Intelligent management method and system of new energy battery

Abstract

The invention relates to the technical field of battery management, and discloses an intelligent management method and system for a new energy battery, and the method comprises the steps: carrying out the monitoring of a driving scene and load performance of a new energy vehicle loaded with the new energy battery, and obtaining the driving scene characteristics and load performance characteristics of the new energy battery; the method comprises the following steps: acquiring operation performance data of a functional module in functional association with a new energy battery in a new energy vehicle, predicting future load pressure of the new energy battery in combination with driving scene characteristics and load performance characteristics to obtain load prediction information, performing adaptive analysis on the load prediction information according to a preset battery scheduling strategy, and determining the load pressure of the new energy battery. And a new energy battery management strategy is obtained.

Description

Technical Field

[0001] This invention relates to the technical field of battery management, and in particular to an intelligent management method and system for new energy batteries. Background Technology

[0002] With increasing global attention to renewable energy and environmentally friendly transportation, new energy vehicles are developing rapidly. As a core component of these vehicles, the performance and management of new energy batteries directly affect the vehicle's range, safety, and overall user experience. Traditional battery management systems mainly rely on static battery monitoring and management strategies, which cannot adapt to changing driving scenarios and load demands in real time. This approach often leads to low battery utilization efficiency and may even cause safety hazards. Summary of the Invention

[0003] The purpose of this invention is to provide an intelligent management method and system for new energy batteries, which aims to solve the problem that the static battery monitoring and management strategies in the prior art cannot adapt to the changing driving scenarios and load requirements in real time.

[0004] This invention is implemented as follows: Firstly, this invention provides an intelligent management method for new energy batteries, comprising: The driving scenario and load performance of new energy vehicles equipped with new energy batteries are monitored to obtain the driving scenario characteristics and load performance characteristics of the new energy batteries. Collect operational performance data of functional modules in new energy vehicles that are functionally related to the new energy battery; By combining the operational performance data, the driving scenario characteristics, and the load performance characteristics, the future load pressure of the new energy battery is predicted to obtain load prediction information; Based on a preset battery scheduling strategy, an adaptive analysis is performed on the load forecast information to obtain a management strategy for the new energy battery.

[0005] In a second aspect, the present invention provides an intelligent management system for a new energy battery, used to implement the intelligent management method for a new energy battery as described in any one of the first aspects, comprising: The data monitoring module is used to monitor the driving scenarios and load performance of new energy vehicles equipped with new energy batteries, and to obtain the driving scenario characteristics and load performance characteristics of the new energy batteries. The performance acquisition module is used to collect the operational performance data of functional modules in new energy vehicles that are functionally related to the new energy battery. The load prediction module is used to combine the operating performance data, the driving scenario characteristics, and the load performance characteristics to predict the future load pressure of the new energy battery and obtain load prediction information. The strategy management module is used to perform adaptive analysis on the load forecast information according to the preset battery scheduling strategy to obtain the management strategy of the new energy battery.

[0006] This invention provides an intelligent management method for new energy batteries, which has the following beneficial effects: This invention provides a foundation for battery management by real-time monitoring of driving scenarios and load performance of vehicles equipped with new energy batteries, extracting key characteristic data of the batteries. By collecting operational data from modules related to battery functions, the system can comprehensively understand the battery's performance in actual operation. Combining driving scenario characteristics and load performance characteristics, the system can accurately predict future load pressure and generate effective load prediction information. Based on this information, it uses a preset battery scheduling strategy for adaptive analysis to form a targeted management strategy. This intelligent management method not only improves battery utilization efficiency and extends its service life but also enhances the safety and reliability of new energy vehicles, laying the foundation for promoting sustainable transportation development. Attached Figure Description

[0007] Figure 1 This is a schematic diagram illustrating the steps of an intelligent management method for new energy batteries provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an intelligent management system for a new energy battery provided in an embodiment of the present invention. Detailed Implementation

[0008] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0009] The implementation of the present invention will be described in detail below with reference to specific embodiments.

[0010] Reference Figure 1 , Figure 2 The diagram shows a preferred embodiment of the present invention.

[0011] In a first aspect, the present invention provides an intelligent management method for new energy batteries, comprising: S1: Monitor the driving scenario and load performance of new energy vehicles equipped with new energy batteries to obtain the driving scenario characteristics and load performance characteristics of the new energy batteries. S2: Collect operational performance data of functional modules in new energy vehicles that are functionally related to the new energy battery; S3: Combine the operational performance data, driving scenario characteristics, and load performance characteristics to predict the future load pressure of the new energy battery and obtain load prediction information; S4: Perform adaptive analysis on the load forecast information according to the preset battery scheduling strategy to obtain the management strategy of the new energy battery.

[0012] Specifically, in step S1 of the embodiment provided by this invention, the vehicle-mounted sensing module may include a camera, radar, weather sensors, etc. The camera can identify road signs, traffic lights, vehicles ahead, etc.; the radar can measure the distance and relative speed to surrounding objects; the weather sensor can acquire meteorological information such as temperature, humidity, and light intensity; and the cloud-based digital map can provide information such as road type (highway, urban road, rural road, etc.), traffic flow, and slope. The combination of these information comprehensively depicts the external environment in which the vehicle is located.

[0013] More specifically, by collecting data on vehicle acceleration, deceleration, and steering, machine learning algorithms are used to classify drivers' driving styles, such as aggressive, mild, and economical. For example, frequent rapid acceleration and braking usually belong to an aggressive driving style, while smooth acceleration and deceleration, and maintaining a constant speed, are more inclined towards an economical driving style.

[0014] More specifically, driving scenarios have a significant impact on the use of new energy batteries. Different external environments and driving styles lead to different charging and discharging modes and power requirements for batteries. For example, in congested urban roads with frequent start-stop cycles, the battery needs to provide a large current frequently to meet the vehicle's acceleration needs. At high speeds, the battery needs to provide a continuous and stable power supply. Aggressive driving styles can subject the battery to a large power surge in a short period of time, affecting its lifespan and performance. On the other hand, gentle driving styles help extend the battery's range and lifespan. Therefore, accurately acquiring the characteristics of driving scenarios helps to more accurately predict the battery's load pressure and formulate reasonable management strategies.

[0015] More specifically, the built-in sensing system of new energy batteries can monitor parameters such as battery voltage, current, temperature, and SOC (State of Charge) in real time. These parameters can reflect the battery's working status and performance. For example, changes in battery voltage can reflect the battery's charging and discharging status; excessively high battery temperature may affect the battery's safety and performance; and SOC directly indicates the battery's remaining capacity.

[0016] More specifically, the collected battery performance data is correlated with driving behavior data (such as acceleration, deceleration, vehicle speed, etc.). Through data mining and machine learning algorithms, the load performance characteristics of the battery under different driving behaviors are identified. For example, during rapid acceleration, the battery current will increase rapidly and the voltage will decrease accordingly; while during constant speed driving, the battery current and voltage are relatively stable.

[0017] More specifically, the battery's load performance characteristics directly reflect its working state and performance in actual use. By collecting and analyzing battery performance data across multiple monitoring items, we can understand the battery's health status, charging and discharging efficiency, and other information. Combining this data with driving behavior data provides a more comprehensive understanding of the battery's load under different driving scenarios, offering a more accurate basis for predicting the battery's future load pressure. For example, if the battery's temperature is found to be too high or its voltage fluctuations are too large under certain driving behaviors, measures can be taken in advance to adjust it and avoid battery safety issues or performance degradation.

[0018] Specifically, in step S2 of the embodiment provided by the present invention, the current energy supply mode of the new energy battery is obtained through the vehicle's battery management system (BMS). The battery management system will automatically adjust the energy supply mode of the battery according to factors such as the vehicle's operating status, battery charge, and temperature. Common energy supply modes include pure electric drive mode and hybrid mode. The current energy supply mode information can be obtained by reading relevant data stored in the BMS or by communicating with the BMS.

[0019] More specifically, under different energy supply modes, the energy distribution and interaction between the new energy battery and various functional modules are different. For example, in pure electric drive mode, the battery directly supplies power to the vehicle's drive motor and other auxiliary functional modules; while in hybrid mode, the battery may work in conjunction with the engine, and the energy distribution is more complex. Understanding the energy supply mode is the basis for subsequently assigning monitoring weights to functional modules. Only by clarifying the energy supply mode can we accurately determine the degree of dependence of each functional module on the battery.

[0020] More specifically, based on pre-set rules and experience, and combined with the importance and impact of each functional module on the battery under different power supply modes, a corresponding monitoring weight is assigned to each functional module. For example, in pure electric drive mode, the drive motor is the main energy-consuming module and has a greater impact on the battery, so it can be assigned a higher monitoring weight; while some auxiliary functional modules, such as interior lighting and audio, have a relatively smaller impact on the battery and can be assigned a lower monitoring weight. A weight allocation table can be used to record the monitoring weight of each functional module under different power supply modes.

[0021] More specifically, different functional modules have varying degrees of impact on the battery. Monitoring all functional modules to the same degree would waste a lot of computing resources and time. By allocating monitoring weights, we can highlight the monitoring of those functional modules that have a greater impact on the battery, thereby improving the efficiency and targeting of monitoring. At the same time, dynamically adjusting the monitoring weights according to the power supply mode can more accurately reflect the actual impact of each functional module on the battery under different operating conditions.

[0022] More specifically, a monitoring weight threshold is set, and functional modules with a monitoring weight greater than the threshold are filtered out as reference objects for new energy batteries. For example, if the threshold is set to 0.5, then functional modules with a monitoring weight greater than 0.5 will be selected. Functional modules that meet the conditions can be filtered out by traversing the monitoring weight list of functional modules.

[0023] More specifically, in new energy vehicles, there are many functional modules that are functionally related to the battery. If detailed operational performance data is collected for all functional modules, it will increase the complexity and cost of the system. By selecting relevant reference objects and focusing on monitoring only those functional modules that have a greater impact on the battery, the system burden can be reduced and the efficiency of data collection and analysis can be improved while ensuring the monitoring effect.

[0024] More specifically, for functional modules that are not selected as associated reference objects, their operational performance data is still collected, but a relatively simple monitoring method is adopted, such as setting some basic operating parameter thresholds. When the operating parameters of a functional module exceed these thresholds, it is determined that the functional module has an abnormal operating value. For example, for the vehicle interior lighting module, its normal operating current range is set to 0-5A. If its operating current is detected to exceed 5A, it is considered to have an abnormal operation. When the abnormal operating value reaches the predetermined standard, the functional module is classified as an associated reference object, and more detailed monitoring begins.

[0025] More specifically, although the unselected functional modules have a relatively small impact on the battery, they may still experience abnormalities during operation. These abnormalities may indirectly affect the battery's performance and safety. By monitoring these functional modules for abnormalities, potential problems can be detected in a timely manner, preventing them from escalating. Once a functional module malfunctions, it can be included in the associated reference objects for focused monitoring, enabling a more comprehensive understanding of the vehicle's operating status and ensuring the safe and stable operation of the new energy battery.

[0026] Specifically, in step S3 of the embodiment provided by the present invention, the operating performance data of each functional module (such as the power consumption and working time of each module) and the load performance data of the new energy battery (such as voltage, current, temperature, SOC, etc.) are first cleaned to remove noise data and outliers, and then normalized to make different types of data comparable.

[0027] More specifically, data mining techniques, such as correlation analysis and causal analysis, can be used to identify potential correlations between functional module performance data and battery load characteristics. For example, the Pearson correlation coefficient can be calculated to measure the linear correlation between different variables. Based on the results of correlation analysis, a load reference model for new energy batteries can be constructed. Machine learning algorithms, such as decision trees and support vector machines, can be used to establish mapping relationships between data and summarize the load patterns of batteries under different functional module operating states.

[0028] More specifically, the operating status of different functional modules will have varying degrees of impact on the load of new energy batteries. By exploring the potential correlation between the operating performance data of functional modules and the battery load performance characteristics, we can gain a deeper understanding of the intrinsic mechanism of battery load changes. The load reference model can provide a basis for accurately predicting the future load pressure of the battery and help us understand the load change trend of the battery under different operating conditions so as to take countermeasures in advance.

[0029] More specifically, driving scenarios are categorized based on their characteristics (such as driving style, road conditions, and external environment), including different scenarios like urban traffic congestion, highway driving, and mountain road driving. For each driving scenario, historical performance data of each functional module under that scenario is analyzed to statistically analyze the patterns and distribution characteristics of its power supply demand. Using methods such as time series analysis and regression analysis, combined with current driving scenario characteristics and historical operating data of functional modules, a predictive model for the future power supply demand of each functional module is established. By inputting current driving scenario information, this model is used to predict the power supply demand of each functional module in the future.

[0030] More specifically, different driving scenarios will cause changes in the usage frequency and power requirements of each functional module. For example, on congested city roads, vehicles start and stop frequently, and the drive motor and braking energy recovery system are used more frequently; while when driving at high speeds, auxiliary functional modules such as air conditioning and lighting run for a longer period of time. Accurately predicting the future power supply requirements of each functional module can provide a basis for rationally allocating battery energy and improving battery efficiency.

[0031] More specifically, the demand forecast information obtained from each functional module is input into the load reference mode. Combined with the current state of the battery (such as SOC, temperature, etc.), it serves as the input data for prediction. Based on the mapping relationship established by the load reference mode, the load pressure of the new energy battery in the future period can be calculated, and load forecast information such as the battery power demand curve and power consumption forecast can be obtained. Considering the uncertainties in actual driving, such as sudden traffic conditions and temporary operations by the driver, the uncertainty assessment of the load forecast results is performed, and the confidence interval of the forecast results is given.

[0032] More specifically, the load reference model reflects the inherent relationship between the operation of functional modules and battery load, while the demand forecast information of each functional module provides the future power supply demand of each module. By substituting the demand forecast information into the load reference model for calculation, multiple factors can be integrated to more accurately predict the future load pressure of new energy batteries. Uncertainty assessment allows users to understand the reliability of the forecast results, providing more comprehensive information for subsequent management strategy formulation and reducing the risks caused by forecast errors.

[0033] Specifically, in step S4 of the embodiment provided by the present invention, relevant data under the current new energy battery power supply mode are extracted from the vehicle's battery management system (BMS). As the core unit for battery monitoring and management, the BMS stores detailed operating information including battery voltage, current, power output, temperature, and SOC (state of charge). Based on the physical principle of battery power supply and the actual operating logic, the acquired data is classified and decomposed. For example, the power output parameters are subdivided into the power allocation of different electrical devices (drive motor, air conditioner, lighting, etc.); the voltage changes during battery charging and discharging are decomposed into voltage thresholds and fluctuation ranges at different stages, ultimately obtaining specific power supply parameters such as charging voltage, upper limit of discharge current, and power allocation ratio of each functional module.

[0034] More specifically, the power supply mode of new energy batteries is defined by multiple power supply parameters. These parameters directly affect the battery's operating status and performance. By breaking down the parameters of the current power supply mode, we can clearly understand the specific working details of the battery in the current state. This provides an operational object for adjusting the power supply strategy based on load forecast information. Only by clarifying each power supply parameter can we make targeted adjustments to meet the battery management needs under different load conditions.

[0035] More specifically, according to the preset battery scheduling strategy, a series of adjustment schemes for energy supply parameters are formulated. For example, when the load forecast shows that the battery will face high load pressure in the future, the power allocation of non-essential functional modules (such as the in-vehicle entertainment system) can be reduced and the charging current can be increased to increase the battery's energy reserve; or during low load periods, the battery's output power can be appropriately reduced to improve energy utilization efficiency. Each adjustment scheme corresponds to a pre-adjustment form.

[0036] More specifically, using a battery simulation model or a prediction model built from historical data, load forecast information and various pre-emptive adjustment modes are input into the model for simulation. The model will calculate various performance indicators of the battery under different adjustment modes based on the input information, such as driving range, battery life loss, and energy conversion efficiency. Based on the various performance indicators obtained from the simulation, the advantages and disadvantages of each pre-emptive adjustment mode are comprehensively evaluated, and corresponding simulation operation value is assigned to it. For example, a comprehensive evaluation function can be set to calculate the simulation operation value of each pre-emptive adjustment mode by weighting factors such as driving range and battery life according to certain weights.

[0037] More specifically, different power supply parameter adjustment methods will have different impacts on battery operation. By adjusting various power supply parameters and forming preliminary adjustment patterns, multiple possible battery management solutions can be explored. Simulating the effects and evaluating the value of these preliminary adjustment patterns allows us to understand their performance in the face of load forecast information before actual application, select better adjustment schemes, avoid the adverse consequences of blindly adjusting parameters, and improve the effectiveness and scientific nature of battery management.

[0038] More specifically, the preliminary adjustment mode with the highest simulated operating value is used as the benchmark. The correlation between the operating mode and the operating value of the other preliminary adjustment modes is analyzed. By comparing the differences of different adjustment modes in various performance indicators, the key factors affecting the simulated operating value are identified, and then the switching conditions between the preliminary adjustment modes are determined. For example, when the simulated operation shows that adjustment mode A can make the battery range the longest within a certain load range, but as the load increases, adjustment mode B has less battery life loss, a load threshold can be set as the switching condition between adjustment modes A and B.

[0039] More specifically, the various preparatory adjustment modes and their corresponding switching conditions are integrated to generate a complete new energy battery management strategy. This strategy should have real-time monitoring capabilities, continuously monitoring the real-time load performance characteristics of the new energy battery (such as power demand, SOC changes, etc.). When the monitored load performance characteristics meet a certain switching condition, the battery's power supply parameters are automatically adjusted accordingly, switching from one preparatory adjustment mode to another more suitable adjustment mode.

[0040] More specifically, a single power supply parameter adjustment method may not be able to adapt to diverse load changes. By using the adjustment method with the highest simulated operating value as a benchmark, analyzing and integrating the switching conditions between various adjustment methods, a flexible and adaptive battery management strategy can be formulated. This strategy can dynamically adjust the power supply parameters according to the real-time load of the battery, ensuring that the battery can operate in the optimal state under different load scenarios, improving the battery's safety, reliability and lifespan, while achieving efficient energy utilization.

[0041] This invention provides an intelligent management method for new energy batteries, which has the following beneficial effects: This invention provides a foundation for battery management by real-time monitoring of driving scenarios and load performance of vehicles equipped with new energy batteries, extracting key characteristic data of the batteries. By collecting operational data from modules related to battery functions, the system can comprehensively understand the battery's performance in actual operation. Combining driving scenario characteristics and load performance characteristics, the system can accurately predict future load pressure and generate effective load prediction information. Based on this information, it uses a preset battery scheduling strategy for adaptive analysis to form a targeted management strategy. This intelligent management method not only improves battery utilization efficiency and extends its service life but also enhances the safety and reliability of new energy vehicles, laying the foundation for promoting sustainable transportation development.

[0042] Preferably, the step of monitoring the driving scenario and load performance of a new energy vehicle equipped with a new energy battery to obtain the driving scenario characteristics and load performance characteristics of the new energy battery includes: S11: Collect external environmental information of new energy vehicles through vehicle-mounted sensor modules and cloud-based digital maps, and obtain the driver's driving style information based on driving behavior data analysis, so as to obtain driving scenario characteristics. S12: Collect performance data of the new energy battery on multiple monitoring items through the built-in sensing system of the new energy battery, and combine the various performance data with driving behavior data to identify the load performance characteristics of the new energy battery and obtain the load performance characteristics of the new energy battery.

[0043] Specifically, the vehicle-mounted sensing module includes various sensors, such as cameras that can identify road signs, traffic lights, vehicles ahead, and pedestrians; radar that can measure the distance and relative speed to surrounding objects; and weather sensors that can acquire meteorological information such as temperature, humidity, and light intensity. These sensors work continuously, collecting environmental data around the vehicle in real time. Through the vehicle's communication module, they connect to a cloud server to obtain information such as road type (highway, urban road, rural road), traffic flow, slope, and curves. The map data is continuously updated based on real-time traffic conditions to ensure the accuracy of the information.

[0044] More specifically, driving behavior data is collected using vehicle sensors, such as the travel of the accelerator and brake pedals, the steering wheel angle and speed, and changes in vehicle speed. Machine learning algorithms are then used to analyze and classify the large amount of driving behavior data collected. For example, driving behaviors involving frequent rapid acceleration, sudden braking, and large speed fluctuations can be classified as aggressive driving style; while smooth acceleration and deceleration, maintaining a constant speed as much as possible, belong to mild driving style. The collected external environmental information and the analyzed driving style information are integrated to form comprehensive driving scenario characteristics. For example, on congested urban roads, an aggressive driving style will result in driving scenario characteristics of high load and frequent start-stop.

[0045] More specifically, different driving scenarios have a significant impact on the performance and usage of new energy batteries. For example, in high-temperature environments, the chemical reaction rate of the battery accelerates, which may lead to overheating of the battery and affect its lifespan and safety. Aggressive driving styles can cause the battery to withstand large power surges in a short period of time, increasing battery wear. Accurate driving scenario characteristics can help to make more accurate predictions of the future load pressure of new energy batteries, thereby formulating more reasonable battery management strategies and improving battery efficiency and safety.

[0046] More specifically, the built-in sensing system of new energy batteries is usually equipped with voltage sensors, current sensors, temperature sensors, and SOC (state of charge) sensors. These sensors monitor the battery's performance data in real time on multiple monitoring items, such as battery voltage, current, temperature, and SOC. The data acquisition frequency can be set according to actual needs to ensure that changes in battery status can be captured in a timely manner.

[0047] More specifically, the collected battery performance data is correlated with driving behavior data. For example, the changes in battery current during rapid acceleration are correlated with the driving behavior data at that moment. Data analysis techniques and machine learning algorithms are used to process and analyze the correlated data to identify the load performance characteristics of new energy batteries under different driving behaviors. For example, in the process of frequent start-stop driving, the voltage fluctuation and SOC change patterns of the battery are analyzed.

[0048] More specifically, battery load performance characteristics can intuitively reflect the battery's working state and performance during actual use. By collecting and analyzing these characteristic data, it is possible to detect abnormalities in the battery in a timely manner, such as overcharging, over-discharging, and overheating. Combining driving behavior data with the analysis of battery load performance characteristics can provide a deeper understanding of the impact of driving behavior on battery load, thereby providing a basis for developing more precise battery management strategies. For example, based on the battery load characteristics under different driving behaviors, the battery charging and discharging strategies can be adjusted to extend the battery's lifespan.

[0049] Preferably, the step of collecting operational performance data of functional modules in the new energy vehicle that are functionally related to the new energy battery includes: S21: Obtain the power supply mode of the new energy battery, and assign monitoring weights to each functional module that is functionally related to the new energy battery according to the power supply mode. S22: Based on the monitoring weight, each of the functional modules is filtered to obtain a number of functional modules that serve as related reference objects for new energy batteries, so as to collect operational performance data.

[0050] Preferably, the performance data of each functional module that is not selected as an associated reference object is collected and monitored to determine the abnormal values ​​of each functional module. When the abnormal values ​​reach a predetermined standard, the functional module is classified as an associated reference object.

[0051] Specifically, the current energy supply mode of the new energy battery is obtained through the vehicle's battery management system (BMS). The BMS will automatically adjust the energy supply mode according to factors such as the vehicle's operating status, battery charge, and temperature. Common energy supply modes include pure electric drive mode, hybrid mode (engine and battery work together), and energy recovery mode. The accurate energy supply mode can be obtained by reading the energy supply mode identification information stored in the BMS or by communicating with the BMS.

[0052] More specifically, based on pre-set rules and experience, and combined with the degree of dependence and impact of each functional module on the battery under different energy supply modes, a monitoring weight is assigned to each functional module that has a functional relationship with the new energy battery. For example, in pure electric drive mode, the drive motor is the main energy-consuming module and has a great impact on the battery, so it can be assigned a higher monitoring weight, such as 0.8; while the in-vehicle audio system has a relatively small impact on the battery and can be assigned a lower monitoring weight, such as 0.1. A weight allocation table can be used to record the monitoring weight of each functional module under different energy supply modes.

[0053] More specifically, the operating status of each functional module and its impact on the battery vary greatly under different energy supply modes. For example, in hybrid mode, the engine takes on the power output task, and the drive motor's dependence on the battery is reduced. In energy recovery mode, the operation of some auxiliary functional modules affects the battery's energy recovery efficiency. Therefore, clearly defining the energy supply mode is the basis for rationally allocating monitoring weights. By assigning monitoring weights to each functional module, we can highlight the monitoring of those functional modules that have a greater impact on the battery, avoid indiscriminate monitoring of all functional modules, thereby improving the efficiency and targeting of monitoring and reducing unnecessary computing resources and data storage overhead.

[0054] More specifically, a monitoring weight threshold is set, and functional modules with a monitoring weight greater than this threshold are filtered out as related reference objects for new energy batteries. For example, if the threshold is set to 0.3, then functional modules with a monitoring weight greater than 0.3 will be selected. By traversing the weight allocation table, functional modules that meet the conditions can be filtered out. For the filtered related reference objects, their operating performance data can be collected by sensors installed on each functional module or by communicating with the control unit of the functional module. For example, for drive motors, data such as current, voltage, and speed can be collected; for air conditioning systems, data such as cooling power and compressor running time can be collected.

[0055] More specifically, new energy vehicles contain numerous functional modules related to batteries. Monitoring all modules in detail would increase system complexity and cost. By selecting relevant reference objects and focusing on monitoring only those functional modules that have a significant impact on the battery, the system burden can be reduced while ensuring monitoring effectiveness. This improves the efficiency of data collection and analysis. Collecting operational performance data from relevant reference objects can provide accurate and crucial data support for predicting future load pressure on new energy batteries and formulating management strategies, thus helping to more accurately assess the battery's working status and performance.

[0056] More specifically, for functional modules not selected as associated reference objects, their operational performance data is still collected through corresponding sensors or communication interfaces, but a relatively simple monitoring method is adopted. For example, some basic operating parameter thresholds are set; for instance, for the ambient lighting inside the vehicle, the normal range of its operating current is set to 0-0.5A. The operating data of these functional modules is continuously monitored to determine whether they exceed the set thresholds. When the operating parameters of a functional module exceed the predetermined threshold, i.e., an abnormal operating value occurs, the functional module is classified as an associated reference object, and more detailed monitoring and data collection begin. At the same time, a corresponding alarm mechanism can be triggered to alert vehicle management personnel or drivers.

[0057] More specifically, although the unselected functional modules have a relatively small impact on the battery, they may still experience abnormalities during operation. These abnormalities may indirectly affect the battery's performance and safety. By monitoring these functional modules, potential problems can be detected in a timely manner, preventing them from escalating and enabling comprehensive risk control of the vehicle system. By classifying abnormal functional modules as associated reference objects, the monitoring scope can be dynamically adjusted according to the actual operating conditions of the functional modules, ensuring that key battery-related information can be accurately grasped under different operating conditions, thereby improving the flexibility and effectiveness of battery management.

[0058] Preferably, the step of predicting the future load pressure of the new energy battery by combining the operational performance data, the driving scenario characteristics, and the load performance characteristics to obtain load prediction information includes: S31: Perform feature mining on the potential correlation between the operational performance data of each functional module and the load performance characteristics of the new energy battery to obtain the load reference mode of the new energy battery. S32: Based on the driving scenario characteristics, predict the future power supply demand of each functional module from the operational performance data to obtain the demand prediction information of each functional module; S33: Based on the load reference mode, predict the future load pressure of the demand forecast information to obtain the load forecast information of the new energy battery.

[0059] Specifically, the operational performance data of each functional module (such as power consumption, working time, etc.) and the load performance characteristic data of new energy batteries (such as voltage, current, temperature, SOC, etc.) are cleaned to remove noise data and outliers. Then, normalization processing is performed to make different types of data comparable. For example, voltage and current data in different ranges are unified into the [0, 1] interval.

[0060] More specifically, association rule mining algorithms in data mining techniques, such as the Apriori algorithm, can be used to identify frequent itemsets and association rules between functional module performance data and battery load performance characteristics. Correlation analysis methods, such as the Pearson correlation coefficient, can also be used to calculate the linear correlation between variables. Based on the results of association analysis, a load reference model for new energy batteries can be constructed. Machine learning algorithms, such as neural networks and decision trees, can be used to establish a mapping relationship between the functional module operating status and battery load. For example, by training a multilayer perceptron neural network, the operating parameters of the functional module are input, and the predicted load value of the battery is output.

[0061] More specifically, the operating status of different functional modules will have varying degrees of impact on the load of new energy batteries. Exploring the potential correlations between them can provide a deeper understanding of the intrinsic mechanism of battery load changes. Load reference models can provide a basis for accurately predicting the future load pressure of batteries, helping us to predict the load change trend of batteries when the operating status of functional modules is known, so as to take countermeasures in advance, such as adjusting the battery charging and discharging strategies.

[0062] More specifically, driving scenarios are classified according to their characteristics (such as driving style, road conditions, external environment, etc.), such as different scenarios like urban traffic congestion, highway driving, and mountain road driving. For each driving scenario, the historical performance data of each functional module under that scenario is analyzed, and the patterns and distribution characteristics of their power supply demand are statistically analyzed. For example, the average power consumption and usage time of functional modules such as air conditioning system and lighting system under urban traffic congestion are statistically analyzed.

[0063] More specifically, by using time series analysis methods (such as the ARIMA model) and regression analysis methods (such as linear regression and multinomial regression), combined with the current driving scenario characteristics and the historical operating data of functional modules, a predictive model for the future power supply demand of each functional module is established. By inputting the current driving scenario information, the model is used to predict the power supply demand of each functional module in the future period of time, thus obtaining the demand prediction information of each functional module.

[0064] More specifically, different driving scenarios will cause changes in the usage frequency and power requirements of each functional module. For example, on congested city roads, vehicles frequently start and stop, and the drive motor needs more energy to accelerate; while when driving at high speeds, auxiliary functional modules such as air conditioning and audio systems run for longer periods, and their power supply requirements also increase accordingly. Accurately predicting the future power supply requirements of each functional module can provide a basis for rationally allocating battery energy and improving battery efficiency, avoiding the impact of insufficient or excessive power supply on the normal operation of the vehicle.

[0065] More specifically, the demand forecast information of each functional module obtained above is input into the load reference mode. At the same time, the current state information of the battery (such as SOC, temperature, etc.) is used as the input data for prediction. According to the mapping relationship established by the load reference mode, the load pressure of the new energy battery in the future period is calculated. For example, by adding the predicted power demand of each functional module and taking into account the energy loss and efficiency of the battery itself, the total power demand forecast value of the battery is obtained. Furthermore, the battery's SOC change trend, temperature change, etc. can be predicted to obtain more comprehensive load forecast information.

[0066] More specifically, considering the uncertainties in actual driving, such as sudden traffic conditions and temporary driver actions, uncertainty assessment of load forecast results can be performed using methods such as Monte Carlo simulation. Through multiple random sampling and simulation calculations, the confidence interval and probability distribution of the forecast results can be given.

[0067] More specifically, the load reference model reflects the inherent relationship between the operation of functional modules and battery load, while the demand forecast information of each functional module provides the future power supply demand of each module. By substituting the demand forecast information into the load reference model for calculation, multiple factors can be comprehensively considered to more accurately predict the future load pressure of new energy batteries. Uncertainty assessment allows us to understand the reliability of the forecast results and the possible fluctuation range, providing a reference for formulating more robust battery management strategies and reducing the risks caused by forecast errors.

[0068] Preferably, the step of performing adaptive analysis on the load forecast information according to a preset battery scheduling strategy to obtain the management strategy for the new energy battery includes: S41: Decompose the parameters of the energy supply mode of the new energy battery at the current moment to obtain several energy supply parameters; S42: Adjust various power supply parameters according to a preset battery scheduling strategy to obtain several preliminary adjustment forms, so as to simulate the effect of the load forecast information and obtain the simulated operation value of each of the preliminary adjustment forms relative to the load forecast information. S43: Based on the simulated operation value of each of the aforementioned pre-adjustment forms, a new energy battery generation management strategy is formulated.

[0069] Specifically, detailed operating data under the current new energy battery power supply mode is obtained from the vehicle's Battery Management System (BMS). The BMS records various battery status information in real time, such as battery output voltage, current, power, temperature, state of charge (SOC), and charge / discharge rate. Based on the physical principles and system architecture of battery power supply, the collected data is analyzed and classified to identify the key parameters constituting the current power supply mode. For example, the power supply mode is subdivided into charging mode and discharging mode. Power supply parameters in charging mode include charging voltage, charging current, and charging time; power supply parameters in discharging mode include discharging power and discharging cutoff voltage. At the same time, parameters such as the power ratio allocated by the battery to various functional modules (such as drive motor, air conditioning system, lighting system, etc.) under different operating conditions also need to be considered.

[0070] More specifically, the power supply mode of new energy batteries is defined and controlled by multiple power supply parameters. These parameters directly affect the battery's operating status, performance, and lifespan. By breaking down the parameters of the current power supply mode, we can clearly understand the specific working details and operating conditions of the battery at the current moment. This provides a basis for targeted adjustments to the power supply parameters based on load forecast information. Only by clarifying each power supply parameter can we accurately assess the impact of different adjustment schemes on battery performance and thus formulate reasonable management strategies.

[0071] More specifically, based on the preset battery scheduling strategy and combined with load forecast information, a series of adjustment schemes for power supply parameters are formulated. For example, if the load forecast shows that the battery will face high load demand in the future, the upper limit of the battery discharge power can be increased, the power allocation ratio of each functional module can be adjusted, and the power supply of key functional modules can be prioritized. If the predicted load is low, the charging rate can be reduced to reduce battery loss. Each adjustment scheme corresponds to a pre-adjustment form.

[0072] More specifically, by using a battery simulation model or a prediction model based on historical data, load forecast information and various pre-set adjustment modes are input into the model for simulation. The simulation model will simulate the battery's operation under different adjustment modes according to the input parameters, and output performance indicators such as battery range, remaining power, temperature change, and battery life loss.

[0073] More specifically, based on the various performance indicators obtained from the simulation operation, the advantages and disadvantages of each preparatory adjustment form are comprehensively evaluated, and a corresponding simulation operation value is assigned to it. A comprehensive evaluation function can be set up to calculate the simulation operation value of each preparatory adjustment form by weighting indicators such as driving range, battery life, and energy utilization efficiency according to certain weights. For example, the driving range weight is 0.5, the battery life weight is 0.3, and the energy utilization efficiency weight is 0.2. The simulation operation value is obtained by calculating the weighted sum.

[0074] More specifically, different power supply parameter adjustment methods will have different effects on battery operation. They may improve battery performance, but they may also increase battery wear or reduce energy utilization efficiency. By developing multiple pre-adjustment methods and conducting effect simulations, we can understand the performance of various adjustment schemes in the face of load forecast information before actual application, select the better adjustment scheme, and evaluate the value of simulation operation. This can provide a quantitative basis for selecting the most suitable adjustment method in the future, avoid the adverse consequences of blindly adjusting parameters, and improve the scientificity and effectiveness of battery management.

[0075] More specifically, the preliminary adjustment mode with the highest simulated operating value is used as the benchmark. The correlation between the operating mode and the operating value of the other preliminary adjustment modes is analyzed. By comparing the differences of different adjustment modes in various performance indicators, the key factors affecting the simulated operating value are identified, and then the switching conditions between the preliminary adjustment modes are determined. For example, when the simulated operation shows that adjustment mode A can make the battery range the longest within a certain load range, but as the load increases, adjustment mode B has less battery life loss, a load threshold can be set as the switching condition between adjustment modes A and B.

[0076] More specifically, the various preparatory adjustment modes and their corresponding switching conditions are integrated to generate a complete new energy battery management strategy. This strategy should have real-time monitoring capabilities, continuously monitoring the real-time load performance characteristics of the new energy battery (such as power demand, SOC changes, etc.). When the monitored load performance characteristics meet a certain switching condition, the battery's power supply parameters are automatically adjusted accordingly, switching from one preparatory adjustment mode to another more suitable adjustment mode.

[0077] More specifically, a single power supply parameter adjustment method cannot adapt to diverse load changes. By using the adjustment method with the highest simulated operating value as a benchmark, analyzing and integrating the switching conditions between various adjustment methods, a flexible and adaptive battery management strategy can be formulated. This strategy can dynamically adjust the power supply parameters according to the real-time load of the battery, ensuring that the battery can operate in the optimal state under different load scenarios, improving the battery's safety, reliability and lifespan, while achieving efficient energy utilization.

[0078] Preferably, the steps for formulating the new energy battery generation management strategy based on the simulated operational value of each of the aforementioned pre-adjustment forms include: S431: Using the pre-adjustment form with the highest simulation operation value as a benchmark, perform a correlation analysis between the operation form and operation value on the other pre-adjustment forms to obtain the form switching conditions between each pre-adjustment form. S432: Based on the form switching conditions, integrate each of the pre-adjustment forms to generate a management strategy for the new energy battery; wherein, the management strategy is used to monitor the real-time load performance characteristics of the new energy battery to determine the form switching conditions and adjust the parameters of the corresponding pre-adjustment forms of the new energy battery.

[0079] Specifically, from several preliminary adjustment methods that have undergone effect simulation and yielded simulated operational value, the one with the highest simulated operational value is selected as the benchmark adjustment method. The simulated operational value is calculated using a preset evaluation function, taking into account various performance indicators such as battery range, lifespan loss, and energy utilization efficiency. The remaining preliminary adjustment methods are then comprehensively compared with the benchmark adjustment method. The comparison includes the adjustment methods of various power supply parameters (such as charging voltage, discharging current, and power allocated to each functional module) and the various performance indicators obtained after simulation. By analyzing the comparison results, the key factors that cause differences in the simulated operational value of different preliminary adjustment methods are identified. For example, some adjustment methods can improve battery energy utilization efficiency under low load conditions, but significantly shorten the range under high load conditions. Therefore, the load size is a key factor. Based on the identified key factors, the switching conditions between each preliminary adjustment method are determined. This can be achieved by setting some parameter thresholds, such as setting load power thresholds and battery state of charge (SOC) thresholds. When the parameters monitored in real time reach these thresholds, the corresponding adjustment method switching is triggered.

[0080] More specifically, different pre-conditioning methods have different advantages under different operating conditions, and a single method cannot always guarantee that the battery is in its optimal operating state. By conducting correlation analysis based on the method with the highest simulated operating value, the differences and applicable scenarios between various methods can be clarified, thereby determining reasonable switching conditions. This allows for flexible adjustment of the battery's power supply parameters according to actual operating conditions, fully leveraging the advantages of different methods and improving the overall performance and efficiency of the battery.

[0081] More specifically, all the proposed adjustment methods and the conditions for switching between them are systematically organized and integrated to form a complete strategy framework. This can be represented using flowcharts or state machines, clearly demonstrating which adjustment method should be used under different conditions. A real-time monitoring system is established to acquire the load performance characteristics of the new energy battery in real time. This can be achieved through various sensors on the vehicle, such as current sensors, voltage sensors, and temperature sensors, continuously collecting data such as battery power demand, SOC changes, and temperature changes.

[0082] More specifically, the real-time monitored data is compared with the previously determined switching conditions. When the monitored data meets a certain switching condition, the system automatically triggers the corresponding operation to adjust the power supply parameters of the new energy battery, so that it switches from the current adjustment mode to a more suitable pre-adjustment mode.

[0083] More specifically, by integrating various pre-adjustment modes and mode switching conditions to generate management strategies, the previous analysis and planning can be transformed into practical and operable solutions. Real-time monitoring of battery load performance characteristics and condition judgment and adjustment execution enable the battery management strategy to be dynamically adaptable. During the actual operation of the vehicle, the battery load is constantly changing. This management strategy can adjust the battery power supply parameters in a timely manner according to the real-time situation, ensuring that the battery can operate stably and efficiently under different operating conditions, extending the battery's lifespan, and improving the overall performance and safety of new energy vehicles.

[0084] Reference Figure 2 As shown, in a second aspect, the present invention provides an intelligent management system for a new energy battery, used to implement the intelligent management method for a new energy battery as described in any one of the first aspects, comprising: The data monitoring module is used to monitor the driving scenarios and load performance of new energy vehicles equipped with new energy batteries, and to obtain the driving scenario characteristics and load performance characteristics of the new energy batteries. The performance acquisition module is used to collect the operational performance data of functional modules in new energy vehicles that are functionally related to the new energy battery. The load prediction module is used to combine the operating performance data, the driving scenario characteristics, and the load performance characteristics to predict the future load pressure of the new energy battery and obtain load prediction information. The strategy management module is used to perform adaptive analysis on the load forecast information according to the preset battery scheduling strategy to obtain the management strategy of the new energy battery.

[0085] In this embodiment, the specific implementation of each module in the above system embodiment is described in the above method embodiment, and will not be repeated here.

[0086] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A smart management method for new energy batteries, characterized in that, include: The driving scenario and load performance of new energy vehicles equipped with new energy batteries are monitored to obtain the driving scenario characteristics and load performance characteristics of the new energy batteries. Collect operational performance data of functional modules in new energy vehicles that are functionally related to the new energy battery; By combining the operational performance data, the driving scenario characteristics, and the load performance characteristics, the future load pressure of the new energy battery is predicted to obtain load prediction information; Based on a preset battery scheduling strategy, an adaptive analysis is performed on the load forecast information to obtain a management strategy for the new energy battery.

2. The intelligent management method for new energy batteries as described in claim 1, characterized in that, The steps for monitoring the driving scenarios and load performance of new energy vehicles equipped with new energy batteries to obtain the driving scenario characteristics and load performance characteristics of the new energy batteries include: The external environment information of new energy vehicles is collected by vehicle-mounted sensing modules and cloud-based digital maps, and the driver's driving style information is obtained based on driving behavior data analysis, so as to obtain the characteristics of driving scenarios. The new energy battery's performance data across multiple monitoring items is collected through its built-in sensing system. This performance data is then combined with driving behavior data to identify the load performance characteristics of the new energy battery.

3. The intelligent management method for new energy batteries as described in claim 1, characterized in that, The steps for collecting operational performance data of functional modules in new energy vehicles that are functionally related to the new energy battery include: The power supply mode of the new energy battery is obtained, and monitoring weights are assigned to each functional module that is functionally related to the new energy battery according to the power supply mode. Based on the monitoring weights, each of the functional modules is filtered to obtain a number of functional modules that serve as relevant reference objects for new energy batteries, so as to collect operational performance data.

4. The intelligent management method for new energy batteries as described in claim 3, characterized in that, The system collects and monitors the operational performance data of each functional module that is not selected as an associated reference object in order to determine the abnormal values ​​of each functional module. When the abnormal values ​​reach a predetermined standard, the functional module is classified as an associated reference object.

5. The intelligent management method for new energy batteries as described in claim 1, characterized in that, The steps for predicting the future load pressure of the new energy battery by combining the operational performance data, the driving scenario characteristics, and the load performance characteristics to obtain load prediction information include: Feature mining is performed on the potential correlation between the operational performance data of each functional module and the load performance characteristics of the new energy battery to obtain the load reference mode of the new energy battery. Based on the driving scenario characteristics, the future power supply demand of each functional module is predicted from the operational performance data to obtain the demand prediction information of each functional module. Based on the load reference model, the future load pressure is predicted using the demand forecast information to obtain the load forecast information for the new energy battery.

6. The intelligent management method for new energy batteries as described in claim 1, characterized in that, The steps for adaptively analyzing the load forecast information based on a preset battery scheduling strategy to obtain the management strategy for the new energy battery include: The power supply mode of the new energy battery at the current moment is decomposed into parameters, resulting in several power supply parameters; Based on the preset battery scheduling strategy, various power supply parameters are adjusted to obtain several preliminary adjustment forms, so as to simulate the effect of the load forecast information and obtain the simulated operation value of each of the preliminary adjustment forms relative to the load forecast information. Based on the simulated operational value of each of the aforementioned pre-adjustment forms, a new energy battery generation management strategy is proposed.

7. The intelligent management method for new energy batteries as described in claim 6, characterized in that, Based on the simulated operational value of each of the aforementioned pre-adjustment forms, the steps for the new energy battery generation management strategy include: Using the pre-adjustment form with the highest simulation operation value as the benchmark, the correlation analysis between the operation form and operation value of the other pre-adjustment forms is performed to obtain the form switching conditions between each pre-adjustment form. Based on the aforementioned switching conditions, the various pre-adjustment modes are integrated to generate a management strategy for the new energy battery. The management strategy is used to monitor the real-time load performance characteristics of the new energy battery to determine the switching conditions and adjust the parameters of the corresponding pre-adjustment modes for the new energy battery.

8. An intelligent management system for a new energy battery, characterized in that, A method for implementing the intelligent management of a new energy battery according to any one of claims 1-7, comprising: The data monitoring module is used to monitor the driving scenarios and load performance of new energy vehicles equipped with new energy batteries, and to obtain the driving scenario characteristics and load performance characteristics of the new energy batteries. The performance acquisition module is used to collect the operational performance data of functional modules in new energy vehicles that are functionally related to the new energy battery. The load prediction module is used to combine the operating performance data, the driving scenario characteristics, and the load performance characteristics to predict the future load pressure of the new energy battery and obtain load prediction information. The strategy management module is used to perform adaptive analysis on the load forecast information according to the preset battery scheduling strategy to obtain the management strategy of the new energy battery.

Images