Quick charging method and device of lithium battery, electronic equipment and storage medium

Abstract

The invention provides a fast charging method and device of a lithium battery, electronic equipment and a storage medium, and relates to the technical field of battery charging, and the fast charging method comprises the following steps: obtaining genome map data and real-time microscopic state monitoring data of the battery; based on the genome map data and the real-time microscopic state monitoring data, generating a dynamic charging parameter sequence through a bionic neuron adaptive charging decision model; and executing a multi-physical field cooperative charging control process based on the dynamic charging parameter sequence. In the mode, risks of local overheating, charge aggregation and the like in the battery can be pre-judged and avoided in advance, and fast charging safety is guaranteed from the source; and meanwhile, through multi-physical field cooperative control, polarization loss is remarkably reduced, and charging efficiency and energy utilization rate are improved, so that the cycle life of the battery is remarkably prolonged while extreme fast charging is realized.

Description

Technical Field

[0001] This invention relates to the field of battery charging technology, and in particular to a fast charging method, apparatus, electronic device, and storage medium for lithium batteries. Background Technology

[0002] With the rapid development of new energy vehicles, consumer electronics, and large-scale energy storage systems, the charging speed of lithium batteries, as the core energy storage unit, has become a key bottleneck restricting user experience and device performance improvement. Traditional fast charging technologies mainly focus on increasing charging current or voltage, but inherent physical and chemical challenges make it difficult to balance efficiency, safety, and battery life.

[0003] In related technologies, static or simple AI regulation is usually achieved by relying on macroscopic parameters, which cannot perceive the microscopic state inside the battery (such as local temperature field and charge distribution). This leads to lag in regulation, causing safety risks and accelerating battery aging. At the same time, poor coordination between modules fails to guide ion migration and recover internal energy, resulting in severe polarization loss and low energy utilization, which restricts the simultaneous improvement of fast charging efficiency and battery life. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a fast charging method, device, electronic device and storage medium for lithium batteries, which can predict and avoid risks such as local overheating and charge accumulation inside the battery in advance, and ensure fast charging safety from the source; at the same time, through multi-physics field coordinated control, polarization loss is significantly reduced, charging efficiency and energy utilization are improved, thereby achieving ultimate fast charging while significantly extending battery cycle life.

[0005] In a first aspect, embodiments of the present invention provide a fast charging method for lithium batteries, the method comprising: acquiring genomic map data and real-time microstate monitoring data of the battery; generating a dynamic charging parameter sequence based on the genomic map data and real-time microstate monitoring data through a biomimetic neuron adaptive charging decision model; and executing a multi-physics field collaborative charging control process based on the dynamic charging parameter sequence.

[0006] In a preferred embodiment of the present invention, the acquisition of the battery's genomic map data and real-time microstate monitoring data includes: acquiring the battery's electrode material crystal structure and SEI film composition data through a laser Raman spectrometer and a secondary ion mass spectrometer to generate a battery genomic map; and acquiring the battery's internal micron-level temperature field distribution and charge migration trajectory data through a quantum dot temperature sensing and charge distribution coupling module.

[0007] In a preferred embodiment of the present invention, the above-mentioned generation of battery genome map includes: constructing the battery's innate genetic feature vector based on electrode material crystal structure data; constructing the battery's acquired genetic feature vector based on SEI film composition and thickness data; and weighting and fusing the innate and acquired genetic feature vectors using pre-set weighting coefficients to generate the battery genome map.

[0008] In a preferred embodiment of the present invention, the above-mentioned generation of dynamic charging parameter sequence through biomimetic neuron adaptive charging decision model includes: inputting genome map data and real-time microstate monitoring data into a three-layer neural network model; dynamically adjusting connection weights based on the principle of neuronal synaptic plasticity; and outputting a parameter sequence including charging current, charging voltage and magnetic field adjustment coefficient.

[0009] In a preferred embodiment of the present invention, the above-mentioned multi-physics field coordinated charging control process based on dynamic charging parameter sequence includes: controlling a micro superconducting magnet array to generate a gradient magnetic field based on a magnetic field adjustment coefficient to guide lithium ions to migrate along a preset path; performing charging control based on charging current and charging voltage; and triggering energy recovery and directional distribution processes based on real-time microstate monitoring data.

[0010] In a preferred embodiment of the present invention, the above-mentioned guiding lithium ions to migrate along a preset path includes: determining the target magnetic field strength based on charge density, local temperature and time parameters; calibrating the actual magnetic field strength through a Helmholtz coil and a Hall sensor; and dynamically adjusting the magnetic field direction based on the charge density gradient direction.

[0011] In a preferred embodiment of the present invention, the method further includes: acquiring energy recovery efficiency data; The weights of acquired gene feature vectors are updated based on energy recovery efficiency data; an updated battery genome map is generated for optimization of the next charging strategy.

[0012] Secondly, embodiments of the present invention also provide a fast charging device for a lithium battery, comprising: a data acquisition module for acquiring genomic map data and real-time microstate monitoring data of the battery; a dynamic charging parameter sequence generation module for generating a dynamic charging parameter sequence based on the genomic map data and real-time microstate monitoring data through a biomimetic neuron adaptive charging decision model; and a control process execution module for executing a multi-physics field coordinated charging control process based on the dynamic charging parameter sequence.

[0013] Thirdly, embodiments of the present invention also provide an electronic device, including a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the fast charging method for the lithium battery described in the first aspect.

[0014] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are invoked and executed by a processor, the computer-executable instructions cause the processor to implement the fast charging method for the lithium battery described in the first aspect.

[0015] The embodiments of the present invention bring the following beneficial effects: This invention provides a fast charging method, apparatus, electronic device, and storage medium for lithium batteries. By acquiring the battery's genomic mapping data and real-time microscopic state monitoring data, a dynamic charging parameter sequence is generated based on the genomic mapping data and the real-time microscopic state monitoring data using a biomimetic neuron adaptive charging decision model. Based on the dynamic charging parameter sequence, a multi-physics field collaborative charging control process is executed. This method can predict and avoid risks such as localized overheating and charge accumulation inside the battery in advance, ensuring fast charging safety from the source. Simultaneously, through multi-physics field collaborative control, polarization loss is significantly reduced, and charging efficiency and energy utilization are improved, thereby significantly extending battery cycle life while achieving ultra-fast charging.

[0016] Other features and advantages of this disclosure will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the techniques described above.

[0017] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a fast charging method for a lithium battery provided in an embodiment of the present invention; Figure 2 A flowchart of another fast charging method for a lithium battery provided in an embodiment of the present invention; Figure 3 A schematic diagram of the structure of a fast charging device for a lithium battery provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions 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, 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.

[0021] With the rapid development of new energy vehicles, consumer electronics, and large-scale energy storage systems, the charging speed of lithium batteries, as the core energy storage unit, has become a key bottleneck restricting user experience and device performance improvement. Traditional fast charging technologies mainly focus on increasing charging current or voltage, but inherent physical and chemical challenges make it difficult to balance efficiency, safety, and battery life.

[0022] In related technologies, static or simple AI regulation is usually achieved by relying on macroscopic parameters, which cannot perceive the microscopic state inside the battery (such as local temperature field and charge distribution). This leads to lag in regulation, causing safety risks and accelerating battery aging. At the same time, poor coordination between modules fails to guide ion migration and recover internal energy, resulting in severe polarization loss and low energy utilization, which restricts the simultaneous improvement of fast charging efficiency and battery life.

[0023] Based on this, the present invention provides a fast charging method, apparatus, electronic device, and storage medium for lithium batteries. This method acquires the battery's genomic mapping data and real-time microscopic state monitoring data. Based on the genomic mapping data and the real-time microscopic state monitoring data, a dynamic charging parameter sequence is generated through a biomimetic neuron adaptive charging decision model. Based on the dynamic charging parameter sequence, a multi-physics field collaborative charging control process is executed. This approach can predict and avoid risks such as localized overheating and charge accumulation within the battery, ensuring fast charging safety from the source. Simultaneously, through multi-physics field collaborative control, polarization loss is significantly reduced, and charging efficiency and energy utilization are improved, thereby significantly extending battery cycle life while achieving ultra-fast charging.

[0024] To facilitate understanding of this embodiment, a fast charging method for a lithium battery disclosed in this embodiment of the invention will first be described in detail.

[0025] Example 1 This invention provides a fast charging method for lithium batteries. Figure 1 This is a flowchart illustrating a fast charging method for a lithium battery provided in an embodiment of the present invention. Figure 1 As shown, the fast charging method for this lithium battery may include the following steps: Step S101: Obtain the genomic map data and real-time microstate monitoring data of the battery.

[0026] Among them, genomic mapping data refers to a set of digital features that can uniquely identify and describe the individual characteristics of a battery. It is not a biological gene, but a biomimetic description of the battery's "innate characteristics" (such as the crystal structure of the electrode materials at the time of manufacture) and "post-natal evolution" (such as changes in the composition and thickness of the SEI film after use).

[0027] Real-time microstate monitoring data refers to micrometer-level physical quantity data collected from inside the battery during charging, which is unavailable from traditional BMS. This mainly includes: micrometer-level local temperature field distribution: real-time temperature of different tiny regions (e.g., 10μm × 10μm) inside the battery, rather than the average temperature or surface temperature of the entire battery; and charge migration trajectory and density distribution: the paths of lithium ions migrating between the positive and negative electrodes and the degree of aggregation in different regions.

[0028] For example, before charging begins, the system scans the negative electrode using a laser Raman spectroscopy instrument and finds that its graphite crystal structure (innate genetic material) remains intact, but SIMS detects an increase in LiF content and a thickness of 80 nm in the SEI film (acquired genetic material). These data are integrated to generate a genome map. Simultaneously, the quantum dot array detects that the initial temperature of the electrode region near the tab is slightly higher (303 K), and the charge density is uneven.

[0029] Step S102: Based on genome map data and real-time microstate monitoring data, a dynamic charging parameter sequence is generated through a biomimetic neuron adaptive charging decision model.

[0030] Among them, the biomimetic neuron adaptive charging decision model is an artificial intelligence algorithm model that simulates the synaptic plasticity (i.e., adjustable connection strength) of neurons in the biological brain. It can dynamically change its internal structure according to input information, thereby adapting to the ever-changing environment.

[0031] The dynamic charging parameter sequence is not a fixed value, but a series of command values ​​that change over time, mainly including: charging current (I), charging voltage (V), and magnetic field adjustment coefficient (Bm).

[0032] For example, after receiving genomic data indicating a "thick SEI membrane" and real-time data indicating a "higher temperature in the electrode region," the model adjusts the corresponding neuronal connection weights. The output might be: using a slightly lower initial current (e.g., 1.5C instead of 2C) and setting a higher initial magnetic field coefficient for the magnetron control module to guide ions away from the overheated region.

[0033] Step S103: Based on the dynamic charging parameter sequence, execute the multi-physics field coordinated charging control process.

[0034] Among them, multi-physics field coordinated charging control refers to simultaneously controlling multiple physical fields such as electricity, magnetism, heat, and force, so that they cooperate with each other and act together on the charging process.

[0035] For example, after receiving Bm(t), the magnetron-controlled ion migration guidance module adjusts the current in the superconducting magnet array to generate a gradient magnetic field of specific intensity and direction. Upon receiving I(t) and V(t), the charging circuit controls the power supply to output the corresponding power. Simultaneously, the energy recovery module begins operation, converting mechanical energy into electrical energy.

[0036] The fast charging method for lithium batteries provided in this invention can acquire the battery's genomic map data and real-time microscopic state monitoring data. Based on the genomic map data and the real-time microscopic state monitoring data, a dynamic charging parameter sequence is generated through a biomimetic neuron adaptive charging decision model. Based on the dynamic charging parameter sequence, a multi-physics field collaborative charging control process is executed. This method can predict and avoid risks such as localized overheating and charge accumulation inside the battery in advance, ensuring fast charging safety from the source. Simultaneously, through multi-physics field collaborative control, polarization loss is significantly reduced, and charging efficiency and energy utilization are improved, thereby significantly extending battery cycle life while achieving ultra-fast charging.

[0037] Example 2 This invention also provides another fast charging method for lithium batteries; this method is implemented based on the method described in the above embodiments.

[0038] Figure 2 A flowchart of another fast charging method for lithium batteries provided in an embodiment of the present invention is shown below. Figure 2 As shown, the fast charging method for this lithium battery may include the following steps: Step S201: Obtain the genomic map data and real-time microstate monitoring data of the battery.

[0039] Specifically, acquiring genomic map data and real-time microstate monitoring data of the battery can include: acquiring the crystal structure of the electrode material and the composition data of the SEI film of the battery through laser Raman spectroscopy and secondary ion mass spectrometry to generate a battery genomic map; and acquiring the micron-level temperature field distribution and charge migration trajectory data inside the battery through a quantum dot temperature sensing and charge distribution coupling module.

[0040] Among them, laser Raman spectroscopy is used for non-destructive testing of the inherent properties of battery electrode materials. By analyzing the scattering spectrum after the laser interacts with the material molecules, the crystal phase structure, chemical bond type, and stress state of the material can be identified.

[0041] Among them, the secondary ion mass spectrometer (SIMS) is used to accurately analyze the acquired characteristics of the battery. It sputters the surface of the battery electrode with a high-energy ion beam and performs mass spectrometry analysis on the sputtered secondary ions to obtain information on the distribution of elemental and compound components along the depth direction of the SEI film.

[0042] For example, in practical applications, a complete SIMS analysis may be completed during battery production or laboratory diagnostics. In routine BMS, simplified online impedance spectroscopy, relaxation voltage analysis, and other methods can be used in conjunction with models built from initial SIMS data to indirectly infer and update the SEI membrane state, achieving "dynamic evolution" of the genome map.

[0043] Among them, quantum dot temperature sensing integrates temperature-sensitive fluorescent quantum dots onto a flexible substrate and embeds them inside a battery. When irradiated with excitation light, their fluorescence intensity or wavelength changes with temperature, and real-time temperature measurement with micron-level spatial resolution can be achieved through calibration.

[0044] Charge distribution coupling is typically achieved using electrochemical impedance spectroscopy (EIT). By applying alternating currents to multiple contacts of the battery and measuring the boundary voltages, an inversion algorithm is used to reconstruct the internal conductivity / impedance distribution map, which directly reflects the concentration and migration of lithium ions (charges).

[0045] The process of generating a battery genome map may include: constructing an innate genetic feature vector of the battery based on the crystal structure data of the electrode materials; constructing an acquired genetic feature vector of the battery based on the composition and thickness data of the SEI film; and generating a battery genome map by weighting and fusing the innate and acquired genetic feature vectors through pre-set weighting coefficients.

[0046] The weighting coefficients are parameters used to balance the importance of innate and acquired genes in decision-making. They are not fixed but dynamically adjusted based on factors such as battery cycle life and historical performance.

[0047] For example, for a brand-new battery, its inherent characteristics, such as electrode material properties, are the dominant factors determining its performance. Therefore, the weighting coefficient α (corresponding to inherent characteristics) might be set to 0.7, and β (corresponding to acquired characteristics) to 0.3. For an aged battery that has undergone 1000 cycles, its acquired characteristics (such as SEI film thickening and active material loss) become the main factors affecting performance. The system will automatically adjust the weighting to α=0.3 and β=0.7, making the decision more dependent on the battery's current health status.

[0048] Step S202: Based on genome map data and real-time microstate monitoring data, a dynamic charging parameter sequence is generated through a biomimetic neuron adaptive charging decision model.

[0049] Specifically, generating a dynamic charging parameter sequence through a biomimetic neuron adaptive charging decision model can include: inputting genomic map data and real-time microstate monitoring data into a three-layer neural network model; dynamically adjusting connection weights based on the principle of neuronal synaptic plasticity; and outputting a parameter sequence containing charging current, charging voltage, and magnetic field regulation coefficients.

[0050] Before inputting genomic mapping data and real-time microscopic state monitoring data into the three-layer neural network model, all data must undergo normalization preprocessing. This normalizes physical quantities of different dimensions and ranges (such as temperature, voltage, and component ratios) to the [0, 1] interval, ensuring the stability and convergence speed of model training. Similarly, the model outputs normalized values, which need to be denormalized back to the actual physical quantity range (such as current 0-5A, voltage 3-4.2V). The system sets a final safety threshold, ensuring that even if the model outputs abnormally, the actuator will not exceed the hardware safety limits.

[0051] Specifically, if the model outputs a high current command and then immediately receives negative feedback about an excessive temperature gradient, the neuron connections along the high current output decision path will be weakened. The next time a similar situation arises, the model will be more inclined to choose a more conservative current value.

[0052] Step S203: Based on the dynamic charging parameter sequence, execute the multi-physics field coordinated charging control process.

[0053] Specifically, the multi-physics field coordinated charging control process based on the dynamic charging parameter sequence can include: controlling the micro superconducting magnet array to generate a gradient magnetic field based on the magnetic field adjustment coefficient to guide lithium ions to migrate along a preset path; performing charging control based on charging current and charging voltage; and triggering energy recovery and directional distribution processes based on real-time microstate monitoring data.

[0054] Guiding lithium ions to migrate along a preset path may include: determining the target magnetic field strength based on charge density, local temperature, and time parameters; calibrating the actual magnetic field strength using a Helmholtz coil and a Hall sensor; and dynamically adjusting the magnetic field direction based on the charge density gradient direction.

[0055] The magnetic field adjustment coefficient (e.g., 0-1) is mapped to a specific magnetic field strength (e.g., 0-1T). Based on the real-time charge distribution map, the system calculates the optimal magnetic field direction and strength, and uses the Lorentz force to guide positively charged lithium ions to bypass congested areas, achieving orderly and rapid embedding.

[0056] The charging control based on the charging current and charging voltage is implemented by power circuits such as high-frequency switching power supplies. However, it no longer works according to a fixed CCCV curve, but strictly follows the real-time instructions (I(t), V(t)) issued by the bionic neuron module to perform precise power output.

[0057] Specifically, when significant mechanical stress is detected inside the battery (indicating that energy can be recovered) and a local area with excessively low charge density is identified (indicating that there is an energy demand), the system triggers the energy recovery and targeted distribution process.

[0058] Among them, through Perform the calculation.

[0059] in, Tesla (T) represents the magnetic field strength generated by a miniature superconducting magnet array and is a key control variable guiding the migration path of lithium ions. Its value determines the magnitude of the Lorentz force applied to lithium ions, directly affecting the direction and efficiency of lithium ion migration.

[0060] in, This represents the internal charge density of a battery, measured in coulombs per cubic meter (Cd). This parameter reflects the density of charge distribution inside the battery. The quantum dot temperature sensor coupled with the charge distribution module monitors this parameter in real time, providing a basis for adjusting the magnetic field strength.

[0061] Here, T represents the local temperature inside the battery, measured in Kelvin (K), and is precisely obtained using a quantum dot fluorescence thermometry array. Temperature changes affect the activity and internal resistance of lithium-ion migration, which in turn influences the appropriate value of the magnetic field strength.

[0062] Where t represents the charging time in seconds (s), as the charging process progresses, the battery state continues to change, and the magnetic field strength needs to be dynamically adjusted at different stages to maintain the optimal migration path of lithium ions.

[0063] in, Here is the charge density coefficient, with a value of 1.2 × 10⁻⁶. -8 (Based on 100 sets of ρ) (Fitting experimental data within the range).

[0064] in, For temperature coefficient, take values ​​of (Applicable to a temperature range of 293-323K).

[0065] in, The time decay coefficient has a value of [value missing]. (Charging time 10-60 minutes).

[0066] The calibration of the actual magnetic field strength using a Helmholtz coil and a Hall sensor is a high-precision closed-loop calibration process. The system periodically (e.g., every 100 cycles) or in real time compares the reference magnetic field (generated by the Helmholtz coil) with the measured magnetic field (read by the Hall sensor), dynamically adjusting the drive current of the superconducting magnet to ensure that the output magnetic field is completely consistent with the instructions of the decision module.

[0067] The magnetic field direction is dynamically adjusted based on the charge density gradient direction: the system calculates the direction of the fastest change in charge density (i.e., the gradient direction) from the charge density distribution map generated by EIT. In order to most effectively "push" ions from high-density regions to low-density regions, the generated magnetic field direction is set to be perpendicular to this gradient direction.

[0068] Step S204: Obtain energy recovery efficiency data.

[0069] The energy recovery efficiency data includes the total energy recovered by the piezoelectric unit during this charging cycle, the storage efficiency of the supercapacitor, and the actual energy value that is directed to the low-charge region.

[0070] Step S205: Update the weights of the acquired gene feature vectors based on energy recovery efficiency data.

[0071] This involves a process of system self-learning and self-optimization. If data shows that targeted energy allocation to a certain type of low-charge region can significantly improve its performance and the effect is lasting, then when updating the "acquired genes," the characteristic value representing the "repairability" or "health" of that region will be positively reinforced.

[0072] Step S206: Generate an updated battery genome map for the next charging strategy optimization.

[0073] This gives the fast charging system the ability to "memorize" and "evolve." Each charge is a deep understanding of the individual battery, and the updated graph ensures that the next charging strategy is more accurate and personalized, achieving optimal performance throughout the battery's entire lifespan.

[0074] Example 3 Corresponding to the above method embodiments, embodiments of the present invention can provide a fast charging system for lithium batteries, including: Quantum dot temperature sensing and charge distribution coupling module: (1) Module Composition and Basic Functions: The core of this module consists of a quantum dot fluorescence thermometry array and an electrochemical impedance tomography (EIT) unit. The quantum dot fluorescence thermometry array can capture the micron-level local temperature field distribution inside the battery, while the EIT unit reconstructs the charge migration trajectory through low-frequency alternating current. The two work together to achieve real-time monitoring of temperature and charge state. This design breaks through the limitations of traditional single-parameter detection and provides multi-dimensional raw data for subsequent coupled analysis; Before installing the quantum dot array, it needs to be calibrated using a micro-positioning system: with the edge of the electrode plate as a reference, the vertical distance between the sensor and the membrane is determined by laser ranging (controlled within 20-50μm), and the initial position coordinates are recorded to avoid displacement errors caused by battery assembly stress; After the quantum dot fluorescence signal is acquired by a spectrometer, it is calibrated using a calibration curve (λ=k). T+c, where k and c are experimentally determined constants, is converted into temperature data. A wavelet transform algorithm is used to filter out ambient light interference, and finally a micrometer-level local temperature field distribution matrix is ​​output. (2) Core Functions and Module Integration: Based on this, the module performs deep coupling analysis on the temperature field gradient and charge density distribution data to generate a dynamic monitoring spectrum. This spectrum is not static data, but is synchronously fed back to the bionic neuron adaptive charging decision module in real time, becoming the microscopic basis for adjusting the charging parameters, thus realizing a seamless connection from "data acquisition" to "decision support"; The dynamic monitoring map uses a 512×512 pixel matrix, with each pixel corresponding to a 10μm×10μm area; temperature data is encoded in pseudo-color (blue - low temperature, red - high temperature), and charge density is represented by grayscale values ​​(0-255 corresponds to 0-10C / m³); when the temperature of three consecutive pixels exceeds 333K or the charge density is lower than 1C / m³, it is judged as an abnormal area and marked.

[0075] Bionic neuron adaptive charging decision module: (1) Module construction and data reception: The module is based on the principle of synaptic plasticity of biological neurons and constructs a dedicated neural network chip. Its core advantage lies in its ability to accurately receive two types of key data: one is the "genome map" output by the battery genome map construction and matching module, and the other is the real-time monitoring data of the quantum dot temperature sensing and charge distribution coupling module, providing comprehensive input for subsequent decision-making; The neural network chip adopts a three-layer architecture: the input layer contains 128 nodes (64 receiving genome map data and 64 receiving real-time monitoring data), the hidden layer contains 64 nodes (using the ReLU activation function), and the output layer contains 3 nodes (outputting current, voltage, and magnetic field adjustment coefficients, respectively); it is trained using 100,000 sets of battery charge-discharge data (covering environments from -20℃ to 50℃), employs the Adam optimizer, and converges after 1000 iterations; Formula for extracting features from battery genome maps: .

[0076] The generated battery "genome map" feature vector is a digital abstraction of the battery's overall state, used to accurately match charging strategies and record changes in battery state. The map contains multi-dimensional feature information such as the crystal structure of electrode materials, SEI film composition and thickness; unlike traditional single-parameter monitoring such as SOC and SOH, this map dynamically balances the 'innate genes' (electrode material characteristics) and 'acquired genes' (SEI film changes) data through weighting coefficients α and β, realizing real-time digital integration of multi-dimensional states throughout the battery's entire life cycle, providing a basis for individualized charging strategies; The data set of "innate genes" such as crystal structure and chemical bond vibration of battery electrode materials obtained by laser Raman spectroscopy reflects the inherent physicochemical characteristics of the battery at the time of manufacture.

[0077] The data set of "acquired genes" such as SEI film composition and lithium dendrite growth traces obtained by secondary ion mass spectrometry (SIMS) during battery use reflects the state changes of the battery at different stages of use.

[0078] α、 The weighting coefficient (dimensionless) was determined through a large amount of experimental data and machine learning algorithms. It is used to balance the relative importance of "innate genes" and "acquired genes" in the generation of the map, so as to ensure that the map can accurately reflect the overall state of the battery. The specific determination method is as follows: 5000 battery samples covering different types (ternary lithium, lithium iron phosphate) and cycle counts (0-2000 times) were selected, and their P and Q data were collected and the corresponding charge-discharge performance degradation rates were labeled; the random forest algorithm was used to train the sample data, with the goal of minimizing the charge-discharge efficiency prediction error, and the optimized values ​​of α were obtained as 0.3-0.6 and β as 0.4-0.7 (where α=0.55±0.05, β=0.45±0.05 for new batteries; and α=0.35±0.05, β=0.65±0.05 after 1000 cycles). (2) Data processing and parameter output: Through the above data fusion, the module dynamically adjusts the connection weights between neurons to generate a charging parameter sequence that adapts to the current battery state, covering current intensity, voltage gradient, magnetic field adjustment coefficient, etc. These parameters do not exist in isolation, but are respectively issued to the magnetically controlled ion migration guidance module and the spatiotemporal energy recovery and redistribution module, becoming the core instruction source driving the multi-module collaboration; When abnormal temperature (exceeding the threshold) and abnormal charge distribution occur simultaneously, the module prioritizes temperature safety control (such as limiting voltage). Once the temperature gradient drops to a safe range, the magnetic field adjustment for charge balance is initiated. The parameter adjustment range follows the principle of 'step-by-step increase', with each adjustment not exceeding 10% of the current value. When the quantum dot module detects a local temperature gradient exceeding 5 K / mm, the module automatically triggers a voltage limiting mechanism; when the EIT unit detects a charge density standard deviation exceeding 0.5 C / m³, it prioritizes adjusting the magnetic field adjustment coefficient to balance the charge distribution, with the adjustment direction being to increase the magnetic field strength in high-charge regions and decrease it in low-charge regions; The biomimetic neuron charging parameter decision model formula is as follows: . Over time The varying charging current intensity, measured in amperes (A), is one of the key parameters controlling the charging rate and the battery reaction process. Over time The varying charging voltage, measured in volts (V), dynamically adjusts to influence the driving force for lithium ion migration between electrodes. This, in conjunction with the current, ensures an efficient and safe charging process. Over time The changing magnetic field adjustment coefficient (dimensionless) of the magnetron-controlled ion migration guidance module determines the relative change in the magnetic field strength generated by the magnetron-controlled module, which in turn affects the lithium-ion migration path. A neural network function, built based on the principle of synaptic plasticity in biological neurons, simulates the neuron's processing and decision-making process for input data. It contains a large number of neurons and dynamically adjusted connection weights to achieve intelligent responses to complex battery states. Input data A and S(t) are first normalized (mapped to the 0-1 range), then weighted and summed through hidden layer nodes before being output via an activation function. Output parameters I(t), V(t), and Bm(t) are denormalized and mapped to the actual physical quantity range (current 0-5A, voltage 2-4.2V, magnetic field adjustment coefficient 0-1). When the output value exceeds a safety threshold, an emergency correction mechanism for synaptic weights is triggered. The "genome map" dataset output by the battery genome map construction and matching module covers multi-dimensional features such as the crystal structure of the battery's innate electrode materials and changes in the SEI film, providing the neural network with basic attribute information of the battery. The quantum dot temperature sensing and charge distribution coupling module monitors battery state data in real time, such as temperature field gradient and charge density distribution, which change over time, providing real-time feedback on the battery's microscopic state to the neural network.

[0079] Magnetically controlled ion migration guidance module: (1) Core control mechanism: The module takes the magnetic field adjustment coefficient output by the bionic neuron adaptive charging decision module as the core input, and generates a gradient magnetic field with controllable intensity by controlling the micro superconducting magnet array. This magnetic field can exert a directional force on lithium ions, guiding them to migrate along the optimal path, avoiding the polarization loss caused by disordered collisions of lithium ions in traditional fast charging; The magnetic field strength calibration steps for the micro superconducting magnet array are as follows: ① A standard magnetic field (0-1T) is generated using a Helmholtz coil; ② The magnetic field adjustment coefficient (0-1) output by the decision module is mapped to the target magnetic field strength; ③ The actual magnetic field value is collected in real time by a Hall sensor, and the magnet drive current is corrected after comparison with the target value to ensure that the error is controlled within ±0.02T. Unlike the natural diffusion and migration of lithium ions in traditional fast charging, this module applies a directional force to lithium ions through a gradient magnetic field and plans the optimal migration path based on the real-time charge distribution, thereby achieving active regulation of the orderly migration of lithium ions. The magnetic field direction is adjusted based on the charge density gradient direction monitored in real time by the quantum dot temperature sensing and charge distribution coupling module. When local charge accumulation is detected, it automatically switches to the opposite magnetic field to disperse the migration path. The direction adjustment response time is synchronized with the charge distribution data sampling frequency (updated every 10ms). Formula for optimizing the magnetic field strength for lithium-ion migration path: Perform the calculation.

[0080] in, Tesla (T) represents the magnetic field strength generated by a miniature superconducting magnet array and is a key control variable guiding the migration path of lithium ions. Its value determines the magnitude of the Lorentz force applied to lithium ions, directly affecting the direction and efficiency of lithium ion migration.

[0081] in, This represents the internal charge density of a battery, measured in coulombs per cubic meter (Cd). This parameter reflects the density of charge distribution inside the battery. The quantum dot temperature sensor coupled with the charge distribution module monitors this parameter in real time, providing a basis for adjusting the magnetic field strength.

[0082] Here, T represents the local temperature inside the battery, measured in Kelvin (K), and is precisely obtained using a quantum dot fluorescence thermometry array. Temperature changes affect the activity and internal resistance of lithium-ion migration, which in turn influences the appropriate value of the magnetic field strength.

[0083] Where t represents the charging time in seconds (s), as the charging process progresses, the battery state continues to change, and the magnetic field strength needs to be dynamically adjusted at different stages to maintain the optimal migration path of lithium ions.

[0084] in, Here is the charge density coefficient, with a value of 1.2 × 10⁻⁶.-8 (Based on 100 sets of ρ) (Fitting experimental data within the range).

[0085] in, For temperature coefficient, take values ​​of (Applicable to a temperature range of 293-323K).

[0086] in, The time decay coefficient has a value of [value missing]. (Charging time 10-60 minutes).

[0087] The function was obtained through COMSOL multiphysics simulation and calibrated by 100 experimental tests.

[0088] (2) Dynamic closed loop and connection: In order to achieve dynamic optimization, the module transmits the real-time magnetic field strength data back to the bionic neuron module. This back feedback and the positive parameter issuance form a complete adjustment closed loop, which enables the magnetic field strength to be adjusted in real time according to the battery state, ensuring that lithium ion migration is always in the optimal state, and deeply synergizing with the overall fast charging strategy; To avoid magnetic field inhomogeneity caused by magnet performance degradation, a calibration procedure is initiated after every 100 charging cycles: the array surface is scanned using a standard magnetic field sensor, the deviation between the actual output and theoretical value of each magnet is recorded, and the deviation is corrected using a drive current compensation algorithm to ensure that the magnetic field uniformity error is controlled within 5%.

[0089] Battery genome mapping and matching module: (1) Map generation mechanism: The module uses a laser Raman spectrometer and a secondary ion mass spectrometer (SIMS) to complete the "gene analysis" of the battery in the initial stage of charging: it identifies both the inherent factory parameters such as the crystal structure of the electrode material and the traces of use such as changes in the SEI film, and finally generates a unique "genome map" to accurately characterize the individual characteristics of the battery; (2) Atlas application and update: The atlas is not only the basis of the initial parameters, but also the basis for parameter setting. On the one hand, it is sent to the bionic neuron decision module. On the other hand, after the charging is completed, the module receives the energy cycle data of the spatiotemporal energy recovery and redistribution module. By integrating these dynamic information, the atlas is updated, providing a more accurate "gene reference" for the next charging. Unlike traditional methods that only record the number of cycles or capacity decay, the genome map generated by this module integrates the dynamic changes of the SEI membrane (acquired genes) and charge migration trajectory (real-time state) in real time, realizing a full-dimensional dynamic characterization of the battery's 'innate characteristics - acquired evolution - real-time state'. After each charge, the Q value weight is updated based on the energy cycle data, so that the map always reflects the latest state of the battery.

[0090] Spatiotemporal Dimension Energy Recovery and Redistribution Module: (1) Energy harvesting and storage: The module integrates a nanoscale piezoelectric energy harvesting unit and a supercapacitor buffer array. During fast charging, the mechanical stress generated inside the battery due to lithium ion insertion / extraction is converted into electrical energy by the piezoelectric unit. This dispersed energy is stored through the supercapacitor array, realizing efficient energy recovery and temporary storage, and improving the overall energy utilization rate. The supercapacitor array's charge and discharge cutoff voltage is set as follows: maximum charging voltage 2.7V, minimum discharging voltage 1.2V; the built-in voltage monitoring unit automatically cuts off the charging and discharging circuit and triggers an alarm signal when overcharging (>2.7V) or over-discharging (<1.2V) is detected. The mechanical stress generated by lithium-ion insertion / deintercalation causes the piezoelectric unit to deform, resulting in the separation of positive and negative charge centers inside to form a potential difference. Current is output to the supercapacitor array through the electrode leads. The direction of the current alternates with the stress change (expansion / contraction) and is converted into DC current for storage by the rectifier circuit. (2) Targeted Allocation and Feedback: At the energy allocation level, the strategy relies closely on the low-charge region location data provided by the quantum dot temperature sensing and charge distribution coupling module to target and replenish the recovered energy to the corresponding region, accurately balancing the charge distribution. At the same time, the energy recovery efficiency and allocation records are synchronously fed back to the battery genome mapping and matching module, becoming key data for updating the battery's "acquired genes"; When the quantum dot module detects a local charge density below 2C / m³, it triggers directional energy distribution; the energy distributed in a single operation does not exceed 30% of the supercapacitor array's storage capacity, and the distribution rate is positively correlated with the amount of charge density loss in that region; the energy recovery and distribution efficiency formulas are as follows: . The overall efficiency (dimensionless) of energy recovery and redistribution of the spatiotemporal dimension energy recovery and redistribution module measures the degree of effective energy utilization of the module during fast charging. The module recovers and successfully distributes electrical energy to the low-charge area of ​​the battery, measured in joules (J), demonstrating the practical effect of energy recovery and distribution. The mechanical stress generated inside the battery due to lithium-ion insertion / deintercalation can theoretically be converted into electrical energy through a nanoscale piezoelectric energy harvesting unit. The unit is joule (J), which is the total potential energy recovery. The energy distribution correction coefficient (dimensionless) ranges from 0 to 1. This coefficient considers factors such as the positioning error of the low-charge area provided by the quantum dot temperature sensing and charge distribution coupling module, and the losses during the energy storage and release process of the supercapacitor array, and is used to more accurately evaluate the energy recovery and distribution efficiency. The specific calculation method is: γ = γ1 × γ2. Where: γ1 is the positioning error correction coefficient: when the quantum dot positioning error ε < 5%, γ1 = 0.9; when 5% ≤ ε ≤ 10%, γ1 = 0.7; when ε > 10%, γ1 = 0.5; γ2 is the supercapacitor loss correction coefficient: γ2 = 1 - δ, where δ is the supercapacitor charge and discharge loss rate (the measured value is 3%-8%, and when the average value is 5%, γ2 = 0.95).

[0091] This system achieves four-module collaboration through a real-time data flow closed loop: the monitoring data (10ms / frame) from the quantum dot module drives the bionic decision module to dynamically output parameters, and the magnetic control and energy recovery modules execute synchronously according to the parameters (response delay <5ms). The execution results are fed back to the quantum dot module in real time to update the monitoring spectrum, forming a seamless linkage of 'monitoring-decision-execution-feedback', which is different from the data interaction delay between modules (usually >100ms) and independent control mode in traditional systems.

[0092] The corresponding method for the above system is as follows, with the steps as follows: S1, Quantum-level Feature Extraction and Gene Matching Stage: S11. Initial State Regulation and Map Generation: The magnetically controlled ion migration guidance module first activates the initial magnetic field, so that lithium ions are in an ordered state in advance, laying the microscopic foundation for subsequent fast charging; simultaneously, the battery genome map construction and matching module completes "genome sequencing" through laser Raman spectroscopy and SIMS, generates map data containing multiple features, and immediately transmits the map to the bionic neuron adaptive charging decision module to construct the "genetic baseline" of initial parameters.

[0093] S12. Anomaly Monitoring and Preprocessing: Simultaneously, the quantum dot temperature sensing and charge distribution coupling module is activated to collect initial charge distribution baseline and temperature field data. If an abnormal local charge density is detected—which may affect the safety of subsequent fast charging—the module will immediately send a trigger signal to the bionic neuron module, prompting it to perform "preprocessing synaptic weight adjustment" to ensure that the subsequently generated charging parameters can adapt to the initial state of the battery, achieving a precise start.

[0094] The time required for feature extraction in the S1 stage is related to the battery type: approximately 30-50 seconds for ternary lithium batteries and approximately 40-60 seconds for lithium iron phosphate batteries (due to differences in the intensity of laser Raman signals from electrode materials).

[0095] The trigger threshold for switching from S1 to S2 is when the baseline acquisition of the initial charge distribution of the battery is completed and the genome map is generated.

[0096] S2, Multi-physics field coordinated fast charging stage: S21. Initial Parameter Output and Migration Regulation: Based on the genome map and initial monitoring data generated in the first stage, the biomimetic neuron adaptive charging decision module outputs initial charging parameters, covering key indicators such as current, voltage, and magnetic field strength. Among them, the magnetic field parameters are sent to the magnetically controlled ion migration guidance module in real time, which guides lithium ions to migrate along the optimal path by adjusting the strength of the magnet array, thus initiating a high-efficiency fast charging process. S22. Dynamic Feedback and Coordinated Adjustment: During continuous fast charging, each module forms a tight dynamic feedback mechanism: the quantum dot temperature sensing and charge distribution coupling module continuously monitors the temperature field gradient and charge distribution changes, and the real-time data is continuously fed back to the bionic neuron module; the bionic neuron module dynamically adjusts the charging parameters accordingly, and synchronously sends new magnetic field commands to the magnetic control module and directional distribution commands to the spatiotemporal energy module. The spatiotemporal energy module, based on the positioning data of the quantum dot module, accurately replenishes the recovered electrical energy to the low charge area, forming a dynamic closed loop of multi-field coordination; The trigger threshold for switching from S2 to S3 is when the battery level reaches 85% of its rated capacity.

[0097] S3, Quantum tunneling effect termination and gene repair stage: S31. End-of-phase parameter control: When the battery charge reaches a set threshold, the system automatically switches to this phase. The bionic neuron adaptive charging decision module drives the charging voltage to increase stepwise at a specific rate, while simultaneously sending instructions to the magnetically controlled ion migration guidance module to reduce the magnetic field strength—this adjustment aims to utilize the quantum tunneling effect to promote more efficient penetration of lithium ions through the SEI film and reduce the charging time in the end-of-phase phase; For batteries with different aging levels, the voltage step amplitude of the quantum tunneling stage is dynamically adjusted: for new batteries (SEI film thickness <50nm), the voltage increases by 0.1V per step, and for aged batteries (SEI film thickness >100nm), the voltage increases by 0.05V per step. By reducing the barrier penetration difficulty to adapt to the characteristics of thick SEI films, individualized regulation is achieved. The difference between this stage's voltage step-up design (0.1V per step, with the dwell time gradually shortening as the charge approaches full) and the traditional constant voltage termination is that it actively regulates the relative relationship between lithium-ion energy (E) and the SEI film barrier (V0) through voltage changes, thereby enhancing the targeting of the quantum tunneling effect, rather than simply maintaining a fixed voltage. The voltage adjustment formula for promoting lithium-ion penetration through the SEI film by the quantum tunneling effect: ; The biomimetic neuron adaptive charging decision module drives the charging voltage adjustment in volts (V) during the quantum tunneling effect tailing stage, which is used to promote lithium ion penetration through the SEI membrane at a specific stage and accelerate the charging process. Constants related to battery materials and structure (unit: The characteristics of the battery electrode materials and the composition of the SEI film are determined by factors such as the battery electrode material properties and the basic response characteristics of the battery to the quantum tunneling effect. The mass of lithium ions, measured in kilograms (kg), is a key physical quantity in the quantum tunneling process, affecting the tunneling probability and the required voltage drive. The barrier height of the SEI film for lithium ions, measured in volts (V), represents the energy barrier that lithium ions need to overcome to penetrate the SEI film. It is related to factors such as the chemical composition and thickness of the SEI film. The energy of lithium ions, measured in joules (J), is related to conditions such as current and voltage during charging, which determine the initial energy state of lithium ions under the influence of an electric field. Reduce Planck's constant to a value of , is a fundamental constant in quantum mechanics and plays a key role in describing the quantum tunneling phenomenon; SEI film thickness, measured in meters (m), is obtained through a battery genome mapping and matching module and related microscopic detection techniques. It is an important structural parameter affecting the difficulty of quantum tunneling. Through in-depth research on the microstructure and quantum mechanical principles of lithium batteries, a mathematical relationship between voltage adjustment and various related physical quantities is established, providing a theoretical basis for voltage regulation in the final stage of charging. S32. Energy Repair and Genome Map Update: Before charging is complete, the spatiotemporal energy recovery and redistribution module plays a crucial finishing role, concentrating the energy recovered in the previous stage into the battery's active material lattice to help repair lattice defects during the fast charging process. After charging is completed, its energy recovery and distribution data is transmitted to the battery genome map construction and matching module to update the battery's "acquired genetic" data, providing an updated "genetic profile" for the next charging strategy optimization, forming a complete charging cycle closed loop. The S3 terminator is marked by the voltage stepping up to 4.2V and the current dropping below 0.05C (C is the battery's rated capacity).

[0098] Example 4 Corresponding to the above method embodiments, this invention provides a fast charging device for lithium batteries. Figure 3 This is a schematic diagram of the structure of a fast charging device for a lithium battery provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the fast charging device for the lithium battery may include: The data acquisition module 301 is used to acquire the battery's genomic map data and real-time microstate monitoring data.

[0099] The dynamic charging parameter sequence generation module 302 is used to generate dynamic charging parameter sequences based on genome map data and real-time microstate monitoring data through a biomimetic neuron adaptive charging decision model.

[0100] The control process execution module 303 is used to execute a multi-physics field coordinated charging control process based on a dynamic charging parameter sequence.

[0101] The fast charging device for lithium batteries provided in this invention can acquire the battery's genomic map data and real-time microscopic state monitoring data. Based on the genomic map data and the real-time microscopic state monitoring data, a dynamic charging parameter sequence is generated through a biomimetic neuron adaptive charging decision model. Based on the dynamic charging parameter sequence, a multi-physics field collaborative charging control process is executed. This method can predict and avoid risks such as localized overheating and charge accumulation inside the battery in advance, ensuring fast charging safety from the source. Simultaneously, through multi-physics field collaborative control, polarization loss is significantly reduced, charging efficiency and energy utilization are improved, thereby significantly extending battery cycle life while achieving ultra-fast charging.

[0102] In some embodiments, the data acquisition module is further configured to acquire data on the crystal structure of the electrode material and the composition of the SEI film of the battery through a laser Raman spectrometer and a secondary ion mass spectrometer, and generate a battery genome map; and to acquire data on the micron-level temperature field distribution and charge migration trajectory inside the battery through a quantum dot temperature sensing and charge distribution coupling module.

[0103] In some embodiments, the data acquisition module is further configured to construct the battery's innate genetic feature vector based on the crystal structure data of the electrode material; construct the battery's acquired genetic feature vector based on the SEI film composition and thickness data; and generate a battery genome map by weighting and fusing the innate and acquired genetic feature vectors using pre-set weighting coefficients.

[0104] In some embodiments, the dynamic charging parameter sequence generation module is further configured to input genomic map data and real-time microstate monitoring data into a three-layer neural network model; dynamically adjust the connection weights based on the principle of neuronal synaptic plasticity; and output a parameter sequence containing charging current, charging voltage, and magnetic field regulation coefficient.

[0105] In some embodiments, the dynamic charging parameter sequence generation module is also used to control the micro superconducting magnet array to generate a gradient magnetic field based on the magnetic field adjustment coefficient, guiding lithium ions to migrate along a preset path; to perform charging control based on charging current and charging voltage; and to trigger energy recovery and directional distribution processes based on real-time microstate monitoring data.

[0106] In some embodiments, the dynamic charging parameter sequence generation module is further configured to determine the target magnetic field strength based on charge density, local temperature, and time parameters; calibrate the actual magnetic field strength using a Helmholtz coil and a Hall sensor; and dynamically adjust the magnetic field direction based on the charge density gradient direction.

[0107] In some embodiments, the dynamic charging parameter sequence generation module is further configured to acquire energy recovery efficiency data; update the weights of acquired gene feature vectors based on the energy recovery efficiency data; and generate an updated battery genome map for optimization of the next charging strategy.

[0108] The device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0109] Example 5 This invention also provides an electronic device for operating the above-described fast charging method for lithium batteries; see [link to previous document]. Figure 4 The diagram shows the structure of an electronic device, which includes a memory 400 and a processor 401. The memory 400 stores one or more computer instructions, which are executed by the processor 401 to implement the fast charging method for the lithium battery described above.

[0110] Furthermore, Figure 4 The electronic device shown also includes a bus 402 and a communication interface 403. The processor 401, the communication interface 403 and the memory 400 are connected via the bus 402.

[0111] The memory 400 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 403 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc. The bus 402 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0112] Processor 401 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 401 or by instructions in software form. Processor 401 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a readily available storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 400, and processor 401 reads information from memory 400 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0113] This invention also provides a computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are called and executed by a processor, they cause the processor to implement the aforementioned fast charging method for lithium batteries. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0114] The computer program product for a fast charging method for lithium batteries provided in this embodiment of the invention includes a computer-readable storage medium storing non-volatile program code executable by a processor. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0115] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0116] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0117] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0118] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0119] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0120] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, 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, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A fast charging method for a lithium battery, characterized in that, The method includes: Acquire genomic mapping data and real-time microscopic state monitoring data of the battery; Based on the genome mapping data and the real-time microstate monitoring data, a dynamic charging parameter sequence is generated through a biomimetic neuron adaptive charging decision model. Based on the dynamic charging parameter sequence, a multi-physics field coordinated charging control process is executed.

2. The method according to claim 1, characterized in that, The acquisition of the battery's genomic mapping data and real-time microstate monitoring data includes: The crystal structure of the electrode material and the composition of the SEI film of the battery were obtained by laser Raman spectroscopy and secondary ion mass spectrometry, and the battery genome map was generated. By using a quantum dot temperature sensing and charge distribution coupling module, micron-level temperature field distribution and charge migration trajectory data inside the battery are obtained.

3. The method according to claim 2, characterized in that, The generated battery genome map includes: Constructing the inherent genetic feature vector of the battery based on the crystal structure data of the electrode material; Constructing the acquired genetic feature vector of the battery based on SEI film composition and thickness data; The innate and acquired gene feature vectors are weighted and fused using pre-set weighting coefficients to generate a battery genome map.

4. The method according to claim 1, characterized in that, The generation of dynamic charging parameter sequences through a biomimetic neuron adaptive charging decision model includes: The genome mapping data and real-time microstate monitoring data are input into a three-layer neural network model; Dynamically adjust connection weights based on the principle of neuronal synaptic plasticity; The output contains a parameter sequence including charging current, charging voltage, and magnetic field adjustment coefficient.

5. The method according to claim 4, characterized in that, The process of executing multi-physics field coordinated charging control based on the dynamic charging parameter sequence includes: Based on the magnetic field adjustment coefficient, the micro superconducting magnet array is controlled to generate a gradient magnetic field, which guides lithium ions to migrate along a preset path. Charging control is performed based on the charging current and charging voltage; Based on the real-time microstate monitoring data, the energy recovery and targeted distribution process is triggered.

6. The method according to claim 5, characterized in that, The method of guiding lithium ions to migrate along a preset path includes: The target magnetic field strength is determined based on charge density, local temperature, and time parameters. The actual magnetic field strength was calibrated using a Helmholtz coil and a Hall sensor. The direction of the magnetic field is dynamically adjusted based on the direction of the charge density gradient.

7. The method according to claim 3, characterized in that, The method further includes: Obtain energy recovery efficiency data; The weights of the acquired gene feature vectors are updated based on the energy recovery efficiency data. An updated battery genome map is generated for optimization of the next charging strategy.

8. A fast charging device for a lithium battery, characterized in that, The device includes: The data acquisition module is used to acquire genomic mapping data and real-time microscopic state monitoring data of the battery; The dynamic charging parameter sequence generation module is used to generate dynamic charging parameter sequences based on the genome map data and the real-time microstate monitoring data, through a biomimetic neuron adaptive charging decision model. The control process execution module is used to execute a multi-physics field coordinated charging control process based on the dynamic charging parameter sequence.

9. An electronic device, characterized in that, The device includes a processor and a memory, the memory storing computer-executable instructions that can be executed by the processor, the processor executing the computer-executable instructions to implement the fast charging method for a lithium battery according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the fast charging method for the lithium battery according to any one of claims 1 to 7.

Images