Abstract: A heterogeneous computing terminal for task scheduling is provided, including a processing unit and multiple computing units. The heterogeneous computing terminal generates a task scheduling strategy. The target computing unit acquires a target upgrade program, is upgrade based on the target upgrade program, processes a target task and sends a processing result to the processing unit. The processing unit combines processing results sent by multiple target computing units to obtain a processing result of an initial task set. The heterogeneous computing terminal can upgrade the computing unit online, that is, dynamically update the computing unit, thereby greatly expanding the versatility of the computing unit of hardware. Scheduling strategy adapted to the task can be generated, and the computing unit can dynamically provide better task processing capabilities. The computing efficiency of the heterogeneous computing terminal is improved.

Abstract: The invention discloses a method for step parameter identification based on an electrochemical model, including: identifying a first type of electrochemical parameters through a reduced-order electrochemical model by utilizing different preset charge-discharge rate data; determining a first type of target electrochemical parameters identified by the reduced-order electrochemical model through extrapolation; the first type of target electrochemical parameters including an approximate value of the first type of electrochemical parameters or the first type of electrochemical parameters at a specific rate; identifying the first type of electrochemical parameters, which includes solid-phase lithium concentration and exchange current, through a full-order electrochemical model by taking the first type of target electrochemical parameters as actual values of the first type of electrochemical parameters of the full-order electrochemical model; and identifying a second type of electrochemical parameters, which include

Abstract: The invention provides a method and system for decoupling electric field of electrochemical model based on a parallel targeting method. The method includes selecting a negative or positive electrode region as a calculation region; selecting a solid or liquid phase current as an observed quantity, and a solid and liquid phase potential as a costate variable; inserting nodes between two endpoints of the calculation region, and determining a target value of the observed quantity of each node; constructing N calculation units; respectively performing a target shooting on the N calculation units; and determining whether a distance between the target shooting value of the observed quantity of the end point of each calculation unit and the target value of the observed quantity of the node corresponding to the end point of the calculation unit is within a preset range.

Abstract: A method for calculating a state of charge of a battery is provided. The method includes: estimating a first state of charge of the battery by using a first state of charge estimation algorithm; estimating a second state of charge of the battery by using a second state of charge estimation algorithm; determining a first weight corresponding to the first state of charge and a second weight corresponding to the second state of charge based on state data of the battery; and calculating the state of charge of the battery based on the first state of charge and the first weight, and the second state of charge and the second weight. With method for calculating a state of charge of a battery in the present disclosure, the accuracy of calculating the state of charge of the battery can be improve d with a lower computation cost.

Abstract: The invention provides a method and system for identifying electrochemical model parameters based on capacity change rate. The method includes: acquiring operating data from an actual operation process of a lithium battery and cleaning an actual operating data set from the operating data; generating a simulated operating data set through simulation of a preset electrochemical model; performing parameter identification based on a preset first loss function, the actual operating data set, and the simulated operating data set; calculating capacity convergence coefficient; comparing capacity convergence coefficient with a preset convergence threshold value; when greater than the preset convergence threshold value, regenerating the simulated operating data set; and when not greater than the preset convergence threshold value, outputting an electrochemical model parameter set as a parameter identification result.

Abstract: A method for monitoring battery cell data comprises: collecting the first set of the battery cell data in real time; retrieving estimation parameter data corresponding to the first set of the battery cell data from a battery cell parameter database in real time; based on the estimation parameter data of the first set of the battery cell data, processing the first set of the battery cell data through a battery model to acquire the second set of the battery cell data in real time; acquiring an error value between the first set and the second set of the battery cell data in real time; acquiring a monitoring result of the first set of the battery cell data in real time based on the error value and an error threshold, the monitoring result is either the error value being greater than the error threshold, or less than the error threshold.

Abstract: A method and a device for forecasting an electric load, an electronic device, and a computer-readable storage medium are provided. The method includes: acquiring historical load data prior to a forecast date; generating a load sequence based on the historical load data; performing variational mode decomposition on the load sequence, to obtain multiple intrinsic mode components and a residual that are corresponding to the load sequence; and inputting the multiple intrinsic mode components and the residual into respective forecasting models, and determining a load value on the forecast date based on forecasting results of all the forecasting models. With the method and the device, the electronic device, and the computer-readable storage medium, the load sequence is decomposed based on the variational mode decomposition, so that more dimensional feature information in the load sequence can be mined. Moreover, the residual is also used as valid data.

Abstract: A thermal-runaway warning method, system, and terminal for a power station are provided. The method comprises: obtaining collected data of a battery module comprised in the power station, wherein the collected data comprises collected temperature values of the battery module collected by temperature measuring devices; normalizing the collected data to obtain a standard dataset; training a CNNLSTM-based temperature predicting model based on the standard dataset to obtain a trained CNNLSTM-based temperature predicting model; and obtaining a predicted temperature value of the battery module within an output time window based on the trained CNNLSTM-based temperature predicting model, and determining whether there is a risk of thermal runaway in the power station based on the predicted temperature value.

Abstract: A battery overheat warning method, a battery overheat warning system, a storage medium, and an electronic device are provided. The battery overheat warning method comprises: obtaining working condition parameters and geometric parameters of a battery; obtaining a theoretical temperature of a target position in the battery based on the working condition parameters and the geometric parameters of the battery; obtaining an actual temperature of the target position in the battery by using a temperature transducer; and sending an overheat warning signal based on the theoretical temperature and the actual temperature of the target position in the battery. The battery overheat warning method has relatively high timeliness and accuracy.

Abstract: The invention discloses a method, a system, and a storage medium for simulating a data set based on an electrochemical model. The method includes the following steps: setting geometric parameters and electrochemical parameters of a lithium battery; generating a volume average concentration of positive lithium ions and a volume average concentration of negative lithium ions under a preset state of charge through a simulation of the electrochemical model; calculating a capacity of the lithium battery through the simulation of the electrochemical model; after adjusting a current state of charge of the lithium battery, inputting a simulated operating current to acquire a simulated data set. The invention can generate operating data of a virtual battery by adjusting lithium battery electrochemical model parameters, facilitating management by a BMS system of battery operating states based on an electrochemical model of a virtual battery.

Abstract: A hot-plugging edge computing system includes at least an elastic database, a data processing module, and hot-plugging computing modules. The elastic database is configured to store data through an SSD array with a configurable number of SSDs. The data processing module is connected to the elastic database and each of the hot-plugging computing modules, and controls data storage in the elastic database, monitors and assigns a task to each of the hot-plugging computing modules. Each of the hot-plugging computing modules performs data computing based on the corresponding task assigned by the data processing module, and returns a computing result to the corresponding data processing module.

Abstract: The invention discloses a method, a system, a device, and a medium for detecting a battery state of health. The method includes extracting a target curve segment from a first charging characteristic curve of a battery under test; and determining, according to a corresponding relation between characteristic parameters of the target curve segment and the battery state of health, the battery state of health matching the characteristic parameters of the target curve segment, and determining the battery state of health as the battery state of health of the battery under test. By utilizing said corresponding relation as the calculation basis, the invention improves the reliability and accuracy of the detection of battery state of health detection. The invention also tracks instances of abusive conditions that accelerate battery aging, assessing whether such conditions accelerate battery degradation and issuing warnings accordingly.

Abstract: The invention discloses a method, a system, an electronic device, and a storage medium for determining performance of a power battery. The method includes the following steps: acquiring historical data of the power battery in at least two charging processes; determining, according to historical data in one charging process, a dQ/dV curve and a direct current internal resistance corresponding to said charging process; calculating a relative change rate of internal resistance capacity in any two charging processes; and determining the performance of the power battery according to the relative change rate of internal resistance capacity and a relative change rate of internal resistance capacity range corresponding to fault type. The invention can effectively determine whether the performance of the power battery is abnormal by combining, in the two charging processes, the target peak value of a dQ/dV curve of the power battery and the change in direct current internal resistance.

Abstract: A method for estimating an internal resistance of a lithium battery, a storage medium, and an electronic device are provided. The method includes: sampling a current and a voltage of the lithium battery at a preset sampling interval; inputting the current and the voltage of the lithium battery to an internal resistance estimation equivalent circuit model, determining to-be-estimated parameters of the model, and determining expressions of an open circuit voltage and an internal resistance of the battery; obtaining a range of each of the to-be-estimated parameters of the model based on a memory factor of the model; and inputting the range of each of the to-be-estimated parameters to an internal resistance distribution model to obtain a total internal resistance of the battery, and determining a distribution of the total internal resistance by repeatedly running the internal resistance distribution model, to obtain different estimated values of the total internal resistance.

Abstract: A method for analyzing battery life degradation, a storage medium, and an electronic device are provided. The method includes: obtaining battery data of a device, where the battery data includes a voltage and a current of a battery of the device; estimating an open circuit voltage of the battery based on the battery data; establishing a function curve between a state of charge and the open circuit voltage of the battery; extracting a life degradation curve based on the function curve; and performing life degradation analysis on the battery based on the life degradation curve. In the present disclosure, a dQ/dV curve of the battery can be accurately extracted under complex working conditions, thereby ensuring accuracy of the battery life degradation analysis, and achieving desirable practical applicability under complex working conditions.

Abstract: The invention discloses a method, a system and a storage medium for consistency analysis of a lithium battery module. The method includes acquiring various microscopic electrochemical parameters corresponding to each single cell in the lithium battery module; respectively establishing a time sequence database of the microscopic electrochemical parameters corresponding to each single cell, based on each of the microscopic electrochemical parameters; and performing consistency analysis on each single cell that meets a preset circuit connection relation based on each time sequence database.

Abstract: The invention discloses method system for detecting lithium precipitation of lithium batteries. The method includes acquiring voltage-time data of lithium batteries of a battery module; performing feature extraction on the voltage-time data to obtain voltage-time data of charging and discharging in accordance with a preset range; performing an inflection point judgment on the voltage-time data of the charging and discharging; determining that there exists the inflection point, and grading the inflection point time when the inflection point occurs; and detecting an amount of lithium precipitation of the lithium batteries based on the grade of the inflection point time. The method combines data feature extraction and electrochemical model in big data and establishes a series of log and threshold system to detect and monitor lithium precipitation and early warn for lithium batteries.

Abstract: The invention provides method, system and storage medium for solving electric field physical quantity in an electrochemical model. The method includes selecting a negative or positive electrode region as a calculation region; selecting a solid or liquid phase current as an observed quantity, and a solid- and liquid-phase potentials as a costate variable; inserting nodes between two endpoints of the calculation region, and determining a target value of the observed quantity of each node; constructing N calculation units; sequentially completing shooting of each of the N calculation units until a convergent solution of the target shooting of the N-th calculation unit is obtained, and taking the convergent solution as a deterministic solution of the costate variable; obtaining the physical quantity of each spatial point at the present time according to the observed quantity of the starting point at the present time and the deterministic solution of the costate variable.

Abstract: The invention provides a method and a system of working condition sensitivity analysis and data processing for parameter identification and/or for training a parameter identification neural network. The method includes according to a selected reference voltage interval, obtaining a voltage data set corresponding to electrochemical model parameters in the reference voltage interval; normalizing voltage values of the voltage data set to obtain a characteristic voltage data set, wherein the number of voltage values corresponding to different electrochemical model parameters in the characteristic voltage data set is equal; and inputting the characteristic voltage data set into a neural network model, and outputting initial values of the electrochemical model parameters to analyze the working condition sensitivity by taking the electrochemical model parameters as labels. The electrochemical model parameters include high sensitivity parameters.

Abstract: The invention discloses method and system for target-based electric field decoupling for an electrochemical model.