New energy automobile battery management system and method

Abstract

The invention relates to the technical field of electric vehicle battery management, and particularly discloses a new energy automobile battery management system and method.The system is provided with a battery pack state analysis module, a single body balance state analysis module, a battery state output module, a battery management error term analysis module and a battery management updating module; the problems that a traditional new energy automobile battery pack management environment and working condition adaptive capacity is insufficient, and battery pack health state evaluation is not accurate enough are solved. And a single battery thermal management system is insufficient in optimization and limited in equalization effect. According to the method, the states of the batteries can be accurately output according to different battery pack states and single battery balance conditions, and the battery management level and the management scheme are determined after errors caused by environmental factors are considered. The loss of the battery in the using process is reduced, the battery performance of the new energy automobile is optimized, and the reliability and safety of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric vehicle battery management, and particularly to a battery management system and method for new energy vehicles. Background Art

[0002] With the development of the global economy, the dependence of traditional fuel vehicles on oil resources has led to a tight energy supply. Against this background, new energy vehicles have received extensive attention as a sustainable transportation solution. In recent years, battery technology has made great progress. Lithium-ion batteries have become the mainstream energy storage devices for new energy vehicles due to their high energy density, low self-discharge rate, long cycle life, etc. However, battery technology still faces many challenges. On the one hand, the improvement of battery performance requires more refined management. On the other hand, to meet the requirements of long driving range and high power output of new energy vehicles, the battery pack is often composed of multiple single cells connected in series and parallel. There are inevitably performance differences between single cells. If not managed, it will lead to a decline in the overall performance of the battery pack and shorten the service life of the battery pack. Under the concept of intelligent connected vehicles, vehicles need to have a higher degree of automation and more reliable safety performance. Through the battery management system, accidents can be effectively prevented and the overall safety of new energy vehicles can be improved.

[0003] Nowadays, there are still some deficiencies in the research on the battery management of new energy vehicles, specifically reflected in the insufficient adaptability of the traditional new energy vehicle battery pack management environment and working conditions, and the inaccurate assessment of the health state of the battery pack. Moreover, the optimization of the single cell thermal management system is insufficient and the balancing effect is limited. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides a battery management system and method for new energy vehicles, which can effectively solve the problems involved in the above background art.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: In the first aspect of the present invention, a battery management system for new energy vehicles is provided, including a battery pack state analysis module, a single cell balance state analysis module, a battery state output module, a battery management error term analysis module, and a battery management update module, where: The battery pack state analysis module is used to analyze the state of the battery pack of a new energy vehicle, and based on the analysis result of the battery pack state of the new energy vehicle, obtain the battery pack state factor of the new energy vehicle; The single cell balance state analysis module is used to analyze the balance state of the single cells of a new energy vehicle to obtain the balance characteristics of the single cells of the new energy vehicle; The battery state output module is used to combine the battery pack state factor and the balance characteristics of the single cells of the new energy vehicle, and use a neural network model to output the battery state of the new energy vehicle; The battery management error term analysis module is used to obtain the battery usage environment data of the new energy vehicle, and based on the obtained battery usage environment data of the new energy vehicle, obtain the battery management error term of the new energy vehicle; The battery management update module is used to obtain the battery management level and management plan based on the battery state of the new energy vehicle and the battery management error term.

[0006] As a further solution, to analyze the state of the battery pack of a new energy vehicle, the specific analysis process is as follows: Considering the capacity loss of the battery pack at different charge and discharge rates, a rate correction coefficient is introduced to obtain an improved ampere-hour integration formula:

[0007]

[0008] In the formula, SOC is the state of charge of the battery pack, SOC0 is the initial state of charge of the battery pack, C n is the rated capacity of the battery pack, I b (t) is the charge and discharge current of the battery pack at time t, K r is the rate correction coefficient stored in the database;

[0009] Calculate the health status of the battery pack:

[0010]

[0011] In the formula, SOH is the health status of the battery pack, C a is the current actual available capacity of the battery pack, and A is the calendar aging factor stored in the database;

[0012] Combining the Arrhenius equation to describe the relationship between the internal resistance growth of the battery pack and temperature, a battery pack internal resistance growth model is constructed:

[0013]

[0014] In the formula, R i is the internal resistance of the battery pack, Ri0 is the initial internal resistance of the battery pack, β and γ are fitting parameters stored in the database, and E a is the activation energy, R is the gas constant, T is the absolute temperature of the battery pack, E is the cumulative charge-discharge energy of the battery pack, and e is the natural constant.

[0015] As a further solution, based on the analysis result of the new energy vehicle battery pack state, the state factor of the new energy vehicle battery pack is obtained. The specific analysis process is as follows: Based on the state of charge of the battery pack, the health status of the battery pack, and the internal resistance of the battery pack, the state factor of the new energy vehicle battery pack is comprehensively analyzed. The state factor of the new energy vehicle battery pack is used as the analysis basis for outputting the state of the new energy vehicle battery;

[0016]

[0017] In the formula, Dcz is the state factor of the new energy vehicle battery pack.

[0018] As a further solution, the balance state of the new energy vehicle single battery is analyzed to obtain the balance characteristics of the new energy vehicle single battery. The specific analysis process is as follows: Obtain the temperature of each single battery of the new energy vehicle. The maximum temperature difference WD of the new energy vehicle single battery is:

[0019]

[0020] In the formula, the temperature of the j-th single battery of the new energy vehicle is WD j , and the temperature of the k-th single battery of the new energy vehicle is WD k , where j and k are the numbers of each single battery, and n is the total number of single batteries;

[0021] Calculate the temperature balance characteristics of the new energy vehicle single battery:

[0022]

[0023] In the formula, Wt is the temperature balance characteristic of the new energy vehicle single battery, υ1 is the compensation factor of the set WD, and e is the natural constant;

[0024] Obtain the current of each single battery of the new energy vehicle. The maximum current difference DL of the new energy vehicle single battery is:

[0025]

[0026] In the formula, the current of the j-th single battery of the new energy vehicle is DL j , and the current of the k-th single battery of the new energy vehicle is DL k ;

[0027] Calculate the current balance characteristics of the new energy vehicle single battery:

[0028]

[0029] Wherein, Lt is the current equalization characteristic of the single battery of the new energy vehicle, and υ2 is the compensation factor of the set DL;

[0030] Obtain the voltages of each single battery of the new energy vehicle. The maximum voltage difference DY of the single battery of the new energy vehicle is:

[0031]

[0032] Wherein, the voltage of the jth single battery of the new energy vehicle is DY j , and the voltage of the kth single battery of the new energy vehicle is DY k ;

[0033] Calculate the voltage equalization characteristic of the single battery of the new energy vehicle:

[0034]

[0035] Wherein, Yt is the voltage equalization characteristic of the single battery of the new energy vehicle, and υ3 is the compensation factor of the set DY;

[0036] Based on the temperature equalization characteristic of the single battery of the new energy vehicle, the current equalization characteristic of the single battery of the new energy vehicle, and the voltage equalization characteristic of the single battery of the new energy vehicle, comprehensively analyze to obtain the equalization characteristic of the single battery of the new energy vehicle, and the equalization characteristic of the single battery of the new energy vehicle is used as the analysis basis for outputting the battery state of the new energy vehicle.

[0037] As a further solution, the equalization characteristic of the single battery of the new energy vehicle, the specific analysis process is:

[0038]

[0039] Wherein, Dtj is the equalization characteristic of the single battery of the new energy vehicle.

[0040] As a further solution, combine the state factor of the new energy vehicle battery pack, the equalization characteristic of the single battery of the new energy vehicle, and use a neural network model to output the state of the new energy vehicle battery. The specific analysis process is: Based on the trained neural network model, input the state factor of the new energy vehicle battery pack and the equalization characteristic of the single battery of the new energy vehicle, and output the state of the new energy vehicle battery; if the output state of the new energy vehicle battery is 0, it means that the state of the new energy vehicle battery is bad; if the output state of the new energy vehicle battery is 1, it means that the state of the new energy vehicle battery is good; if the output state of the new energy vehicle battery is 2, it means that the state of the new energy vehicle battery is excellent.

[0041] As a further solution, obtain the new energy vehicle battery usage environment data. Based on the obtained new energy vehicle battery usage environment data, obtain the new energy vehicle battery management error term. The specific analysis process is as follows: Obtain the new energy vehicle battery usage environment data, which specifically includes the battery usage environment temperature, the battery usage environment humidity, and the battery usage environment electric field strength. Based on the obtained new energy vehicle battery usage environment data, comprehensively analyze to obtain the new energy vehicle battery management error term, and the new energy vehicle battery management error term is used as the analysis basis for obtaining the new energy vehicle battery management level.

[0042] As a further solution, for the new energy vehicle battery management error term, the specific analysis process is as follows:

[0043]

[0044] In the formula, λ is the new energy vehicle battery management error term, hw is the battery usage environment temperature, hs is the battery usage environment humidity, dcq is the battery usage environment electric field strength, θ1 is the compensation factor for the set hw, θ2 is the compensation factor for the set hs, and θ3 is the compensation factor for the set dcq.

[0045] As a further solution, based on the new energy vehicle battery state and the new energy vehicle battery management error term, obtain the new energy vehicle battery management level and the management plan. The specific analysis process is as follows: Store the new energy vehicle battery state and the new energy vehicle battery management error term as a specified label, obtain the specified label - new energy vehicle battery management level mapping table pre-stored in the database, and by looking up the mapping table, according to the specified label, find the matching new energy vehicle battery management level. Obtain the new energy vehicle battery management level - new energy vehicle battery management plan mapping table pre-stored in the database, and by looking up the mapping table, according to the new energy vehicle battery management level, find the matching new energy vehicle battery management plan.

[0046] The second aspect of the present invention provides a new energy vehicle battery management method, including the following steps: Analyze the new energy vehicle battery pack state, and based on the analysis result of the new energy vehicle battery pack state, obtain the new energy vehicle battery pack state factor. Analyze the balance state of the new energy vehicle single battery to obtain the balance characteristics of the new energy vehicle single battery. Combine the new energy vehicle battery pack state factor, the balance characteristics of the new energy vehicle single battery, and use a neural network model to output the new energy vehicle battery state. Obtain the new energy vehicle battery usage environment data, and based on the obtained new energy vehicle battery usage environment data, obtain the new energy vehicle battery management error term. Based on the new energy vehicle battery state and the new energy vehicle battery management error term, obtain the new energy vehicle battery management level and the management plan.

[0047] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0048] (1) By providing a new energy vehicle battery management system and method, the present invention focuses on the entire battery pack through the battery pack status analysis module, considers its overall performance indicators, and the single-cell balance status analysis module delves into each single-cell battery to analyze the balance situation between single cells and obtain the single-cell battery balance characteristics, avoiding the evaluation deviation caused by only focusing on the whole or single cells.

[0049] (2) The battery status output module of the present invention uses a neural network model to accurately output the battery status according to different battery pack statuses and single-cell balance situations. The battery management error term analysis module is specifically used to obtain battery usage environment data, enabling the battery management system to more accurately understand the true status of the battery. After considering the errors caused by environmental factors, the battery management update module can determine the battery management level and management plan according to the battery status and management error terms.

[0050] (3) Through the new energy vehicle battery status and the new energy vehicle battery management error terms, the present invention obtains the new energy vehicle battery management level and management plan, and can take the most appropriate management measures for batteries in different states. The battery management error terms consider the influence of factors such as the battery usage environment on the accuracy of the battery management system. Different environmental conditions will cause errors in the battery management system when monitoring and controlling the battery. By considering these error terms, the management plan can be adjusted more precisely. Precise management level division and plan implementation help reduce battery loss during use, optimize the performance of new energy vehicle batteries, and improve system reliability and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The present invention will be further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the following drawings.

[0052] Figure 1 It is a schematic diagram of the connection of the system modules of the present invention;

[0053] Figure 2 It is a schematic diagram of the method step flow of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0055] Referring to Figure 1 as shown in the figure, the first aspect of the present invention provides a battery management system for a new energy vehicle, including a battery pack state analysis module, a single cell balance state analysis module, a battery state output module, a battery management error term analysis module, and a battery management update module.

[0056] The battery pack state analysis module is used to analyze the state of the battery pack of the new energy vehicle, and based on the analysis result of the state of the battery pack of the new energy vehicle, obtain the state factor of the battery pack of the new energy vehicle.

[0057] The specific analysis process is as follows: Considering the capacity loss of the battery pack at different charge and discharge rates, a rate correction coefficient is introduced to obtain an improved ampere-hour integration formula:

[0058]

[0059] In the formula, SOC is the state of charge of the battery pack, SOC0 is the initial state of charge of the battery pack, C n is the rated capacity of the battery pack, I b (t) is the charge and discharge current of the battery pack at time t, and K r is the rate correction coefficient stored in the database;

[0060] Calculate the health status of the battery pack:

[0061]

[0062] In the formula, SOH is the health status of the battery pack, C a is the current actual available capacity of the battery pack, and A is the calendar aging factor stored in the database;

[0063] Combined with the Arrhenius equation to describe the relationship between the internal resistance growth of the battery pack and temperature, a battery pack internal resistance growth model is constructed:

[0064]

[0065] In the formula, R i is the internal resistance of the battery pack, R i0 is the initial internal resistance of the battery pack, β and γ are the fitting parameters stored in the database, E a is the activation energy, R is the gas constant, T is the absolute temperature of the battery pack, E is the cumulative charge and discharge energy of the battery pack, and e is the natural constant.

[0066] The electrochemical reaction occurring inside the battery requires the reactant molecules to overcome a certain energy barrier to proceed, and this energy barrier is the activation energy. As the internal conditions of the battery change during use, the activation energy will affect the magnitude of the battery internal resistance.

[0067] The physical and chemical processes inside the battery are similar to those related to molecular motion and energy relationships described by the ideal gas state equation. The gas constant stored in the database helps quantify the relationship between the internal resistance of the battery and temperature changes.

[0068] Based on the analysis results of the state of the new energy vehicle battery pack, the state factor of the new energy vehicle battery pack is obtained. The specific analysis process is as follows: Based on the state of charge of the battery pack, the health status of the battery pack, and the internal resistance of the battery pack, the state factor of the new energy vehicle battery pack is comprehensively analyzed. The state factor of the new energy vehicle battery pack is used as the analysis basis for outputting the state of the new energy vehicle battery.

[0069]

[0070] In the formula, Dcz is the state factor of the new energy vehicle battery pack.

[0071] In practical applications, the charging and discharging current of the battery is constantly changing. This corrected state of charge assessment can more accurately reflect the actual state of charge of the battery under complex working conditions. For example, in the case of frequent acceleration and deceleration of the vehicle, which leads to frequent current changes, it can avoid the problem of inaccurate SOC estimation caused by the cumulative error of the traditional ampere-hour integration method.

[0072] The assessment of the state of health (SOH) not only focuses on the attenuation of the battery capacity but also takes into account the influence of time factors on battery aging. This helps to more comprehensively understand the health status of the battery because even without charging and discharging operations, the performance of the battery will decline over time during long-term storage or use. The internal resistance of the battery is an important factor affecting battery performance and life.

[0073] Through the constructed internal resistance growth model of the battery pack, the change of the internal resistance can be accurately predicted according to the working temperature of the battery. For example, in a high-temperature environment, the internal resistance of the battery may increase, resulting in an increase in energy loss during the charging and discharging process. It is possible to understand in advance and take corresponding measures, such as adjusting the charging strategy or starting the thermal management system.

[0074] By integrating SOC, SOH, and internal resistance to obtain the state factor of the battery pack, it provides a comprehensive index for evaluating the state of the new energy vehicle battery. It can be used as the analysis basis for outputting the state of the new energy vehicle battery, helping the battery management system to better understand the overall performance of the battery, and then taking more reasonable management strategies, such as optimizing charging and discharging control, and deciding whether battery balancing is required, etc.

[0075] The single-cell balancing state analysis module is used to analyze the balancing state of the new energy vehicle single-cell battery and obtain the balancing characteristics of the new energy vehicle single-cell battery.

[0076] The specific analysis process is as follows: Obtain the temperature of each single battery of the new energy vehicle. The maximum temperature difference WD of the single batteries of the new energy vehicle is:

[0077]

[0078] In the formula, the temperature of the j-th single battery of the new energy vehicle is WD j , and the temperature of the k-th single battery of the new energy vehicle is WD k , where j and k are the numbers of each single battery, and n is the total number of single batteries;

[0079] Calculate the temperature balance characteristic of the single batteries of the new energy vehicle:

[0080]

[0081] In the formula, Wt is the temperature balance characteristic of the single batteries of the new energy vehicle, and υ1 is the compensation factor of the set WD;

[0082] Obtain the current of each single battery of the new energy vehicle. The maximum current difference DL of the single batteries of the new energy vehicle is:

[0083]

[0084] In the formula, the current of the j-th single battery of the new energy vehicle is DL j , and the current of the k-th single battery of the new energy vehicle is DL k ;

[0085] Calculate the current balance characteristic of the single batteries of the new energy vehicle:

[0086]

[0087] In the formula, Lt is the current balance characteristic of the single batteries of the new energy vehicle, and υ2 is the compensation factor of the set DL;

[0088] Obtain the voltage of each single battery of the new energy vehicle. The maximum voltage difference DY of the single batteries of the new energy vehicle is:

[0089]

[0090] In the formula, the voltage of the j-th single battery of the new energy vehicle is DY j , and the voltage of the k-th single battery of the new energy vehicle is DY k ;

[0091] Calculate the voltage balance characteristic of the single batteries of the new energy vehicle:

[0092]

[0093] Wherein, Yt is the voltage equalization characteristic of a single battery of a new energy vehicle, and υ3 is the compensation factor of the set DY;

[0094] Based on the temperature equalization characteristic of a single battery of a new energy vehicle, the current equalization characteristic of a single battery of a new energy vehicle, and the voltage equalization characteristic of a single battery of a new energy vehicle, the equalization characteristic of a single battery of a new energy vehicle is comprehensively analyzed, and the equalization characteristic of a single battery of a new energy vehicle is used as the analysis basis for outputting the state of the new energy vehicle battery.

[0095] The equalization characteristic of a single battery of a new energy vehicle, the specific analysis process is as follows:

[0096]

[0097] Wherein, Dtj is the equalization characteristic of a single battery of a new energy vehicle.

[0098] Calculating the maximum temperature difference of a single battery can intuitively reflect the dispersion degree of the temperatures of the single batteries in the battery pack. In practical applications, the uneven temperatures of the single batteries in the battery pack will affect the overall performance and service life of the battery pack. Calculating the temperature equalization characteristic of a single battery, taking into account both the temperature difference and the compensation factor, can more accurately quantify the temperature equalization situation of a single battery and provide a basis for subsequent battery management.

[0099] Calculating the maximum current difference of a single battery, during the charging and discharging process of the battery pack, the uneven current of a single battery will cause some batteries to be overcharged or over-discharged, affecting the battery life. The current equalization characteristic of a single battery can comprehensively consider the current difference and the compensation factor and more accurately reflect the current equalization state of a single battery.

[0100] The voltage imbalance of a single battery is one of the common problems in the battery pack. Voltage imbalance will cause the overall performance of the battery pack to decline. After long-term use, the voltages of some batteries may vary greatly due to different aging degrees, and this voltage imbalance phenomenon can be detected in time through monitoring.

[0101] Comprehensively considering the temperature, current, and voltage equalization characteristics of a single battery, the equalization characteristic of a single battery is obtained, which can be used as an important basis for judging the state of the new energy vehicle battery. Through the analysis of the equalization characteristic of a single battery, the battery management system can more accurately understand the working state of each single battery in the battery pack, and then adopt effective equalization strategies, such as active equalization or passive equalization, to ensure the efficient and stable operation of the battery pack and extend the service life of the battery pack.

[0102] The battery state output module is used to combine the state factors of the new energy vehicle battery pack, the equalization characteristic of a single battery of a new energy vehicle, and use a neural network model to output the state of the new energy vehicle battery.

[0103] The specific analysis process is as follows: Based on the trained neural network model, the state factors of the new energy vehicle battery pack and the equalization characteristics of the individual batteries of the new energy vehicle (there are two neurons in the input layer) are input, and the state of the new energy vehicle battery is output; if the output state of the new energy vehicle battery is 0, it represents that the state of the new energy vehicle battery is poor; if the output state of the new energy vehicle battery is 1, it represents that the state of the new energy vehicle battery is good; if the output state of the new energy vehicle battery is 2, it represents that the state of the new energy vehicle battery is excellent.

[0104] Regarding the training of the neural network model:

[0105] Collect a large amount of relevant data on new energy vehicle batteries, including battery pack state factors (covering state of charge SOC, state of health SOH, internal resistance, etc. under different working conditions), equalization characteristics of individual batteries (temperature, current, voltage equalization-related data), and the actual state of the corresponding batteries (poor, good, excellent). At the same time, collect battery usage environment data (temperature, humidity, electric field strength) for subsequent analysis of its impact on the model.

[0106] Clean the collected data to remove outliers and incorrect data. For example, check whether the SOC and SOH values are within a reasonable range, and whether there are obvious measurement errors in the current and voltage data, etc.

[0107] Normalize the data to map data with different dimensions to the same scale. For example, normalize the values of SOC, SOH, etc. in the battery pack state factors to the interval [0, 1], which helps to improve the efficiency and stability of model training.

[0108] According to the characteristics of the problem and the nature of the data, select an appropriate neural network structure, such as a multi-layer perceptron (MLP). Determine the number of neurons in the input layer. For example, in this article, the battery pack state factors and the equalization characteristics of individual batteries are used as inputs, and the corresponding neurons may be set according to the specific number of indicators. For example, SOC, SOH, internal resistance, equalization characteristics of individual battery temperature, equalization characteristics of current, equalization characteristics of voltage, etc. may correspond to different input neurons.

[0109] Determine the number of hidden layers and the number of neurons in each layer. The optimal structure can be determined by experimenting with different structural combinations and evaluating the model performance using the validation set. Generally, start with a simple structure, such as 1 - 2 hidden layers, and the number of neurons in each layer is between the number of input neurons and the number of output neurons.

[0110] Determine that the number of neurons in the output layer is 1 because the final output is the battery state (0, 1, 2), and the output can be transformed into a probability distribution of the corresponding category through an appropriate activation function (such as the softmax function).

[0111] Select an appropriate loss function, such as the cross-entropy loss function, to measure the difference between the model output and the true labels (battery states). The cross-entropy loss function can handle multi-classification problems well and is suitable for classifying battery states in this case.

[0112] Determine the optimizer, such as Stochastic Gradient Descent (SGD), Adagrad, Adadelta, Adam, etc. These optimizers have different advantages in different scenarios. The Adam optimizer usually performs well in practice. It adaptively adjusts the learning rate and can converge faster during training. Set an appropriate learning rate. The initial learning rate can be tried between 0.001 - 0.1 and adjusted according to the change of loss during training. If the loss drops too slowly, the learning rate can be appropriately increased; if there are oscillations or non-convergence, the learning rate is decreased.

[0113] Set the number of training epochs. A relatively large value can be set first, such as 100 - 1000 epochs. However, during training, observe metrics such as the loss and accuracy of the validation set. When the performance of the model on the validation set no longer improves, stop training early to prevent overfitting. At the same time, set an appropriate batch size, such as 32, 64, 128, etc. A larger batch size can utilize the advantages of matrix operations to improve the training speed, but it may occupy more memory and needs to be selected according to hardware resources and data characteristics.

[0114] Divide the preprocessed data into training set, validation set, and test set, usually in the ratio of 70%, 15%, 15%. During training, each time take data from the training set according to the batch size and input it into the neural network. Perform forward propagation to calculate the output, and then calculate the loss according to the loss function. Update the parameters of the neural network through backpropagation of the optimizer.

[0115] After training a certain number of epochs (such as 10 epochs), evaluate the performance of the model on the validation set, calculate metrics such as accuracy, recall, F1 value, etc., and observe whether the model shows overfitting or underfitting. If the loss on the validation set continues to increase or the accuracy no longer improves, it may be necessary to adjust the model structure, training parameters, or increase the amount of data, etc.

[0116] After training is completed, use the test set to finally evaluate the model and obtain the performance metrics of the model in actual applications. If the model performance does not meet the expectations, further analyze the reasons, such as data quality, model structure complexity, training parameter settings, etc. Optimize and improve the model, such as adjusting the number of neurons in the hidden layer, changing the activation function, optimizing the data preprocessing method, etc., and then retrain and evaluate until the model performance meets the requirements.

[0117] The neural network model takes the battery pack state factor and the individual cell balancing characteristics as inputs. The battery pack state factor covers the overall performance indicators of the battery pack, while the individual cell balancing characteristics reflect the performance differences among the individual cells within the battery pack, including voltage balancing, current balancing, and temperature balancing, etc. Considering these two key factors comprehensively can fully characterize the actual condition of the battery and avoid the one-sidedness brought by evaluating the battery state relying on a single factor only.

[0118] The neural network has a powerful non-linear fitting ability. The relationship between the battery state and the battery pack state factor and the individual cell balancing characteristics is often non-linear. The neural network can fit this complex non-linear relationship by learning a large amount of data, so as to accurately judge the battery state and give a relatively reliable evaluation result whether under normal working conditions or extreme conditions.

[0119] The battery state is divided into three levels: poor (0), good (1), and excellent (2). This classification method is simple and intuitive, which is convenient for users and vehicle management systems to understand and operate.

[0120] The battery management error term analysis module is used to obtain the battery usage environment data of new energy vehicles, and based on the obtained battery usage environment data of new energy vehicles, the battery management error term of new energy vehicles is obtained.

[0121] The specific analysis process is as follows: Obtain the battery usage environment data of new energy vehicles. The battery usage environment data of new energy vehicles specifically includes the battery usage environment temperature, the battery usage environment humidity, and the battery usage environment electric field strength. Based on the obtained battery usage environment data of new energy vehicles, comprehensively analyze to obtain the battery management error term of new energy vehicles, and the battery management error term of new energy vehicles is used as the analysis basis for obtaining the battery management level of new energy vehicles.

[0122] For the battery management error term of new energy vehicles, the specific analysis process is as follows:

[0123]

[0124] In the formula, λ is the battery management error term of new energy vehicles, hw is the battery usage environment temperature, hs is the battery usage environment humidity, dcq is the battery usage environment electric field strength, θ1 is the compensation factor of the set hw, θ2 is the compensation factor of the set hs, and θ3 is the compensation factor of the set dcq.

[0125] By obtaining the new energy vehicle battery usage environment data, including factors such as battery usage environment temperature, humidity, and electric field strength, the battery management error term is calculated. These environmental factors have an important impact on battery performance and the accuracy of the battery management system. Temperature affects the chemical reaction rate of the battery, thereby affecting the charge and discharge performance of the battery; humidity may affect the insulation performance of the battery; electric field strength may interfere with the electronic components of the battery management system.

[0126] The battery management error term can be used as an analysis basis for obtaining the new energy vehicle battery management level. Accurate error term analysis helps to formulate reasonable battery management strategies. Under different environmental conditions, the performance and management requirements of the battery are different. Through the analysis of the battery management error term, the battery management system can dynamically adjust the management strategy according to the current environmental conditions. Precise battery management error term analysis helps to prevent excessive attenuation of battery performance and ensure battery safety.

[0127] The battery management update module is used to obtain the new energy vehicle battery management level and management plan based on the new energy vehicle battery state and the new energy vehicle battery management error term.

[0128] The specific analysis process is as follows: Store the new energy vehicle battery state and the new energy vehicle battery management error term as a specified label, obtain the pre-stored specified label - new energy vehicle battery management level mapping table in the database, and by looking up the mapping table, according to the specified label, find the matching new energy vehicle battery management level; obtain the pre-stored new energy vehicle battery management level - new energy vehicle battery management plan mapping table in the database, and by looking up the mapping table, according to the new energy vehicle battery management level, find the matching new energy vehicle battery management plan.

[0129] By storing the battery state and the battery management error term as a specified label and determining the management level and plan based on the pre-stored mapping table, the standardization of new energy vehicle battery management is realized. This standardization helps to adopt a unified management specification between different vehicles and different battery systems, avoiding chaos caused by inconsistent management methods. The pre-stored mapping table is constructed based on a large amount of experimental data and actual operation experience, and can accurately match the battery state, management error term with the appropriate management level and plan. This avoids the subjectivity and uncertainty that may occur in human judgment, ensures that the battery always operates under the best management strategy, and thus improves the performance and service life of the battery.

[0130] By accurately determining the management level and plan according to the battery state and management error term, the safety of the battery can be better guaranteed. When the battery management error term is large, indicating that the battery may be affected by adverse environmental factors, the corresponding management plan can be found in the mapping table in time, such as increasing the monitoring frequency, reducing the charging rate or strengthening the temperature monitoring, and replacing the battery if necessary, to prevent safety hazards such as overheating, overcharging and damage of the battery.

[0131] Referring to Figure 2 As shown, the second aspect of the present invention provides a new energy vehicle battery management method, including the following steps: analyzing the state of the new energy vehicle battery pack, and obtaining the new energy vehicle battery pack state factor based on the analysis result of the new energy vehicle battery pack state.

[0132] Analyzing the balance state of the new energy vehicle single battery to obtain the new energy vehicle single battery balance characteristic.

[0133] Combining the new energy vehicle battery pack state factor, the new energy vehicle single battery balance characteristic, and using a neural network model to output the new energy vehicle battery state.

[0134] Obtaining the new energy vehicle battery usage environment data, and obtaining the new energy vehicle battery management error term based on the obtained new energy vehicle battery usage environment data.

[0135] Based on the new energy vehicle battery state and the new energy vehicle battery management error term, obtaining the new energy vehicle battery management level and management plan.

[0136] The above content is only an example and illustration of the structure of the present invention. Those skilled in the art of this technology can make various modifications or supplements or use similar methods to replace the specific embodiments described, as long as they do not deviate from the structure of the invention or exceed the scope defined by this claims, they should all belong to the protection scope of the present invention.

Claims

1. A battery management system for a new energy vehicle, characterized in that, It includes a battery pack state analysis module, a single-cell balancing state analysis module, a battery state output module, a battery management error term analysis module, and a battery management update module, where: The battery pack state analysis module is used to analyze the state of the new energy vehicle battery pack, and based on the analysis result of the new energy vehicle battery pack state, obtain the new energy vehicle battery pack state factor; The single-cell balancing state analysis module is used to analyze the balancing state of the new energy vehicle single cells, and obtain the new energy vehicle single-cell balancing characteristics; The battery state output module is used to combine the new energy vehicle battery pack state factor and the new energy vehicle single-cell balancing characteristics, and use a neural network model to output the new energy vehicle battery state; The battery management error term analysis module is used to obtain the new energy vehicle battery usage environment data, and based on the obtained new energy vehicle battery usage environment data, obtain the new energy vehicle battery management error term; The battery management update module is used to obtain the new energy vehicle battery management level and management plan based on the new energy vehicle battery state and the new energy vehicle battery management error term.

2. The battery management system of a new energy vehicle according to claim 1, characterized in that: The analysis of the new energy vehicle battery pack state, the specific analysis process is as follows: Considering the capacity loss of the battery pack at different charge and discharge rates, introducing a rate correction coefficient, and obtaining an improved ampere-hour integration formula: Where SOC is the state of charge of the battery pack, SOC0 is the initial state of charge of the battery pack, C n is the rated capacity of the battery pack, I b (t) is the charging and discharging current of the battery pack at time t, K r is the rate correction coefficient stored in the database; Calculating the health status of the battery pack: where SOH is the health status of the battery pack, C a is the current actual available capacity of the battery pack, and A is the calendar aging factor stored in the database; Combining the Arrhenius equation to describe the relationship between the internal resistance growth of the battery pack and temperature, and constructing a battery pack internal resistance growth model: Wherein, R i is the internal resistance of the battery pack, R i0 is the initial internal resistance of the battery pack, β and γ are fitting parameters stored in the database, E a is the activation energy, R is the gas constant, T is the absolute temperature of the battery pack, E is the cumulative charge-discharge energy of the battery pack, and e is the natural constant.

3. The battery management system for a new energy vehicle according to claim 2, characterized in that: The obtaining of the new energy vehicle battery pack state factor based on the analysis result of the new energy vehicle battery pack state, the specific analysis process is as follows: Based on the state of charge of the battery pack, the health status of the battery pack, and the internal resistance of the battery pack, comprehensively analyze to obtain the new energy vehicle battery pack state factor, and the new energy vehicle battery pack state factor is used as the analysis basis for outputting the new energy vehicle battery state; In the formula, Dcz is the new energy vehicle battery pack state factor.

4. A new energy vehicle battery management system according to claim 1, characterized in that: The analysis of the new energy vehicle single-cell balancing state, obtaining the new energy vehicle single-cell balancing characteristics, the specific analysis process is as follows: Obtaining the temperature of each new energy vehicle single cell, and the maximum temperature difference WD of the new energy vehicle single cells is: Wherein, the temperature of the j-th single battery of the new energy vehicle is WD j and the temperature of the k-th single battery of the new energy vehicle is WD k , where j and k are the numbers of each single battery, and n is the total number of single batteries; Calculating the temperature balancing characteristics of the new energy vehicle single cells: In the formula, Wt is the temperature balancing characteristic of the new energy vehicle single cells, υ1 is the compensation factor of the set WD, and e is the natural constant; Obtaining the current of each new energy vehicle single cell, and the maximum current difference DL of the new energy vehicle single cells is: wherein, the current of the j-th single battery of the new energy vehicle is DL j , and the current of the k-th single battery of the new energy vehicle is DL k ; Calculating the current balancing characteristics of the new energy vehicle single cells: In the formula, Lt is the current balancing characteristic of the new energy vehicle single cells, and υ2 is the compensation factor of the set DL; Obtaining the voltage of each new energy vehicle single cell, and the maximum voltage difference DY of the new energy vehicle single cells is: wherein, the voltage of the j-th single battery of the new energy vehicle is DY j , and the voltage of the k-th single battery of the new energy vehicle is DY k ; Calculating the voltage balancing characteristics of the new energy vehicle single cells: In the formula, Yt is the voltage balancing characteristic of the new energy vehicle single cells, and υ3 is the compensation factor of the set DY; Based on the temperature balancing characteristic of the new energy vehicle single cells, the current balancing characteristic of the new energy vehicle single cells, and the voltage balancing characteristic of the new energy vehicle single cells, comprehensively analyze to obtain the new energy vehicle single-cell balancing characteristics. The balanced characteristics of individual batteries in new energy vehicles serve as the basis for analyzing the state of new energy vehicle batteries.

5. A new energy vehicle battery management system according to claim 4, characterized in that: The specific analysis process of the balanced characteristics of individual batteries in new energy vehicles is as follows: In the formula, Dtj represents the balanced characteristics of individual batteries in new energy vehicles.

6. The battery management system for a new energy vehicle according to claim 1, characterized in that: The specific analysis process of combining the state factor of the new energy vehicle battery pack, the balanced characteristics of individual batteries in new energy vehicles, and using a neural network model to output the state of the new energy vehicle battery is as follows: Based on the trained neural network model, input the state factor of the new energy vehicle battery pack and the balanced characteristics of individual batteries in new energy vehicles, and output the state of the new energy vehicle battery; If the output state of the new energy vehicle battery is 0, it means the state of the new energy vehicle battery is poor; If the output state of the new energy vehicle battery is 1, it means the state of the new energy vehicle battery is good; If the output state of the new energy vehicle battery is 2, it means the state of the new energy vehicle battery is excellent.

7. The battery management system for a new energy vehicle according to claim 1, wherein: The specific analysis process of obtaining the usage environment data of the new energy vehicle battery and obtaining the management error term of the new energy vehicle battery based on the obtained usage environment data of the new energy vehicle battery is as follows: Obtain the usage environment data of the new energy vehicle battery. The usage environment data of the new energy vehicle battery specifically includes the battery usage environment temperature, the battery usage environment humidity, and the battery usage environment electric field strength; Based on the obtained usage environment data of the new energy vehicle battery, comprehensively analyze to obtain the management error term of the new energy vehicle battery. The management error term of the new energy vehicle battery serves as the basis for analyzing the management level of the new energy vehicle battery.

8. A new energy vehicle battery management system according to claim 7, characterized in that: The specific analysis process of the management error term of the new energy vehicle battery is as follows: In the formula, λ is the management error term of the new energy vehicle battery, hw is the battery usage environment temperature, hs is the battery usage environment humidity, dcq is the battery usage environment electric field strength, θ1 is the compensation factor of the set hw, θ2 is the compensation factor of the set hs, and θ3 is the compensation factor of the set dcq.

9. A new energy vehicle battery management system according to claim 1, characterized in that: The specific analysis process of obtaining the management level and management plan of the new energy vehicle battery based on the state of the new energy vehicle battery and the management error term of the new energy vehicle battery is as follows: Store the state of the new energy vehicle battery and the management error term of the new energy vehicle battery as a specified label, obtain the pre-stored specified label - new energy vehicle battery management level mapping table in the database, and by looking up the mapping table, according to the specified label, find the matching new energy vehicle battery management level; Obtain the pre-stored new energy vehicle battery management level - new energy vehicle battery management plan mapping table in the database, and by looking up the mapping table, according to the new energy vehicle battery management level, find the matching new energy vehicle battery management plan.

10. A battery management method for a new energy vehicle, applied to a battery management system for a new energy vehicle according to any one of claims 1-9, characterized in that, It includes the following steps: Analyze the state of the new energy vehicle battery pack, and based on the analysis result of the state of the new energy vehicle battery pack, obtain the state factor of the new energy vehicle battery pack; Analyze the balanced state of individual batteries in new energy vehicles to obtain the balanced characteristics of individual batteries in new energy vehicles; Combine the state factor of the new energy vehicle battery pack, the balanced characteristics of individual batteries in new energy vehicles, and use a neural network model to output the state of the new energy vehicle battery; Obtain the usage environment data of new energy vehicle batteries, and based on the obtained usage environment data of new energy vehicle batteries, obtain the battery management error term of new energy vehicles; Based on the battery state of new energy vehicles and the battery management error term of new energy vehicles, obtain the battery management level and management plan of new energy vehicles.

Images