2909 results about "Battery capacity" patented technology

The invention discloses a vehicle idling start and stop control system and method. The control system judges whether a vehicle has idling start and stop conditions by monitoring the water temperatureof an engine, the capacity of a storage battery, a safety belt and other information, judges whether the vehicle has conditions of stopping the engine by monitoring the rotating speed of the engine, the speed of the vehicle, the brake air pressure and other conditions, and judges whether the vehicle has conditions of starting the engine by monitoring the gear of a gearbox, the speed of the vehicle, a hand brake and other information. When the relevant conditions are met, start and stop work signals are sent to the engine though a CAN bus. In order to guarantee the reliability of frequent startand stop of the engine, the system strengthens flywheel gear rings of a starter and the engine. In order to ensure that the battery does not lose power, a storage battery capacity sensor is added tothe system on the basis of increasing the capacity of the storage battery, and the idling start and stop are allowed when the state of charge (SOC) of the storage battery satisfies a safe starting threshold. The idling start and stop control system has advantages of low cost and high reliability, and is especially suitable for commercial vehicles.

The invention relates to the technical field of battery monitoring, in particular to an electric vehicle battery state real-time monitoring system based on deep learning. Comprising a battery data acquisition module, a feature extraction module, a battery state prediction module, a fault monitoring module and a safety regulation and control module. The battery data acquisition module acquires battery parameters in real time, the feature extraction module extracts key features through deep learning, and the battery state prediction module predicts battery capacity, health state and performance degradation based on a neural network and a differential equation. The fault monitoring module adopts integrated learning to detect abnormity and output an alarm signal, and the safety regulation and control module optimizes a charging and discharging strategy through reinforcement learning and fuzzy control to guarantee safe and stable operation of the battery. According to the invention, accurate prediction and intelligent monitoring of the battery state are realized through the deep learning technology, comprehensive state evaluation and fault early warning are provided, and the accuracy and stability of battery state monitoring are effectively improved, so that the operation safety of the electric vehicle is improved, and the service life of the battery is prolonged.

The invention relates to the technical field of motor train unit battery pack evaluation, and provides a motor train unit battery health state evaluation and life prediction method and system, and the method comprises the steps: building a database through voltage fluctuation and temperature data in a floating charge state, and analyzing a correlation mechanism between target parameters, such as a battery capacity retention ratio and active lithium stock, and internal chemical substance loss; respectively extracting driving behavior characteristics, temperature parameters and electrochemical impedance spectroscopy by adopting second-level, minute-level and hour-level time granularity, and aligning multi-frequency data by utilizing a dynamic time warping algorithm; constructing a graph structure model taking the electrochemical parameters as nodes and cross-level association as edges, and extracting a battery aging characteristic topological relation through a graph neural network; and finally, establishing a prediction model fused with multi-dimensional features, and realizing accurate prediction of the residual life and the capacity recession inflection point of the battery. And the multi-scale characteristics are combined with an electrochemical mechanism, so that the accuracy of battery health state evaluation under a complex working condition is improved.

The invention discloses a power construction unmanned aerial vehicle path planning method and system, and relates to the technical field of space calculation, and the method comprises the following steps: determining a target region needing power construction and a preset construction point coordinate; obtaining a topographic map of the target area based on the geographic information database, constructing a three-dimensional map model, and marking the preset construction point coordinates; generating an initial construction path of the unmanned aerial vehicle; the method comprises the following steps: acquiring meteorological data in real time through meteorological data of a meteorological station in a target area, establishing a meteorological obstacle three-dimensional model, and dividing a preset radius threshold with a meteorological obstacle as a circle center into non-flying areas according to the severity level of the meteorological obstacle; adjusting the initial construction path based on the non-flying area; the cruise height is adjusted according to the meteorological data and topographic relief, a relief tracking path is generated, and the constant relative height is kept; and combining the battery capacity, the flight speed and the task priority, dynamically distributing inspection road sections, and generating a corresponding power construction unmanned aerial vehicle flight path.

The invention discloses a battery capacity attenuation prediction method and device, equipment and a medium. The method comprises the following steps: acquiring operation parameter information and current working condition information of a to-be-detected battery; performing feature extraction according to the operation parameter information, and determining a battery feature parameter set; according to the current working condition information, the pre-training state evaluation model set and the battery characteristic parameter set, determining a health state evaluation value of the to-be-detected battery; and determining a capacity attenuation prediction value according to the health state evaluation value, the battery characteristic parameter set and the pre-training time convolutional network model. A pre-training state evaluation model corresponding to the current working condition of a to-be-detected battery is firstly determined, a health state evaluation value is determined in combination with a battery characteristic parameter set, and then a capacity attenuation prediction value is determined in combination with a pre-training time convolutional network model. The influence of working condition fluctuation on prediction is reduced, the prediction precision, robustness and long-term adaptability are improved, and a foundation is laid for subsequently prolonging the service life of the battery and reducing the operation and maintenance cost.

The invention discloses a storage battery capacity checking method for a parallel intelligent direct-current power supply system, and relates to the technical field of storage battery capacity checking, which comprises the following steps of: respectively deploying electromagnetic sensing modules with nanosecond-level response capability at a master control end and a slave node end of a communication bus, acquiring voltage disturbance waveform signals of the communication bus in an operation process, and performing feature extraction operation on the transient high-frequency interference pulse detected each time, and constructing a multi-dimensional feature sequence of the high-energy transient electromagnetic interference. By deploying the high-response electromagnetic sensing module and combining an active suppression mechanism of interference feature extraction and risk index driving, time alignment modeling and self-adaptive regulation and control of electromagnetic interference and communication performance are realized, the communication stability, the battery state recognition accuracy and the capacity accounting continuity of the system in a strong interference environment are effectively improved, and the system reliability is improved. And the anti-interference capability and the operation safety of the parallel direct-current power supply system are obviously enhanced.

The invention relates to a lithium battery health degree detection method and system based on artificial intelligence, and relates to the technical field of artificial intelligence, and the lithium battery health degree detection method comprises the steps: evaluating vehicle basic features according to vehicle source data, and obtaining a battery feature data table; taking the charging state of the battery as a research object, analyzing a charging segment, determining a sampling time threshold value, and judging data missing and interpolation filling according to the residual charge of the battery; calculating the battery capacity based on the charge charging time, and analyzing the battery capacity transversely and longitudinally to obtain an initial capacity value; extracting effective capacity data in all the initial capacity values according to a preset travel constraint condition; training a single-pack health degree evaluation matrix or a double-pack health degree evaluation matrix, predicting a charging fragment sequence, and constructing a battery health degree evaluation model; the single-pack health degree evaluation matrix or the double-pack health degree evaluation matrix is corrected, an optimal health degree evaluation weight matrix is obtained, and lithium battery health degree detection is completed in combination with a physical compensation mechanism; according to the method, upward fluctuation of the SOH is avoided, and the SOH estimation precision and the model adaptability are improved.

The invention discloses a storage battery capacity attenuation trend prediction method, and belongs to the technical field of storage battery prediction. By collecting voltage, current and temperature data of each monomer in real time and combining historical capacity attenuation and internal resistance growth data, the method identifies a voltage and capacity difference value, evaluates cyclic stress non-uniform distribution, and determines a current sharing proportion and a load unbalance degree. Identifying an abnormal mode of new battery overload and aged battery deep discharge, constructing a mixing abnormal working condition identification mode, if the unbalance degree exceeds the standard, adaptively adjusting the charging and discharging time and the current switching frequency, establishing a load balance control framework, predicting the capacity attenuation rate and the residual cycle index of each monomer, and determining the capacity matching degree and the life matching degree; finally, a comprehensive residual life estimation value and a credibility interval are generated through fusion; the performance balance of the mixed battery pack is remarkably improved, the overall service life is prolonged, and the method is suitable for real-time monitoring of a battery management system.

The invention discloses a lithium battery residual life prediction method and system and terminal equipment, and relates to the technical field of lithium battery health management. The method comprises the following steps: receiving a battery capacity attenuation sequence as an original input sequence, detecting and filtering abnormal data by adopting a 3 sigma criterion, and carrying out noise suppression processing on the battery capacity attenuation sequence through a Dropout mask; and carrying out normalization processing on the preprocessed battery capacity attenuation sequence, dividing the battery capacity attenuation sequence into a training set, a verification set and a test set through a sliding window algorithm, and generating a time sequence characteristic matrix and a corresponding residual service life label. According to the method, a neural network structure fusing trend prior perception and dynamic attention regulation is constructed, a multi-scale capacity modeling strategy is introduced to separate a degradation trend, fluctuation disturbance and high-frequency noise, and compared with a traditional time sequence neural network or a single attention model, pseudo fluctuation characteristics caused by capacity regeneration can be more effectively recognized, and the method is more efficient and more reliable. And the judgment accuracy of the model in a complex degradation scene is improved.

The invention relates to a lithium ion battery life prediction method, and belongs to the field of battery life prediction and intelligent maintenance. The method comprises the steps that S1, a battery capacity degradation sequence is collected, and integrity is checked and normalized; s2, decomposing the sequence by using an improved complete set empirical mode decomposition algorithm, and dividing the sequence into a high-frequency component and a low-frequency component according to a zero-crossing rate; s3, modeling the high-frequency component: fusing multi-scale channel interactive attention, a time sequence convolutional network and a hybrid expert model, and extracting short-term fluctuation and capacity recovery features; s4, modeling a low-frequency component: introducing a two-way gating circulation unit network constrained by a double-index degradation model, and simulating a long-term trend; and S5, constructing a high-frequency migration module through tensor decomposition, improving cross-battery generalization, and fusing high and low frequency results to output a residual life prediction value. According to the method, a dual-channel framework combining signal decomposition, deep learning and physical modeling is combined, the prediction precision and adaptability under complex degradation are improved, and the method is suitable for various battery systems.

The invention discloses a battery capacity performance testing method and device and a storage medium, and relates to the technical field of battery capacity performance testing. By constructing a dynamic load model and a multi-load test protocol and combining a high-precision data acquisition and filtering algorithm, adaptive data analysis and a machine learning regression model, the problems of difficulty in balancing precision and efficiency, large data acquisition error, fixed test protocol and the like in the traditional battery test are solved; by dynamically adjusting test parameters and environmental conditions, complex working conditions of the battery in actual use are accurately simulated, meanwhile, dynamic updating and optimization of a test protocol are achieved, the test precision, the data reliability and the test efficiency are remarkably improved, and a comprehensive, efficient and high-adaptability solution is provided for battery performance evaluation and health management.

The invention discloses a real vehicle power battery capacity attenuation trajectory prediction method based on a de-noising diffusion model. According to the method, a diffusion generation model is applied to the field of battery capacity prediction for the first time, multi-modal features are constructed for charging and discharging data under a real vehicle working condition, feature expressions are extracted through Transform and CNN, and the features are integrated into high-dimensional embedded vectors. And then, a DDPM model based on a ContextUnet architecture is utilized to learn a dynamic change rule of capacity attenuation in a noise environment through a noise diffusion and reverse denoising process under the guidance of multi-modal features, so that high-precision capacity prediction is realized. The training process is further combined with an implicit denoising mechanism of DDIM, and the reasoning speed is increased while the prediction quality is improved. Finally, a capacity attenuation track confidence interval is obtained by performing multiple times of prediction sampling calculation on a predicted capacity attenuation result, and the capacity attenuation track confidence interval can be used for deducing key indexes such as the state of health (SOH) and the remaining service life (RUL) of the battery. The method has the characteristics of high prediction precision and strong adaptability, obviously enhances the intelligent level of the battery management system, and has important practical value for health assessment and life management of the new energy automobile battery.

The invention relates to a charging station management method and system based on an intelligent box, and relates to the field of the vehicle charging technology, and the method comprises the steps: obtaining the overall power of a power grid and the charging demand power of each current charging pile; determining the overall required power according to each charging required power, and determining the available power of the power grid according to the overall power of the power grid and the anti-disturbance coefficient; when the overall demand power is greater than the available power of the power grid, acquiring the battery capacity percentage, the residual charging duration and the vehicle priority coefficient of each vehicle according to each charging pile; calculating according to the battery capacity percentage, the residual charging duration and the vehicle priority coefficient to determine a vehicle basic weight; and calculating according to the available power of the power grid, the basic weight of the vehicle and the charging demand power to determine effective distribution power, and controlling each charging pile to operate at the corresponding effective distribution power. The method and the device have the effect of improving the charging experience when the vehicle is charged by using the charging station.

The invention relates to a joint estimation method for SOC and SOH of a power battery, in particular to a joint estimation method for SOC and SOH of a lithium ion power battery based on FOASEKF-EKF, comprising fractional order equivalent circuit models of two parallel fractional order CPE branches, and providing a hybrid genetic algorithm HGA fusing a differential evolution strategy and an adaptive variation mechanism. Accurate estimation of SOC and terminal voltage under a fast time scale is realized by introducing a sliding-mode observer and an FOASEKF, periodic online correction is performed on model parameters and battery capacity based on an EKF under a slow time scale, and high-precision and high-robustness battery SOC and SOH joint estimation is realized. The method is suitable for complex industrial environments such as electric automobiles and rail transit, does not need to set a large number of hyper-parameters, does not excessively depend on the quality and quantity of data, has good interpretability, adaptability and engineering practicability, can still achieve high-precision cooperative estimation of SOC and SOH especially under the working conditions of frequent start and stop and unsteady operation, and has good application prospects. And misjudgment and drift estimation risks are obviously reduced.

Methods, systems, and devices for wireless communications are described. A user equipment (UE) may perform event-based energy harvesting reporting to a network entity providing a signal for wireless charging or powering of the UE. The UE may signal its energy harvesting-related capabilities. and the network entity may signal to the UE a configuration for energy harvesting and event-based energy harvesting reporting. The configuration may include an indication of an energy harvesting charging range of the network entity. In some examples, the UE may indicate a maximum battery capacity of the UE, so that the network entity may determine to stop charging when the battery capacity is reached. The UE may be configured to report energy harvesting procedures according to triggering events, such as battery level of the UE or a switch in bandwidth or frequency of a charging signal.

The invention relates to an optical storage and charging integrated station energy storage system scheduling method based on a CNN-SAC algorithm, and belongs to the technical field of optical storage and charging integrated station energy storage systems. According to the technical scheme, an energy storage system operation efficiency evaluation model and a battery capacity decline prediction model are constructed; establishing an operation analysis model with the optimal economic benefit of the optical storage and charging integrated station as a target; and an energy storage system optimization mechanism based on deep reinforcement learning is established, and autonomous learning and decision making of an optimal strategy are realized by applying a CNN-SAC (Consensus Networks-Consensus Consensus) algorithm and a deep reinforcement learning algorithm. According to the method, a multi-dimensional operation analysis model is constructed by taking the optimal economic benefit of the photovoltaic charging station as a target, so that the operation cost can be reduced, the synergistic effect of photovoltaic power generation and an energy storage system can be fully utilized, and the overall economic benefit is improved. By introducing the CNN-SAC deep reinforcement learning algorithm, the efficient intelligent scheduling of the energy storage system of the optical storage and charging integrated station is realized, and the operation efficiency and decision precision of the system are remarkably improved.

The invention provides an energy storage power station optimization operation mode decision-making method and system, and relates to the technical field of energy storage power station optimizing.A hybrid prediction model is constructed to realize high-precision decomposition prediction of power load, and meanwhile, the internal resistance of a battery is estimated in real time by adopting a recursive least square method; and the battery capacity and internal resistance parameters are dynamically corrected in combination with a temperature compensation mechanism. Through health state multi-index fusion evaluation, self-adaptive distribution of charging and discharging power is achieved, and compared with the prior art, the problem that a traditional static model cannot adapt to complex environment changes is solved. The battery capacity fading risk can be predicted in advance by introducing a double-compensation mechanism of an environmental influence index and an electric power influence index. According to the scheme, the response speed and economical efficiency of energy storage in a high fluctuation load scene are remarkably improved, and a reliable dynamic optimization decision support system is provided.

The embodiment of the invention provides a preparation method of a negative electrode active material, the negative electrode active material, a battery and equipment. Fluorine-containing gas is used as discharge gas, and discharge current is introduced into a plasma treatment device in the process of performing vibration dispersion treatment on a porous carbon substrate through the plasma treatment device; the fluorine-containing gas is used for carrying out plasma discharge treatment on the porous carbon matrix, so that the fluorine element provided by the fluorine-containing gas can react with carbon atoms on the surface of the porous carbon matrix to form chemical bonding, and the chemical bonding uniformity between the fluorine element and the carbon atoms on the surface of the porous carbon matrix can be improved; and the preparation cost of the negative electrode active material can be reduced, and the preparation efficiency of the negative electrode active material is improved, so that the battery capacity and the cycle performance of a secondary battery prepared from the negative electrode active material disclosed by the embodiment of the invention can be improved.

The invention discloses a lithium battery life prediction method, which comprises the following steps of: establishing an account ID (Identity) of each electric vehicle on a charging pile, and recording data of each electric vehicle during charging in the account ID to obtain historical charging data; collecting current charging data of the battery in real time through the charging pile; evaluating the health state of the battery based on the historical charging data and the current charging data, wherein the health state evaluation comprises battery capacity attenuation, internal resistance change and charging efficiency evaluation; using a battery recession model to predict the remaining life of the battery; generating early warning prompts of the health state and the residual life of the battery according to the prediction result; according to the scheme, the comprehensive analysis model based on historical data and real-time data of the charging pile is established, so that the problems of low accuracy, single evaluation dimension, imperfect early warning mechanism and the like in an existing battery life prediction method are solved, and the intelligent degree of battery life prediction and management is improved.

The invention discloses a power supply intelligent management system of an AGV trolley, and relates to the technical field of intelligent management, during operation of the system, data monitoring is performed through various sensors, measuring equipment and a battery management system BMS, and internal resistance data, battery capacity attenuation conditions and battery charging and discharging conditions of a battery of the AGV trolley are acquired in real time; the battery health index is comprehensively calculated through the battery internal resistance coefficient, the battery capacity attenuation coefficient and the battery charging and discharging efficiency coefficient, the output power of the battery is dynamically adjusted, the charging and discharging process of the battery is automatically adjusted according to data collected in real time and a load evaluation result, and intelligent scheduling is achieved according to needs. By analyzing the health data, the charging and discharging behaviors and the working environment of the battery, the battery fault is predicted in time, automatic fault detection and early warning are supported, system shutdown or performance reduction caused by the battery fault is avoided, an interactive interface between a user and the system is provided, and remote monitoring and control are supported at the same time.

The invention discloses a lithium ion battery capacity inflection point prediction method and system based on a multi-parameter data fusion decision. The method comprises the following steps: collecting multi-parameter data of a lithium battery and preprocessing the multi-parameter data; constructing an inflection point prediction model based on deep learning, and extracting time sequence data characteristics of current, voltage and temperature; based on an attention-enhanced graph convolutional neural network AGCN, an attention mechanism is introduced into a graph convolutional neural network GCN to dynamically learn the association weight of a multi-parameter feature matrix, and multi-parameter data fusion features are obtained; dynamic decision making is carried out on the battery multi-parameter data fusion features, linear transformation is carried out on a dynamic decision making result to obtain a predicted value of an inflection point, and construction of an inflection point prediction model is completed; carrying out training optimization on the whole model, and predicting the residual cycle period of the battery to the inflection point; according to the method, inflection point high-precision prediction of any stage of the battery can be realized by depending on relatively short cycle period data.

The invention relates to the technical field of energy storage systems, and provides an energy storage system capacity configuration optimization method based on battery capacity attenuation trajectory prediction. The method comprises the following steps: acquiring operation state data of a battery module in the energy storage system, establishing a historical operation database and a battery capacity attenuation trajectory prediction model, calculating an attenuation trajectory of battery capacity along with time through a temperature accelerated aging factor and a cyclic aging factor, and obtaining a capacity attenuation prediction curve in a future time period; and establishing a capacity configuration optimization function taking net present value maximization as a target by combining a load demand curve and an economic index of the energy storage system, dynamically adjusting charge and discharge depth limitation and a power distribution proportion, dynamically adjusting charge and discharge power of each battery module according to a real-time capacity state, and realizing optimized operation of the energy storage system. According to the invention, accurate prediction of battery capacity attenuation and optimization of full life cycle capacity configuration are realized, and the economic benefit and operation reliability of the energy storage system are improved.

The invention relates to the technical field of battery management, in particular to a battery replacement cabinet battery real-time monitoring and scheduling method, the health state of a battery is analyzed and evaluated according to a preset algorithm model, and the health state of the battery is evaluated by comparing a comprehensive health score, an internal resistance change rate and a capacity fading rate with corresponding threshold values; and determining a corresponding processing mode based on the evaluation result, including generating and sending abnormal alarm information to the operation and maintenance terminal, or executing an adjustable charging mode according to the state of residual electric quantity of the battery, or executing a protective charging mode according to the deterioration degree of the battery, the health state of the battery is actively evaluated to accurately identify an abnormal battery, for example, the electric quantity may be not low but potential safety hazards exist, in advance, so that targeted charging scheduling can be realized. According to the invention, real-time monitoring and active protection of the health and safety state of the battery are realized, so that the operation efficiency is improved on the premise of ensuring the safety.

The invention discloses a medical simulator battery life prediction method based on dynamic weight and physical constraint, and relates to the field of medical equipment battery health management, and the method comprises the steps: building a dynamic fusion weight, a battery capacity physical prediction model and a battery capacity LSTM prediction model according to the physical characteristics of a medical simulator battery; the battery capacity physical prediction model and the LSTM battery capacity prediction model are fused through dynamic fusion weights, a physical constraint loss function, an LSTM loss function and a joint loss function are established, parameters of the prediction models are updated through the loss functions, and finally a medical simulator battery life prediction result is obtained. Through fusion of the battery capacity physical prediction model and the LSTM battery capacity prediction model, the problems that time sequence characteristics of a traditional LSTM model are insufficient to capture and a pure data driving method neglects a battery physical mechanism are solved, and the accuracy and reliability of medical simulator battery life prediction are improved.

The invention discloses a digital twin drive life prolonging system and method in a lithium battery aging process, the system comprises a sensor detection module, an AI control module and a regulation and control module, the sensor detection module detects pressure, temperature, gas components, SEI film conditions and voltage data between a conductive layer and an anode, and inputs the data into the AI control module; the AI control module performs electrochemical-thermodynamic-mechanics multi-physics field coupling modeling by applying a digital twinborn technology, performs data analysis and processing in combination with cross-working-condition model migration, screens out an optimal regulation and control scheme according to a mirage optimization algorithm, sends an instruction to the regulation and control module, and controls the regulation and control module according to the instruction of the AI control module. Parameters in the energy storage cabin are adjusted, the SEI film state is maintained, and lithium dendrite precipitation is controlled, so that the service life of the lithium battery is prolonged; according to the method, the digital twinborn model is utilized to identify battery capacity attenuation inflection points, trigger lithium supplement or charge strategy optimization and other regulation measures, irreversible damage is avoided, and the replacement frequency is reduced.

The invention relates to the technical field of electric energy storage control, in particular to an energy storage thermal power generating unit frequency modulation capability assessment method and system, and the method comprises the following steps: based on thermal power storage operation data, identifying node indexes and state records, extracting fluctuations and frequencies, assessing frequency response fitness, analyzing a regulation rate and a cooperation ratio, and screening risk units. And outputting the frequency modulation capability evaluation interval. According to the invention, through integration and identification of operation data of the energy storage thermal power generating unit, electric quantity fluctuation, an energy storage state and load change are monitored in real time, a response period of an energy storage unit is optimized, stability of a frequency modulation process is ensured, battery capacity, a temperature rise rate and a cycle frequency are comprehensively monitored, overload and efficiency reduction are avoided, stable scheduling of a power grid is guaranteed, and the power generation efficiency is improved. Through health risk identification and frequency modulation response space demarcation, cooperation of energy storage and thermal power generating units is realized, the regulation capability and long-term reliability of a power grid for dealing with fluctuating energy are enhanced, and the problem of response delay or efficiency in a traditional method is avoided.

The invention discloses a storage battery capacity prediction method based on multi-source asynchronous perception and time hybrid modeling, and the method comprises the steps: collecting electrochemical parameters of a storage battery pack, carrying out the preprocessing, obtaining a time sequence sample, and extracting a capacity time sequence; constructing a multi-channel convolution encoder family module, and performing independent feature extraction on the electrochemical parameters by taking a time sequence sample as input to obtain spatial feature mapping; constructing a time hybrid modeling module, and obtaining capacity time sequence feature mapping by taking the capacity time sequence as input; constructing a cross-parameter feature fusion layer, and inputting spatial feature mapping and capacity time sequence feature mapping to obtain health state features; inputting the health state characteristics into a regression prediction head, and outputting a prediction value of the storage battery pack; and constructing a main loss function to carry out model training. The method realizes an integrated prediction mechanism for the transformer substation storage battery capacity degradation process, can effectively adapt to the complex operation environment of a transformer substation, and has relatively high engineering feasibility and popularization and application values.

The invention discloses a storage and charging system battery capacity calculation method, and relates to the technical field of storage and charging system optimization control, and the method comprises the steps: collecting multi-modal data of a battery pack, and generating time-space aligned multi-modal data through a timestamp alignment and three-dimensional coordinate conversion algorithm; extracting local temperature gradient characteristics of an infrared thermogram and dynamic time characteristics of a charging and discharging curve through DSC and Bi LSTM based on the multi-modal data of space-time alignment, segmenting spatial distribution characteristics of electrolyte flow abnormity of an ultrasonic image by using U-Net, dynamically distributing weights of the multi-modal characteristics through a space-time attention mechanism, and generating a fusion characteristic vector; and inputting the fusion feature vector into a GRU-Transform hybrid model to generate a dynamic capacity prediction value, and identifying an aging type by dynamically analyzing historical data. According to the invention, multi-modal features are extracted through DSC, Bi LSTM, U-Net and other technologies, and comprehensive monitoring and dynamic adjustment of the battery health state are realized.

The invention belongs to the technical field of batteries, and discloses a composite lithium supplement agent, a positive pole piece, a battery and electric equipment. The composite lithium supplement agent comprises an inner core and a shell covering the inner core, wherein the shell comprises a carbon coating layer; the carbon coating layer comprises a cage-shaped ball structure, and the carbon coating layer has elasticity; the inner core comprises a lithium supplementing material. The composite lithium supplement agent can adapt to the volume change of the lithium supplement material during the first lithium removal, and the contact between the electrolyte and the interior of the composite lithium supplement agent or a decomposition product is avoided, so that the side reaction of an interface is reduced, the gas production is reduced, the battery capacity is improved, and the stability and safety of the battery are favorably improved.

A lithium battery life prediction method based on modal decomposition and Informer-LSTM belongs to the field of battery life prediction, and adopts a CEEMDAN method to decompose a battery capacity data sequence into a plurality of intrinsic modal components serving as high-frequency components and a residual component serving as a low-frequency component, so as to reduce the influence caused by the irregular recovery phenomenon of the battery capacity; inputting the low-frequency component into the LSTM network model to obtain a low-frequency component prediction result; a high-frequency component is secondarily decomposed into a trend term and a residual term by adopting a Dlinear method, and the fluctuation degree of the high-frequency component is reduced while key information is reserved, so that the prediction stability is improved. Respectively inputting a trend term and a residual term decomposed by each high-frequency component into an Informer network model for prediction, then superposing results, extracting implicit features in the complex fluctuation data, and obtaining a prediction result of the high-frequency component; and carrying out weighted fusion on the low-frequency component prediction result and the prediction results of the plurality of high-frequency components to obtain a final prediction result.