Adaptive charging method and system for polarized battery based on multi-dimensional thermal-electric coupling perception

Abstract

The application provides a polar charging battery adaptive charging method and system based on multi-dimensional thermal-electric coupling sensing, and relates to the technical field of adaptive charging. The method comprises the following steps: collecting multi-dimensional thermal-electric parameters of a polar charging battery, constructing a time-space synchronous thermal-electric parameter sequence, extracting a thermal-electric parameter sequence characteristic code, and obtaining a thermal-electric coupling track through the characteristic code mapping; analyzing the thermal-electric coupling track to extract a coupling vector and calculate a thermal-electric matching degree; generating a monitoring label, extracting a coupling balance feature in the label carrier, and marking a thermal-electric balance point; determining a charging channel, calculating the coupling bearing capacity of the charging channel, optimizing the charging parameters, and calculating an optimized thermal-electric coordination ratio; generating an adaptive charging seed, and generating a charging strategy with the coupling synergy optimization as the target. The application generates an adaptive charging strategy through multi-dimensional thermal-electric parameter collection and coupling analysis, and improves the safety, efficiency and intelligent level of the polar charging battery charging.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of adaptive charging, in particular to an adaptive charging method and system for polar charging battery based on multi-dimensional thermal-electric coupling sensing. BACKGROUND

[0002] With the rapid development of electric two-wheeled vehicle industry, the demand for charging efficiency of users is increasingly urgent. Polar charging technology can greatly shorten the charging time and become the core of industry research. At the same time, other power transmission and distribution and control equipment manufacturing fields such as ground alternating current and underground alternating current charging piles also face the demand for technology upgrading. The popularization of polar charging scenarios puts forward higher requirements for the power density, thermal management capability and intelligent level of charging piles, and promotes the evolution of related equipment towards high compatibility and high safety.

[0003] Under the polar charging scenario, large current input can easily lead to dramatic changes in thermal and electrical parameters inside the battery, such as temperature rise, voltage imbalance and other problems, which not only restrict the charging efficiency, but also bring serious safety hazards, and therefore precise state sensing and adaptive control technology is urgently needed. The traditional adaptive charging method focuses on single electrical parameter monitoring and ignores the thermal-electric coupling law, which is difficult to cope with the complex working conditions during polar charging. At the same time, the problems of time and space asynchronization in parameter collection and the lack of coupling state quantization lead to poor adaptability of the charging strategy to the actual state of the battery. Under this background, a multi-dimensional thermal-electric coupling sensing technology system emerges as the times require, aiming to solve the core contradiction between polar charging safety and efficiency through full-dimensional state capture and dynamic regulation. SUMMARY

[0004] The present application provides an adaptive charging method for polar charging battery based on multi-dimensional thermal-electric coupling sensing to solve the defects in the prior art.

[0005] The adaptive charging method for polar charging battery based on multi-dimensional thermal-electric coupling sensing provided by the present application comprises:

[0006] S1: Collecting multi-dimensional thermal and electrical parameters of the polar charging battery, constructing a time and space synchronized thermal and electrical parameter sequence, extracting a thermal and electrical parameter sequence feature code, and obtaining a thermal and electrical coupling trajectory through the feature code mapping.

[0007] S2: Using a time and space gradient algorithm to analyze and extract a coupling vector from the thermal and electrical coupling trajectory, and calculating a thermal and electrical matching degree according to the coupling vector.

[0008] S3: Constructing a thermal and electrical coupling state dynamic model according to the thermal and electrical matching degree, analyzing state events in real time during the charging process, labeling the state events to generate monitoring labels, extracting coupling balance features in the label carrier, and marking thermal and electrical balance points.

[0009] S4: Determine the charging channel according to the thermoelectric balance point, calculate the coupling bearing capacity of the charging channel and optimize the charging parameters, and calculate the optimized thermoelectric coordination ratio according to the optimized charging parameters.

[0010] S5: Generate an adaptive charging seed according to the thermoelectric coordination ratio, query the coupling safety parameters and coupling protection rules of the seed, and generate a charging strategy with the goal of coupling synergy optimization.

[0011] According to the application, the specific steps of obtaining the thermoelectric coupling trajectory in step S1 are:

[0012] S11: Use a distributed sensing array to collect the cell temperature, single cell voltage, loop current and entropy change parameter of the extreme charging battery, and obtain discrete thermoelectric original parameters.

[0013] S12: Sort the discrete thermoelectric original parameters according to the time stamp, and associate the spatial collection position information to construct a space-time parameter sequence.

[0014] S13: Use a deep learning algorithm to extract the core features of the space-time parameter sequence, and generate a unique thermoelectric parameter feature code.

[0015] S14: Input the extracted feature code into a pre-trained model, and output the thermoelectric coupling trajectory through a feature matching and trajectory mapping algorithm.

[0016] According to the application, the specific steps of obtaining the thermoelectric matching degree according to the coupling vector in step S2 are:

[0017] S21: Perform coupling gradient analysis on the thermoelectric coupling trajectory using a space-time gradient algorithm, calculate the thermoelectric parameter change rate at different time nodes and spatial positions, and generate a gradient sequence.

[0018] S22: Extract the coupling vector of different space-time sections according to the gradient sequence, and integrate them into a coupling vector set.

[0019] S23: Calculate the thermoelectric matching degree according to the coupling vector, establish a correlation model between the thermoelectric parameters and the energy conversion efficiency, solve the quantitative index of thermoelectric parameter synergy matching, and quantify the coupling synergy.

[0020] According to the application, the specific steps of marking the thermoelectric balance point in step S3 are:

[0021] S31: Based on the thermoelectric matching degree, combine the time sequence thermoelectric parameter sequence of the extreme charging process, construct a nonlinear dynamic model, optimize the model parameters through Kalman filtering algorithm, and output the thermoelectric coupling state dynamic evolution curve.

[0022] S32: Monitor the thermal-electric coupling state dynamic evolution curve mutation, gradient anomaly characteristics, identify over-temperature, potential imbalance state events, adopt One-Hot coding to label event type, occurrence space-time coordinates, and generate a monitoring label set containing event attributes.

[0023] S33: Extract the coupling balance features in the monitoring label set, screen through feature threshold values, locate the space-time nodes that meet the balance conditions, and mark the specific thermal-electric balance point coordinates and time sequence positions.

[0024] According to the adaptive charging method for extreme battery based on multi-dimensional thermal-electric coupling perception provided by the application, in step S32, the specific steps for generating a monitoring label set containing event attributes are as follows:

[0025] S321: Obtain the thermal-electric coupling state dynamic evolution curve and the normal curve fluctuation range, capture the mutation points deviating from the normal range and the abnormal segments with gradient values exceeding the threshold value, and output preliminary feature data.

[0026] S322: According to the preliminary feature data, compare the curve mutation amplitude threshold value corresponding to the over-temperature state, confirm the specific state event type of the mutation through feature matching, record the time node and space position information of the event occurrence, and form an event basic information table.

[0027] S323: According to the event basic information table, construct independent One-Hot coding dimensions for different state event types and each space-time coordinate, convert the type and space-time attributes of each event into a binary coding vector, and generate a monitoring label set.

[0028] According to the adaptive charging method for extreme battery based on multi-dimensional thermal-electric coupling perception provided by the application, in step S4, the specific steps for calculating the optimized thermal-electric coordination ratio according to the optimized charging parameters are as follows:

[0029] S41: According to the current thermal-electric coordination state reflected by the thermal-electric balance point, match the charging channel with parameter transmission capability, and determine the target charging channel.

[0030] S42: Taking the target charging channel as the object, monitor the channel transmission state, analyze the influence of the channel state on the thermal-electric coupling balance, calculate the upper limit of the coupling load that the channel can bear according to the influence degree, and obtain the channel coupling bearing capacity.

[0031] S43: Adjust the charging parameters according to the channel coupling bearing capacity, calculate the optimized thermal regulation rate and electric input rate according to the adjusted charging parameters, and obtain the thermal-electric coordination ratio of the thermal regulation rate and the electric input rate.

[0032] According to the multi-dimensional thermal-electric coupling perception based adaptive charging method for polar charging battery provided by the application, in step S42, the specific steps for obtaining the channel coupling bearing capacity are as follows:

[0033] S421: According to the target charging channel, the transmission rate and stability are collected in real time, the current transmission state of the channel is comprehensively monitored, and complete channel state data is formed.

[0034] S422: Based on the collected channel state data, the action mechanism of different state parameters on thermal-electric parameter coordination and energy balance is analyzed, and the influence degree of channel state on thermal-electric coupling balance is quantified.

[0035] S423: According to the influence degree of channel state on thermal-electric coupling balance, the maximum value of coupling load that can be stably supported by the channel is derived in combination with the thermal-electric bearing limit of the battery, and the channel coupling bearing capacity is obtained.

[0036] According to the multi-dimensional thermal-electric coupling perception based adaptive charging method for polar charging battery provided by the application, in step S5, the specific steps for generating the charging strategy are as follows:

[0037] S51: According to the thermal-electric coordination ratio and the dynamic coupling demand of the polar charging process, an adaptive charging seed is generated through a feature mapping algorithm.

[0038] S52: Extracting the safety parameters of the adaptive charging seed analyzes the thermal-electric coupling protection rules in the safety identifier.

[0039] S53: Taking thermal-electric coupling synergy optimization as the core target, the charging seed and the safety parameters are fused to construct a strategy generation model, and a dynamically adjusted charging strategy is generated.

[0040] According to the multi-dimensional thermal-electric coupling perception based adaptive charging method for polar charging battery provided by the application, in step S53, the specific steps for constructing the strategy generation model are as follows:

[0041] S531: Taking the coupling protection rules as the constraint framework and the thermal-electric coupling synergy optimization core target, the dynamic driving characteristics of the charging seed and the boundary limit conditions of the safety parameters are deeply fused to construct a multi-dimensional parameter synergy strategy generation model.

[0042] S532: The fused charging seed and safety parameters are input into the strategy generation model, the adjustment coefficient of the charging voltage and current is dynamically calculated through an adaptive algorithm, and a charging strategy that changes in real time with the coupling state is generated.

[0043] S533: In the output report of the generated charging strategy, the time sequence evolution data of the coupling trajectory and the quantification index of the thermal-electric matching degree are supplemented, the whole process data is integrated, and a coupling management link is formed.

[0044] This invention also provides an adaptive charging system for high-capacity batteries based on multi-dimensional thermal-electric coupling sensing, the charging system comprising:

[0045] The parameter acquisition module is used to collect multi-dimensional thermoelectric parameters of the extreme charge battery, construct a spatiotemporally synchronized thermoelectric parameter sequence, extract the feature code of the thermoelectric parameter sequence, and obtain the thermoelectric coupling trajectory through feature code mapping.

[0046] The hotspot matching module is used to analyze the thermoelectric coupling trajectory using a spatiotemporal gradient algorithm to extract the coupling vector, and calculate the thermoelectric matching degree based on the coupling vector.

[0047] The hotspot balancing module is used to construct a dynamic model of thermoelectric coupling state based on thermoelectric matching degree, analyze state events in real time during the charging process, label the state events to generate monitoring tags, extract coupling balance features from the tag carrier, and mark the thermoelectric equilibrium point.

[0048] The hotspot coordination module is used to determine the charging channel based on the thermoelectric equilibrium point, calculate the coupling carrying capacity of the charging channel and optimize the charging parameters, and calculate the optimized thermoelectric coordination ratio based on the optimized charging parameters.

[0049] The charging strategy module is used to generate an adaptive charging seed based on the thermoelectric coordination ratio, query the coupling safety parameters and coupling protection rules of the seed, and generate a charging strategy with the goal of optimal coupling coordination.

[0050] The adaptive charging method for high-capacity batteries based on multi-dimensional thermo-electric coupling sensing provided by this invention generates a coupled charging strategy through multi-dimensional thermoelectric parameter acquisition and coupling analysis. First, parameters are acquired to obtain the coupling trajectory. Then, the thermoelectric matching degree is calculated through gradient analysis. After locating the thermoelectric equilibrium point, the charging parameters are optimized to obtain the thermoelectric coordination ratio. Finally, the coordination ratio is used to generate a coupled-driven charging seed. Combined with safety rules, an adaptive charging strategy is output. The beneficial effects achieved are as follows:

[0051] This invention employs a distributed sensor array to construct a comprehensive acquisition system for cell temperature, individual cell voltage, circuit current, and entropy change parameters. It not only ensures the accuracy of raw data by configuring one high-precision NTC temperature sensor and one high-precision voltage acquisition module for every two cells, but also innovatively integrates an entropy change monitoring unit, covering the core dimensions of heat, electricity, and thermodynamics. This solves the problem that traditional acquisition methods have single parameters and are difficult to reflect the overall state of the battery.

[0052] This invention breaks through the limitations of traditional qualitative analysis. It generates a gradient sequence containing coupling strength and rate of change through a spatiotemporal gradient algorithm, extracts the coupling vector, and substitutes it into a model derived based on the energy conservation equation to calculate the thermoelectric matching degree. This achieves precise quantification of coupling synergy, providing a clear quantitative basis for charging strategy optimization and avoiding strategy deviations caused by previous reliance on experience-based judgments. Based on the thermoelectric matching degree, a nonlinear dynamic model is constructed, and Kalman filtering is used to optimize parameters, outputting a coupling state evolution curve. By monitoring abrupt changes in the curve and gradient anomalies, problems such as overheating and potential imbalance are identified. This enables full-process control of the battery coupling state, from dynamic monitoring to anomaly identification and precise positioning of the equilibrium point, effectively avoiding safety risks caused by coupling imbalance.

[0053] In the charging channel adaptation and parameter optimization stage, this invention selects suitable charging channels based on the thermoelectric equilibrium point to ensure that the channels can maintain the battery's thermoelectric balance. By analyzing the impact of channel transmission status on thermoelectric coupling and calculating the channel coupling capacity in conjunction with the battery's thermoelectric carrying capacity limit, a reasonable boundary is defined for adjusting charging parameters. Then, the charging voltage and current are optimized with capacity as a constraint, and the thermoelectric coordination ratio is calculated. This achieves a precise match between charging parameters, channel carrying capacity, and battery thermoelectric state, avoiding transmission instability caused by channel overload and preventing battery thermal runaway or low charging efficiency caused by improper parameters. Based on the thermoelectric coordination ratio, an adaptive charging seed is generated, corresponding safety parameters are queried and protection rules are identified, and a dynamic charging strategy is generated with the goal of optimal coupling and coordination. The report also supplements core data such as coupling trajectory and matching degree, forming a closed-loop control of the entire process from state perception, strategy generation to execution feedback. It can not only dynamically adjust the charging strategy according to the real-time coupling state of the battery to ensure charging safety and efficiency, but also provide support for subsequent strategy optimization and fault tracing through full-process data recording. Overall, it improves the safety, efficiency and intelligence level of ultra-chargeable battery charging, and provides a reliable technical solution for the application of ultra-chargeable scenarios on a large scale. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0055] Fig. 1 This is a flowchart illustrating the steps of the adaptive charging method for high-capacity batteries based on multi-dimensional thermal-electric coupling sensing provided in an embodiment of the present invention.

[0056] Fig. 2 This is a block diagram of an adaptive charging system for high-capacity batteries based on multi-dimensional thermal-electric coupling sensing, provided in an embodiment of the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0058] The following is combined with Figs. 1-2 This invention describes an adaptive charging method and system for high-capacity batteries based on multi-dimensional thermo-electric coupling sensing.

[0059] Fig. 1 This invention provides an adaptive charging method for high-capacity batteries based on multi-dimensional thermal-electric coupling sensing.

[0060] like Figs. 1-2 As shown in the embodiment of the present invention, the adaptive charging method for high-capacity batteries based on multi-dimensional thermal-electric coupling sensing includes:

[0061] S1: Collect multi-dimensional thermoelectric parameters of the charged battery, including temperature, voltage, current, and entropy change, using distributed sensors to construct a spatiotemporally synchronized thermoelectric parameter sequence. Extract parameter feature codes based on coupling correlation analysis, and detect the coupling trajectory reflecting the thermoelectric interaction law through feature code mapping to achieve initial perception of the coupling state.

[0062] S11: A distributed sensor array is used to collect the cell temperature, individual cell voltage, loop current, and entropy change parameters of the high-capacity battery to obtain the original parameters for heat dissipation. Specifically, a high-precision NTC temperature sensor is configured for every two cells in the battery pack to simultaneously collect the cell surface and tab temperatures. A high-precision voltage acquisition module obtains the real-time voltage of each individual cell, and a Hall current sensor collects the loop current. An entropy change monitoring unit is also integrated to calculate the entropy change parameters based on the relationship between heat changes and voltage changes during battery charging and discharging, ensuring that the collected original parameters cover the core dimensions of heat, electricity, and thermodynamics.

[0063] S12: Sort the raw thermoelectric parameters by timestamp and associate them with spatial acquisition location information to construct a spatiotemporal parameter sequence. First, the discrete data collected by each sensor are timestamped, with a unified sampling time interval of 10ms to eliminate asynchronous data errors. Then, the corresponding spatial acquisition coordinates are marked for each parameter, establishing a three-dimensional data structure of "time-space-parameter value." Missing data is supplemented through linear interpolation to generate a continuous and ordered spatiotemporal parameter sequence, ensuring that the data fully reflects the changes in the battery's thermoelectric state at different times and locations.

[0064] S13: Deep learning algorithms are used to extract core features of the spatiotemporal parameter sequence, generating unique thermoelectric parameter feature codes. A 3D-CNN network is employed to extract the spatial features and temporal dependencies of the spatiotemporal parameter sequence. An LSTM layer captures the dynamic changes of parameters over time, and a fully connected layer compresses the feature dimensionality. The extracted high-dimensional features are normalized and converted into fixed-length binary codes using a hash algorithm, which are the unique thermoelectric parameter feature codes. These codes accurately characterize the thermoelectric state features of a specific charging stage of the battery.

[0065] S14: The extracted feature codes are input into the pre-trained model, and the thermoelectric coupling trajectory is output through feature matching and trajectory mapping algorithms. The pre-trained model is generated based on a large amount of battery thermoelectric data under different operating conditions. After the feature codes are input, they are matched with the feature templates stored in the model using a cosine similarity algorithm to determine the corresponding thermoelectric state type. Then, through the trajectory mapping algorithm, the variation law of the thermoelectric parameters corresponding to the feature codes is mapped into a visualized coupling trajectory curve, clearly showing the interaction relationship and dynamic change trend of parameters such as temperature, voltage, and current, providing an intuitive basis for subsequent charging strategy optimization.

[0066] S2: Based on the thermoelectric coupling trajectory, a spatiotemporal gradient algorithm is used to perform coupling gradient analysis, generating a gradient sequence containing the thermoelectric coupling strength and rate of change. The coupling vector is extracted from the sequence, and the thermoelectric matching degree is calculated based on an algorithm derived from the energy conservation equation to quantify the coupling synergy.

[0067] S21: A spatiotemporal gradient algorithm is used to perform coupling gradient analysis on the thermoelectric coupling trajectory. By calculating the rate of change of thermoelectric parameters at different time points and spatial locations, a gradient sequence containing the thermoelectric coupling strength and rate of change is generated. Specifically, based on the temperature, voltage, and current data at each moment in the trajectory, the ratio of parameter difference to distance between adjacent spatiotemporal points is solved using the spatiotemporal gradient formula to obtain the coupling strength coefficient and rate of change value, which are then arranged in chronological order to form a gradient sequence.

[0068] S22: Based on the gradient sequence, the coupling vectors of different time and space segments are extracted. The vectors contain information on the direction and magnitude of the coupling strength and rate of change in the gradient sequence. The coupling components of each dimension are separated from the sequence data by the vector decomposition algorithm and integrated into a set of coupling vectors that characterize the dynamic features of thermoelectric coupling, ensuring that the vectors can accurately reflect the core change law of the gradient sequence.

[0069] S23: Substitute the coupling vector into the algorithm derived based on the energy conservation equation to calculate the thermoelectric matching degree. A correlation model between thermoelectric parameters and energy conversion efficiency is established through the energy conservation equation. The amplitude and direction parameters of the coupling vector are substituted into the model to solve for the quantitative index of thermoelectric parameter synergy, thus quantifying the coupling synergy and providing a quantitative basis for the dynamic optimization of the charging strategy.

[0070] Substituting the coupling vector into the quantization model derived from the energy conservation equation, the formulas for calculating electrical and thermal energy are expressed as follows:

[0071]

[0072]

[0073] in, U is the electrical energy, U is the average voltage of a single cell, and I is the charging current.

[0074] t is the sampling time interval. m is the mass of the battery cell, c is the specific heat capacity of the battery, and ΔT is the temperature change during the sampling time.

[0075] The formula for calculating the matching degree is expressed as follows:

[0076]

[0077] Where M is the thermoelectric matching degree, θ is the direction angle, and A is the amplitude. Solving for the specific thermoelectric matching degree values ​​between 0 and 100 completes the synergy quantification, providing a clear basis for charging strategy optimization.

[0078] S3: Based on the thermoelectric matching degree in step two, construct a dynamic model of the thermoelectric coupling state to analyze coupling imbalance and cooperative state events in real time during charging. Tag the events to generate monitoring tags, extract coupling balance features from the tag carriers, mark the thermoelectric equilibrium point, and achieve precise positioning of the coupling state.

[0079] S31: Based on thermoelectric matching degree and combined with the time-series thermoelectric parameter sequence of the extreme charging process, a nonlinear dynamic model is constructed. The model parameters are optimized by Kalman filtering algorithm, and the dynamic evolution curve of thermoelectric coupling state is output.

[0080] S32: Monitor abrupt changes and gradient anomalies in the dynamic evolution curve of thermoelectric coupling state, identify over-temperature and potential imbalance state events, and use One-Hot coding to label the event type and spatiotemporal coordinates to generate a set of monitoring tags containing event attributes.

[0081] First, obtain the dynamic evolution curve of the thermoelectric coupling state. Combined with the preset normal curve fluctuation range during the charging process, scan the curve trend time by time to capture the abrupt change points that deviate from the normal range and the abnormal segments where the gradient value exceeds the threshold. Output preliminary feature data including the abrupt change time and the abnormal gradient interval.

[0082] Based on preliminary feature data, the threshold of curve mutation amplitude corresponding to the over-temperature state is compared with the gradient anomaly pattern corresponding to the potential imbalance. The specific state event type corresponding to the mutation or anomaly is confirmed by feature matching. At the same time, the time node and spatial location information of the event are recorded to form a basic event information table.

[0083] Based on the event basic information table, independent One-Hot encoding dimensions are constructed for different event types and spatiotemporal coordinates. The type and spatiotemporal attributes of each event are converted into binary encoding vectors. All encoding vectors are then integrated to generate a set of monitoring tags containing complete event attributes.

[0084] S33: Extract coupling balance features from the monitoring tag set, filter by feature threshold, locate spatiotemporal nodes whose features satisfy the equilibrium conditions, and mark the specific thermoelectric equilibrium point coordinates and time sequence location.

[0085] The monitoring tag set is obtained, and the coupling balance related features such as the coordinated change law of thermoelectric parameters and the stability of energy conversion efficiency contained in the tags are analyzed. The core feature vector that can characterize the thermoelectric coupling equilibrium state is extracted by feature extraction algorithm, forming a coupling balance feature set.

[0086] Using the coupling equilibrium feature set as input, combined with the feature benchmark value under the ideal thermoelectric equilibrium state of the extreme charge battery, a reasonable feature threshold range is set, and each core feature in the feature set is compared and screened one by one. Features that meet the equilibrium conditions and their corresponding spatiotemporal information are retained to obtain candidate equilibrium feature data.

[0087] Based on candidate equilibrium feature data, the time node and spatial coordinates corresponding to each feature that meets the conditions are traced. Through spatiotemporal coordinate correlation analysis, the spatiotemporal nodes that meet all equilibrium conditions are accurately located, and finally the specific thermoelectric equilibrium point coordinates and time sequence location information are marked.

[0088] S4: Based on the thermoelectric equilibrium point, determine the charging channel suitable for the current coupling state. Detect the impact of channel transmission status on thermoelectric coupling and calculate the channel coupling carrying capacity. Optimize charging parameters based on the capacity and calculate the optimized thermoelectric coordination ratio of thermal regulation rate / electrical input rate.

[0089] S41: Based on the current thermoelectric synergy state reflected by the thermoelectric equilibrium point, retrieve the preset charging channel parameter library, compare the compatibility of different channels with the thermoelectric parameters under this equilibrium state, and combine the current temperature and potential distribution characteristics of the battery to select the appropriate charging channel that can maintain thermoelectric balance.

[0090] S42: Taking a defined adaptive charging channel as the object, collect real-time status data such as voltage stability and current transmission efficiency of the channel during transmission, analyze the influence of these data changes on thermoelectric coupling parameters, and calculate the maximum thermoelectric coupling load that the channel can withstand based on the degree of influence and the channel's own transmission limit.

[0091] S421: Based on the target charging channel, collect key indicators such as transmission rate and stability in real time, comprehensively monitor the current transmission status of the channel, and form complete channel status data.

[0092] S422: Based on the collected channel state data, analyze the mechanism of action of different state parameters on the synergy of thermoelectric parameters and energy balance, and quantify the degree of influence of channel state on thermoelectric coupling balance.

[0093] S423: Based on the influence of channel conditions on thermoelectric coupling balance and combined with the battery thermoelectric load capacity limit, the maximum value of the coupled load that the channel can stably support is derived, and the channel coupling capacity is obtained.

[0094] S43: Using the calculated channel coupling carrying capacity as a key constraint, and combining it with the reference parameters of the thermoelectric equilibrium point, adjust the core parameters such as charging voltage and current to adapt to the capacity limit. After the parameter optimization is completed, the thermal regulation rate and electrical input rate at this time are simultaneously measured to obtain the corresponding thermoelectric coordination ratio.

[0095] Using channel coupling capacity as the key constraint and combining the reference parameters of the thermoelectric equilibrium point, a charging parameter adjustment model is established. The core parameters such as charging voltage and current are adjusted through a dynamic adaptation algorithm to ensure that the parameter range does not exceed the capacity limit, thus obtaining an optimized charging parameter set.

[0096] Based on the optimized charging parameter set and relying on the battery thermoelectric response model, the thermal regulation rate and electrical input rate of the battery under these parameters are calculated simultaneously to ensure that the rate data corresponds one-to-one with the optimized parameters, thus forming complete rate monitoring data.

[0097] Based on the calculated thermal regulation rate and electrical input rate, the ratio between the two is calculated through rate coordination analysis. This ratio is the thermoelectric coordination ratio that adapts to the current channel capacity and thermoelectric equilibrium state, thus completing the final parameter coordination quantization.

[0098] S5: Generate adaptive charging seeds driven by coupling state based on the thermoelectric coordination ratio. Query the coupling safety parameters corresponding to the seed and identify the coupling protection rules in the safety identifier. Generate a charging strategy with optimal coupling coordination as the goal, and add core sensing data such as coupling trajectory and matching degree to the report to achieve closed-loop management of the entire coupling process.

[0099] S51: Based on the thermoelectric coordination ratio reflecting the thermoelectric synergy characteristics, and combined with the dynamic coupling requirements of the extreme charging process, a charging seed that can drive adaptive adjustment of charging parameters is generated through a feature mapping algorithm.

[0100] S52: Using the generated adaptive charging seed as an index, query the preset coupling safety parameter database, extract the safety parameters such as the upper limit of voltage and temperature threshold corresponding to the seed, and at the same time parse the thermoelectric coupling protection logic and execution rules contained in the safety identifier.

[0101] S53: Based on the identification of coupling protection rules, with the optimal synergy of thermoelectric coupling as the core objective, it integrates charging seeds and safety parameters to build a strategy generation model, generates dynamically adjusted charging strategies, and supplements core perception data such as coupling trajectory and matching degree in the output report, realizing closed-loop control of the entire coupling process from state monitoring to strategy execution.

[0102] S531: Using coupling protection rules as a constraint framework and thermoelectric coupling synergy as the core objective, it deeply integrates the dynamic driving characteristics of charging seeds with the boundary constraints of safety parameters to construct a multi-dimensional parameter synergy strategy generation model.

[0103] S532: The fused charging seed and safety parameter input strategy are used to generate a model. The adjustment coefficients of charging voltage and current are dynamically calculated through an adaptive algorithm to generate a charging strategy that changes in real time with the coupling state.

[0104] S533: In the generated charging strategy output report, supplement the time-series evolution data of the coupling trajectory and the quantitative index of thermoelectric matching degree, integrate the data of the whole process, and form a coupling control link.

[0105] like Fig. 2 As shown, the present invention also provides an adaptive charging system for high-capacity batteries based on multi-dimensional thermal-electric coupling sensing, comprising:

[0106] The parameter acquisition module is used to collect multi-dimensional thermoelectric parameters of the extreme charge battery, construct a spatiotemporally synchronized thermoelectric parameter sequence, extract the feature code of the thermoelectric parameter sequence, and obtain the thermoelectric coupling trajectory through feature code mapping.

[0107] The hotspot matching module is used to analyze the thermoelectric coupling trajectory using a spatiotemporal gradient algorithm to extract the coupling vector, and calculate the thermoelectric matching degree based on the coupling vector.

[0108] The hotspot balancing module is used to construct a dynamic model of thermoelectric coupling state based on thermoelectric matching degree, analyze state events in real time during the charging process, label the state events to generate monitoring tags, extract coupling balance features from the tag carrier, and mark the thermoelectric equilibrium point.

[0109] The hotspot coordination module is used to determine the charging channel based on the thermoelectric equilibrium point, calculate the coupling carrying capacity of the charging channel and optimize the charging parameters, and calculate the optimized thermoelectric coordination ratio based on the optimized charging parameters.

[0110] The charging strategy module is used to generate an adaptive charging seed based on the thermoelectric coordination ratio, query the coupling safety parameters and coupling protection rules of the seed, and generate a charging strategy with the goal of optimal coupling coordination.

[0111] The adaptive charging method for high-capacity batteries based on multi-dimensional thermo-electric coupling sensing provided by this invention generates the following through multi-dimensional thermoelectric parameter acquisition and coupling analysis: First, parameters are acquired to obtain the coupling trajectory; then, the thermoelectric matching degree is calculated through gradient analysis; after locating the thermoelectric equilibrium point, the charging parameters are optimized to obtain the thermoelectric coordination ratio; finally, the coordination ratio is used to generate a coupling-driven charging seed; and combined with safety rules, an adaptive charging strategy is output. The beneficial effects achieved are as follows:

[0112] This invention breaks through the limitations of traditional qualitative analysis. It generates a gradient sequence containing coupling strength and rate of change through a spatiotemporal gradient algorithm, extracts the coupling vector, and substitutes it into a model derived based on the energy conservation equation to calculate the thermoelectric matching degree. This achieves precise quantification of coupling synergy, providing a clear quantitative basis for charging strategy optimization and avoiding strategy deviations caused by previous reliance on experience-based judgments. Based on the thermoelectric matching degree, a nonlinear dynamic model is constructed, and Kalman filtering is used to optimize parameters, outputting a coupling state evolution curve. By monitoring abrupt changes in the curve and gradient anomalies, problems such as overheating and potential imbalance are identified. This enables full-process control of the battery coupling state, from dynamic monitoring to anomaly identification and precise positioning of the equilibrium point, effectively avoiding safety risks caused by coupling imbalance.

[0113] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, including several instructions to cause a computer device (which may be a personal computer, server, or network device) to execute the methods of various embodiments or some parts of embodiments.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An adaptive charging method for high-capacity batteries based on multi-dimensional thermal-electric coupling sensing, characterized in that, include: S1: Collect multi-dimensional thermoelectric parameters of the extreme charge battery, construct a spatiotemporally synchronized thermoelectric parameter sequence, extract the feature code of the thermoelectric parameter sequence, and obtain the thermoelectric coupling trajectory through feature code mapping; S2: Use the spatiotemporal gradient algorithm to analyze the thermoelectric coupling trajectory and extract the coupling vector, and calculate the thermoelectric matching degree based on the coupling vector; S3: Construct a dynamic model of thermoelectric coupling state based on the thermoelectric matching degree, analyze the state events during the charging process in real time, label the state events to generate monitoring tags, extract the coupling balance features in the tag carrier, and mark the thermoelectric equilibrium point. S4: Determine the charging channel based on the thermoelectric equilibrium point, calculate the coupling carrying capacity of the charging channel and optimize the charging parameters, and calculate the optimized thermoelectric coordination ratio based on the optimized charging parameters; S5: Generate an adaptive charging seed based on the thermoelectric coordination ratio, query the coupling safety parameters and coupling protection rules of the seed, and generate a charging strategy with the goal of optimal coupling coordination; In step S1, the specific steps for obtaining the thermoelectric coupling trajectory are as follows: S11: A distributed sensor array is used to collect the cell temperature, single cell voltage, loop current and entropy change parameters of the battery to obtain the original parameters of the heat dissipation battery. S12: Sort the original parameters of the heat dissipation device by timestamp and associate them with spatial acquisition location information to construct a spatiotemporal parameter sequence; S13: Use deep learning algorithms to extract the core features of the spatiotemporal parameter sequence and generate a unique thermoelectric parameter feature code; S14: Input the extracted feature code into the pre-trained model, and output the thermoelectric coupling trajectory through feature matching and trajectory mapping algorithm.

2. The adaptive charging method for high-capacity batteries based on multi-dimensional thermal-electric coupling sensing according to claim 1, characterized in that, In step S2, the specific steps for calculating the thermoelectric matching degree based on the coupling vector are as follows: S21: The spatiotemporal gradient algorithm is used to perform coupled gradient analysis on the thermoelectric coupling trajectory, calculate the rate of change of thermoelectric parameters at different time nodes and spatial locations, and generate gradient sequences. S22: Extract coupling vectors for different spatiotemporal segments based on the gradient sequence and integrate them into a set of coupling vectors; S23: Calculate the thermoelectric matching degree based on the coupling vector, establish a correlation model between thermoelectric parameters and energy conversion efficiency, solve the quantitative index of thermoelectric parameter cooperative matching, and quantify the coupling synergy.

3. The adaptive charging method for high-capacity batteries based on multi-dimensional thermal-electric coupling sensing according to claim 1, characterized in that, In step S3, the specific steps for marking the thermoelectric equilibrium point are as follows: S31: Based on thermoelectric matching degree and combined with the time-series thermoelectric parameter sequence of the extreme charging process, a nonlinear dynamic model is constructed. The model parameters are optimized by Kalman filtering algorithm, and the dynamic evolution curve of thermoelectric coupling state is output. S32: Monitor abrupt changes and gradient anomalies in the dynamic evolution curve of thermoelectric coupling state, identify over-temperature and potential imbalance state events, and use One-Hot coding to label the event type and spatiotemporal coordinates to generate a set of monitoring tags containing event attributes. S33: Extract coupling balance features from the monitoring tag set, filter by feature threshold, locate spatiotemporal nodes whose features meet the equilibrium conditions, and mark the specific thermoelectric equilibrium point coordinates and time sequence location.

4. The adaptive charging method for high-capacity batteries based on multi-dimensional thermal-electric coupling sensing according to claim 3, characterized in that, In step S32, the specific steps for generating a set of monitoring tags containing event attributes are as follows: S321: Obtain the dynamic evolution curve and normal curve fluctuation range of thermoelectric coupling state, capture abrupt change points that deviate from the normal range and abnormal segments where the gradient value exceeds the threshold, and output preliminary feature data. S322: Based on the preliminary feature data, compare the curve mutation amplitude threshold corresponding to the over-temperature state, confirm the specific state event type of the mutation through feature matching, record the time node and spatial location information of the event, and form an event basic information table. S323: Based on the event basic information table, construct independent One-Hot encoding dimensions for different state event types and spatiotemporal coordinates, convert the type and spatiotemporal attributes of each event into binary encoding vectors, and generate a set of monitoring tags.

5. The adaptive charging method for high-capacity batteries based on multi-dimensional thermal-electric coupling sensing according to claim 1, characterized in that, In step S4, the specific steps for calculating the optimized thermoelectric compatibility ratio based on the optimized charging parameters are as follows: S41: Based on the current thermoelectric synergy state reflected by the thermoelectric equilibrium point, match a charging channel with parameter transmission capability and determine the target charging channel. S42: Taking the target charging channel as the object, monitor the channel transmission status, analyze the impact of the channel status on the thermoelectric coupling balance, calculate the upper limit of the coupling load that the channel can carry based on the degree of impact, and obtain the channel coupling carrying capacity. S43: Adjust the charging parameters according to the channel coupling carrying capacity, calculate the optimized thermal regulation rate and electrical input rate according to the charging parameters, and obtain the thermoelectric coordination ratio of the thermal regulation rate and electrical input rate.

6. The adaptive charging method for high-capacity batteries based on multi-dimensional thermo-electric coupling sensing according to claim 5, characterized in that, In step S42, the specific steps for obtaining the channel coupling capacity are as follows: S421: Based on the target charging channel, real-time acquisition of transmission rate and stability, comprehensive monitoring of the current transmission status of the channel, and formation of complete channel status data; S422: Based on the collected channel state data, analyze the mechanism of action of different state parameters on the synergy of thermoelectric parameters and energy balance, and quantify the degree of influence of channel state on thermoelectric coupling balance; S423: Based on the influence of channel conditions on thermoelectric coupling balance and combined with the battery thermoelectric load capacity limit, the maximum value of the coupled load that the channel can stably support is derived, and the channel coupling capacity is obtained.

7. The adaptive charging method for high-capacity batteries based on multi-dimensional thermal-electric coupling sensing according to claim 1, characterized in that, In step S5, the specific steps for generating the charging strategy are as follows: S51: Based on the thermoelectric compatibility ratio and the dynamic coupling requirements of the extreme charging process, an adaptive charging seed is generated through a feature mapping algorithm; S52: Extract safety parameters from adaptive charging seeds and analyze thermoelectric coupling protection rules in safety identifiers; S53: With thermoelectric coupling optimization as the core objective, it integrates charging seeds and safety parameters to construct a strategy generation model and generate dynamically adjusted charging strategies.

8. The adaptive charging method for high-capacity batteries based on multi-dimensional thermal-electric coupling sensing according to claim 7, characterized in that, In step S53, the specific steps for constructing the policy generation model are as follows: S531: Using coupling protection rules as a constraint framework and thermoelectric coupling synergy as the core objective, the dynamic driving characteristics of the charging seed and the boundary constraints of safety parameters are deeply integrated to construct a multi-dimensional parameter synergy strategy generation model. S532: The fused charging seed and safety parameter input strategy are used to generate a model. The adjustment coefficients of charging voltage and current are dynamically calculated through an adaptive algorithm to generate a charging strategy that changes in real time with the coupling state. S533: In the generated charging strategy output report, supplement the time-series evolution data of the coupling trajectory and the quantitative index of thermoelectric matching degree, integrate the data of the whole process, and form a coupling control link.

9. An adaptive charging system for high-capacity batteries based on multi-dimensional thermal-electric coupling sensing, which employs the adaptive charging method for high-capacity batteries based on multi-dimensional thermal-electric coupling sensing as described in any one of claims 1 to 8, characterized in that, The charging system includes: The parameter acquisition module is used to collect multi-dimensional thermoelectric parameters of the high-capacity battery, construct a spatiotemporally synchronized thermoelectric parameter sequence, extract the feature code of the thermoelectric parameter sequence, and obtain the thermoelectric coupling trajectory through feature code mapping. The thermoelectric matching module is used to analyze the thermoelectric coupling trajectory using a spatiotemporal gradient algorithm to extract the coupling vector, and calculate the thermoelectric matching degree based on the coupling vector; The thermoelectric equilibrium module is used to construct a dynamic model of thermoelectric coupling state based on the thermoelectric matching degree, analyze state events in real time during the charging process, label the state events to generate monitoring tags, extract coupling balance features from the tag carrier, and mark the thermoelectric equilibrium point. The thermoelectric coordination module is used to determine the charging channel based on the thermoelectric equilibrium point, calculate the coupling carrying capacity of the charging channel and optimize the charging parameters, and calculate the optimized thermoelectric coordination ratio based on the optimized charging parameters. The charging strategy module is used to generate an adaptive charging seed based on the thermoelectric coordination ratio, query the coupling safety parameters and coupling protection rules of the seed, and generate a charging strategy with the goal of optimal coupling coordination.

Images