Discharging strategy optimization method and system for battery pack

Abstract

The invention provides a discharge strategy optimization method and system for a battery pack, and the method comprises the steps: collecting the internal state data of the battery pack and the real-time operation data of load equipment, carrying out the multi-source data fusion through combining with environment state information, and obtaining a fusion perception parameter; performing mode recognition on the load equipment and the battery pack based on the fusion sensing parameters to generate a current discharge mode; and querying a preset strategy mapping table according to the current discharge mode, and performing discharge regulation and control in combination with the fused sensing parameter to obtain a discharge regulation and control parameter. According to the invention, discharge regulation and control can be carried out by combining real-time fusion sensing parameters, accurate dynamic management of the output power of the battery is realized, and the efficiency and stability of the discharge process are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery packs, in particular to a discharge strategy optimization method and system for battery packs. BACKGROUND

[0002] As the core energy source of electric vehicles and various portable electronic devices, the optimization of the discharge strategy of the battery pack is of great significance to improving the performance of the device and prolonging the service life of the battery. With the continuous improvement of the intelligence and functional complexity of the power consumption device, more precise management and adaptive control of the battery discharge process are required. The existing discharge strategy optimization methods usually focus on the state parameters of the battery itself and fail to fully integrate the real-time running requirements of the load device and the influence of external environmental changes, resulting in insufficient adaptability and accuracy of the strategy, which may affect the working efficiency of the battery and accelerate its performance degradation. SUMMARY

[0003] To overcome the problems in the related art, the present application provides a discharge strategy optimization method and system for battery packs, which can combine real-time fusion perception parameters for discharge regulation and control, realize precise dynamic management of the battery output power, and effectively improve the efficiency and stability of the discharge process.

[0004] The present application provides a discharge strategy optimization method for battery packs, comprising: Collecting internal state data of the battery pack and real-time running data of the load device, combining environmental state information for multi-source data fusion to obtain fusion perception parameters; Performing mode recognition on the load device and the battery pack based on the fusion perception parameters to generate a current discharge mode; According to the current discharge mode, querying a pre-set strategy mapping table and combining the fusion perception parameters for discharge regulation and control to obtain discharge regulation and control parameters.

[0005] Further, the collecting of the internal state data of the battery pack and the real-time running data of the load device, the combining of the environmental state information for multi-source data fusion to obtain fusion perception parameters, comprises: Identifying the single cell voltage, total voltage and charge and discharge current of the battery pack through the built-in sensor of the load device, performing battery state integration to obtain the internal state data; Reading the power demand, running frequency and vibration readings of the load device, performing state calculation to obtain the real-time running data; Collecting real-time environmental information of the load device through the built-in sensor, performing environmental recognition to obtain the environmental state information; Fusing the internal state data, the real-time running data and the environmental state information, performing battery perception to obtain the fusion perception parameters.

[0006] Further, the mode recognition of the load device and the battery pack based on the fusion perception parameter generates a current discharge mode, comprising: Based on the fusion perception parameter, the battery health of the battery pack is calculated, the battery degradation calculation is performed, and the battery state degradation data is obtained. According to the fusion perception parameter, the working condition data of the load device is identified, the load analysis is performed, and the load working condition data is obtained. The battery state degradation data and the load working condition data are associated for battery energy supply, and the associated feature information is obtained. Based on the preset discharge mode set, the current mode recognition of the associated feature information is performed, and the current discharge mode is obtained.

[0007] Further, the battery health of the battery pack is calculated based on the fusion perception parameter, the battery degradation calculation is performed, and the battery state degradation data is obtained, comprising: The battery performance parameters of the battery pack are analyzed in combination with the internal state data and the fusion perception parameter; According to the preset battery health threshold, the battery health value is calculated based on the battery performance parameters; The historical health value of the battery pack is obtained, the battery degradation trend analysis is performed on the battery health value, and the battery degradation information is obtained; According to the battery degradation information and the battery performance parameters, the degradation state evaluation is performed, and the battery state degradation data is obtained.

[0008] Further, the current discharge mode is queried from the preset strategy mapping table, the discharge regulation is performed in combination with the fusion perception parameter, and the discharge regulation parameter is obtained, comprising: The current discharge mode is analyzed to obtain a power distribution coefficient and a temperature control response level; According to the power distribution coefficient, the preset strategy mapping table is queried and dynamic compensation correction is performed in combination with the fusion perception parameter, and real-time regulation parameters are generated; According to the temperature control response level and the real-time regulation parameters, energy consumption balance optimization is performed, and collaborative control parameters are generated; The safety boundary check and execution feasibility verification are performed on the collaborative control parameters, and the discharge regulation parameters are output.

[0009] Further, according to the power distribution coefficient, the preset strategy mapping table is queried and dynamic compensation correction is performed in combination with the fusion perception parameter, and real-time regulation parameters are generated, comprising: According to the power distribution coefficient, the preset strategy mapping table is indexed and queried, and the basic discharge current parameter and the basic output voltage parameter are obtained. extracting temperature distribution features in the fusion perception parameters and performing change trend analysis to obtain thermal distribution characteristic parameters and dynamic trend parameters; performing thermal characteristic compensation on the basic discharge current parameters according to the thermal distribution characteristic parameters to obtain temperature compensation currents; performing impedance matching adjustment on the temperature compensation currents and the basic output voltage parameters in combination with the state trend parameters to generate the real-time regulation parameters.

[0010] Further, the output power of the battery pack is adjusted according to the discharge regulation parameters, and the discharge information of the battery pack is continuously monitored to output power control information, including: performing instruction analysis on the discharge regulation parameters to obtain a power distribution instruction group; performing power output adjustment on the output units of the battery pack according to the power distribution instruction group to obtain output power results; monitoring the discharge information of the battery pack based on the output power results to obtain battery monitoring data; performing state power analysis on the battery monitoring data and the load device to obtain power control information.

[0011] Further, the power output adjustment on the output units of the battery pack according to the power distribution instruction group to obtain output power results includes: performing instruction priority sorting on the power distribution instruction group to obtain a power distribution priority sequence; performing power distribution on the output units of the battery pack according to the power distribution priority sequence to obtain unit power scheduling information; performing dynamic power adjustment on the output units based on the unit power scheduling information to obtain a dynamic power output state; performing power feedback calibration on the output units according to the dynamic power output state to obtain calibrated power output data; performing power integration on the output units based on the calibrated power output data to obtain the output power results.

[0012] The application also provides a discharge strategy optimization system for a battery pack, which is applied to the discharge strategy optimization method of any one of the above-mentioned embodiments and includes: a collection module, which is used to collect internal state data of the battery pack and real-time running data of the load device, perform multi-source data fusion in combination with environmental state information, and obtain fusion perception parameters; an analysis module, which is used to perform mode recognition on the load device and the battery pack based on the fusion perception parameters to generate a current discharge mode; An association module is configured to query a preset strategy mapping table according to the current discharge mode, and to perform discharge regulation and control in combination with the fusion perception parameter to obtain a discharge regulation and control parameter.

[0013] The technical scheme provided in the application can have the following beneficial effects. The application significantly improves the comprehensiveness of the perception of the overall working state of the system by fusing multiple-source data such as the internal state of the battery, the real-time operation of the load, and the environmental state, and provides a more reliable data basis for the formulation of the discharge strategy. Based on the fusion perception parameter, the collaborative mode recognition of the load device and the battery pack is performed to generate the current discharge mode, so that the strategy formulation can adapt to different application scenarios and working condition changes, and the adaptability and pertinence of the discharge management are enhanced. According to the identified discharge mode, the preset strategy mapping table is queried, and the discharge regulation and control is performed in combination with the real-time fusion perception parameter, so that the precise dynamic management of the battery output power is realized, and the efficiency and stability of the discharge process are effectively improved. Through continuous monitoring of the battery pack discharge information and closed-loop feedback, adaptive adjustment of the output power is formed, which is beneficial to maintaining the battery in an optimal state, so as to meet the load demand while delaying the performance degradation of the battery and prolonging the service life of the battery.

[0014] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the application. BRIEF DESCRIPTION OF DRAWINGS

[0015] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which like reference characters refer to like parts throughout the different views of the drawings and in which:

[0016] Figure 1 A flow chart of a battery pack discharge strategy optimization method provided in the application; Figure 2 A structure diagram of a battery pack discharge strategy optimization system provided in the application DETAILED DESCRIPTION The preferred embodiments of the present application will be described in detail with reference to the drawings. Although the preferred embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0017] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting. As used in this application and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and / or," as used herein, refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0018] It should be understood that although the terms "first," "second," "third," etc. can be used herein to describe various information, these terms are not intended to denote a particular order or hierarchy. These terms are merely used to distinguish one type of information from another. For example, a first information can also be referred to as a second information, and similarly, a second information can also be referred to as a first information, without departing from the scope of the present application. As such, features defined with "first," "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "a plurality" is two or more, unless otherwise specifically defined.

[0019] Referring to Figure 1 The present application provides a discharge strategy optimization method for a battery pack, comprising: Step S1: Collecting internal state data of the battery pack and real-time running data of the load device, combining environmental state information for multi-source data fusion to obtain fusion perception parameters; Step S2: Mode recognition of the load device and the battery pack based on the fusion perception parameters to generate a current discharge mode; Step S3: Querying a preset strategy mapping table according to the current discharge mode, combining the fusion perception parameters for discharge regulation to obtain discharge regulation parameters.

[0020] Based on the above steps, the detailed step process is shown as follows: Step S1: The internal state data set representing electrochemical characteristics is formed by acquiring the single cell voltage, total voltage, charge and discharge current, and temperature readings of the battery pack through the built-in sensing unit of the battery management system. The power demand, running frequency, and mechanical vibration signal of the load device are monitored synchronously to extract real-time running data reflecting the working intensity of the device. The environmental state information is collected by temperature, humidity, and air pressure sensors arranged at key positions of the device to represent the external working conditions of the battery pack.

[0021] The multi-source data fusion process adopts time sequence alignment and feature weighting method to perform spatial registration and dimensionless normalization of the three types of heterogeneous data under the same time stamp, eliminating the data asynchronization problem caused by sensor acquisition error and communication delay. The fused perception parameters constitute a comprehensive state vector including electrical, thermal, mechanical, and environmental dimensions, providing a high confidence input source for subsequent mode recognition.

[0022] Step S2: The battery state degradation calculation and the load working condition analysis are performed in parallel with the fusion perception parameters as input. The battery state degradation calculation calculates the current health index and capacity attenuation trend of the battery by extracting the voltage, current and temperature sequences in the fusion parameters, and outputs the battery state degradation data. The load working condition analysis identifies the running strength and dynamic characteristics of the load device by analyzing the time-frequency characteristics of the power demand, running frequency and vibration signal, and generates load working condition data. The battery state degradation data and the load working condition data are matched by the correlation analysis module to extract the coupling relationship features between the battery power supply capacity and the load demand.

[0023] The preset discharge mode set contains strategy templates in various typical working scenarios, and the optimal current discharge mode is determined by similarity matching of the correlation feature information and the mode template. The mode reflects the available capacity attenuation state of the battery and the instantaneous power demand of the load at the same time, and provides a classification basis for strategy mapping.

[0024] Step S3: The current discharge mode is matched with the mode label in the preset strategy mapping table through the mode matching engine, and the basic discharge strategy framework corresponding to the mode is obtained by indexing. The basic discharge strategy framework includes parameters such as reference discharge current curve, voltage output range and power adjustment threshold. The real-time battery internal resistance, temperature distribution and load power demand dynamic change in the fusion perception parameters are introduced into the strategy adjustment algorithm to correct the parameters in the basic strategy framework online.

[0025] The correction process adopts a multi-objective optimization method, which meets the instantaneous power demand of the load while considering the thermal balance state of the battery, and eliminates the system instability factors caused by voltage drop and current jump through dynamic compensation calculation. The final generated discharge control parameters are a set of standardized instruction sequences, including key control variables such as target output voltage, maximum allowed discharge current and power adjustment rate, which provide accurate control basis for the power execution unit.

[0026] The discharge control parameters are received by the digital power management chip, which converts them into pulse width modulation signals and digital analog converter output values to directly control the conduction duty cycle and output voltage reference value of the power MOSFET switch tube. The output power of the battery pack is closed-loop regulated according to the target voltage and current limit values in the control parameters, and a proportional-integral-derivative controller is used to maintain output stability. High-precision sampling circuit real-time collects battery pack terminal voltage, output current and temperature data to form a discharge information feedback flow.

[0027] The discharge information feedback stream is compared and analyzed with the regulation parameters to generate power control information containing power output deviation, adjustment suggestions and abnormal warning signs. The power control information is uploaded to the upper monitoring system through the communication interface, and is used for updating the adaptive learning algorithm of the local controller to realize continuous optimization of the discharge strategy.

[0028] The application provides a discharge strategy optimization method for a battery pack. The method comprehensively perceives the overall working state of the system by fusing multi-source data such as the internal state of the battery, the real-time operation of the load and the environmental state, significantly improving the comprehensiveness of the perception of the overall working state of the system and providing a more reliable data basis for the formulation of the discharge strategy. The collaborative mode of the load device and the battery pack is identified based on the fused perception parameters to generate the current discharge mode, so that the strategy formulation can adapt to different application scenarios and working condition changes, and the adaptability and pertinence of the discharge management are enhanced. The preset strategy mapping table is queried according to the identified discharge mode, and the discharge regulation is performed in combination with the real-time fused perception parameters to realize accurate dynamic management of the battery output power, effectively improving the efficiency and stability of the discharge process. The output power is adaptively adjusted through continuous monitoring of the battery pack discharge information and closed-loop feedback, which is conducive to maintaining the battery in an optimal state, thereby meeting the load demand while delaying the performance degradation of the battery and prolonging the service life of the battery.

[0029] In one embodiment, the internal state data of the battery pack and the real-time operation data of the load device are collected, and multi-source data fusion is performed in combination with environmental state information to obtain fused perception parameters, including: The end voltage of each single battery cell in the battery pack is synchronously sampled by using a high-precision analog-to-digital converter, and the sampling accuracy reaches the millivolt level. The charging and discharging current value in the battery loop is measured by using a Hall effect sensor. The total voltage of the battery is obtained by directly measuring the potential difference between the positive and negative electrodes of the battery string. All electrical parameter collection is transmitted by using shielded twisted pair lines to suppress electromagnetic interference, and preliminary digital filtering is performed at the sensor node.

[0030] In the battery state integration stage, the collected raw data is time-stamped and aligned and unitized, and a structured data set containing a voltage matrix, a current sequence and a time sequence is established. After the data set is verified for effectiveness and abnormal values are removed, internal state data with time sequence integrity is generated, which contains characteristic indicators such as single cell voltage dispersion, total voltage fluctuation range, current direction and amplitude.

[0031] The power demand data is obtained by monitoring the power instruction signal sent by the load controller, and the dynamic change trajectory of the power set value is analyzed by using a digital signal processor. The collection of the running frequency is achieved by measuring the switching frequency of the power electronic converter or the PWM carrier frequency of the motor driver, and the instantaneous value and fluctuation characteristics of the frequency signal are captured by using a frequency counter.

[0032] The vibration readings are acquired by MEMS acceleration sensors mounted on the key mechanical structure of the load device, collecting time-domain waveform data of three-axis vibration acceleration. The state calculation process extracts features from the above raw readings: the power demand data is filtered by moving average to obtain the power trend curve; the running frequency data is analyzed by transformation to obtain the fundamental and harmonic components; the vibration readings are analyzed by envelope demodulation to extract the characteristic frequency amplitude representing the mechanical load characteristics. The generated real-time operation data contains multi-dimensional information such as standardized power demand parameters, running frequency spectrum characteristics, and vibration feature vectors.

[0033] A multi-type environmental sensor group distributed on the battery pack shell and key parts of the load device is used to synchronously collect temperature, humidity, and atmospheric pressure parameters. Temperature measurement uses a PT1000 high-precision platinum resistance temperature sensor with a measurement range of -40°C to 125°C. At least six temperature measurement points are arranged in the gaps between battery modules and heat dissipation structures to form a temperature monitoring network.

[0034] Humidity monitoring is achieved through a capacitive polymer sensor with a measurement accuracy of ±2% RH. It is installed at the sealed interface of the battery pack and the ventilation port of the device. Atmospheric pressure data is collected by a MEMS barometric pressure sensor to compensate for the influence of altitude changes on battery performance.

[0035] The environmental recognition stage performs spatial interpolation calculation and time series smoothing processing on the original sensor data to generate temperature field distribution cloud maps, humidity gradient distribution maps, and pressure change curves. The final environmental state data includes temperature extreme point coordinates, humidity coupling coefficients, and pressure change rates, which are output in the form of a structured environmental state matrix.

[0036] A multi-source data fusion architecture is used to establish a state space model containing electrical, mechanical, and environmental characteristics. The voltage and current sequences in the internal state data, the power spectrum characteristics in the real-time operation data, and the temperature and humidity distribution parameters in the environmental state matrix are time-synchronized and spatially registered. The weight coefficients of each data source are determined through covariance analysis.

[0037] The fusion algorithm first performs frequency domain correlation analysis on electrical parameters and mechanical vibration data to extract the coupling relationship between battery impedance characteristics and load mechanical vibration. Then, the environmental temperature field data are introduced to compensate for the electrical-thermal coupling effect, eliminating the influence of temperature gradient on electrical parameter measurement. The battery perception stage outputs a unified fusion perception parameter vector, which contains normalized voltage-power transfer functions, temperature-current coupling coefficients, and vibration-impedance correlation factors, forming a perception data set representing the comprehensive state of the battery system.

[0038] The application synchronously collects battery electrical parameters, load operation characteristics and environmental state information through multi-source sensors, generates comprehensive perception parameters by using a weighted fusion algorithm, and significantly improves the comprehensiveness and accuracy of battery system state monitoring. Based on multi-dimensional perception data, the battery and the load are cooperatively identified, the adaptive matching of the discharge strategy and the real-time working condition is realized, and the response capability of the system in different application scenarios is enhanced. The discharge control parameters are generated by combining the preset strategy mapping and real-time parameter compensation, the accurate dynamic management of the battery output power is realized, and the contradiction between the load demand and the battery life is effectively balanced.

[0039] In one embodiment, based on the fusion perception parameters, the load device and the battery pack are identified, and the current discharge mode is generated, including: The battery voltage, current and temperature time series data are extracted from the fusion perception parameters, the current actual capacity is calculated by using the ampere-hour integral method and the open circuit voltage joint estimation method, and the current internal resistance value of the battery is obtained by using the direct current internal resistance test method. The capacity retention rate and the internal resistance change rate are introduced into the battery health degree calculation to form a double-index evaluation system. The capacity retention rate is calculated by the percentage of the current actual capacity and the rated capacity, and the internal resistance change rate is calculated by the ratio of the current internal resistance value and the initial internal resistance value.

[0040] The battery degradation calculation establishes a capacity attenuation model and an internal resistance growth model based on time series, uses linear regression analysis method to fit the change trend curve of capacity and internal resistance, and extracts the characteristic parameters of capacity attenuation slope and internal resistance growth acceleration. The finally generated battery state degradation data includes health index value, attenuation trend parameter and residual life prediction value, forming a quantitative data set representing the degradation degree of battery performance.

[0041] The time domain and frequency domain characteristics of power demand, running frequency and vibration signal are analyzed from the fusion perception parameters. The power demand analysis uses the sliding time window statistical method to calculate the average power, peak power and power change rate index. The running frequency identification extracts the fundamental frequency, harmonic component and frequency stability coefficient through frequency spectrum analysis. The envelope spectrum analysis method is used to obtain the characteristic frequency amplitude and vibration energy distribution of the vibration signal.

[0042] The power-frequency-vibration three-dimensional correlation relationship is established in the load analysis stage, and the typical working modes of the load are identified through cluster analysis, including steady-state operation, dynamic switching and overload state and other working condition characteristics. The finally output load working condition data includes power characteristic parameters, frequency spectrum feature vector and vibration modal matrix, forming a standardized data set that completely describes the running state of the load device.

[0043] A matching degree evaluation model between battery power supply capability and load demand is established, and a dynamic time warping algorithm is used to align the time series of battery state degradation data and load working condition data. The battery power supply capability evaluation is based on the health index and the attenuation trend parameter, and the maximum sustainable discharge power, the peak power support time length and the voltage drop risk coefficient are calculated.

[0044] The load demand feature extraction obtains the instantaneous power demand, dynamic response requirement and operation stability threshold from the power characteristic parameters and frequency spectrum feature vector. The correlation analysis calculates the matching degree of the power supply capability and the demand feature through a multi-dimensional feature matching algorithm, and generates a correlation matrix containing power matching degree, time sequence synchronization and risk warning index. The final output of the correlation feature information constitutes a multi-dimensional feature vector containing supply-demand balance coefficient, dynamic response capability evaluation and system stability index.

[0045] The correlation feature information is compared with the feature templates in the preset discharge mode set. The preset discharge mode set includes constant power output mode, dynamic adjustment mode, energy saving mode and protection mode and other strategy templates in typical working conditions, and each template defines complete feature parameter range and boundary conditions.

[0046] The mode recognition determines the optimal matching mode by calculating the Euclidean distance between the correlation feature vector and each mode template using the nearest neighbor classification algorithm. For the correlation features with fuzzy boundaries, a fuzzy logic decision mechanism is introduced for mode weight distribution and composite mode generation. The output current discharge mode includes mode type identification, mode confidence score and mode parameter adjustment suggestion, forming a classification decision result for guiding discharge strategy formulation.

[0047] The present application calculates the battery health and load working condition by fusing multi-source perception data, establishes an accurate correlation model between battery power supply capability and load demand, and realizes deep cognition of the system running state. Based on the feature matching algorithm, the current discharge mode is identified, so that the discharge strategy can adaptively match the battery degradation state and load dynamic demand, and the accuracy and adaptability of system regulation are improved. Through the combination of the preset mode set and the real-time correlation feature, an optimization strategy considering battery life and equipment performance is generated, which effectively balances the energy supply relationship under different working conditions.

[0048] In one embodiment, the battery health of the battery pack is calculated based on the fused perception parameters, the battery degradation is calculated, and the battery state degradation data is obtained, including: Through the multi-source data collaborative processing mode, the voltage and current measurement values in the internal state data are time-synchronized and spatially corresponding with the temperature distribution and load characteristics in the fused perception parameters. The battery performance parameter analysis uses an electrical-thermal-load coupling relationship analysis method to synchronously process the interaction relationship between electrical parameters and thermodynamic parameters.

[0049] The voltage sequence is calculated by time window statistics to obtain the average working voltage, voltage fluctuation characteristics and voltage drop change trend; the current signal is processed by frequency spectrum conversion to extract the direct current component and alternating current ripple component; and the temperature distribution data is processed by temperature field reconstruction to generate the temperature gradient distribution characteristics.

[0050] The analysis process introduces the load power demand as a constraint condition, calculates the output characteristics of the battery under different load states, and finally forms a battery performance parameter set containing actual capacity, internal resistance characteristics, thermal stability performance and power output capability.

[0051] A multi-index comprehensive evaluation method is used, and the preset threshold includes capacity attenuation limit, internal resistance growth limit and temperature change limit, etc. The health degree calculation first performs standardization conversion on the battery performance parameters, converts the actual capacity into a capacity retention ratio, converts the internal resistance value into an internal resistance growth ratio, and converts the temperature gradient into a thermal stability coefficient.

[0052] The weights of each index are adjusted according to the battery type and application environment. Lithium ion batteries focus on capacity and internal resistance indicators, and lead-acid batteries focus on voltage stability indicators. The calculation process uses a multi-factor decision method to calculate the compliance of each index with the corresponding threshold, and obtains the overall health degree value through comprehensive scoring. The final output battery health value is a standardized percentage value, which also contains the health status evaluation results of each sub-index.

[0053] By accessing the historical data storage unit of the battery management system, the health value records on the continuous time sequence are extracted to form the health degree change trajectory. The degradation trend analysis uses time series analysis method to calculate the average change rate, decay acceleration and periodic fluctuation characteristics of the health value. The analysis process establishes the corresponding relationship curve between health degree and running time, identifies the stage characteristics of health degree change, including linear decay stage, accelerated degradation stage and plateau characteristics.

[0054] For abnormal fluctuation data points, a sliding window filtering method is used for data smoothing to eliminate measurement deviations caused by accidental factors. The final generated battery degradation information includes health degree decline rate, expected life indicator and degradation stage identifier, forming a complete feature set describing the battery performance attenuation process.

[0055] A multi-dimensional comprehensive evaluation method is used to cross-verify the trend characteristics in the battery degradation information and the real-time measured values in the battery performance parameters. The evaluation process establishes the mapping relationship between performance parameters and degradation characteristics, and by comparing the matching degree of the current performance parameters and the historical degradation law, the specific degradation state of the battery is determined.

[0056] For capacity degradation evaluation, the remaining available capacity is calculated by combining the actual capacity value with the health degradation rate; for internal resistance change evaluation, the degree of degradation of the conductive performance is evaluated by combining the current internal resistance measurement value with the internal resistance growth trend; for thermal stability evaluation, the thermal management capability degradation is analyzed by referring to the temperature characteristic parameter and health change relationship. The output battery state degradation data includes health evaluation results, degradation stage determination conclusions, and performance risk warning information, forming a quantitative state description that can be used for discharge strategy development.

[0057] The embodiment obtains battery performance parameters through multi-source data fusion analysis, combines with the preset health threshold to calculate the health, and realizes accurate quantitative evaluation of the battery state. The battery degradation trend is analyzed through the historical health value sequence, and a complete performance degradation trajectory description is established to provide a reliable basis for life prediction. Based on the comprehensive evaluation of degradation information and real-time performance parameters, the current degradation state and risk level of the battery are accurately judged, and comprehensive state degradation data is formed. The evaluation method takes into account the historical trend and real-time state, so that the discharge strategy can adapt to the characteristic changes of the battery in different degradation stages, and the adaptability and accuracy of battery management are improved.

[0058] In one embodiment, the preset strategy mapping table is queried according to the current discharge mode, the discharge control is regulated in combination with the fusion perception parameters, and discharge control parameters are obtained, including: The feature vector of the current discharge mode is decoded and processed to extract key control elements in the mode parameter set. The power allocation coefficient analysis uses eigenvalue decomposition method to separate the power allocation weight vector from the discharge mode matrix, which contains the allocation proportion and priority parameters of each power output channel.

[0059] The temperature control response level analysis obtains the corresponding temperature response level identifier from the preset temperature control strategy library through mode feature matching, which defines parameters such as temperature control sensitivity, heat dissipation starting threshold, and temperature rise rate limit.

[0060] The mapping relationship between mode parameters and execution parameters is established during the analysis process to ensure that the power allocation coefficient matches the load demand characteristics and the temperature control response level adapts to the battery thermal characteristics. The final output power allocation coefficient includes the reference power value, dynamic adjustment range, and power change gradient requirement, and the temperature control response level includes the temperature control mode, heat dissipation intensity level, and overheat protection threshold.

[0061] The power allocation coefficient is matched with the index label in the preset strategy mapping table to obtain the corresponding basic discharge strategy template. The basic discharge strategy template includes core parameters such as reference output voltage, maximum allowed current, and power adjustment step size. Dynamic compensation correction introduces real-time temperature distribution, internal resistance change, and load fluctuation data in the fusion perception parameters, and uses a multi-parameter collaborative adjustment algorithm to optimize the basic strategy parameters online.

[0062] The temperature compensation module adjusts the output current limit value according to the temperature gradient distribution, the internal resistance compensation module corrects the output voltage reference according to the impedance characteristics, and the load compensation module dynamically adjusts the power response speed according to the power demand change. The correction process adopts a gradual adjustment strategy to ensure the stability of parameter changes and system stability. The finally generated real-time control parameters include the compensated target voltage value, current limit range, power output curve and adjustment rate parameters.

[0063] The coordination mechanism of heat and electricity is used to handle the coordination between temperature management and power output. The temperature control response level provides a framework for temperature control strategy, including heat dissipation starting conditions, cooling rate requirements and temperature monitoring frequency, etc. The energy consumption balancing optimization adopts a multi-factor coordination method to ensure the power output characteristics of real-time control parameters while considering the temperature control energy consumption in the overall energy efficiency consideration range. The optimization process establishes a correlation model between temperature control and power output, dynamically adjusts the cooling intensity and power distribution ratio according to the current temperature distribution of the battery, and ensures that the heat management energy consumption and the total energy consumption of the system maintain a reasonable proportion.

[0064] For high-power output conditions, a phased temperature control scheme is used to gradually increase the cooling intensity; for temperature sensitive areas, a protective control combining local directional cooling and power limitation is implemented. The finally generated cooperative control parameters include the optimized power output curve, temperature control instruction combination and energy efficiency distribution scheme, forming a complete control strategy of electric-thermal cooperation.

[0065] The safety compliance check program is used to verify the cooperative control parameters in multiple dimensions. The safety boundary check refers to the battery technical specifications to verify whether the parameters meet the voltage safety range, current bearing limit and temperature allowable range. The feasibility verification detects the time sequence feasibility of control instructions, the response matching degree of actuators and the stability of state transition from the perspective of system response characteristics.

[0066] The verification process adopts a gradual adjustment mechanism to automatically limit the parameters that exceed the safety boundary, and to re-distribute the time or smooth the amplitude of the instructions that lack execution feasibility. Conflict detection and resolution are performed simultaneously during the verification process to ensure that there is no execution logic contradiction or resource allocation conflict between the control instructions. The finally output discharge control parameters are converted into a standardized format to form a control instruction sequence that can be directly issued to the power execution unit, including the verified target parameter value, safety tolerance range and abnormal handling strategy.

[0067] The embodiment obtains power distribution and temperature control parameters by analyzing the discharge mode, performs dynamic compensation based on preset strategies and real-time sensing data, and generates real-time regulation parameters that are highly matched with the current working conditions. Through a thermoelectric collaborative optimization mechanism, power output and temperature control are coordinated to achieve collaborative control parameter configuration with optimal energy efficiency. Multi-dimensional safety verification is adopted to ensure that the control parameters meet safety specifications and execution feasibility, and finally the discharge regulation parameters that have passed complete verification are output.

[0068] In one embodiment, the real-time regulation parameters are generated by querying the preset strategy mapping table according to the power distribution coefficient and performing dynamic compensation correction in combination with the fused sensing parameters, including: The power distribution coefficient is correspondingly looked up with the index identifier in the preset strategy mapping table through a strategy matching mechanism. The power distribution coefficient includes total power demand value, output channel power weight, and power adjustment priority, etc. The preset strategy mapping table uses a multi-dimensional data structure for storage, wherein each index point is associated with a set of verified basic discharge parameter combinations.

[0069] In the query process, the nearest neighbor matching algorithm is used to find the index point closest to the current power distribution coefficient to obtain the corresponding reference discharge parameter set. The basic discharge current parameters include rated output current value, current allowable fluctuation range, and current change rate limit; the basic output voltage parameters include nominal output voltage, voltage regulation accuracy requirement, and voltage stability index. These parameters constitute the basic framework of discharge control and provide initial reference values for subsequent dynamic compensation.

[0070] Temperature-related data is separated from the fused sensing parameters, including real-time temperature readings of multiple temperature measurement points, historical temperature records, and spatial distribution information. The temperature distribution feature extraction uses a spatial interpolation calculation method to reconstruct the overall temperature field of the battery pack according to the data of discrete temperature measurement points, generating a temperature contour distribution map and hot spot area coordinates.

[0071] The change trend analysis calculates the instantaneous temperature change rate and acceleration index of each region by differentiating the temperature time series data. The thermal distribution characteristic parameters include the maximum temperature value, temperature range, gradient distribution coefficient, and thermal uniformity index; the dynamic trend parameters include temperature rise rate, thermal diffusion speed, and temperature fluctuation frequency characteristics. These parameters collectively describe the thermal state characteristics of the battery pack and their change laws, providing data support for thermal characteristic compensation.

[0072] Through temperature-current compensation relationship analysis, the maximum temperature value and temperature gradient distribution coefficient in the thermal distribution characteristic parameters are associated with the basic discharge current parameters. The compensation calculation uses a multi-section compensation method to determine the basic compensation amount based on the difference between the temperature extreme value and the safety threshold, and adjusts the compensation amount in space in combination with the temperature distribution uniformity index.

[0073] The current limiting strategy is implemented for high temperature area, and the current output is gradedly reduced according to the temperature overrun degree; the original output characteristic is maintained for the normal temperature area, and a temperature margin buffer space is reserved. The concept of thermal time constant is introduced in the compensation process, and the response speed of current compensation is adjusted according to the temperature change inertia to avoid system oscillation caused by excessive regulation. The final temperature compensation current contains the adjusted current output value, the current change rate limit and the temperature feedback adjustment parameter, which controls the battery temperature rise while maintaining the power supply stability.

[0074] Through the multi-parameter coordination mechanism, the temperature rise rate, thermal diffusion characteristics and electrical output parameters in the dynamic trend parameters are optimized. The impedance matching adjustment adopts a forward-looking control strategy, which predicts the direction of change of the battery internal resistance according to the temperature change trend, and adjusts the output voltage compensation scheme accordingly. For fast temperature rise conditions, a preventive current regulation combined with voltage compensation is used to offset the pressure drop caused by the increase of internal resistance in advance; for steady-state thermal conditions, the output voltage waveform quality is optimized to improve energy conversion efficiency.

[0075] The adjustment process takes into account the chemical properties and thermodynamic behavior of the battery, and establishes a dynamic balance relationship among current, voltage and temperature. The generated real-time control parameters include accurate discharge current control curve, output voltage compensation value, power regulation gradient and thermal protection parameters, forming a complete set of control instructions that can be immediately executed.

[0076] The embodiment obtains basic discharge parameters by querying the preset strategy mapping table through the power distribution coefficient, and combines the temperature distribution characteristics in the fusion sensing parameters to perform dynamic compensation and correction, thereby realizing accurate temperature compensation of the discharge current. Through comprehensive analysis of the thermal distribution characteristics and dynamic trend parameters, a multi-parameter coordination mechanism of current, voltage and temperature is established, and real-time control parameters highly matched with the battery thermal state are generated. The compensation method can implement differentiated current control according to temperature distribution unevenness, effectively improving the thermal balance of the battery pack. The impedance matching adjustment optimizes the output voltage characteristics, overcomes the influence of temperature change on the battery internal resistance, and maintains the stability of the discharge process. The formation process of real-time control parameters takes into account the thermal safety and power quality requirements, preventing the battery from overheating while ensuring the power supply reliability of the load equipment.

[0077] In one embodiment, the output power of the battery pack is adjusted according to the discharge regulation parameters, and the discharge information of the battery pack is continuously monitored, and the output power control information includes: The control instruction sequence contained in the discharge regulation parameter is processed by the instruction analysis engine to convert it into a standardized instruction format that can be recognized and executed by the power execution unit. The instruction analysis adopts a hierarchical decoding method, first identifying the instruction type identifier to distinguish between current control instructions, voltage regulation instructions, and power management instructions, etc.; then analyzing the instruction parameter content, including target values, change rates, effective time points, and duration, etc.

[0078] During the analysis process, the instruction logic is verified to ensure that there is no execution conflict or timing contradiction between instructions. The final generated power distribution instruction set contains a set of control commands with strict timing relationships, each command explicitly specifying the output channel identifier, target parameter value, adjustment time sequence, and exception handling strategy, forming a complete power distribution scheme.

[0079] The instruction set is converted into specific hardware control signals by the power output adjustment module to drive the power switch devices to perform the corresponding power adjustment actions. The output unit contains multiple groups of parallel power MOSFET switch tubes and corresponding drive circuits, each switch tube responsible for the conduction control of a specific power output channel. The power output adjustment adopts a closed-loop control method, which compares the difference between the instruction target value and the actual output value in real time, and generates PWM modulation signals to accurately control the conduction duty cycle of the switch tube.

[0080] During the adjustment process, the load balancing state of each output channel is monitored synchronously, and the power distribution ratio of each channel is dynamically adjusted to ensure that all power devices work within a safe margin. The final output power result contains actual output voltage value, output current value, total power value, and channel power distribution data, which form the actual effect record of power regulation.

[0081] Real-time collection of various operating parameters of the battery pack during discharge is achieved through a distributed data acquisition system. The monitoring data includes electrical, thermal, and chemical characteristics. Electrical characteristics are monitored by high-precision ADC sampling circuits to obtain the terminal voltage, total output voltage, load current, and ripple coefficient of each cell; thermal characteristics are monitored by a network of temperature sensors to collect battery surface temperature distribution, radiator temperature, and ambient temperature; chemical characteristics are monitored by impedance spectrum analyzers to obtain changes in battery internal resistance, polarization voltage, and capacitive reactance characteristics.

[0082] All monitoring data is synchronized using a unified timestamp and is processed through digital filtering to eliminate measurement noise. The final battery monitoring data includes voltage stability indicators, temperature gradient distribution maps, internal resistance change curves, and capacity attenuation characteristics, etc.

[0083] The battery monitoring data is associated with the real-time power demand of the load device for evaluation by the state analysis module. The analysis process establishes a dynamic balance model between the battery supply capacity and the load demand, calculates the stability coefficient, efficiency index and risk level of the current power output. For the working condition with large voltage fluctuation, voltage compensation suggestion instruction is generated; for the working condition with rapid temperature rise, power limitation adjustment scheme is proposed; for the load mutation condition, dynamic response optimization strategy is developed. The power control information includes real-time adjustment suggestion, warning level identification, optimization strategy parameter and abnormal treatment scheme, forming complete power management guidance information.

[0084] The embodiment generates a power distribution instruction group by analyzing the discharge regulation parameters, and realizes accurate regulation of the output power of the battery pack. Based on the multi-dimensional monitoring of the battery discharge information of the output power result, complete monitoring data including electrical characteristics, thermal characteristics and chemical characteristics are obtained. Through the state power analysis of the battery monitoring data and the load device, the dynamic balance relationship between the battery supply capacity and the load demand is established, and the power control information with foresight is generated. The monitoring method can real-time identify the working conditions such as voltage fluctuation, temperature abnormality and load mutation, and timely develop the corresponding voltage compensation, power limitation and dynamic response strategy. The power control information is used for real-time adjustment of the discharge process, and also provides data support for system adaptive learning, effectively improving the intelligent level and operation reliability of battery management.

[0085] In one embodiment, the output unit of the battery pack is regulated according to the power distribution instruction group, and the output power result is obtained, including: The process analyzes the execution urgency and importance level of each instruction in the power distribution instruction group through the instruction analysis module. The priority sorting adopts a multi-factor weighted evaluation method, which comprehensively considers the timeliness requirement, power adjustment amplitude, load device criticality and system safety influence degree of the instruction.

[0086] The timeliness of the instruction determines the urgency according to the effective time point and duration specified in the instruction; the power adjustment amplitude is evaluated by calculating the deviation degree of the target value and the current value; the criticality of the load device is assigned by referring to the pre-defined device priority list; the system safety influence degree is evaluated according to the safety protection parameters involved in the instruction.

[0087] The sorting process generates an instruction execution queue with strict sequence relationship, ensures that high-priority instructions obtain priority processing permission, and at the same time maintains the logical coherence and time sequence rationality between instructions. The finally obtained power distribution priority sequence contains instruction execution sequence number, priority weight coefficient and execution time window constraint parameters.

[0088] The priority sequence is converted into a specific output unit control scheme. The power distribution adopts a split-channel independent control method, and according to the current load capacity, heat dissipation state and connection equipment characteristics of each output unit, the corresponding power output task is allocated.

[0089] In the scheduling process, a matching model of power demand and supply capacity is established, and the important load channel corresponding to the high-priority instruction is given priority to obtain power resource allocation, and the auxiliary load channel corresponding to the low-priority instruction is adaptively adjusted according to the remaining power capacity.

[0090] For multiple instructions executed in parallel, a time slice rotation method is used to allocate processing resources to ensure that each instruction can be executed within a specified time window. The generated unit power scheduling information includes target power values, power change time series, channel enable state flags and power margin indication parameters of each output channel, forming an executable power distribution scheme.

[0091] The process converts the scheduling information into specific power control actions through a power regulation execution mechanism. Dynamic power regulation adopts a closed-loop feedback control mechanism to monitor the actual power output value of each output unit in real time and compare it with the target value in the scheduling information. According to the load change characteristics and system response speed, a gradual adjustment strategy is adopted to smoothly change the output power during the adjustment process to avoid system impact caused by power sudden changes. For important load channels, the principle of priority protection is adopted to ensure the stability of power supply; for adjustable load channels, an adaptive adjustment strategy is implemented to optimize power distribution efficiency.

[0092] The dynamic adjustment process synchronously records the power change trajectory, response time characteristics and adjustment accuracy data of each output unit, forming a complete power output state record. The final dynamic power output state includes actual output power value, power stability index, adjustment response time and load adaptation characteristics, etc. multi-dimensional state information.

[0093] By analyzing the deviation characteristics of the actual value and the target value in the dynamic power output state. Power feedback calibration uses a multi-parameter compensation algorithm to consider the influence of factors such as voltage drift, current measurement error, temperature influence and transmission loss. The calibration calculation first establishes a corresponding relationship model between the output deviation and the influencing factors, and determines the compensation coefficients of each influencing factor through regression analysis; then, according to the real-time monitoring data, the compensation parameters are dynamically adjusted to eliminate the influence of systematic error and random error.

[0094] The calibration process uses an iterative optimization method to gradually improve the accuracy and stability of the output power. For output channels with large deviations, key calibration and special processing are implemented; for output channels with stable performance, a maintenance calibration strategy is adopted. The final generated calibration power output data includes corrected power output value, calibration compensation parameter, accuracy level identifier and reliability evaluation index.

[0095] The calibration data of each output unit is comprehensively processed by a power integration processor. The power integration adopts a data fusion method to integrate the dispersed unit power information into a system-level power output description. The integration process first performs data space-time alignment to ensure that the data of each unit has a unified time reference and dimension standard; then the system total output power is calculated by a weighted average algorithm, and the corresponding weight coefficients are allocated according to the importance and reliability of each unit; data validity verification is performed to eliminate abnormal data points and supplement reasonable estimates.

[0096] The integration result includes comprehensive indicators such as system total power output, unit power contribution, power distribution efficiency, and system stability coefficient. The final output power result constitutes a complete power output performance report, providing accurate data basis for subsequent monitoring and analysis.

[0097] The present embodiment prioritizes the power distribution instruction set, establishes an instruction execution queue with strict sequential relationship, and ensures that critical loads obtain priority power distribution. Based on the priority sequence, the output unit is power scheduled to realize reasonable distribution and efficient use of power resources. Through dynamic power regulation mechanism, the output state is monitored in real time, and the gradual adjustment strategy is adopted to ensure the smoothness of power change. The power feedback calibration function eliminates system error through multi-parameter compensation algorithm, improves the accuracy and stability of output power. Finally, the system-level output result is generated by power integration processing, which fully reflects the power contribution of each unit and the overall performance of the system.

[0098] Referring to Figure 2 The present application also provides a battery pack discharge strategy optimization system, which is applied to the battery pack discharge strategy optimization method of any one of the above, comprising: The acquisition module is used for acquiring internal state data of the battery pack and real-time running data of the load device, and combining environmental state information to perform multi-source data fusion to obtain fusion perception parameters; The analysis module is used for mode recognition of the load device and the battery pack based on the fusion perception parameters to generate a current discharge mode; The association module is used for querying a preset strategy mapping table according to the current discharge mode, combining the fusion perception parameters to perform discharge regulation and control, and obtaining discharge regulation and control parameters.

[0099] The application provides a discharge strategy optimization system of a battery pack. The system is capable of comprehensively sensing the overall working state of the system by fusing multi-source data such as the internal state of the battery, the real-time operation of the load and the environmental state, thereby providing a more reliable data basis for the formulation of the discharge strategy. The system is capable of identifying the collaborative mode of the load device and the battery pack based on the fused sensing parameters, generating the current discharge mode, thereby enabling the strategy formulation to adapt to different application scenarios and working condition changes and enhancing the adaptability and pertinence of the discharge management. The system is capable of querying the preset strategy mapping table according to the identified discharge mode and performing discharge regulation and control in combination with the real-time fused sensing parameters, thereby realizing the accurate dynamic management of the battery output power and effectively improving the efficiency and stability of the discharge process. The system is capable of continuously monitoring the discharge information of the battery pack and feeding back in a closed loop, thereby forming adaptive adjustment of the output power, which is conducive to maintaining the battery in an optimal state, thereby meeting the load demand while delaying the performance degradation of the battery and prolonging the service life of the battery.

[0100] As to the system in the above embodiments, the specific manner in which the various modules perform operations has been described in detail in the embodiments related to the method in which the various modules perform operations, and thus will not be described in detail here.

[0101] The solutions of the application have been described in detail above with reference to the drawings. In the above embodiments, the description of each embodiment is focused on different aspects, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments. It should also be known by those skilled in the art that the actions and modules involved in the specification are not necessarily required by the application. In addition, it can be understood that the steps in the method embodiments of the application can be adjusted, combined and reduced in sequence according to actual needs, and the modules in the system embodiments of the application can be combined, divided and reduced according to actual needs.

[0102] In addition, the method according to the application can also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing part or all of the steps in the above method of the application.

[0103] Alternatively, the application can also be implemented as a non-transitory machine readable storage medium (or computer readable storage medium, or machine readable storage medium) having executable code (or computer program, or computer instruction code) stored thereon, which, when executed by a processor of an electronic device (or electronic device, server, etc.), causes the processor to execute part or all of the steps of the above method according to the application.

[0104] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the present disclosure can be implemented as electronic hardware, computer software, or combinations of both.

[0105] The computer software can comprise one or more computer program elements on one or more non-transitory computer readable media. Such computer program elements can be implemented in a high-level procedural or object-oriented programming language, or in assembly or machine language. The software can be implemented using a variety of

[0106] Embodiments of the present application have been described above, with the understanding that these embodiments are exemplary only, and are not restrictive in nature. Many modifications and variations of the disclosed embodiments are possible in light of the above teachings. The terminology used herein is for the purpose of describing particular embodiments only, and is not intended to limit the scope of the embodiments disclosed herein, which is defined solely by the appended claims. The use of any and all examples, or exemplary language (e.g., "may", "can", "will", "should", "else", "weath- er", "provide", "might", "might be", "could", "would", "might", "might be", "can be", "might be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may be", "may

Claims

1. A method for optimizing the discharge strategy of a battery pack, characterized in that, The method comprises the following steps: Collecting internal state data of the battery pack and real-time operation data of the load device, combining environmental state information for multi-source data fusion to obtain fusion perception parameters; Based on the fusion perception parameters, mode recognition is performed on the load device and the battery pack to generate a current discharge mode; According to the current discharge mode, a preset strategy mapping table is queried, and discharge regulation is performed in combination with the fusion perception parameters to obtain discharge regulation parameters.

2. The method of claim 1, wherein, The collection of internal state data of the battery pack and real-time operation data of the load device, combined with environmental state information for multi-source data fusion, obtains fusion perception parameters, including: The internal state data is obtained by identifying the single cell voltage, total voltage and charge and discharge current of the battery pack through the built-in sensor of the load device, and performing battery state integration; The real-time operation data is obtained by reading the power demand, operating frequency and vibration reading of the load device, and performing state calculation; The environmental state information is obtained by collecting real-time environmental information of the load device through the built-in sensor and performing environmental identification; The internal state data, real-time operation data and environmental state information are fused to obtain the fusion perception parameters.

3. The method of claim 1, wherein, The mode recognition based on the fusion perception parameters is performed on the load device and the battery pack to generate a current discharge mode, including: The battery health degree of the battery pack is calculated based on the fusion perception parameters to perform battery degradation calculation and obtain battery state degradation data; The working condition data of the load device is identified according to the fusion perception parameters to perform load analysis and obtain load working condition data; The battery state degradation data and the load working condition data are associated for battery energy supply to obtain associated feature information; The current mode recognition is performed on the associated feature information based on a preset discharge mode set to obtain the current discharge mode.

4. The method of claim 3, wherein, The battery health degree of the battery pack is calculated based on the fusion perception parameters to perform battery degradation calculation and obtain battery state degradation data, including: The battery performance parameters of the battery pack are analyzed in combination with the internal state data and the fusion perception parameters; The battery health value is obtained by calculating the battery health degree of the battery performance parameters according to a preset battery health threshold; The battery degradation information is obtained by analyzing the battery health value based on the historical health value of the battery pack; The battery state degradation data is obtained by evaluating the degradation state according to the battery degradation information and the battery performance parameters.

5. The method of claim 1, wherein, The discharge regulation parameters are obtained by querying a preset strategy mapping table according to the current discharge mode, and combining the fusion perception parameters for discharge regulation, including: The power distribution coefficient and temperature control response level are obtained by analyzing the current discharge mode; The real-time regulation parameters are generated by querying the preset strategy mapping table according to the power distribution coefficient and combining the fusion perception parameters for dynamic compensation correction; The collaborative control parameters are generated by energy consumption balancing optimization according to the temperature control response level and the real-time regulation parameters; The discharge regulation parameters are output by performing safety boundary checking and execution feasibility verification on the collaborative control parameters.

6. The method of claim 5, wherein, The preset strategy mapping table is queried according to the power distribution coefficient, and dynamic compensation correction is combined with the fusion perception parameter to generate a real-time regulation parameter, including: The preset strategy mapping table is indexed and queried according to the power distribution coefficient, to obtain a basic discharge current parameter and a basic output voltage parameter; Temperature distribution characteristics in the fusion perception parameter are extracted, and change trend analysis is performed to obtain a thermal distribution characteristic parameter and a dynamic trend parameter; The thermal distribution characteristic parameter is used for thermal characteristic compensation of the basic discharge current parameter, to obtain a temperature compensation current; The temperature compensation current and the basic output voltage parameter are adjusted for impedance matching in combination with the dynamic trend parameter, to generate the real-time regulation parameter.

7. The method of claim 1, wherein, Further comprising, adjusting the output power of the battery pack according to the discharge regulation parameter, and continuously monitoring the discharge information of the battery pack to output power control information: The discharge regulation parameter is analyzed for instructions to obtain a power distribution instruction group; The output unit of the battery pack is adjusted for power output according to the power distribution instruction group, to obtain an output power result; The discharge information of the battery pack is monitored based on the output power result, to obtain battery monitoring data; The state power of the load device is analyzed based on the battery monitoring data, to obtain power control information.

8. The method of claim 7, wherein, The output unit of the battery pack is adjusted for power output according to the power distribution instruction group, to obtain an output power result, including: The power distribution instruction group is sorted for instruction priority to obtain a power distribution priority sequence; The output unit of the battery pack is distributed for power according to the power distribution priority sequence, to obtain unit power scheduling information; The output unit is dynamically adjusted for power based on the unit power scheduling information, to obtain a dynamic power output state; The output unit is calibrated for power feedback according to the dynamic power output state, to obtain calibrated power output data; The output unit is integrated for power based on the calibrated power output data, to obtain the output power result.

9. A battery pack discharge strategy optimization system, comprising: Applied to the discharge strategy optimization method of the battery pack in any one of the above claims 1-8, including: A collection module, the collection module is used for collecting internal state data of the battery pack and real-time running data of the load device, combining environmental state information for multi-source data fusion to obtain a fusion perception parameter; An analysis module, the analysis module is used for mode recognition of the load device and the battery pack based on the fusion perception parameter to generate a current discharge mode; An association module, the association module is used for querying a preset strategy mapping table according to the current discharge mode, combining the fusion perception parameter for discharge regulation to obtain a discharge regulation parameter.

Images