charging electronic method according to claim 1, characterized in that, The process of judging whether the charging process is stable is as follows: Monitor the power output, efficiency curve, battery temperature rise rate, and attitude change amplitude during the charging process in real time; Calculate the charging efficiency change rate within a continuous time window and compare it with the set threshold; If the change rate of the charging efficiency within a continuous time window is less than the set threshold, it is determined that the current charging process is stable; If the change rate of the charging efficiency within a continuous time window is greater than or equal to the set threshold, it is determined that the current charging process is unstable.

7. A portable wireless charging electronic method according to claim 1, characterized in that, The process of performing environmental adaptability correction on the charging efficiency by applying the multi-dimensional real-time feedback algorithm is as follows: Obtain external environmental variable information, and based on the deep neural network model, construct a mapping function between the environmental variables and the charging efficiency; Input the current environmental state into the mapping function and output the correction parameter vector.

8. A portable wireless charging electronic method according to claim 1, characterized in that The process of dynamically adjusting the charging strategy is as follows: Based on the correction parameters and the stability judgment result, determine and switch the currently adopted charging mode; Control the output power amplitude and frequency range of the transmitting end; When detecting the movement or attitude adjustment of the device, dynamically adjust the coil excitation mode and the time series waveform to maintain a stable coupling state.

9. A portable wireless charging electronic method according to claim 1, characterized in that, The process of performing real-time monitoring on the charging process and automatically adjusting the charging method is as follows: Through the central control unit, perform multi-channel data fusion analysis to determine whether there is a risk in the current charging method; If it is detected that the risk factor exceeds the safety threshold, immediately call the most suitable charging method for the current state to replace the original mode.

10. A portable wireless charging electronic system, applied to the method according to any one of claims 1-9, characterized in that, Including: Environmental data acquisition module: used to obtain perception data, and combine the electromagnetic field intensity parameters to construct a battery charging environment data set of the device; Charging state modeling module: used to perform dynamic feature extraction on the environmental data, and construct a charging state model based on real-time electromagnetic field simulation, and introduce an adaptive compensation mechanism to optimize the model training process; Charging stability evaluation module: used to monitor the change of the charging efficiency, determine whether the charging process is stable, and record the stage efficiency data and the dynamically adjusted position information under stable conditions; Charging strategy optimization module: used to perform environmental adaptability correction on the charging efficiency according to the electromagnetic field coupling effect, apply the multi-dimensional real-time feedback algorithm, and generate correction parameters; Charging control module: used to perform real-time monitoring and automatic charging method adjustment on the charging process based on the optimized charging strategy and combined with the device state detection.

Images