Rare earth lithium battery high-speed fast charging intelligent management system based on rare earth composite material

Abstract

The invention relates to the technical field of lithium battery intelligent management, and discloses a rare earth lithium battery high-speed fast charging intelligent management system based on a rare earth composite material. According to the system, a complete charging track composed of a charging state snapshot sequence is formed through a charging track construction module; processing through a multi-scale segmentation module to generate charging sub-spaces with different time spans; key charge and discharge event points representing the characteristics of the rare earth material are identified and marked in each subspace by an event identification and marking module; the space-time alignment mapping module is used for mapping a labeling result and a historical reference mode; and the control strategy generation module dynamically outputs a real-time charging instruction accordingly. Through multi-scale analysis of a charging track, predictive perception of a battery state evolution trend is realized; through accurate identification and mapping of the rare earth characteristic key event, the charging control strategy is enabled to deeply accord with the intrinsic characteristics of the material, so that the fast charging efficiency is improved on the premise of ensuring the safety and the service life of the battery.

Description

Technical Field

[0001] This invention relates to the field of intelligent management technology for lithium batteries, specifically to an intelligent management system for high-speed fast charging of rare earth lithium batteries based on rare earth composite materials. Background Technology

[0002] Currently, with the increasing demands for charging rates from electric vehicles and large-scale energy storage systems, rare-earth lithium batteries, possessing high energy density and excellent fast-charging potential, have become a research hotspot. The application of rare-earth composite materials in battery electrodes can improve lithium-ion transport numbers and electrode structural stability, but their charging and discharging processes also introduce complex electrochemical behaviors distinct from conventional lithium batteries. Existing battery management systems generally employ control strategies based on preset thresholds and fixed charging curves. These strategies primarily rely on real-time monitoring and feedback adjustment of individual cell parameters such as voltage, current, and temperature.

[0003] Such general-purpose management schemes have inherent flaws. Their control logic is based on parameter points within instantaneous or short time windows, lacking a continuous and holistic perspective on the dynamic evolution of the battery throughout the charging process. The system cannot effectively capture the evolution trajectory and inherent patterns of the charging state over time, making it difficult to distinguish between normal electrochemical processes and potential risk precursors, resulting in lagging and coarse control behavior. To ensure safety, charging strategies often tend to be conservative, failing to fully exploit the fast-charging capabilities of rare-earth composite battery materials.

[0004] Existing technologies are not designed specifically for the characteristics of rare-earth composite materials. Conventional battery models and historical databases are mostly built upon traditional materials such as lithium iron phosphate and ternary lithium, which cannot identify and interpret the unique electrochemical signals induced by rare-earth elements. This leads to a disconnect between management strategies and the inherent properties of the battery materials. It makes it impossible to perform precise and powerful charging within the optimal fast-charging range for the materials, and also difficult to intervene early during material-sensitive stages, thus limiting the full realization of the performance advantages of rare-earth lithium batteries. Summary of the Invention

[0005] The purpose of this invention is to provide a high-speed, fast-charging intelligent management system for rare-earth lithium batteries based on rare-earth composite materials, so as to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides a high-speed fast-charging intelligent management system for rare-earth lithium batteries based on rare-earth composite materials, the system comprising:

[0007] The charging trajectory construction module is used to construct the complete charging trajectory of a single battery cell during the charging process. The complete charging trajectory consists of a series of charging state snapshots arranged in time stamp order.

[0008] The multi-scale segmentation module is used to segment the complete charging trajectory into multiple scales to generate multiple charging subspaces with different time spans.

[0009] The event identification and labeling module is used to identify and label key charge and discharge event points that characterize the properties of rare earth composite battery within each charging subspace;

[0010] The spatiotemporal alignment and mapping module is used to perform spatiotemporal alignment and mapping between the labeled multiple charging subspaces and the reference charging modes in the battery cell historical database;

[0011] The control strategy generation module is used to dynamically generate a real-time charging control strategy for the battery cell based on the mapping result, and then send the real-time charging control strategy to the charging execution device.

[0012] Preferably, the complete charging trajectory of the constructed battery cell during the charging process includes:

[0013] The voltage, current, and temperature sequences of individual battery cells during the charging process are collected at a fixed frequency.

[0014] A unique timestamp is assigned to each voltage, current, and temperature value collected at each time point;

[0015] Combine the voltage, current and temperature values ​​at the same timestamp into a single charging state snapshot.

[0016] All charging status snapshots are linked together in chronological order of timestamps to form the complete charging trajectory.

[0017] Preferably, the step of multi-scale segmentation of the complete charging trajectory to generate multiple charging subspaces with different time spans includes:

[0018] Define multiple time window scales, each time window scale corresponding to a specific time length;

[0019] Each time window scale is used as a sliding window to slide on the complete charging trajectory, and a segment of the trajectory is captured each time the sliding is performed.

[0020] Define the trajectory segment captured in each slide as a charging subspace;

[0021] Each charging subspace is assigned a spatial identifier, which records its corresponding time window scale information and the start and end timestamps in the complete charging trajectory.

[0022] Preferably, identifying and labeling key charge and discharge event points characterizing the rare-earth composite material battery properties within each charging subspace includes:

[0023] For a given charging subspace, extract the voltage, current, and temperature sequences of all charging state snapshots contained therein;

[0024] Calculate the first-order and second-order difference sequences of the voltage sequence, and identify voltage inflection points as potential critical event points;

[0025] Calculate the fluctuation characteristics of the current sequence and identify current abrupt change points as potential critical event points;

[0026] Calculate the rising slope of the temperature sequence and identify temperature rise anomalies as potential critical event points;

[0027] Based on the preset rules for the electrochemical properties of rare earth composite materials, all potential key event points are screened and merged to finally determine the key charge and discharge event points in the charge e-space and label them with event types.

[0028] Preferably, the step of spatiotemporally aligning and mapping the labeled multiple charging subspaces with reference charging modes in the battery cell historical database includes:

[0029] Retrieve all historical charging records with the same identifier as the battery cell from the battery cell historical database;

[0030] Extract the reference charging pattern stored in each historical charging record. The reference charging pattern includes the type, occurrence time, and context information of historical key event points.

[0031] The multiple charging subspaces generated during the current charging process and marked with key charging and discharging event points are matched with the retrieved reference charging modes respectively.

[0032] The matching process includes: adjusting the time axis of the charging subspace to align it with the time axis of the reference charging mode, and calculating the consistency measure of key event points in the charging subspace with historical key event points in the reference charging mode in terms of type and relative timing.

[0033] Preferably, the step of dynamically generating a real-time charging control strategy for the battery cell based on the mapping result includes:

[0034] For each charging subspace, a matching confidence score is calculated based on its mapping result with the reference charging mode;

[0035] If the matching confidence level is higher than the preset threshold, the corresponding historical charging control parameters are extracted from the successfully matched reference charging mode as basic parameters.

[0036] Based on the specific numerical characteristics of key charging and discharging event points in the current charging subspace, the basic parameters are fine-tuned to generate real-time charging control parameters suitable for the current moment.

[0037] The real-time charging control parameters generated by all charging subspaces are integrated in chronological order to form the real-time charging control strategy.

[0038] Preferably, the step of fine-tuning the basic parameters based on the specific numerical characteristics of key charging and discharging event points within the current charging subspace to generate real-time charging control parameters suitable for the current moment includes:

[0039] Extract the voltage, current, and temperature measurements at each key charging / discharging event point within the current charging subspace;

[0040] Calculate the characteristic deviation between the measured value of each key charge / discharge event point and the corresponding reference value in the basic parameters;

[0041] Based on the direction and magnitude of the characteristic deviation, determine the adjustment direction and adjustment range of the charging current setting value, cutoff voltage threshold and temperature control threshold in the basic parameters;

[0042] The proportional-integral-derivative control algorithm is used to convert the adjustment direction and adjustment magnitude into specific correction amounts for the basic parameters;

[0043] The correction amount is superimposed with the basic parameters to obtain real-time charging control parameters applicable to the current charging subspace time range;

[0044] Preferably, the method further includes a verification and updating step for the real-time charging control strategy:

[0045] After applying the real-time charging control strategy, subsequent charging status snapshots of individual battery cells are collected to form a verification trajectory segment.

[0046] The verified trajectory segment is compared with the expected charging behavior model to calculate the strategy execution deviation.

[0047] If the deviation of the strategy execution exceeds the allowable range, the control strategy update mechanism is triggered. The control strategy update mechanism includes: re-executing the mapping steps with the reference charging mode based on the new key event points identified in the verification trajectory segment, and generating an updated real-time charging control strategy.

[0048] Preferably, the method further includes an embedded evaluation step of the health status of individual battery cells:

[0049] During the construction of the complete charging trajectory, feature vectors that reflect the structural stability of rare earth composite materials inside the battery are extracted simultaneously.

[0050] The feature vector is input into a pre-trained battery health assessment model, which outputs a current health index.

[0051] The current health index is incorporated as a hidden variable into the generation logic of the real-time charging control strategy, so that the real-time charging control strategy takes into account the real-time health status of individual battery cells when it is formulated.

[0052] Preferably, the method further includes a collaborative management step across individual battery cells:

[0053] When the management target is a battery pack containing multiple battery cells, a complete charging trajectory is independently constructed for each battery cell in the battery pack and a separate real-time charging control strategy is generated.

[0054] Establish a coordinator at the battery pack level, which receives real-time charging control strategies from all individual battery cells;

[0055] The coordinator optimizes the real-time charging control strategy for each battery cell based on the current health index and real-time charging status of all individual cells, generating a set of coordinated charging control commands to ensure the balance and safety of the overall charging process of the battery pack.

[0056] Compared with the prior art, the beneficial effects of the present invention are:

[0057] By constructing a complete charging trajectory consisting of a series of charging state snapshots and segmenting it at multiple scales, a panoramic state perception from microscopic transients to macroscopic trends is achieved. This method elevates the battery charging process from a discrete sequence of data points to a continuous spatiotemporal trajectory object. Within charging subspaces across different time spans, the system can simultaneously analyze long-term health state evolution, medium-term thermodynamic characteristics, and short-term dynamic responses. This analytical dimension enables the control system to discern the evolutionary trends behind instantaneous parameter fluctuations and identify early characteristics of anomalous patterns masked at a single time scale. This allows for a shift from passive response to proactive predictive decision-making, making it possible to implement extreme optimization charging within absolute safety boundaries.

[0058] By identifying and labeling key event points characterizing the properties of rare-earth composite materials within each charging subspace, and aligning and mapping these spatiotemporal sequences with specific event markers to historical reference patterns, a deep coupling between the control strategy and the intrinsic properties of the material is achieved. The definition of key event points is rooted in the specific electrochemical behavior of rare-earth composite materials. The spatiotemporal alignment mapping technology ensures that, under different initial conditions and external disturbances, the current charging state can find the most suitable historical optimal charging path as a reference. This allows the charging control energy to be tailored to the kinetic characteristics of the material, maximizing the charging current within the phase or voltage window where the rare-earth composite material exhibits high stability and high ionic conductivity, while avoiding sensitive regions or windows prone to side reactions determined by the material properties, thereby achieving a simultaneous improvement in safety and fast charging efficiency. Attached Figure Description

[0059] Figure 1 This is a schematic diagram illustrating the working principle of the high-speed fast charging intelligent management system for rare earth lithium batteries based on rare earth composite materials described in this invention.

[0060] Figure 2 A flowchart for constructing the complete charging trajectory of a single battery cell during the charging process;

[0061] Figure 3 A flowchart for identifying and labeling key charge and discharge event points within each charging subspace;

[0062] Figure 4 A spatiotemporal alignment consistency measurement diagram between the charging e-space and historical reference patterns for fast-charging rare-earth lithium batteries.

[0063] Figure 5 This is a graph showing the dynamic changes in the charging current during the rapid charging of a rare-earth lithium battery. Detailed Implementation

[0064] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0065] Please see Figure 1This invention provides a high-speed, fast-charging intelligent management system for rare-earth lithium batteries based on rare-earth composite materials. The system includes: a charging trajectory construction module responsible for collecting voltage, current, and temperature data at a fixed frequency during battery charging, assigning a timestamp to each data point, combining multiple parameter values ​​at the same timestamp into a charging state snapshot, and then linking these snapshots in chronological order to form a complete charging trajectory; a multi-scale segmentation module using multiple predefined time window scales as sliding windows to slide across the complete charging trajectory to extract trajectory segments of different time spans, each segment being defined as a charging subspace and assigned a unique identifier; an event identification and labeling module analyzing the differential characteristics and fluctuation patterns of voltage, current, and temperature sequences within each charging subspace, identifying key event points consistent with the electrochemical characteristics of rare-earth composite materials, such as voltage inflection points or current abrupt changes, and labeling them accordingly; and a spatiotemporal alignment and mapping module matching the labeled charging subspaces with reference charging patterns in a historical database, adjusting the time axis alignment, and calculating a consistency measure of event point types and timing. The control strategy generation module calculates the matching confidence based on the mapping results, extracts basic parameters from the historical matching patterns, fine-tunes the generation of real-time charging control parameters by combining the characteristics of the current event point, and integrates them into a strategy to be sent to the charging device.

[0066] Example 1: See Figure 2 During the construction of the battery cell charging trajectory, the system collects voltage, current, and temperature sequences at a fixed frequency. The sampling frequency is set according to battery characteristics and system accuracy requirements, such as collecting data once per second or using a higher frequency, such as ten times per second. Each sampling moment corresponds to a unique timestamp for the sensor readings of voltage, current, and temperature. The timestamp is derived from a high-precision clock chip, ensuring that all data points have a globally consistent and strictly monotonically increasing time sequence throughout the charging process. In specific implementations, the voltage sequence is obtained through a high-precision analog-to-digital converter, the current sequence is sampled using a Hall current sensor, and the temperature sequence is obtained through thermocouples or multi-point temperature sensor arrays attached to the surface of the battery cell. The voltage, current, and temperature values ​​at the same timestamp are combined into a charging state snapshot. The data structure of the charging state snapshot is typically in record form, including a timestamp field, a voltage value field, a current value field, and a temperature value field. Based on the chronological order of timestamps, the system links all charging state snapshots together. The linking operation is implemented through pointers or array indexes to form a complete charging trajectory. The complete charging trajectory is stored and managed in memory in the form of a time-series database or a circular buffer to support efficient data writing and traversal querying.

[0067] In the multi-scale segmentation stage, the system defines multiple time window scales. The types and lengths of these time window scales are set based on prior knowledge of the electrochemical relaxation process of rare-earth composite battery. In specific implementations, these time window scales can include second-level, minute-level, and ten-minute-level windows. For example, a specific configuration includes three scales: a short-scale window of ten seconds to capture fast transient responses; a medium-scale window of one minute to analyze polarization processes with moderate time constants; and a long-scale window of five minutes to observe slow thermal accumulation and material phase transition trends. Each time window scale is used as a sliding window, sliding across the complete charging trajectory. The step size of the sliding window can be set to a fixed value, such as half the window length, to achieve local overlap and coverage of the complete charging trajectory, avoiding the omission of key features that appear at the window boundaries. Each sliding operation extracts a continuous trajectory segment from the complete charging trajectory. The extraction process is completed by calculating the position indices of the start and end timestamps within the complete charging trajectory. Each trajectory segment captured by each sliding motion is defined as a charging subspace. The charging subspace is an independent data unit, which contains a complete data copy or reference pointer of all charging state snapshots within the time window.

[0068] Each charging subspace is assigned a spatial identifier, which employs a structured encoding method. The encoded information records at least its corresponding time window scale information and the start and end timestamps in the complete charging trajectory. In some embodiments, the spatial identifier can be a composite key, composed of a window scale code, a trajectory start index, and a trajectory end index. The spatial identifier enables subsequent processing modules to quickly locate the spatiotemporal attributes and scale range of the charging subspace. The multi-scale segmentation module performs the above sliding window segmentation operation in parallel or serially on all predefined time window scales, ultimately generating a set of multiple charging subspaces with different time spans. These charging subspaces collectively constitute a multi-granularity perspective representation of the same charging process.

[0069] In practical implementation, the construction of the complete charging trajectory and the multi-scale segmentation process can be executed in a pipeline manner. That is, after the charging process begins, the charging trajectory construction module generates new charging state snapshots in real time and appends them to the complete charging trajectory, while the multi-scale segmentation module continuously monitors the growth of the complete charging trajectory and dynamically applies a sliding window to generate new charging subspaces. It is understood that the sliding window truncation operation needs to consider data boundary handling. For example, when the sliding window approaches the end of the complete charging trajectory, if the remaining data is insufficient to fill the entire window, zero-padding, hold, or waiting strategies can be adopted. Optionally, the system can attach metadata to each charging subspace, including statistical features such as the mean of the voltage sequence and the variance of the current sequence within that space, for the event recognition module to pre-screen.

[0070] Example 2: See Figure 3 The event identification and labeling module operates on a charging subspace, extracting the voltage, current, and temperature sequences from all charging state snapshots within the subspace. The voltage sequence consists of voltage measurements arranged in timestamp order within the charging subspace. The first-order difference sequence of the voltage sequence is calculated by performing a backward difference operation on the voltage values ​​at consecutive timestamps; that is, subtracting the previous voltage value from the next. The second-order difference sequence is obtained by performing the same backward difference operation on the first-order difference sequence. Identifying voltage inflection points as potential critical event points involves setting a difference threshold. When the absolute value of the second-order difference sequence exceeds a preset threshold, the corresponding voltage sequence point is marked as a potential voltage inflection point. The fluctuation characteristics of the current sequence are evaluated by calculating the standard deviation of the current values ​​within a sliding window. The length of the sliding window is configurable, for example, containing five consecutive sampling points. When the calculated standard deviation value is greater than a set fluctuation threshold, the current sampling point at the center of the window is identified as a current abrupt change point. The slope of the temperature sequence is calculated using a linear fitting method. A least-squares linear regression is performed on a continuous range of temperature data points within the charging battery space, and the slope of the fitted line is the slope. When the slope exceeds the upper limit of the normal range set based on the thermal properties of the battery materials, the corresponding temperature sequence interval is marked as an abnormal temperature rise point.

[0071] Based on pre-defined rules governing the electrochemical properties of rare-earth composite materials, all potential critical event points are screened and merged. These rules specifically reflect the influence of rare-earth element doping on the lattice structure and ion diffusion dynamics of electrode materials. In practice, the rule base contains multiple logical judgment conditions. For example, a rule might stipulate that if two voltage inflection points are too close in time and their voltage change directions are consistent, they are merged into a single event point representing a solid solution phase transition. Another rule might stipulate that a current abrupt change is only retained as a valid point when it is accompanied by a voltage inflection point and the temperature change is within a specific tolerance range. This corresponds to interfacial side reactions that may occur in rare-earth composite materials. Finally, the critical charge-discharge event points within the charge electrolyte space are determined and labeled with event types. The event type labels come from a predefined set, which may include categories directly related to the properties of rare-earth composite materials, such as "rare-earth lattice ordering transition," "interfacial lithium deposition initiation," and "solid electrolyte interfacial film reconstruction."

[0072] The spatiotemporal alignment mapping module retrieves all historical charging records with the same identifier as the currently charging battery cell from the battery cell historical database. This identifier is typically a unique code for the battery cell. The module extracts the reference charging pattern stored in each historical charging record. This reference charging pattern is a data structure that encapsulates key information from the historical charging process, including the type of historical key event points, the absolute occurrence time of each historical key event point during the historical charging process or its relative occurrence time relative to the start of charging, and the contextual information of the historical key event points. The contextual information may include auxiliary parameters such as the average current and ambient temperature at the time of the event. Multiple charging subspaces generated during the current charging process and labeled with key charge / discharge event points are then matched with the retrieved reference charging patterns.

[0073] The core of the matching process is timeline alignment and consistency metric calculation. Adjusting the timeline of the charging subspace involves linearly transforming the timestamps of all event points within the charging subspace to align its timeline with the timeline of the reference charging pattern in both length and phase. The scaling factor *s* is determined by comparing the total time span of the charging subspace with the corresponding time span of the reference charging pattern, while the translation factor *t* is determined by finding the time offset between the first critical event point in the charging subspace and the first historical critical event point in the reference charging pattern. A consistency metric is calculated between the critical event points in the charging subspace and the historical critical event points in the reference charging pattern in terms of type and relative timing. It can be calculated using a weighted function:

[0074]

[0075] Where: characters Represents the final consistency metric; character Represents the weighting coefficients assigned to the similarity of event types; characters The event type similarity score is calculated based on the degree of matching between the key event point type within the charging subspace and the corresponding historical key event point type in the reference charging mode; character Represents the weight coefficients assigned to the similarity of event sequences; characters The event sequence similarity score is calculated based on the degree of matching between the relative time intervals of key event points on the aligned timeline. In some embodiments, a dynamic time warping algorithm can be used to calculate... This algorithm can handle nonlinear scaling along the time axis. It's understandable that the matching process might find multiple candidate reference charging modes for the same charging subspace; in this case, the reference charging mode with the highest consistency metric C is selected as the final mapping object. Optionally, the matching process can also incorporate spatial scale matching, that is, prioritizing mapping charging subspaces with similar time window scales to reference charging modes with similar analytical granularity. The entire spatiotemporal alignment mapping process provides important historical data and comparison benchmarks for subsequent control strategy generation.

[0076] See Figure 4 This diagram is the core visualization result of the spatiotemporal alignment mapping process. After identifying key event points in the charging subspace, they need to be matched with reference charging modes in the battery history database. This diagram represents the quantification result of this matching process. The horizontal axis represents four historical reference charging modes, and the vertical axis represents the consistency metric value. The purpose of this diagram is to provide a basis for the generation of subsequent control strategies: the system selects the reference mode with the highest consistency metric, extracts its historical charging control parameters as basic parameters, and then fine-tunes them to obtain the current real-time charging strategy. This result also demonstrates that the system can accurately match historical charging paths adapted to the characteristics of rare earth composite materials, providing data support for the material adaptability of subsequent fast charging strategies.

[0077] Example 3: The control strategy generation module initiates a processing flow for each charging subspace. The system calculates a matching confidence score based on the mapping result between the charging subspace and the reference charging mode. The matching confidence score is obtained by normalizing the consistency metric value obtained during the mapping process, with the normalization range set between zero and one. If the calculated matching confidence score is higher than a preset threshold (which can be configured as 0.8 or other empirical values), the corresponding historical charging control parameters are extracted from the successfully matched reference charging mode as basic parameters. The basic parameters typically include key control variables such as the charging current setpoint, cutoff voltage threshold, and temperature control threshold. The basic parameters are fine-tuned based on the specific numerical characteristics of key charging and discharging event points within the current charging subspace. The voltage measurement value, current measurement value, and temperature measurement value of each key charging and discharging event point within the current charging subspace are extracted. These measurements are directly read from the charging state snapshot. Calculate the characteristic deviation between the measured value and the corresponding reference value in the basic parameters for each key charge and discharge event point. The direction of the characteristic deviation is determined by comparing the magnitude of the measured value and the reference value. For example, when the voltage measured value is greater than the reference value, the deviation direction is positive. The magnitude of the characteristic deviation is calculated by the absolute difference or the relative difference. The relative difference is the percentage difference between the measured value and the reference value.

[0078] Based on the direction and magnitude of the characteristic deviation, the adjustment direction and magnitude of the charging current setpoint, cutoff voltage threshold, and temperature control threshold in the basic parameters are determined. The adjustment direction is determined by the sign of the deviation, and the adjustment magnitude is proportional to the magnitude of the deviation. A proportional-integral-derivative (PID) control algorithm is used to convert the adjustment direction and magnitude into specific corrections to the basic parameters. The proportional term of the PID algorithm processes the characteristic deviation at the current moment, the integral term accumulates the sum of historical deviations, and the derivative term predicts the trend of deviation changes. The correction amount can be expressed by the following formula:

[0079]

[0080] Where: characters This represents the specific amount of correction to the basic parameters, including adjustments to multiple parameters such as current and voltage; characters Represents the proportional gain coefficient, which controls the intensity of the response to the current deviation; character Represents the currently calculated feature deviation value; character Represents the integral gain coefficient, which controls the correction strength for accumulated historical deviations; character The integral of the characteristic deviation over time is obtained by multiplying the deviation value by the time interval. The result is obtained by summing the characters. Represents the differential gain coefficient, controlling the degree of suppression of the rate of change of deviation; character The rate of change representing the characteristic deviation is calculated by dividing the difference between the current deviation and the deviation at the previous time step by the time interval. The calculated correction amount is then... The parameters are superimposed on the base parameters using vector addition to obtain real-time charging control parameters applicable to the current charging subspace time range. All real-time charging control parameters generated in all charging subspaces are then integrated in chronological order, sorted based on the start and end timestamps in the spatial identifiers of the charging subspaces, forming a complete real-time charging control strategy. This strategy is ultimately converted into a device-recognizable instruction sequence and sent to the charging execution device.

[0081] In practical implementation, the calculation of matching confidence can incorporate weighting factors. For example, the consistency metric can be weighted based on the historical usage frequency of the reference charging mode or the health status of individual battery cells before normalization. Extraction of basic parameters may involve interpolation or extrapolation. When the timescale of the reference charging mode is not entirely consistent with the current charging subspace, the system resamples historical control parameters along the time axis to match the current context. The calculation of characteristic deviations can employ a multivariate comprehensive deviation index, such as weighting and fusing voltage, current, and temperature deviations into a single characteristic deviation value. Then, the proportional-integral-derivative (PID) control algorithm is input. Optionally, fuzzy logic control can be introduced into the fine-tuning process, combining the fuzzy set of characteristic deviations with the fuzzy rule base of the adjustment amount to handle nonlinear characteristic deviations. The integration of real-time charging control parameters needs to consider the time overlap problem. When the time ranges of adjacent charging subspaces overlap, the system performs a weighted average of the parameters in the overlapping region or selects the parameter value with higher confidence.

[0082] See Figure 5 This diagram visualizes the control strategy generation process. Based on the spatiotemporal mapping results, fundamental parameters are extracted and fine-tuned using the characteristics of current key event points to generate real-time charging control parameters. This diagram specifically illustrates the adjustment process of the charging current parameters. The horizontal axis represents charging time, and the vertical axis represents charging current; the dashed line represents the base current, and the solid line represents the adjusted current. This diagram intuitively demonstrates the design of the control strategy dynamically adapting to the battery state: through fine-tuning, it avoids the efficiency loss of conservative charging while also adapting to the electrochemical characteristics of rare-earth composite materials, achieving a balance between fast charging efficiency and safety.

[0083] Example 4: After applying the real-time charging control strategy, the system continues to collect subsequent charging state snapshots of individual battery cells at a fixed frequency. These snapshots include voltage, current, and temperature readings, and are arranged in timestamp order to form a verification trajectory segment. The duration of the verification trajectory segment covers the entire cycle from the application of the control strategy to the next evaluation point. The system compares the verification trajectory segment with the expected charging behavior model, which is a reference trajectory trained based on a large amount of historical normal charging data. This model describes the standard pattern of how battery voltage, current, and temperature should change over time under ideal control. The strategy execution deviation is calculated; it is a scalar indicator that quantifies the difference between the verification trajectory segment and the expected charging behavior model. It can be calculated using the following formula:

[0084]

[0085] Where: characters Represents the final calculated policy execution deviation; character Represents the total number of charging state snapshots contained in the verification trajectory segment; characters Represents the weighting coefficients of the voltage sequence; characters Represents the voltage measurement value of the i-th snapshot in the verification trajectory segment; character This represents the voltage reference value at the corresponding time point in the expected charging behavior model; character Represents the weighting coefficients of the current sequence; characters Represents the current measurement value of the i-th snapshot in the verification trajectory segment; character This represents the current reference value at the corresponding time point in the expected charging behavior model; character Weighting coefficients representing the temperature series; characters Represents the temperature measurement value of the i-th snapshot in the verification trajectory segment; character This represents the temperature reference value at the corresponding time point in the expected charging behavior model. If the calculated strategy execution deviation... If the preset allowable range is exceeded, the control strategy update mechanism is triggered. The control strategy update mechanism includes re-executing the mapping steps with the reference charging mode based on the new key event points identified in the verification trajectory segment, and generating an updated real-time charging control strategy.

[0086] The embedded evaluation step of battery cell health status is executed synchronously during the construction of the complete charging trajectory. The system synchronously extracts feature vectors reflecting the stability of the rare-earth composite material structure inside the battery. These feature vectors contain multi-dimensional indicators. The extracted feature vectors are input into a pre-trained battery health assessment model, which is trained using a supervised learning algorithm. The model outputs a current health index, a value ranging from zero to one, with values ​​closer to one indicating better health. This current health index is incorporated as a hidden variable into the generation logic of the real-time charging control strategy. This hidden variable means that the current health index is not directly output as a control parameter but rather serves as an internal input condition for the strategy generation algorithm. When formulating the real-time charging control strategy, the real-time health status of the battery cells is considered through a weighted approach using constraints or objective functions. For example, when fine-tuning the charging current setpoint, a scaling factor based on the current health index is introduced; when the health index is low, the upper limit of the current adjustment is automatically reduced.

[0087] In practical implementation, the expected charging behavior model can be a multi-dimensional time series model, such as a vector autoregression model or a long short-term memory network model, capable of predicting the expected evolution path of battery parameters under a given control strategy. The allowable range of strategy execution deviation can be dynamically set according to the battery type and application scenario; for example, a typical allowable range value can be set to 0.05. The control strategy update mechanism can be triggered immediately or delayed. Immediate triggering means that an update is initiated as soon as the deviation exceeds the limit, while delayed triggering allows the deviation to persist for several sampling periods before confirming the update, in order to avoid misjudgments caused by noise. Refer to Table 1 for the specific composition of the feature vector input to the battery health assessment model.

[0088] Table 1: Feature Vector Composition Table for Battery Health Status Assessment

[0089] Feature Name Data source describe Constant current charging internal resistance change rate Voltage series, current series Calculate the change in ohmic internal resistance per unit time during the constant current phase. Charge transfer impedance fitting value Electrochemical impedance spectroscopy or relaxation voltage analysis Charge transfer impedance parameters obtained by fitting an equivalent circuit model Voltage relaxation time constant Voltage recovery curve after charging stops The time constant characterizing the polarization voltage dissipation rate Peak shift of differential capacitance curve Differential curve of voltage with respect to capacity Analyze the shift of the peak value of the differential capacitance relative to the new battery state. Steady-state value of heat generation rate Temperature sequence, current sequence The steady increase in battery temperature per unit time under a stable charging current.

[0090] It is understandable that feature vector extraction relies on in-depth analysis of the complete charging trajectory, particularly the capture of features during the charging relaxation phase and specific current step responses. The training data for the battery health assessment model comes from extensive cyclic testing data of the same battery cell model throughout its entire lifespan. Currently, the specific way to integrate the health index into the control strategy generation logic can be by modifying the gain coefficient of the proportional-integral-derivative (PID) control algorithm. Optionally, the system can establish a mapping table between the health index and the maximum allowable charging current, directly limiting the upper limit of the current setpoint in the real-time charging control parameters.

[0091] Example 5: When the management target is a battery pack containing multiple battery cells, the system independently constructs a complete charging trajectory for each battery cell in the battery pack and generates its own real-time charging control strategy. The construction process of the complete charging trajectory for each battery cell follows the same sampling and snapshot linking rules, and the generation process of the real-time charging control strategy for each battery cell is independent and does not interfere with each other. A coordinator at the battery pack level is established. The coordinator operates as an independent software module or hardware logic unit. The coordinator receives the real-time charging control strategies of all battery cells. The received data includes the identifier of each battery cell, the sequence of real-time charging control parameters, and timestamp information. The coordinator performs overall optimization of the real-time charging control strategies of each battery cell based on the current health index and real-time charging status of all battery cells. The current health index comes from the output of the health status assessment model of each battery cell, and the real-time charging status includes the current voltage, current, and temperature measurements of each battery cell. The overall optimization process aims to generate a set of coordinated charging control commands. These coordinated charging control commands will replace the independent real-time charging control strategies of each battery cell and be issued to the charging execution device to ensure the balance and safety of the overall charging process of the battery pack.

[0092] In practical implementation, the coordinator can employ a multi-objective optimization algorithm for comprehensive calculation. The objective function is typically set to minimize the voltage standard deviation among all cells within the battery pack, minimize the difference between the maximum and average temperatures, and maximize the overall charging efficiency of the battery pack. The optimization process is subject to a series of constraints, including the maximum allowable charging current limit for each battery cell, the total input power limit of the battery pack, and the cutoff voltage safety threshold for each battery cell. By solving this constrained multi-objective optimization problem, the coordinator obtains a set of Pareto optimal solutions and then selects an optimal solution based on the priority of the actual application scenario, thereby determining the adjustment amount of the real-time charging control strategy for each battery cell. When generating coordinated charging control commands, the coordinator encapsulates the optimized parameters, such as the corrected charging current value and voltage threshold for each battery cell, into a unified command format.

[0093] It's understandable that inconsistencies between individual battery cells within a battery pack are normal. The coordinator's core role is to suppress the escalation of these inconsistencies through global optimization. The coordinator receives the current health index of all battery cells. Cells with lower health indices are assigned more conservative charging parameters during optimization, such as a reduced weight for their charging current, to protect weak cells and prevent accelerated aging. The coordinator also monitors the real-time charging status of all battery cells. If it detects an abnormal spike in voltage or temperature in a battery cell, the coordinator immediately intervenes, dynamically adjusting the constraints of the optimization problem, temporarily limiting the charging power of the abnormal cell, or even initiating a pause charging command. Simultaneously, it adjusts the charging strategies of other healthy cells to maintain the overall charging progress of the battery pack.

[0094] In some embodiments, the coordinator's optimization algorithm can be implemented based on a model predictive control framework (MMC). The MMC utilizes an equivalent circuit model or electrochemical model of the battery pack to predict the state evolution of individual cells over a future period, thereby making more forward-looking optimization decisions. The coordinator maintains a battery pack topology mapping table, which records the series and parallel relationships between battery cells. Since the current in series circuits must be consistent, and the voltage between parallel branches needs to be balanced, topology information is crucial for feasible region calculation and instruction generation. Optionally, the coordinator can introduce a dynamic weight adjustment mechanism, assigning different weights to different sub-objectives in the optimization objective function at different stages of charging; for example, prioritizing efficiency in the early stages of charging and voltage balance in the later stages. The coordinated charging control commands are ultimately sent via a communication bus to the charging execution devices corresponding to each battery cell, such as bidirectional DC-DC converters or contactor controllers.

[0095] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A high-speed, fast-charging intelligent management system for rare-earth lithium batteries based on rare-earth composite materials, characterized in that, The system includes: The charging trajectory construction module is used to construct the complete charging trajectory of a single battery cell during the charging process. The complete charging trajectory consists of a series of charging state snapshots arranged in time stamp order. The multi-scale segmentation module is used to segment the complete charging trajectory into multiple scales to generate multiple charging subspaces with different time spans. The event identification and labeling module is used to identify and label key charge and discharge event points that characterize the properties of rare earth composite battery within each charging subspace; The spatiotemporal alignment and mapping module is used to perform spatiotemporal alignment and mapping between the labeled multiple charging subspaces and the reference charging modes in the battery cell historical database; The control strategy generation module is used to dynamically generate a real-time charging control strategy for the battery cell based on the mapping result, and then send the real-time charging control strategy to the charging execution device.

2. The high-speed fast-charging intelligent management system for rare-earth lithium batteries based on rare-earth composite materials according to claim 1, characterized in that, The complete charging trajectory of the constructed battery cell during the charging process includes: The voltage, current, and temperature sequences of individual battery cells during the charging process are collected at a fixed frequency. A unique timestamp is assigned to each voltage, current, and temperature value collected at each time point; Combine the voltage, current and temperature values ​​at the same timestamp into a single charging state snapshot. All charging status snapshots are linked together in chronological order of timestamps to form the complete charging trajectory.

3. The high-speed fast-charging intelligent management system for rare-earth lithium batteries based on rare-earth composite materials according to claim 2, characterized in that, The step of segmenting the complete charging trajectory into multiple charging subspaces with different time spans at multiple scales includes: Define multiple time window scales, each time window scale corresponding to a specific time length; Each time window scale is used as a sliding window to slide on the complete charging trajectory, and a segment of the trajectory is captured each time the sliding is performed. Define the trajectory segment captured in each slide as a charging subspace; Each charging subspace is assigned a spatial identifier, which records its corresponding time window scale information and the start and end timestamps in the complete charging trajectory.

4. The high-speed fast-charging intelligent management system for rare-earth lithium batteries based on rare-earth composite materials according to claim 3, characterized in that, Within each of the charging sub-spaces, key charge and discharge event points characterizing the rare-earth composite material battery properties are identified and labeled, including: For a given charging subspace, extract the voltage, current, and temperature sequences of all charging state snapshots contained therein; Calculate the first-order and second-order difference sequences of the voltage sequence, and identify voltage inflection points as potential critical event points; Calculate the fluctuation characteristics of the current sequence and identify current abrupt change points as potential critical event points; Calculate the rising slope of the temperature sequence and identify temperature rise anomalies as potential critical event points; Based on the preset rules for the electrochemical properties of rare earth composite materials, all potential key event points are screened and merged to finally determine the key charge and discharge event points in the charge e-space and label them with event types.

5. The high-speed fast-charging intelligent management system for rare-earth lithium batteries based on rare-earth composite materials according to claim 4, characterized in that, The step of spatiotemporally aligning and mapping the labeled multiple charging subspaces with reference charging modes in the battery cell historical database includes: Retrieve all historical charging records with the same identifier as the battery cell from the battery cell historical database; Extract the reference charging pattern stored in each historical charging record. The reference charging pattern includes the type, occurrence time, and context information of historical key event points. The multiple charging subspaces generated during the current charging process and marked with key charging and discharging event points are matched with the retrieved reference charging modes respectively. The matching process includes: adjusting the time axis of the charging subspace to align it with the time axis of the reference charging mode, and calculating the consistency metric between key event points in the charging subspace and historical key event points in the reference charging mode in terms of type and relative timing. It can be calculated using a weighted function: Where: characters Represents the final consistency metric; character Represents the weighting coefficients assigned to the similarity of event types; characters The event type similarity score is calculated based on the degree of matching between the key event point type within the charging subspace and the corresponding historical key event point type in the reference charging mode; character Represents the weight coefficients assigned to the similarity of event sequences; characters The score represents the similarity score of the event sequence, calculated based on the degree of matching between the relative time intervals of key event points on the aligned timeline.

6. The high-speed fast-charging intelligent management system for rare-earth lithium batteries based on rare-earth composite materials according to claim 5, characterized in that, The step of dynamically generating a real-time charging control strategy for the battery cell based on the mapping result includes: For each charging subspace, a matching confidence score is calculated based on its mapping result with the reference charging mode; If the matching confidence level is higher than the preset threshold, the corresponding historical charging control parameters are extracted from the successfully matched reference charging mode as basic parameters. Based on the specific numerical characteristics of key charging and discharging event points in the current charging subspace, the basic parameters are fine-tuned to generate real-time charging control parameters suitable for the current moment. The real-time charging control parameters generated by all charging subspaces are integrated in chronological order to form the real-time charging control strategy.

7. The high-speed fast-charging intelligent management system for rare-earth lithium batteries based on rare-earth composite materials according to claim 6, characterized in that, The process of fine-tuning the basic parameters based on the specific numerical characteristics of key charging and discharging event points within the current charging subspace to generate real-time charging control parameters suitable for the current moment includes: Extract the voltage, current, and temperature measurements at each key charging / discharging event point within the current charging subspace; Calculate the characteristic deviation between the measured value of each key charge / discharge event point and the corresponding reference value in the basic parameters; Based on the direction and magnitude of the characteristic deviation, determine the adjustment direction and adjustment range of the charging current setting value, cutoff voltage threshold and temperature control threshold in the basic parameters; The proportional-integral-derivative control algorithm is used to convert the adjustment direction and adjustment magnitude into specific correction amounts for the basic parameters; The correction amount is superimposed with the basic parameters to obtain real-time charging control parameters applicable to the current charging subspace time range; The correction amount can be calculated using the following formula: Where: characters This represents the specific amount of correction to the basic parameters, including adjustments to multiple parameters such as current and voltage; characters Represents the proportional gain coefficient, which controls the strength of the response to the current deviation; character Represents the currently calculated feature deviation value; character Represents the integral gain coefficient, which controls the correction strength for accumulated historical deviations; character The integral of the characteristic deviation over time is obtained by multiplying the deviation value by the time interval. The result is obtained by summing the characters. Represents the differential gain coefficient, controlling the degree of suppression of the rate of change of deviation; character The rate of change of the characteristic deviation is calculated by dividing the difference between the current deviation and the deviation at the previous time by the time interval.

8. The high-speed fast-charging intelligent management system for rare-earth lithium batteries based on rare-earth composite materials according to claim 6, characterized in that, The method also includes a verification and update step for the real-time charging control strategy: After applying the real-time charging control strategy, subsequent charging status snapshots of individual battery cells are collected to form a verification trajectory segment. The verified trajectory segment is compared with the expected charging behavior model to calculate the strategy execution deviation. If the deviation of the strategy execution exceeds the allowable range, the control strategy update mechanism is triggered. The control strategy update mechanism includes: re-executing the mapping steps with the reference charging mode based on the new key event points identified in the verification trajectory segment, and generating an updated real-time charging control strategy.

9. The high-speed fast-charging intelligent management system for rare-earth lithium batteries based on rare-earth composite materials according to claim 8, characterized in that, The method also includes an embedded evaluation step for the health status of individual battery cells: During the construction of the complete charging trajectory, feature vectors that reflect the structural stability of rare earth composite materials inside the battery are extracted simultaneously. The feature vector is input into a pre-trained battery health assessment model, which outputs a current health index. The current health index is incorporated as a hidden variable into the generation logic of the real-time charging control strategy, so that the real-time charging control strategy takes into account the real-time health status of individual battery cells when it is formulated.

10. The high-speed fast-charging intelligent management system for rare-earth lithium batteries based on rare-earth composite materials according to claim 9, characterized in that, The method also includes a collaborative management step across individual battery cells: When the management target is a battery pack containing multiple battery cells, a complete charging trajectory is independently constructed for each battery cell in the battery pack and a separate real-time charging control strategy is generated. Establish a coordinator at the battery pack level, which receives real-time charging control strategies from all individual battery cells; The coordinator optimizes the real-time charging control strategy for each battery cell based on the current health index and real-time charging status of all individual cells, generating a set of coordinated charging control commands to ensure the balance and safety of the overall charging process of the battery pack.

Images