Intelligent control method and system for high-power charging module

Abstract

The present invention relates to the technical field of charging control and provides an intelligent control method and system for a high-power charging module. The method comprises obtaining a charging state sequence of the charging module, performing feature extraction and pattern recognition processing on the charging state sequence to obtain charging safety control parameters; performing hierarchical calculations on the charging safety control parameters to obtain dynamic safety levels, using the dynamic safety levels to generate overcharge protection signals and overcurrent protection signals, performing data mapping calculations on the overcharge protection signals and overcurrent protection signals to obtain a real-time protection strategy; generating charging module control instructions based on the real-time protection strategy, and controlling the charging process of the charging module based on the charging module control instructions. By hierarchically calculating the charging safety control parameters and generating charging module control instructions to control the charging process, the system improves the problems of low charging efficiency and poor safety in scenarios with complex charging environments and dynamically changing charging demands.

Description

Technical Field

[0001] The present application relates to the technical field of charging control, and in particular to an intelligent control method and system for a high-power charging module. Background Art

[0002] With the increasing popularity of electric vehicles and smart devices, the market demand for efficient, safe, and intelligent charging modules is growing. High-power charging technology has become a critical support for electric vehicles and portable devices. Especially in the era of fast charging, optimizing this technology is particularly critical. However, the increasing complexity and performance requirements of charging modules also place higher demands on their control methods, including accuracy, dynamic adaptability, and safety.

[0003] Related technologies typically employ charging control methods based on fixed-parameter current-voltage control (CC-CV mode). These methods employ a series of preset control thresholds and optimize the charging curve to adjust the charging voltage and current, thereby achieving a balance between charging speed and battery life. Some systems also incorporate overvoltage and overcurrent protection to mitigate safety hazards caused by overcharging. These existing technologies provide a basic level of control and protection for the charging process.

[0004] Regarding the above technical solution, although stable and efficient charging control can be achieved through fixed parameter control and simple protection mechanisms, in scenarios where the charging environment is complex and demand changes dynamically, the existing technology has problems such as insufficient control accuracy and poor adaptability. This limitation leads to reduced efficiency or safety hazards during the charging process. Summary of the Invention

[0005] In order to improve the problems of low charging efficiency and poor safety in scenarios where the charging environment is complex and the demand changes dynamically, the present application provides an intelligent control method and system for a high-power charging module.

[0006] The present invention provides an intelligent control method for a high-power charging module, comprising: obtaining a charging state sequence of the charging module, performing feature extraction and pattern recognition processing on the charging state sequence to obtain a charging state feature matrix; constructing a voltage mapping relationship and a current mapping relationship based on the charging state feature matrix, calculating the voltage mapping relationship and the current mapping relationship to obtain charging control parameters; performing time series prediction analysis on the charging control parameters to obtain predicted charging adjustment parameters and predicted safety thresholds, generating charging control instructions based on the predicted charging adjustment parameters, correcting the predicted safety thresholds using the charging control instructions, and generating corresponding charging safety control parameters based on the corrected safety thresholds; performing hierarchical calculations on the charging safety control parameters to obtain dynamic safety levels, generating overcharge protection signals and overcurrent protection signals using the dynamic safety levels, performing data mapping calculations on the overcharge protection signals and the overcurrent protection signals to obtain a real-time protection strategy; generating charging module control instructions according to the real-time protection strategy, and controlling the charging process of the charging module based on the charging module control instructions.

[0007] As a preferred solution, the step of obtaining a charging state sequence of the charging module, performing feature extraction and pattern recognition processing on the charging state sequence, and obtaining a charging state feature matrix includes: obtaining real-time voltage data, real-time current data, and temperature data of the charging module, and constructing an initial charging state sequence based on the real-time voltage data, the real-time current data, and the temperature data;

[0008] Based on the data distribution law of the initial sequence of charging states, a charging state hierarchical sequence is constructed, and the charging state hierarchical sequence is optimized in time to obtain a charging state time series matrix; data dimensionality reduction analysis is performed on the charging state time series matrix to obtain a charging key feature set, and the charging key feature set is used to perform feature mapping calculation on the charging state time series matrix to obtain an initial state feature matrix; data correlation analysis is performed based on the initial state feature matrix to obtain feature association parameters, and a feature relationship topology graph is constructed using the feature association parameters; graph decomposition is performed on the feature relationship topology graph to obtain a charging mode classification result and a feature classification weight, and the initial state feature matrix is ​​updated using the charging mode classification result and the feature classification weight to obtain a charging state feature matrix.

[0009] As a preferred solution, the steps of constructing a stratified charging state sequence based on the data distribution law of the initial charging state sequence, performing time series optimization on the stratified charging state sequence, and obtaining a charging state time series matrix include: obtaining historical data and real-time data of the initial charging state sequence, aligning the features of the historical data and the real-time data to obtain a data alignment sequence, dividing the data alignment sequence into time windows, classifying and labeling the initial charging state sequence based on the time window division result to obtain a stratified charging state sequence; calculating data aggregation parameters based on the statistical distribution characteristics of the stratified charging state sequence, and optimizing the stratified charging state sequence using the data aggregation parameters. The method comprises the following steps: hierarchically aggregating a state sequence to obtain a charging state hierarchical sequence; sorting data using the timestamp information of the charging state hierarchical sequence, calculating a charging state time series distribution parameter based on the data sorting result, and constructing a time series feature mapping relationship according to the charging state time series distribution parameter; performing time compensation calculation on the charging state hierarchical sequence according to the time series feature mapping relationship to obtain a time-compensated charging state sequence, and calculating a charging state correlation matrix based on the time-compensated charging state sequence; performing feature fusion calculation on the charging state correlation matrix, and performing timing optimization on the time-compensated charging state sequence based on the feature fusion calculation result to obtain a charging state time series matrix.

[0010] As a preferred embodiment, the steps of constructing a voltage mapping relationship and a current mapping relationship based on the charging state characteristic matrix, calculating the voltage mapping relationship and the current mapping relationship, and obtaining charging control parameters include: using the charging state characteristic matrix to analyze the voltage change characteristics of different charging stages to obtain voltage characteristic curves and current characteristic curves, and constructing a voltage mapping relationship and a current mapping relationship based on the voltage characteristic curves and the current characteristic curves; and calculating the charging stage control parameters using the voltage mapping relationship and the current mapping relationship to obtain the charging control parameters.

[0011] As a preferred solution, the steps of performing time series forecasting and analysis on the charging regulation parameters to obtain predicted charging adjustment parameters and predicted safety thresholds, generating charging control instructions based on the predicted charging adjustment parameters, correcting the predicted safety thresholds using the charging control instructions, and generating corresponding charging safety control parameters based on the corrected safety thresholds include: obtaining historical charging data of the charging regulation parameters, constructing a charging strategy time series based on the historical charging data, and performing trend decomposition on the charging strategy time series to obtain charging trend parameters and charging fluctuation parameters; performing forecasting and calculation on the charging strategy time series using the charging trend parameters and the charging fluctuation parameters to obtain a charging forecast trend curve and a charging short-term fluctuation curve, and generating predicted charging adjustment parameters based on the charging forecast trend curve and the charging short-term fluctuation curve; calculating a charging safety range based on the predicted charging adjustment parameters to obtain a charging safety initial threshold and a charging safety dynamic threshold, and performing comprehensive calculation on the charging safety initial threshold and the charging safety dynamic threshold to obtain a predicted safety threshold; generating a charging control instruction using the predicted charging adjustment parameters, correcting the predicted safety threshold based on the charging control instruction, and generating corresponding charging safety control parameters based on the corrected safety threshold.

[0012] As a preferred solution, the steps of performing hierarchical calculation on the charging safety control parameters to obtain a dynamic safety level, generating an overcharge protection signal and an overcurrent protection signal using the dynamic safety level, performing data mapping calculation on the overcharge protection signal and the overcurrent protection signal to obtain a real-time protection strategy include: performing hierarchical calculation on the charging safety control parameters to obtain a safety level parameter and a charging abnormality judgment parameter, and calculating a dynamic safety level based on the safety level parameter and the charging abnormality judgment parameter; constructing a charging protection decision matrix based on the dynamic safety level, calculating an overcharge protection factor and an overcurrent protection factor according to the charging protection decision matrix, generating an overcharge protection signal using the overcharge protection factor, and generating an overcurrent protection signal using the overcurrent protection factor; constructing a safety control mapping relationship through the overcharge protection signal and the overcurrent protection signal, performing feature calculation on the safety control mapping relationship to obtain a safety control adjustment parameter, calculating the charging protection strategy based on the safety control adjustment parameter, and obtaining a real-time protection strategy.

[0013] As a preferred solution, the step of generating a charging module control instruction according to the real-time protection strategy and controlling the charging process of the charging module based on the charging module control instruction includes: generating charging safety control parameters according to the real-time protection strategy, calculating charging protection adjustment parameters based on the charging safety control parameters, and generating an initial charging safety strategy using the charging protection adjustment parameters; adjusting the charging process of the charging module in real time using the initial charging safety strategy to obtain charging dynamic control parameters and charging terminal protection parameters, and calculating a target charging safety strategy based on the charging dynamic control parameters and charging terminal protection parameters; generating a charging module control instruction using the target charging safety strategy, and controlling the charging process of the charging module based on the charging module control instruction.

[0014] The present application also provides an intelligent control system for a high-power charging module, comprising: an acquisition module for acquiring a charging state sequence of the charging module, performing feature extraction and pattern recognition processing on the charging state sequence, and obtaining a charging state feature matrix; an adjustment module for constructing a voltage mapping relationship and a current mapping relationship based on the charging state feature matrix, and calculating the voltage mapping relationship and the current mapping relationship to obtain charging control parameters; an analysis module for performing time series prediction analysis on the charging control parameters to obtain predicted charging adjustment parameters and predicted safety thresholds, generating charging control instructions based on the predicted charging adjustment parameters, correcting the predicted safety thresholds using the charging control instructions, and generating corresponding charging safety control parameters based on the corrected safety thresholds; a calculation module for performing hierarchical calculations on the charging safety control parameters to obtain dynamic safety levels, generating overcharge protection signals and overcurrent protection signals using the dynamic safety levels, and performing data mapping calculations on the overcharge protection signals and the overcurrent protection signals to obtain a real-time protection strategy; and a control module for generating charging module control instructions according to the real-time protection strategy, and controlling the charging process of the charging module based on the charging module control instructions.

[0015] Compared with the existing technology, the present application has the following beneficial effects: fast charging efficiency and high safety. By extracting features and performing pattern recognition on the charging state sequence of the charging module, a charging state feature matrix is ​​generated; the charging state feature matrix is ​​used to construct voltage mapping relationships and current mapping relationships, thereby calculating charging regulation parameters and predicting safety thresholds, and then generating charging control instructions to correct the predicted safety thresholds to form charging safety control parameters; by hierarchically calculating the charging safety control parameters, a dynamic safety level is generated to trigger overcharge protection signals and overcurrent protection signals, and with the help of a real-time protection strategy, charging module control instructions are generated to control the charging process, thereby improving the problems of low charging efficiency and poor safety in scenarios with complex charging environments and dynamically changing demands. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] The structures, proportions, sizes, etc. depicted in the drawings of this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with this technology. They are not intended to limit the conditions under which the present invention can be implemented and therefore have no substantive technical significance. Any structural modifications, changes in proportional relationships, or adjustments in size should still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and objectives that can be achieved by the present invention.

[0018] Figure 1 1 is a flow chart of an intelligent control method for a high-power charging module provided by an embodiment of the present invention;

[0019] Figure 2 It is a schematic block diagram of the structure of the intelligent control system of the high-power charging module provided by an embodiment of the present invention.

[0020] Description of reference numerals:

[0021] 10. Intelligent control system of high-power charging module; 11. Acquisition module; 12. Adjustment module; 13. Analysis module; 14. Calculation module; 15. Control module. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. 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.

[0023] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0024] It should also be understood that the terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0025] It should be further understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0026] The technical solution of the present invention will be further described below with reference to the accompanying drawings and through specific implementation methods.

[0027] Example 1:

[0028] like Figure 1 As shown, the present application provides an intelligent control method for a high-power charging module, including steps S100 to S500.

[0029] Step S100: Acquire a charging state sequence of a charging module, perform feature extraction and pattern recognition processing on the charging state sequence, and obtain a charging state feature matrix.

[0030] In this step, real-time data from the charging module is collected during operation to form a charging state sequence. Specifically, the charging state sequence includes parameters such as voltage, current, and temperature. A multi-scale feature extraction algorithm is used to process each parameter in the charging state sequence, extracting key features that affect charging performance. Pattern recognition techniques are then used to classify and identify these features, thereby forming a charging state feature matrix.

[0031] For example, when a charging module operates in different temperature environments, the temperature parameters in the generated charging state sequence will be summarized into specific patterns through the feature extraction algorithm, and combined with the voltage parameters to form the corresponding charging state feature matrix.

[0032] Step S200: constructing a voltage mapping relationship and a current mapping relationship based on the charging state characteristic matrix, calculating the voltage mapping relationship and the current mapping relationship, and obtaining charging control parameters.

[0033] In this step, the characteristic data in the charging state characteristic matrix is ​​analyzed, and the voltage and current mapping relationships are constructed based on the voltage variation trend and current adjustment rules of the charging module. Specifically, multi-dimensional calculations are performed on the voltage and current mapping relationships to generate charging control parameters.

[0034] For example, in the early stages of charging, the charge state characteristic matrix of an electric vehicle shows a nonlinear relationship between voltage change and current increase. Based on this data, voltage and current mapping relationships are constructed, and charging control parameters are calculated and dynamically adjusted in the later stages of charging to maximize charging efficiency.

[0035] Step S300: Perform time series forecasting analysis on the charging control parameters to obtain predicted charging adjustment parameters and predicted safety thresholds, generate charging control instructions based on the predicted charging adjustment parameters, use the charging control instructions to correct the predicted safety thresholds, and generate corresponding charging safety control parameters based on the corrected safety thresholds.

[0036] In this step, a time series prediction model is applied to analyze charging control parameters to predict future charging adjustment parameters and safety thresholds. Specifically, the predicted charging adjustment parameters are dynamically updated based on voltage and current mapping relationships, while the predicted safety thresholds are modified based on the charging module's environmental parameters and device status, ultimately generating charging safety control parameters.

[0037] For example, if the external temperature of a charging module suddenly rises during operation, its predicted safety threshold will be updated in real time to reflect the environmental changes, and the charging control instructions will also adjust the operating parameters of the charging module to adapt to the new environment.

[0038] Step S400: Perform hierarchical calculation on the charging safety control parameters to obtain a dynamic safety level, use the dynamic safety level to generate an overcharge protection signal and an overcurrent protection signal, perform data mapping calculation on the overcharge protection signal and the overcurrent protection signal, and obtain a real-time protection strategy.

[0039] In this step, a hierarchical analysis of charging safety control parameters is performed to determine dynamic safety levels based on their safety levels. Specifically, the dynamic safety levels are used to generate overcharge and overcurrent protection signals. These signals are then analyzed and transformed using data mapping technology to form a real-time protection strategy to ensure charging safety.

[0040] For example, when the dynamic safety level reaches a high-risk state, the real-time protection strategy will quickly trigger the overcurrent protection signal and correct the operating parameters of the charging module to prevent damage.

[0041] Step S500: Generate a charging module control instruction according to the real-time protection strategy, and control the charging process of the charging module based on the charging module control instruction.

[0042] In this step, a real-time protection strategy generates control instructions for the charging module to adjust operating parameters during the charging process. Specifically, this instruction integrates the charging module's charging control parameters and dynamic safety level to ensure the dual goals of charging efficiency and safety.

[0043] For example, during the charging process, the control instructions generated by the real-time protection strategy enable the charging module to dynamically adjust under high-power operation to avoid overcharging and improve the stability of the charging process.

[0044] In this embodiment, by obtaining the charging state sequence of the charging module, feature extraction and pattern recognition processing are performed on the charging state sequence to generate a charging state feature matrix; then, a voltage mapping relationship and a current mapping relationship are constructed based on the charging state feature matrix, and charging control parameters are generated by calculating the voltage mapping relationship and the current mapping relationship; then, a time series prediction analysis is performed on the charging control parameters to obtain predicted charging adjustment parameters and predicted safety thresholds, and charging control instructions are generated based on the predicted charging adjustment parameters. At the same time, the predicted safety thresholds are corrected using the charging control instructions, and corresponding charging safety control parameters are generated based on the corrected safety thresholds; the charging safety control parameters are graded and calculated to generate dynamic safety levels, and overcharge protection signals and overcurrent protection signals are generated according to the dynamic safety levels; finally, a real-time protection strategy is generated by performing data mapping calculations on the overcharge protection signal and the overcurrent protection signal, and a charging module control instruction is generated based on the real-time protection strategy to accurately control the charging process of the charging module.

[0045] Through the above workflow, this technical solution achieves high-precision dynamic control of the charging module, ensuring significantly improved efficiency and safety during the charging process. Feature extraction and pattern recognition of charging state sequences enhance the system's perception capabilities, allowing charging control parameters to adapt to dynamic changes in the charging environment. Time series analysis for predicting charging adjustment parameters and safety thresholds enhances the system's foresight and intelligence. Real-time protection strategies and the generation of dynamic safety levels further ensure the stability and safety of the charging module, effectively resolving the issues of insufficient control precision and poor adaptability in existing technologies.

[0046] Example 2:

[0047] In step S100 , real-time voltage data, real-time current data, and temperature data of the charging module are acquired, and an initial sequence of charging states is constructed based on the real-time voltage data, real-time current data, and temperature data.

[0048] By collecting real-time voltage, current, and temperature data from the charging module during operation, the data acquisition module monitors the module's operating status in real time and generates an initial charging status sequence. Specifically, the real-time voltage data reflects the voltage variation trend of the charging module during charging, the real-time current data monitors the dynamic current fluctuations, and the temperature data provides the ambient temperature and the module's internal temperature. This data is integrated with timestamps to construct the initial charging status sequence, ensuring comprehensive data support for the charging process.

[0049] For example, when the charging module is fast charging, the collected real-time voltage data shows that the module voltage changes in a periodic oscillation state, while the real-time current data shows a relatively stable linear growth trend. The temperature data records the stability of the external ambient temperature and the dynamic changes in the module's internal temperature. By integrating this data into the initial charging status sequence, the current operating status of the charging module and external environmental conditions can be accurately reflected, providing basic support for subsequent data processing and optimization.

[0050] A charging state hierarchical sequence is constructed based on the data distribution law of the initial charging state sequence, and the charging state hierarchical sequence is optimized to obtain a charging state timing matrix.

[0051] By analyzing the distribution patterns of historical and real-time data from the initial state-of-charge sequence and combining it with a hierarchical processing approach, the data features are extracted hierarchically to construct a hierarchical state-of-charge sequence. Specifically, the sequence is optimized hierarchically using the long-term trends of historical data and the short-term dynamic changes of real-time data. A time series processing algorithm is then introduced to uniformly adjust the time information in the hierarchical state-of-charge sequence, forming a charge state time series matrix that provides standardized data input for subsequent optimization calculations.

[0052] For example, analyzing historical data from the initial sequence of charging status revealed daily periodic fluctuations in voltage, while real-time data showed significant dynamic changes in the instantaneous voltage of the charging module. By stratifying and classifying voltage data with other monitoring data and optimizing the timing using timestamps, we created a charging status time series matrix, providing a clear, structured input for data analysis.

[0053] Perform data dimensionality reduction analysis on the charging state time series matrix to obtain a charging key feature set, and use the charging key feature set to perform feature mapping calculation on the charging state time series matrix to obtain an initial state feature matrix.

[0054] By applying principal component analysis (PCA) and factor analysis (FA) to the state-of-charge time series matrix, data dimensionality reduction is performed, merging highly correlated features and screening for key features that significantly impact charging performance. This results in a set of key charging features, while extracting the remaining information as a set of auxiliary charging features. Specifically, the multi-dimensional features of the state-of-charge time series matrix are standardized, and the importance of each feature is evaluated using a statistical model. Based on the dimensionality reduction results, a set of key charging features is established. Then, based on the set of key charging features, a mapping rule is constructed to compress the high-dimensional spatial features of the time series matrix into low-dimensional structured features. Ultimately, the initial state feature matrix is ​​obtained, providing an efficient feature representation for subsequent calculations.

[0055] For example, the charging state timing matrix includes multiple features such as voltage, current, temperature, and charging time. Dimensionality reduction analysis revealed that voltage fluctuation amplitude and current change rate are the primary factors influencing charging performance. These two parameters are considered the key charging feature set, while temperature variation and charging time are classified as auxiliary charging feature sets. Using the key feature set, the timing matrix is ​​mapped and calculated to form an initial state feature matrix containing the important voltage and current features.

[0056] Based on the initial state feature matrix, data correlation analysis is performed to obtain feature association parameters, and feature relationship topology graph is constructed using feature association parameters.

[0057] By performing statistical correlation and causal analysis on each feature in the initial state feature matrix, and calculating correlation parameters between features, including the Pearson correlation coefficient and partial correlation coefficient, the dependencies between charging features are quantified. Specifically, bivariate and multivariate interaction analyses are performed on key features such as voltage and current, and auxiliary features such as temperature, to derive correlation parameters that describe the strength of feature interactions. Based on these correlation parameters, a graph theory approach is used to construct a feature relationship topology diagram, which intuitively represents the complex connections between various charging features.

[0058] For example, analysis of the initial state characteristic matrix revealed a strong positive correlation between voltage and current, with temperature indirectly influencing voltage changes. Based on these calculations, a characteristic relationship topology diagram was constructed, where nodes represent features and edge weights indicate the strength of the association. This diagram provides a clear understanding of the inherent connections between various parameters in the charging state.

[0059] The characteristic relationship topology graph is decomposed to obtain the charging mode classification results and feature classification weights. The charging mode classification results and feature classification weights are used to update the initial state feature matrix to obtain the charging state feature matrix.

[0060] By applying a spectral clustering algorithm and modular analysis to the feature relationship topology graph, the authors uncovered the charging modes and feature classification rules hidden within the topology. Specifically, the feature relationship topology graph is divided into subgraphs, each representing a charging mode. Feature classification weights are calculated based on the weight information of the subgraph nodes, extracting the core feature categories that influence charging efficiency and safety. The charging mode classification results and feature classification weights are then used to rearrange and update the initial state feature matrix to form a charging state feature matrix, providing high-quality data support for subsequent charging control parameters.

[0061] For example, through graph decomposition analysis, three typical charging modes are identified: fast charging mode, stable charging mode and safety protection mode. At the same time, the characteristic weights of voltage and current in each mode are calculated, and these results are used to update the initial state characteristic matrix to obtain a more accurate charging state characteristic matrix for dynamic control of the charging process.

[0062] Among them, the steps of constructing a charging state hierarchical sequence based on the data distribution law of the initial charging state sequence, performing time series optimization on the charging state hierarchical sequence, and obtaining a charging state time series matrix include: obtaining historical data and real-time data of the initial charging state sequence, aligning features of the historical data and the real-time data to obtain a data alignment sequence, dividing the data alignment sequence into time windows, and classifying and labeling the initial charging state sequence based on the time window division result to obtain a hierarchical charging state sequence.

[0063] By comprehensively analyzing the initial state-of-charge sequence, historical and real-time data are integrated onto a unified timeline to achieve feature alignment. Specifically, the dynamic time warping (DTW) algorithm is used to align historical and real-time data, ensuring synchronization and consistency between the two datasets on the timeline and generating a data-aligned sequence. Subsequently, a sliding window technique is applied to divide the data-aligned sequence into multiple time windows. The feature data within each time window is classified and labeled according to its category and change trend, resulting in a hierarchical state-of-charge sequence, ensuring the hierarchical and temporal nature of the charge-state features.

[0064] For example, historical data shows a clear linear increase in voltage during the initial charging phase, while real-time data shows slight current fluctuations during the same phase. A feature alignment process synchronizes both voltage and current onto a common timeline, dividing this timeframe into multiple windows, such as 5-minute windows. This ultimately generates a hierarchical sequence of charging states labeled with the "initial charging" state.

[0065] A data aggregation parameter is calculated based on the statistical distribution characteristics of the stratified charge state sequence, and the stratified charge state sequence is hierarchically aggregated using the data aggregation parameter to obtain a stratified charge state sequence.

[0066] By analyzing the statistical distribution characteristics of each feature in the stratified state of charge sequence, such as the mean, variance, and peak value, parameters describing the degree of data aggregation, such as the stratified center point and inter-layer correlation coefficient based on cluster analysis, are extracted. Specifically, a clustering algorithm is used to hierarchically classify the stratified state of charge sequence. The sequence features of different charge states are dynamically grouped according to the data aggregation parameters, generating a hierarchical data structure and forming a stratified state of charge sequence to improve the efficiency and reliability of data processing.

[0067] For example, in the hierarchical charging state sequence, cluster analysis of voltage data shows that there are three typical levels: low voltage, medium voltage, and high voltage. By calculating the distribution center points and correlation degrees of these levels, a high-resolution charging state hierarchical sequence was successfully generated, providing a solid foundation for subsequent analysis and optimization.

[0068] The timestamp information of the charging state hierarchical sequence is used to sort the data, and the charging state time series distribution parameters are calculated based on the data sorting results. The time series feature mapping relationship is constructed according to the charging state time series distribution parameters.

[0069] By sorting each record entry in the hierarchical sequence of charging states from earliest to latest timestamps, the data exhibits a natural temporal sequence. Statistical analysis of the sorted data then generates charging state temporal distribution parameters, including the mean, rate of change, and peak time of the time interval. Specifically, based on the characteristic variation trends during charging module operation, a time series feature mapping diagram is drawn based on the temporal distribution parameters, visually reflecting the correlation strength and variation patterns between features at different charging stages.

[0070] For example, the voltage and current data of a certain time period showed obvious symmetry after sorting. Using the time series distribution parameters, it was found that the charging state reached its peak at 20 minutes. By constructing a time series feature mapping relationship, the effect of current growth on voltage fluctuations was clearly shown, facilitating subsequent strategy adjustments.

[0071] A time compensation calculation is performed on the charging state layered sequence according to the time series feature mapping relationship to obtain a time compensated charging state sequence, and a charging state correlation matrix is ​​calculated based on the time compensated charging state sequence.

[0072] By performing time compensation calculations for time drift or missing data in the time series feature mapping, inconsistent information in the stratified state of charge sequence is corrected. Specifically, an interpolation algorithm is used to estimate gaps in the time series data, and an extrapolation method is used to adjust outliers to generate a time-compensated state of charge sequence. Furthermore, by calculating the state of charge correlation matrix based on the time-compensated state of charge sequence, the mutual influence and connection between different state features are revealed, providing a reference for further optimization.

[0073] For example, when there is missing sampling in the current data of a charging process, the interpolation method is used to compensate for the missing values. By calculating the correlation matrix, it is found that current fluctuations have a significant impact on voltage regulation, thereby further improving the description information of the charging state.

[0074] The charging state correlation matrix is ​​subjected to feature fusion calculation, and the time-compensated charging state sequence is optimized based on the feature fusion calculation result to obtain the charging state timing matrix.

[0075] By performing feature fusion calculations on the data in the state-of-charge correlation matrix, multi-dimensional features are integrated and redundant information is removed, thereby improving the overall expressiveness of charging data. Specifically, by using weighted averaging and principal component analysis to reduce the dimensionality of the features in the correlation matrix, the time-compensated state-of-charge sequence is optimized into a highly accurate and continuous state-of-charge timing matrix.

[0076] For example, it was found in the charging state correlation matrix that there is a strong correlation between voltage fluctuations and temperature changes. By integrating the correlation data of these two features, the optimization results are mapped to the charging state timing matrix, thus laying the foundation for further intelligent charging regulation.

[0077] In step S200, the voltage variation characteristics of different charging stages are analyzed using a charging state characteristic matrix to obtain a voltage characteristic curve and a current characteristic curve, and a voltage mapping relationship and a current mapping relationship are constructed based on the voltage characteristic curve and the current characteristic curve.

[0078] Through nonlinear regression analysis, the various variables of the voltage and current characteristic curves are fitted to generate a charge state adjustment factor to correct voltage or current deviations caused by environmental changes. Error compensation parameters are also calculated to improve fitting accuracy and system reliability. Specifically, the voltage mapping relationship is adjusted based on the fitting model to make it closer to the actual voltage characteristics. Simultaneously, the current mapping relationship is optimized to reduce fluctuations that occur during high-power charging, thereby forming an accurate mapping model.

[0079] For example, in an actual test, the external temperature rise caused the voltage mapping relationship to deviate from the design value. This was corrected by adjusting the factor and compensating for the measurement error. The final voltage mapping relationship can accurately reflect the voltage change law under different temperature environments and ensure the stability of the charging process.

[0080] The voltage mapping relationship and the current mapping relationship are used to calculate the charging stage control parameters to obtain the charging control parameters.

[0081] By integrating voltage and current mapping relationships into a unified calculation framework, the voltage and current during the charging process are dynamically controlled in stages. Specifically, the initial charging control parameters are calculated to determine the optimal voltage and current values ​​at the start of charging. Then, adjustment parameters are introduced in the charging stage to adapt to the changing requirements during the subsequent charging process, thereby optimizing the entire charging curve.

[0082] For example, in the early stages of charging, the initial control parameters are set to a higher current to quickly increase battery capacity. In the middle and late stages, the current is dynamically reduced through staged parameter adjustments to slow battery aging and prevent overheating. These control parameters ensure the efficiency and safety of the entire charging process.

[0083] In step S300, historical charging data of charging control parameters are obtained, a charging strategy time series is constructed based on the historical charging data, and trend decomposition is performed on the charging strategy time series to obtain charging trend parameters and charging fluctuation parameters.

[0084] By performing a structured analysis of historical charging data on charging control parameters, the data features are chronologically integrated into a charging strategy time series. Specifically, a sliding window approach is used to extract features representing long-term stable trends in the charging data, while short-term fluctuations are refined to decompose the charging trend parameter and the charging fluctuation parameter. The charging trend parameter reflects the overall variation in charging efficiency, while the charging fluctuation parameter reveals subtle instabilities in the charging process, providing basic data for subsequent prediction models.

[0085] For example, by analyzing the historical charging data of a device, we found that the long-term trend of voltage showed a slow increase, while the short-term fluctuation frequency of current was high. Based on this, the generated trend parameter represents the change in voltage stability, while the fluctuation parameter quantifies the dynamic impact of current, providing a reliable basis for further prediction of charging strategies.

[0086] The charging strategy time series is predicted and calculated using the charging trend parameters and the charging fluctuation parameters to obtain a charging prediction trend curve and a charging short-time fluctuation curve. Predicted charging adjustment parameters are generated based on the charging prediction trend curve and the charging short-time fluctuation curve.

[0087] By applying time series forecasting algorithms, such as ARIMA models and LSTM neural networks, we model and calculate the trend and fluctuation parameters in the charging strategy time series, generating predicted charging trend curves and short-term charging fluctuation curves. These curves provide a basis for adjusting the charging strategy by predicting future charging conditions and performance. Specifically, the predicted trend curve depicts the direction of long-term stability, while the short-term fluctuation curve reveals localized non-uniformities that occur during the charging process. Based on this combined data, we generate predicted charging adjustment parameters to achieve precise optimization of the charging strategy.

[0088] For example, in a fast-charging scenario, the prediction model indicates that the future voltage trend curve will gradually approach saturation, while the short-term fluctuation curve indicates the random current fluctuations in the later stages of charging. Combining this information, the generated predicted charging adjustment parameters will optimize the voltage ramp-up strategy while appropriately limiting the current fluctuation amplitude.

[0089] The charging safety range is calculated based on the predicted charging adjustment parameters to obtain the charging safety initial threshold and the charging safety dynamic threshold. The charging safety initial threshold and the charging safety dynamic threshold are comprehensively calculated to obtain the predicted safety threshold.

[0090] By dynamically analyzing the predicted charging adjustment parameters and comprehensively considering the safety range under different charging conditions, the initial charging safety threshold and the dynamic charging safety threshold are gradually refined into the predicted safety threshold. Specifically, the initial charging safety threshold provides a fixed safety baseline for the charging process, while the dynamic charging safety threshold reflects the impact of external environmental changes on safety through real-time data updates. This comprehensive calculation process combines the advantages of both, laying the foundation for the stability and flexibility of the predicted safety threshold.

[0091] For example, when the temperature changes rapidly, the initial threshold provides a basic temperature tolerance range, while the dynamic threshold further adjusts the adaptation strategy through real-time measurement, so that the generated predicted safety threshold can fully adapt to the current environmental conditions, thereby ensuring the safety of the charging process.

[0092] The predicted charging adjustment parameter is used to generate a charging control instruction, and the predicted safety threshold is corrected based on the charging control instruction, and the corresponding charging safety control parameter is generated based on the corrected safety threshold.

[0093] By inputting predicted charging adjustment parameters into the charging control system, real-time charging control instructions are generated, gradually adjusting various safety thresholds during the charging process to form precise charging safety control parameters. Specifically, the charging control instructions modify the predicted safety thresholds based on real-time needs to adapt to changing charging conditions and improve charging efficiency and safety. The final safety control parameters incorporate the latest charging status characteristics, providing an important basis for the implementation of subsequent protection strategies.

[0094] For example, in high-power charging mode, the real-time generated charging control instructions fine-tune the predicted safety threshold to adapt to the sudden increase in the equipment load, thereby forming stable and reliable charging safety control parameters and effectively avoiding potential overheating or overcurrent problems.

[0095] In step S400, charging safety control parameters are graded and calculated to obtain safety level parameters and charging abnormality determination parameters, and a dynamic safety level is calculated based on the safety level parameters and the charging abnormality determination parameters.

[0096] By performing a multi-dimensional analysis of charging safety control parameters, combined with the operating status of the charging module and external environmental parameters, a step-by-step hierarchical calculation is performed for safety level parameters and charging anomaly determination parameters. Specifically, the safety level parameter indicates the safety status of the charging module at different stages, including low risk, medium risk, and high risk levels. The charging anomaly determination parameter uses threshold determination technology to detect anomalies during the charging process in real time, such as current overload or voltage drift. The combined calculation of these two parameters generates a dynamic safety level, which intuitively reflects the safety status of the current charging process.

[0097] For example, in the early stages of the charging process, the safety level parameters indicate a low risk. However, when the current rises rapidly, the charging abnormality judgment parameters indicate an overcurrent problem. The final calculated dynamic safety level indicates that the charging module has entered a medium-risk state and protective measures need to be taken in a timely manner.

[0098] A charging protection decision matrix is ​​constructed based on the dynamic safety level, and the overcharge protection factor and the overcurrent protection factor are calculated according to the charging protection decision matrix. The overcharge protection factor is used to generate an overcharge protection signal, and the overcurrent protection factor is used to generate an overcurrent protection signal.

[0099] By utilizing dynamic safety levels as a key factor, a charging protection decision matrix is ​​constructed to clearly define protection measures for different charging risk levels. Specifically, the overcharge protection factor and overcurrent protection factor are calculated based on the rules in the decision matrix. The overcharge protection factor assesses the impact of excessive voltage on charging safety, while the overcurrent protection factor analyzes the potential risk of current overload. These factors generate protection signals through real-time monitoring, triggering the overcharge protection signal and overcurrent protection signal, respectively, providing important guarantees for the safety of the charging process.

[0100] For example, when the charging protection decision matrix detects that the voltage exceeds the preset threshold, the overcharge protection factor is activated and an overcharge protection signal is generated to promptly slow down the voltage rise to avoid overcharging problems; similarly, when the current is transiently overloaded, the overcurrent protection factor generates an overcurrent protection signal to limit the current flow to protect the safety of the charging module and battery.

[0101] A safety control mapping relationship is constructed through overcharge protection signals and overcurrent protection signals, and characteristics of the safety control mapping relationship are calculated to obtain safety control adjustment parameters. The charging protection strategy is calculated based on the safety control adjustment parameters to obtain a real-time protection strategy.

[0102] By combining overcharge protection signals and overcurrent protection signals, a safety control mapping relationship for the charging module is established, clarifying the relationship between each protection signal and the charging module's operating parameters. Specifically, feature calculation technology is used to extract core information from the safety control mapping relationship, generate safety control adjustment parameters, and formulate a charging protection strategy based on this information to achieve real-time protection for the charging module. This real-time protection strategy effectively improves the safety and stability of the charging process by dynamically analyzing protection signals.

[0103] For example, in a certain environment, the charging module triggers an overcurrent protection signal due to a rapid increase in external temperature. Through the constructed safety control mapping relationship, adjustment parameters are generated to optimize the current curve of the module and adjust the voltage change rate at the same time, ultimately forming a real-time protection strategy, thereby effectively avoiding overcurrent risks and improving module stability.

[0104] In step S500 , charging safety control parameters are generated according to the real-time protection strategy, charging protection adjustment parameters are calculated based on the charging safety control parameters, and an initial charging safety strategy is generated using the charging protection adjustment parameters.

[0105] By applying the real-time protection strategy to the charging module's control system, charging safety control parameters are generated, which are then used to calculate charging protection adjustment parameters. Specifically, the charging protection adjustment parameters are used to modify the key characteristic values ​​of the safety strategy to generate an initial charging safety strategy, ensuring that the protection requirements of the charging module are met at all stages. The initial charging safety strategy integrates the status characteristics of the charging module to provide precise guidance for subsequent control.

[0106] For example, after the charging module enters high-power mode, the real-time protection strategy provides a safe range of charging voltage. The safety control parameters further optimize this range through a feedback mechanism. After adjusting the parameters, the initial charging safety strategy is generated to achieve comprehensive protection for high-power charging.

[0107] The initial charging safety strategy is used to adjust the charging process of the charging module in real time to obtain charging dynamic control parameters and charging terminal protection parameters. The target charging safety strategy is calculated based on the charging dynamic control parameters and charging terminal protection parameters.

[0108] By applying the initial charging safety strategy in real time, the charging module operating parameters are refined and adjusted to generate dynamic charging control parameters and charging terminal protection parameters. Specifically, the dynamic control parameters optimize the module's voltage and current curves in real time, while the terminal protection parameters ensure module safety at the end of charging. Combining these two, a target charging safety strategy for the entire charging process is calculated. This target charging safety strategy is continuously optimized through a feedback mechanism to ensure stable operation of the charging process.

[0109] For example, in the later stage of the charging module, the current fluctuation amplitude increases, and the dynamic control parameters are adjusted to stabilize the current, while the terminal protection parameters correct the voltage peak when the module stops charging. The final target safety strategy achieves coordinated protection of the entire charging process.

[0110] The target charging safety strategy is used to generate a charging module control instruction, and the charging process of the charging module is controlled based on the charging module control instruction.

[0111] The targeted charging safety strategy generates control instructions specifically for the charging module, guiding real-time management of the charging process. Specifically, these control instructions combine a comprehensive adjustment strategy for voltage, current, and temperature to dynamically control module operation, ensuring optimal charging performance and safety.

[0112] For example, in fast charging mode, the charging module control instructions are optimized for both voltage rise rate and current stability, thereby improving charging efficiency while avoiding overheating or overload problems, ensuring an efficient and safe charging process.

[0113] In this embodiment, an initial charging state sequence is constructed through in-depth analysis of real-time and historical data from the charging module. A hierarchical sequence is generated based on its distribution pattern. This hierarchical sequence is then time-optimized to form a charging state time series matrix, effectively integrating multidimensional charging characteristics. Dimensionality reduction analysis of the time series matrix further extracts key and auxiliary features. A feature relationship topology is constructed based on feature correlation parameters. This decomposition generates charging mode classification results and feature weights, thereby updating and optimizing the charging state feature matrix. Based on the optimized feature matrix, voltage and current characteristics at different charging stages are fitted and calculated to generate charging control parameters. A time series prediction model is used to further analyze historical data on charging control parameters to generate predicted adjustment parameters and predicted safety thresholds. Based on these safety thresholds, charging safety control parameters are generated to support subsequent protection strategies. Dynamic safety levels are introduced into the hierarchical calculation of safety control parameters to generate a charging protection decision matrix. Protection factors are calculated based on this matrix, and overcharge and overcurrent protection signals are generated. Finally, a mapping relationship is constructed based on the protection signals to generate safety control adjustment parameters and design a real-time protection strategy. This feedback mechanism optimizes the operating status of the charging module in real time. The entire embodiment adopts a multi-level feature analysis and dynamic control strategy, which significantly improves the efficiency, intelligence and safety of the charging process, and comprehensively solves the problems of insufficient adaptability and control accuracy in existing technologies.

[0114] Example 3:

[0115] like Figure 2 As shown, the present application also provides an intelligent control system 10 for a high-power charging module, including an acquisition module 11, an adjustment module 12, an analysis module 13, a calculation module 14 and a control module 15.

[0116] The acquisition module 11 is mainly used to acquire the charging state sequence of the charging module, perform feature extraction and pattern recognition processing on the charging state sequence, and obtain a charging state feature matrix.

[0117] The adjustment module 12 is mainly used to construct a voltage mapping relationship and a current mapping relationship based on the charging state characteristic matrix, calculate the voltage mapping relationship and the current mapping relationship, and obtain charging control parameters.

[0118] The analysis module 13 is mainly used to perform time series prediction analysis on the charging control parameters, obtain predicted charging adjustment parameters and predicted safety thresholds, generate charging control instructions based on the predicted charging adjustment parameters, use the charging control instructions to correct the predicted safety thresholds, and generate corresponding charging safety control parameters based on the corrected safety thresholds.

[0119] The calculation module 14 is mainly used to perform hierarchical calculations on charging safety control parameters to obtain dynamic safety levels, generate overcharge protection signals and overcurrent protection signals using the dynamic safety levels, perform data mapping calculations on the overcharge protection signals and overcurrent protection signals, and obtain real-time protection strategies.

[0120] The control module 15 is mainly used to generate a charging module control instruction according to the real-time protection strategy, and control the charging process of the charging module based on the charging module control instruction.

[0121] In this embodiment, the acquisition module 11 monitors and collects the charging state sequence of the charging module in real time. Combining feature extraction and pattern recognition techniques, it generates a charging state feature matrix, providing data support for subsequent operations. The adjustment module 12 uses the charging state feature matrix to dynamically construct voltage and current mapping relationships and generate charging control parameters through high-precision calculations, achieving efficient and intelligent charging control. The analysis module 13 uses a time series prediction model to conduct in-depth analysis of the charging control parameters, generating predicted charging adjustment parameters and predicted safety thresholds. Based on these data, it generates charging control instructions and, after correcting the predicted safety thresholds, further derives charging safety control parameters, ensuring the safety of the charging process. The calculation module 14 performs hierarchical calculations on the charging safety control parameters, generating dynamic safety levels that trigger overcharge and overcurrent protection signals. It also generates real-time protection strategies based on the mapping calculations of the protection signals, enabling rapid response to emerging risks. The control module 15 generates charging module control instructions based on the real-time protection strategies, dynamically adjusting the operating state of the charging module to ensure the safety and stability of the entire charging process. The entire system solves the shortcomings of existing charging modules in dynamic adaptability, control accuracy and safety assurance through the collaborative work of five major modules: acquisition, adjustment, analysis, calculation and control, and significantly improves the efficiency and intelligence level of the charging system.

[0122] It should be noted that, those skilled in the art will clearly understand that, for the sake of convenience and brevity of description, the specific working processes of the above-described system and each module can refer to the corresponding processes in the aforementioned embodiment 1 and will not be repeated here.

[0123] The structures, proportions, sizes, etc. depicted in the drawings of this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with this technology. They are not intended to limit the conditions under which the present invention can be implemented and therefore have no substantive technical significance. Any structural modifications, changes in proportional relationships, or adjustments in size should still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and objectives that can be achieved by the present invention.

[0124] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent control method for a high-power charging module, characterized in that: include: Acquiring a charging state sequence of a charging module, performing feature extraction and pattern recognition processing on the charging state sequence, and obtaining a charging state feature matrix; Analyzing voltage variation characteristics at different charging stages using the charging state characteristic matrix to obtain voltage characteristic curves and current characteristic curves, and constructing voltage mapping relationships and current mapping relationships based on the voltage characteristic curves and the current characteristic curves; Calculating a charging stage control parameter using the voltage mapping relationship and the current mapping relationship to obtain a charging control parameter; performing a time series forecast analysis on the charging control parameters to obtain a predicted charging adjustment parameter and a predicted safety threshold, generating a charging control instruction based on the predicted charging adjustment parameter, modifying the predicted safety threshold using the charging control instruction, and generating a corresponding charging safety control parameter based on the modified safety threshold; performing hierarchical calculation on the charging safety control parameters to obtain safety level parameters and charging abnormality determination parameters, and calculating a dynamic safety level based on the safety level parameters and the charging abnormality determination parameters; constructing a charging protection decision matrix based on the dynamic safety level, calculating an overcharge protection factor and an overcurrent protection factor according to the charging protection decision matrix, generating an overcharge protection signal using the overcharge protection factor, and generating an overcurrent protection signal using the overcurrent protection factor; Building a safety control mapping relationship using the overcharge protection signal and the overcurrent protection signal, performing feature calculation on the safety control mapping relationship to obtain a safety control adjustment parameter, and calculating a charging protection strategy based on the safety control adjustment parameter to obtain a real-time protection strategy; A charging module control instruction is generated according to the real-time protection strategy, and the charging process of the charging module is controlled based on the charging module control instruction.

2. The intelligent control method of the high-power charging module according to claim 1, characterized in that: The step of obtaining a charging state sequence of the charging module, performing feature extraction and pattern recognition processing on the charging state sequence, and obtaining a charging state feature matrix includes: Acquire real-time voltage data, real-time current data, and temperature data of a charging module, and construct an initial charging state sequence based on the real-time voltage data, the real-time current data, and the temperature data; constructing a charging state hierarchical sequence based on the data distribution law of the charging state initial sequence, and performing time sequence optimization on the charging state hierarchical sequence to obtain a charging state time sequence matrix; Performing data dimensionality reduction analysis on the charging state time series matrix to obtain a charging key feature set, and performing feature mapping calculation on the charging state time series matrix using the charging key feature set to obtain an initial state feature matrix; Performing data correlation analysis based on the initial state feature matrix to obtain feature association parameters, and constructing a feature relationship topology map using the feature association parameters; The characteristic relationship topology graph is subjected to graph decomposition to obtain a charging mode classification result and a characteristic classification weight, and the initial state characteristic matrix is ​​updated using the charging mode classification result and the characteristic classification weight to obtain a charging state characteristic matrix.

3. The intelligent control method of the high-power charging module according to claim 2, characterized in that: The steps of constructing a charging state layered sequence based on the data distribution law of the charging state initial sequence, performing timing optimization on the charging state layered sequence, and obtaining a charging state timing matrix include: Acquiring historical data and real-time data of the initial sequence of charging states, performing feature alignment on the historical data and the real-time data to obtain a data-aligned sequence, dividing the data-aligned sequence into time windows, and classifying and labeling the initial sequence of charging states based on the time window division results to obtain a hierarchical charging state sequence; Calculating a data aggregation parameter based on the statistical distribution characteristics of the hierarchical charge state sequence, and performing hierarchical aggregation on the hierarchical charge state sequence using the data aggregation parameter to obtain a hierarchical charge state sequence; sorting data using the timestamp information of the charging state hierarchical sequence, calculating charging state time series distribution parameters based on the data sorting result, and constructing a time series feature mapping relationship according to the charging state time series distribution parameters; performing time compensation calculation on the charging state hierarchical sequence according to the time series feature mapping relationship to obtain a time-compensated charging state sequence, and calculating a charging state correlation matrix based on the time-compensated charging state sequence; A feature fusion calculation is performed on the charging state correlation matrix, and a timing optimization is performed on the time-compensated charging state sequence based on the feature fusion calculation result to obtain a charging state timing matrix.

4. The intelligent control method of the high-power charging module according to claim 1, characterized in that: The steps of performing time series forecasting analysis on the charging control parameters to obtain predicted charging adjustment parameters and predicted safety thresholds, generating charging control instructions based on the predicted charging adjustment parameters, correcting the predicted safety thresholds using the charging control instructions, and generating corresponding charging safety control parameters based on the corrected safety thresholds include: Acquiring historical charging data of the charging control parameters, constructing a charging strategy time series based on the historical charging data, and performing trend decomposition on the charging strategy time series to obtain a charging trend parameter and a charging fluctuation parameter; Using the charging trend parameter and the charging fluctuation parameter to predict and calculate the charging strategy time series, obtain a charging prediction trend curve and a charging short-time fluctuation curve, and generate a predicted charging adjustment parameter based on the charging prediction trend curve and the charging short-time fluctuation curve; Calculating a charging safety range based on the predicted charging adjustment parameter to obtain a charging safety initial threshold and a charging safety dynamic threshold, and performing a comprehensive calculation on the charging safety initial threshold and the charging safety dynamic threshold to obtain a predicted safety threshold; A charging control instruction is generated using the predicted charging adjustment parameter, and the predicted safety threshold is corrected based on the charging control instruction, and a corresponding charging safety control parameter is generated based on the corrected safety threshold.

5. The intelligent control method of the high-power charging module according to claim 1, characterized in that: The step of generating a charging module control instruction according to the real-time protection strategy and controlling the charging process of the charging module based on the charging module control instruction includes: generating charging safety control parameters according to the real-time protection strategy, calculating charging protection adjustment parameters based on the charging safety control parameters, and generating an initial charging safety strategy using the charging protection adjustment parameters; Using the initial charging safety strategy to adjust the charging process of the charging module in real time, obtaining charging dynamic control parameters and charging terminal protection parameters, and calculating a target charging safety strategy based on the charging dynamic control parameters and charging terminal protection parameters; The target charging safety strategy is used to generate a charging module control instruction, and the charging process of the charging module is controlled based on the charging module control instruction.

6. An intelligent control system for a high-power charging module, characterized in that: include: an acquisition module, configured to acquire a charging state sequence of the charging module, perform feature extraction and pattern recognition processing on the charging state sequence, and obtain a charging state feature matrix; an adjustment module, configured to analyze voltage variation characteristics at different charging stages using the charging state characteristic matrix to obtain a voltage characteristic curve and a current characteristic curve, and construct a voltage mapping relationship and a current mapping relationship based on the voltage characteristic curve and the current characteristic curve; Calculating a charging stage control parameter using the voltage mapping relationship and the current mapping relationship to obtain a charging control parameter; an analysis module, configured to perform time series forecasting analysis on the charging control parameters to obtain predicted charging adjustment parameters and predicted safety thresholds, generate charging control instructions based on the predicted charging adjustment parameters, modify the predicted safety thresholds using the charging control instructions, and generate corresponding charging safety control parameters based on the modified safety thresholds; a calculation module, configured to perform hierarchical calculations on the charging safety control parameters to obtain safety level parameters and charging abnormality determination parameters, and calculate a dynamic safety level based on the safety level parameters and the charging abnormality determination parameters; constructing a charging protection decision matrix based on the dynamic safety level, calculating an overcharge protection factor and an overcurrent protection factor according to the charging protection decision matrix, generating an overcharge protection signal using the overcharge protection factor, and generating an overcurrent protection signal using the overcurrent protection factor; Building a safety control mapping relationship using the overcharge protection signal and the overcurrent protection signal, performing feature calculation on the safety control mapping relationship to obtain a safety control adjustment parameter, and calculating a charging protection strategy based on the safety control adjustment parameter to obtain a real-time protection strategy; The control module is used to generate a charging module control instruction according to the real-time protection strategy, and control the charging process of the charging module based on the charging module control instruction.

Images