Automobile emergency starting power supply control system and method thereof

Abstract

The invention provides an automobile emergency starting power supply control system and a method thereof, and relates to the field of automobile power supply intelligent management.The method comprises the steps that firstly, voltage time sequence data of an automobile battery and a battery in an automobile emergency power supply are collected, and then the voltage time sequence data are transmitted to an MCU control module; and the MCU control module deeply analyzes the voltage time sequence data to obtain a corresponding control result, and performs charging operation on an internal battery of the automobile emergency power supply according to the control result. Therefore, real-time monitoring and intelligent management of the state of the battery in the automobile emergency power supply can be realized, the reliability and practicability of the automobile emergency power supply at a critical moment can be improved, and a powerful guarantee can be provided for normal operation of an automobile.

Description

Technical Field

[0001] The present application relates to the field of intelligent management of automobile power supplies, and more specifically, to an automobile emergency starting power supply control system and method thereof. Background Art

[0002] As modern cars become more electrified and intelligent, it is particularly important to ensure the stability and reliability of the vehicle battery system. Especially in cold weather or when the car is parked for a long time, the car battery may not be able to start the engine due to insufficient power. Therefore, the car emergency starting power supply, as a backup power solution, can provide the necessary power support at critical moments to ensure the normal operation of the vehicle.

[0003] Patent CN108288869B proposes an online emergency power supply control circuit and an online emergency power supply. Specifically, the MCU control module receives the start signal and controls the charge and discharge according to the data of the voltage detection module; the start module covers external device signals, remote control and voltage change trigger wake-up; the voltage detection module monitors the internal and external battery voltages to ensure automatic charging or auxiliary start-up when it is below the threshold; the power supply module ensures stable power for the MCU and other components; the charge and discharge control module manages the energy flow between the internal and external batteries to achieve charge and discharge management.

[0004] The judgment of automatically charging the internal battery or assisting in starting the car battery in this patent mainly relies on the real-time voltage information and preset threshold conditions provided by the voltage detection module. However, fixed voltage thresholds (such as 12.2 volts for the car battery and 10 volts for the internal battery) lack flexibility and cannot adapt to different usage scenarios or environmental changes. For example, at extreme temperatures, the optimal operating voltage of the battery may be significantly different from that at normal temperature conditions, but the fixed threshold cannot be automatically adjusted to cope with these changes, which may lead to improper charging and discharging timing, affecting performance and life. In addition, systems based on fixed thresholds can only respond after a problem occurs, and cannot provide early warning of potential failures, which limits the ability of preventive maintenance and increases the risk of sudden failures.

[0005] Therefore, an optimized automobile emergency starting power supply control solution is desired, which can improve the overall reliability of the system by dynamically optimizing by utilizing real-time data. Summary of the invention

[0006] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a vehicle emergency starting power supply control system and method thereof.

[0007] According to one aspect of the present application, a vehicle emergency starting power supply control system is provided, which includes: a voltage detection module, which is used to collect vehicle battery voltage timing data and internal battery voltage timing data of the vehicle emergency power supply; a data transmission module, which is used to transmit the vehicle battery voltage timing data and the internal battery voltage timing data of the vehicle emergency power supply to an MCU control module; the MCU control module is used to analyze the vehicle battery voltage timing data and the internal battery voltage timing data of the vehicle emergency power supply to obtain a control result; a charge and discharge control module is used to determine whether to charge the internal battery of the vehicle emergency power supply based on the control result; wherein the MCU control module includes:

[0008] A battery voltage timing analysis unit, used for recursively processing the vehicle battery voltage timing data and the internal battery voltage timing data of the vehicle emergency power supply and extracting spatial domain features to obtain vehicle battery voltage timing spatial domain features and internal battery voltage timing spatial domain features;

[0009] A car battery-internal voltage interaction unit, used for performing fine-grained spatial domain interaction encoding on the car battery voltage temporal spatial domain features and the internal battery voltage temporal spatial domain features to obtain a car battery-internal battery voltage temporal spatial domain semantic interaction encoding feature;

[0010] The control result generating unit is used to obtain the control result based on the semantic interaction coding feature of the automobile battery-internal battery voltage time series space domain, and control the charge and discharge control module based on the control result.

[0011] According to another aspect of the present application, a method for controlling an automobile emergency starting power supply is provided, which is used to execute the automobile emergency starting power supply control system as described above, and comprises:

[0012] Recursively processing the automobile battery voltage time series data and the internal battery voltage time series data of the automobile emergency power supply and extracting spatial domain features to obtain automobile battery voltage time series spatial domain features and internal battery voltage time series spatial domain features;

[0013] Performing fine-grained spatial domain interaction coding on the automotive battery voltage temporal spatial domain features and the internal battery voltage temporal spatial domain features to obtain automotive battery-internal battery voltage temporal spatial domain semantic interaction coding features;

[0014] Based on the semantic interaction coding characteristics of the automobile battery-internal battery voltage time series space domain, a control result is obtained, and based on the control result, the charge and discharge control module is controlled.

[0015] Compared with the prior art, the automobile emergency starting power supply control system and method provided by the present application first collects the voltage timing data of the automobile battery and the internal battery of the automobile emergency power supply, and then transmits these voltage timing data to the MCU control module, where the MCU control module conducts in-depth analysis of these voltage timing data to obtain corresponding control results, and based on this control result, performs charging or discharging operations on the automobile battery or the internal battery of the automobile emergency power supply. In this way, real-time monitoring and intelligent management of the status of the automobile battery and the internal battery of the automobile emergency power supply can be achieved, which is conducive to improving the reliability and practicality of the automobile emergency power supply at critical moments, and thus can provide strong guarantee for the normal operation of the automobile. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0017] Figure 1 The system block diagram of the automobile emergency starting power supply control system according to an embodiment of the present application.

[0018] Figure 2 The present invention is a block diagram of an MCU control module in an automobile emergency starting power supply control system according to an embodiment of the present application.

[0019] Figure 3 The present invention is a block diagram of a battery voltage timing analysis unit in an automobile emergency starting power supply control system according to an embodiment of the present application.

[0020] Figure 4 The block diagram is a car battery-internal voltage interaction unit in a car emergency starting power control system according to an embodiment of the present application.

[0021] Figure 5 The present invention is a block diagram of a control result generating unit in an automobile emergency starting power supply control system according to an embodiment of the present application.

[0022] Figure 6 The figure is a flow chart of a method for controlling an automobile emergency starting power supply according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0024] With the continuous improvement of the electrification and intelligence level of modern automobiles, the stability and reliability of vehicle battery systems are becoming more and more critical, especially in cold climates or long-term parking situations, the problem of battery exhaustion causing the engine to fail to start is particularly prominent. For this reason, the automotive emergency starting power supply, as an effective backup power solution, can provide the necessary power support for the vehicle in an emergency and ensure smooth operation of the vehicle.

[0025] Patent CN108288869B proposes an online emergency power supply control circuit and an online emergency power supply. Specifically, the MCU control module receives the start signal and accurately controls the charge and discharge according to the data of the voltage detection module. The start module integrates external device signals, remote control and voltage change trigger wake-up functions; the voltage detection module is responsible for monitoring the internal and external battery voltages to ensure automatic charging or auxiliary starting when the voltage is lower than the preset threshold; the power supply module provides stable power guarantee for the MCU and other components; the charge and discharge control module is responsible for the energy flow management between the internal and external batteries.

[0026] However, the patent uses a fixed voltage threshold (such as 12.2 volts for the car battery and 10 volts for the internal battery) to determine whether to automatically charge the internal battery or assist in starting the car battery. This method lacks flexibility and is difficult to adapt to different usage scenarios or environmental changes. Under extreme temperature conditions, the optimal operating voltage of the battery may be significantly different from that at normal temperature, but the fixed threshold cannot be adjusted automatically, which may lead to improper charging and discharging timing and have an adverse effect on the performance and life of the battery. In addition, the system based on fixed thresholds can only respond after the fact and cannot warn of potential failures in advance, thereby limiting the effectiveness of preventive maintenance and increasing the risk of sudden failures.

[0027] Based on this, the present application proposes an automobile emergency starting power supply control system. Figure 1 FIG. 1 is a system block diagram of a vehicle emergency starting power supply control system according to an embodiment of the present application. Figure 1 As shown, in the automobile emergency starting power supply control system 100, it includes: a voltage detection module 110, which is used to collect the automobile battery voltage timing data and the internal battery voltage timing data of the automobile emergency power supply; a data transmission module 120, which is used to transmit the automobile battery voltage timing data and the internal battery voltage timing data of the automobile emergency power supply to the MCU control module; the MCU control module 130, which is used to analyze the automobile battery voltage timing data and the internal battery voltage timing data of the automobile emergency power supply to obtain a control result; and a charge and discharge control module 140, which is used to determine whether to charge the internal battery of the automobile emergency power supply based on the control result.

[0028] In the embodiment of the present application, the voltage detection module 110 is used to collect the automobile battery voltage timing data and the internal battery voltage timing data of the automobile emergency power supply. It should be understood that the automobile battery voltage timing data is a data sequence reflecting the voltage change of the automobile battery over a period of time. It can reflect the voltage fluctuation of the automobile battery under different working conditions (such as starting, driving, parking, etc.), and can provide basic information for the subsequent analysis of the performance status of the automobile battery. The internal battery voltage timing data of the automobile emergency power supply is similar to the automobile battery voltage timing data, which is the voltage change sequence of the internal battery in the corresponding time period. By collecting these data, the charging history of the internal battery, the trend of the remaining power change, and whether there are potential performance problems can be understood, which is an indispensable part of the comprehensive evaluation of the status of the automobile emergency power supply system. In general, the automobile battery is the main source of power for the normal operation of the vehicle, and the internal battery of the emergency power supply is a backup guarantee when there is a problem with the automobile battery. Obtaining the voltage timing data of both can monitor the operating status of the entire battery system in real time, ensuring that the power supply of the vehicle can be clearly understood at any time. For example, during long-distance driving, by continuously monitoring the vehicle battery voltage timing data, it is possible to promptly detect whether the battery power is sufficient to support the remaining journey. If the power is insufficient, charging can be planned in advance or the emergency power supply can be used to supplement the power. At the same time, the voltage timing data of the battery inside the emergency power supply can also reflect its own readiness status, ensuring that it can be put into reliable use when needed.

[0029] The specific implementation process of collecting the vehicle battery voltage time series data and the vehicle emergency power supply internal battery voltage time series data involves many aspects of careful design and operation to ensure the accuracy, completeness and effectiveness of the data, thereby providing a solid foundation for the stable operation of the entire system. The following is a detailed description of its implementation process:

[0030] First of all, the selection and connection of hardware equipment is crucial. For car batteries and internal batteries of emergency power supplies, suitable voltage sensors must be carefully selected. These sensors must not only have high precision, high sensitivity and excellent stability, but also be perfectly compatible with battery characteristics and automotive electrical systems. For example, for car batteries, sensors with a measurement range of 0-16V and an accuracy of ±0.05V may be selected. Their high input impedance can avoid excessive consumption of battery power and ensure that the accuracy of measurement and battery performance are not affected. In the connection process, the sensor must be closely connected to the positive and negative poles of the battery in strict accordance with the correct polarity to ensure a firm connection and extremely low contact resistance. At the same time, protective measures such as series fuses should be taken to prevent short-circuit abnormalities. For the internal battery of the emergency power supply, it is also necessary to ensure that the sensor is connected correctly and the wiring is reasonable to avoid electromagnetic interference. The collected voltage signal is transmitted to the subsequent data acquisition circuit or equipment through high-quality wires.

[0031] At the same time, the reasonable configuration of data acquisition equipment is indispensable. A microcontroller or dedicated data acquisition card with sufficient sampling accuracy (at least 12 bits) and speed (more than 1000 times per second) must be selected to receive and process the analog signal from the voltage sensor. During the initial configuration process, the sampling parameters must be accurately set, such as setting the sampling frequency to 500 times per second initially, and flexibly adjusting it according to actual needs. At the same time, a high-speed serial communication interface (such as SPI or I2C interface) must be configured to ensure that data can be quickly transmitted to the MCU control module.

[0032] In the process of data collection, strict data verification and preprocessing algorithms must also be incorporated. By setting a reasonable voltage range threshold, the validity of the collected data can be checked and abnormal data (such as data that exceeds the normal working voltage range) can be identified in a timely manner. These abnormalities may be caused by factors such as sensor failure or interference. For abnormal data, interpolation correction or direct abandonment can be performed based on the trend of the previous and subsequent data, and the abnormal situation can be recorded in detail to provide a basis for subsequent in-depth analysis. At the same time, the collected data is preprocessed by filtering and other means to effectively remove noise interference and significantly improve the accuracy and smoothness of the data.

[0033] Finally, it is crucial to reasonably determine the time and frequency of data collection to fully and accurately grasp the battery status. At each stage of the vehicle's operation, carefully plan the data collection time according to different working conditions. At the moment of vehicle startup, the battery load suddenly changes, causing the voltage to change sharply. At this time, focus on collecting the data before and after, which will help to deeply analyze the battery's startup performance and health status; during driving, regularly collect data (such as every 1 minute) to monitor the discharge characteristics and remaining power change trends during normal operation of the battery; continue to collect data for a period of time after parking to observe the battery's self-discharge. In addition, dynamically adjust the acquisition frequency according to the battery's working status and system requirements. In the stage of drastic voltage changes (such as startup or fast charging), increase the acquisition frequency to 1000 times per second to accurately capture the details of dynamic changes; in the relatively stable voltage state (such as long-term parking or stable driving), appropriately reduce it to 100 times per second, while ensuring monitoring needs while optimizing system resource utilization and data storage capacity.

[0034] Through the above comprehensive and detailed implementation process, reliable voltage timing data of the car battery and the internal battery of the emergency power supply can be collected.

[0035] In an embodiment of the present application, the data transmission module 120 is used to transmit the automobile battery voltage timing data and the internal battery voltage timing data of the automobile emergency power supply to the MCU control module. It should be understood that the states of the two batteries, the automobile battery and the internal battery of the emergency power supply, are interrelated and jointly affect the power supply of the vehicle. The automobile emergency starting power supply control system needs to accurately manage the states of these two batteries to ensure that reliable power support can be provided to the vehicle under various circumstances. Therefore, in this application, it is necessary to transmit the automobile battery voltage timing data and the internal battery voltage timing data to the MCU control module so that all key data can be concentrated in a core control module for processing, and then the states of the automobile battery and the internal battery of the emergency power supply can be more accurately grasped, which is conducive to the intelligent management of different batteries to better serve the actual power demand of the automobile.

[0036] In the embodiment of the present application, the MCU control module 130 is used to analyze the vehicle battery voltage timing data and the internal battery voltage timing data of the vehicle emergency power supply to obtain a control result.

[0037] Correspondingly, in the MCU control module, the technical concept of the present application is to use a data analysis and processing algorithm based on deep learning to recursively process the automotive battery voltage timing data and the internal battery voltage timing data of the automotive emergency power supply and extract spatial domain features, so as to intelligently judge whether to charge the internal battery of the automotive emergency power supply and control the charge and discharge control module based on the fine-grained spatial semantic interaction representation between the automotive battery voltage timing spatial domain features and the internal battery voltage timing spatial domain features. In this way, it is possible to capture subtle patterns and trends in voltage changes, and dynamically adjust the charging strategy to ensure optimal performance in various usage scenarios. This not only enhances the flexibility of the system, but also solves the problem that the fixed threshold method cannot cope with environmental changes, thereby effectively protecting battery performance and extending its service life.

[0038] Specifically, Figure 2 FIG. 1 is a block diagram of an MCU control module in an automobile emergency starting power supply control system according to an embodiment of the present application. Figure 2As shown, the MCU control module 130 includes: a battery voltage timing analysis unit 131, which is used to recursively process the automobile battery voltage timing data and the internal battery voltage timing data of the automobile emergency power supply and extract spatial domain features to obtain automobile battery voltage timing spatial domain features and internal battery voltage timing spatial domain features; an automobile battery-internal voltage interaction unit 132, which is used to perform fine-grained spatial domain interaction encoding on the automobile battery voltage timing spatial domain features and the internal battery voltage timing spatial domain features to obtain automobile battery-internal battery voltage timing spatial domain semantic interaction encoding features; a control result generation unit 133, which is used to obtain a control result based on the automobile battery-internal battery voltage timing spatial domain semantic interaction encoding features, and control the charge and discharge control module based on the control result.

[0039] In the embodiment of the present application, the battery voltage timing analysis unit 131 is used to recursively process the vehicle battery voltage timing data and the internal battery voltage timing data of the vehicle emergency power supply and extract spatial domain features to obtain the vehicle battery voltage timing spatial domain features and the internal battery voltage timing spatial domain features. Specifically, Figure 3 FIG. 1 is a block diagram of a battery voltage timing analysis unit in an automobile emergency starting power supply control system according to an embodiment of the present application. Figure 3 As shown, the battery voltage timing analysis unit 131 includes: a battery voltage timing data recursive graph calculation subunit 1311, which is used to respectively calculate the recursive graphs of the vehicle battery voltage timing data and the internal battery voltage timing data of the vehicle emergency power supply to obtain a vehicle battery voltage timing recursive graph and an internal battery voltage timing recursive graph; a battery voltage timing spatial domain feature extraction subunit 1312, which is used to pass the vehicle battery voltage timing recursive graph and the internal battery voltage timing recursive graph through a voltage timing spatial domain feature extractor based on MCNN to obtain a vehicle battery voltage timing spatial domain feature graph as the vehicle battery voltage timing spatial domain feature and an internal battery voltage timing spatial domain feature graph as the internal battery voltage timing spatial domain feature.

[0040] In an embodiment of the present application, the battery voltage timing data recursive graph calculation subunit 1311 is used to calculate the recursive graphs of the vehicle battery voltage timing data and the internal battery voltage timing data of the vehicle emergency power supply to obtain the vehicle battery voltage timing recursive graph and the internal battery voltage timing recursive graph. It should be understood that the internal battery of the vehicle battery and the emergency power supply may exhibit complex nonlinear dynamic characteristics, such as voltage fluctuations or abnormal patterns. Therefore, in order to gain a deeper understanding of the timing coding trend of the battery over time, to reveal the subtle changes and dynamic characteristics of the battery behavior, and to better understand the timing dynamic behavior of the battery, in the technical solution of the present application, the recursive graphs of the vehicle battery voltage timing data and the internal battery voltage timing data of the vehicle emergency power supply are calculated to obtain the vehicle battery voltage timing recursive graph and the internal battery voltage timing recursive graph. It can be understood that the recursive graph is a technique for analyzing time series data, which visualizes the repeatability of the system state by comparing the points in the time series with its own state at different time points. Specifically, the recursive graph shows the similarity between the state at a certain time point t and the state at another time point s. If two states are very close, a point is marked at the corresponding position in the graph; otherwise, no mark is made. This graphical representation method can reveal the hidden patterns and structures inside the time series data, including periodicity and chaotic behavior. In this way, the dynamic characteristics of the battery and the complex internal pattern changes can be more accurately identified.

[0041] In the automobile emergency starting power supply control system, calculating the recursive graph of the battery voltage time series data of the automobile battery and the emergency power supply is a complex and critical task. Its specific implementation process involves many aspects of theoretical knowledge and technical operations. It aims to obtain recursive graph information that can accurately reflect the battery status through in-depth analysis of the dynamic characteristics of the voltage time series data, so as to provide strong support for subsequent system control and decision-making. The following is a detailed description of its implementation process:

[0042] The core of recursive graph calculation lies in state space reconstruction and similarity judgment. First of all, for the voltage time series data of the car battery and the internal battery of the emergency power supply, accurately selecting the appropriate time delay parameter p and embedding dimension m is a crucial starting step. There are various methods to determine the time delay p, among which the autocorrelation function method is one of the commonly used methods. Taking the car battery voltage time series data as an example, by calculating the autocorrelation function, observe the change of the function value with time delay. When the autocorrelation function value drops to close to 0 for the first time, it indicates that the correlation between the data points is low at this time, and the corresponding time delay is a more appropriate p value. In actual analysis, it may be found that when p = 5 (unit: sampling interval), the autocorrelation function of the car battery voltage time series data presents this feature, thereby determining the value of p.

[0043] The selection of embedding dimension m is usually done with the help of technical means such as the false nearest neighbor method. For the internal battery voltage time series data of the emergency power supply, the false nearest neighbor method is used for calculation. Under different embedding dimension values, the change in the false nearest neighbor ratio is observed. When the false nearest neighbor ratio is significantly reduced, it indicates that the embedding dimension selected at this time can better capture the intrinsic structure of the data. After careful calculation and analysis, it can be determined that when m=7, the intrinsic structure of the internal battery voltage time series data of the emergency power supply can be presented more accurately.

[0044] After determining p and m, the voltage time series data is reconstructed in state space. Taking the automobile battery voltage time series data as V(t), the reconstructed vector sequence can be expressed as This process converts the one-dimensional voltage time series data into a multi-dimensional vector sequence, thus laying the foundation for the subsequent recursive graph calculation.

[0045] When constructing a recursive graph, a suitable threshold ε is set to determine the similarity between two state vectors. The selection of the threshold is usually related to the statistical characteristics of the data. For example, the threshold ε can be taken as 0.5×standard deviation (car battery voltage time series data). Calculate the value of any two vectors and The distance between them is generally calculated using the Euclidean distance formula. ij and the threshold ε, construct the vehicle battery voltage timing recursive diagram. ij <ε, the corresponding position in the recursive graph is marked as 1, indicating that the two states are similar; otherwise, it is marked as 0, indicating that they are not similar. The same calculation process is applied to the internal battery voltage timing data of the emergency power supply, thereby obtaining the internal battery voltage timing recursive graph.

[0046] The above calculation process requires the help of efficient algorithms and tools. In terms of algorithm selection, fast nearest neighbor search algorithms (such as kd tree algorithm or ball tree algorithm) can significantly improve the calculation efficiency, especially for processing large-scale voltage time series data. Taking the kd tree algorithm as an example, its core principle is to reasonably divide the data space and organize the data into a tree structure. During the calculation process, when it is necessary to search for the nearest neighbor point, the area where the target point is located can be quickly located according to the tree structure, thereby greatly reducing the calculation complexity. When applying the kd tree algorithm, the algorithm parameters are further optimized according to the characteristics of the battery voltage time series data of the vehicle battery and the emergency power supply. For example, if the vehicle battery voltage time series data fluctuates greatly, when selecting the segmentation dimension in the kd tree algorithm, the dimension with large data changes is given priority for segmentation, which can more effectively narrow the search range and improve the search efficiency.

[0047] In terms of programming implementation, programming languages ​​(such as Python, C++, etc.) can be used to implement the recursive graph calculation algorithm. Taking Python as an example, its rich scientific computing libraries (such as NumPy, SciPy, etc.) provide strong support for the calculation process. NumPy's array operation function can easily process voltage time series data and implement operations such as vector calculation; SciPy's spatial search module can be used to implement a fast nearest neighbor search algorithm, simplifying the complexity of programming. At the same time, with the help of professional data processing and analysis tools (MATLAB), the calculation results can be visualized and verified. MATLAB provides a wealth of drawing functions that can intuitively draw the recursive graph of the car battery and internal battery voltage time series. By observing the structure and characteristics of the recursive graph, the rationality of the calculation results can be preliminarily judged. In addition, MATLAB's built-in statistical analysis tools can also be used to deeply verify and analyze the calculation results to ensure the accuracy of the calculation.

[0048] In the actual calculation process, parameter adjustment and optimization are the key links to improve the calculation quality of recursion graphs. Sensitivity analysis of parameters such as time delay, embedding dimension and threshold is an essential step. By changing the parameter values ​​and carefully observing the structural changes of the recursion graph, the optimal range of parameter values ​​can be determined. Taking the automotive battery voltage time series data as an example, when p changes between 3-7, the periodic structure of the recursion graph will change significantly. After in-depth analysis, it is found that when p=5, the main periodic characteristics of the battery voltage can be clearly displayed. For the embedding dimension m, when m changes between 5-9, the recursion graph has different levels of detail in describing the dynamic characteristics of the system. After comparative studies, when m=7 is determined, the intrinsic structure of the data can be better captured without excessively increasing the computational complexity.

[0049] In addition to sensitivity analysis, it is also necessary to formulate an adaptive parameter adjustment strategy based on the working state and environmental changes of the battery. The electrochemical characteristics of automotive batteries will change at different working temperatures, which will in turn affect the voltage change law. When the temperature rises, the battery voltage fluctuation may intensify. At this time, the threshold can be appropriately reduced to more sensitively capture the similarity structure in the voltage change. At the same time, the time delay is dynamically adjusted according to the frequency of voltage change to ensure that the reconstructed state space can accurately reflect the dynamic characteristics of the battery. In order to achieve more accurate parameter optimization, historical data and real-time monitoring data can also be combined to establish a parameter optimization model. The parameters are automatically optimized through machine learning algorithms (such as neural networks, support vector machines, etc.). The model is trained with historical data to enable the model to learn the optimal value law of parameters under different working conditions. Then, the model is input according to the real-time monitoring data to obtain the optimal parameter value under the current situation, thereby realizing the adaptive adjustment of the parameters, further improving the accuracy and effectiveness of the recursive graph calculation, and providing more reliable guarantee for the stable operation of the automotive emergency starting power control system.

[0050] In an embodiment of the present application, the battery voltage time series space domain feature extraction subunit 1312 is used to obtain the automobile battery voltage time series space domain feature diagram as the automobile battery voltage time series space domain feature and the internal battery voltage time series space domain feature diagram as the internal battery voltage time series space domain feature through the voltage time series space domain feature extractor based on MCNN. Accordingly, considering that the automobile battery voltage time series recursion diagram and the internal battery voltage time series recursion diagram contain spatial feature information, such as the diagonal structure in the recursion diagram usually indicates the periodic behavior of the system, which may correspond to charging cycles or other periodic events; disordered or randomly distributed points may indicate that the system is in a chaotic state or experiencing abnormal conditions, and this non-periodicity may be due to voltage changes caused by factors such as temperature fluctuations and load changes. Based on this, in the technical solution of the present application, the automotive battery voltage timing recursive graph and the internal battery voltage timing recursive graph are extracted through a voltage timing spatial domain feature extractor based on MCNN to utilize the powerful pattern recognition ability of MCNN to more accurately capture subtle changes and long-term spatial temporal dependencies from complex voltage timing data, and obtain the automotive battery voltage timing spatial domain feature graph and the internal battery voltage timing spatial domain feature graph. In particular, MCNN (multi-channel convolutional neural network) is a deep learning model specially designed for processing multidimensional data. It extends the traditional convolutional neural network (CNN) by introducing multiple input channels to simultaneously process data of different types or sources. Each channel can be regarded as an independent feature map, allowing the network to capture information in the input data from different angles. In this way, different channels can be used to optimize for specific types of features, for example, one channel focuses on capturing and mining the periodic timing pattern of the battery, and the other channel focuses on the non-periodic changes in the battery state, such as continuous fluctuations in the short term, thereby improving the understanding and analysis of the local spatial structure and temporal correlation in the recursive graph.

[0051] In the embodiment of the present application, the vehicle battery-internal voltage interaction unit 132 is used to perform fine-grained spatial domain interaction encoding on the vehicle battery voltage temporal spatial domain features and the internal battery voltage temporal spatial domain features to obtain the vehicle battery-internal battery voltage temporal spatial domain semantic interaction encoding features. Specifically, Figure 4 FIG. 1 is a block diagram of a vehicle battery-internal voltage interaction unit in a vehicle emergency starting power supply control system according to an embodiment of the present application. Figure 4As shown, the vehicle battery-internal voltage interaction unit 132 includes: a battery voltage shared feature interaction subunit 1321, which is used to perform feature decomposition on the vehicle battery voltage time series spatial domain feature graph and the internal battery voltage time series spatial domain feature graph, and calculate the shared semantic features between the decomposed vehicle battery voltage time series local spatial domain semantic feature matrix set and the internal battery voltage time series local spatial domain semantic feature matrix set to obtain a vehicle battery-internal battery voltage fine-grained local shared semantic feature matrix set; a battery voltage semantic compensation text subunit 1322, which is used to calculate the vehicle battery-internal battery voltage fine-grained local shared semantic feature matrix set. The semantic compensation text features of each automobile battery-internal battery voltage fine-grained local shared semantic feature matrix in the set of local shared semantic feature matrices are used to obtain a set of automobile battery-internal battery voltage semantic compensation text feature matrices; a battery voltage feature aggregation subunit 1323 is used to perform weighted aggregation on the set of automobile battery-internal battery voltage fine-grained local shared semantic feature matrices based on the set of automobile battery-internal battery voltage semantic compensation text feature matrices to obtain a automobile battery-internal battery voltage time-space domain semantic interaction coding feature map as the automobile battery-internal battery voltage time-space domain semantic interaction coding feature.

[0052] It should be understood that the automotive battery voltage time series spatial domain features and the internal battery voltage time series spatial domain features show complex nonlinear dynamic characteristics in different time periods, and there is also shared semantic information between the two. Therefore, in order to be able to explore the interaction between the automotive battery and the internal battery of the emergency power supply at a deeper level and capture the complex dynamic relationship between the two, in the technical solution of the present application, the automotive battery voltage time series spatial domain features and the internal battery voltage time series spatial domain features are fine-grained spatial domain interaction encoded to obtain automotive battery-internal battery voltage time series spatial domain semantic interaction encoding features. In particular, the purpose of the fine-grained spatial domain interaction encoding is to fine-tune the feature interaction process through prompt learning, thereby utilizing the prior knowledge of large models to perform detailed semantic enhancement on feature interactions, thereby producing richer and more accurate feature expressions.

[0053] Specifically, in the embodiment of the present application, the battery voltage shared feature interaction subunit is used to: perform feature decomposition on the vehicle battery voltage time series space domain feature graph and the internal battery voltage time series space domain feature graph along the channel dimension of the vehicle battery voltage time series space domain feature graph and the internal battery voltage time series space domain feature graph to obtain a set of the vehicle battery voltage time series local space domain semantic feature matrices and a set of the internal battery voltage time series local space domain semantic feature matrices. The process can be expressed as:

[0054] Decouple(F1)={F11 ,F 12 ,...,F 1i ,...,F 1n}

[0055] Decouple(F2)={F 21 ,F 22 ,...,F 2i ,...,F 2n}

[0056] Among them, F1 and F2 are the time series spatial domain feature graph of the vehicle battery voltage and the time series spatial domain feature graph of the internal battery voltage, respectively. Decouple(·) is a feature decomposition operation on the feature graph. 11 , F 12 , F 1i and F 1n are the first, second, i-th and n-th automobile battery voltage time series local space domain semantic feature matrices in the set of automobile battery voltage time series local space domain semantic feature matrices, F 21 , F 22 , F 2i and F 2n They are the first, second, i-th and n-th internal battery voltage time series local space domain semantic feature matrices in the set of internal battery voltage time series local space domain semantic feature matrices;

[0057] For each set of corresponding channel dimensions of the automobile battery voltage time series local space domain semantic feature matrix and the internal battery voltage time series local space domain semantic feature matrix in the set of the automobile battery voltage time series local space domain semantic feature matrix and the internal battery voltage time series local space domain semantic feature matrix, a twin structure shared semantic feature extraction is performed to obtain the set of the automobile battery-internal battery voltage fine-grained local shared semantic feature matrix. The process can be expressed as:

[0058]

[0059] Among them, F 1i is the i-th car battery voltage time series local space domain semantic feature matrix in the set of car battery voltage time series local space domain semantic feature matrices, F 2i is the i-th internal battery voltage time series local space domain semantic feature matrix in the set of internal battery voltage time series local space domain semantic feature matrices, ⊙ and They are point-by-point addition, point-by-point multiplication, and point-by-point subtraction. Concat(·;·;·) is cascade processing. Cov 1×1 (·) is the point convolutional coding, sigmoid(·) is the sigmoid function, Si Yes F 1i and F 2i The car battery-internal battery voltage fine-grained local shared semantic feature matrix.

[0060] It should be understood that the automotive battery voltage time series spatial domain feature map and the internal battery voltage time series spatial domain feature map contain rich and complex information, which reflects the status of the battery voltage from different angles. By performing feature decomposition on these two feature maps along the channel dimension, the various types of information originally integrated in the feature map can be separated according to the different abstract levels corresponding to the channels, thereby mining out the more detailed and targeted feature information about the battery voltage hidden therein, so as to understand the battery voltage characteristics more comprehensively and deeply, and this feature decomposition method can also provide a basis for subsequent fine-grained analysis. Next, the shared semantic features of the automotive battery voltage time series local spatial domain semantic feature matrix and the internal battery voltage time series local spatial domain semantic feature matrix corresponding to the channel dimension in each set of the automotive battery voltage time series local spatial domain semantic feature matrix and the internal battery voltage time series local spatial domain semantic feature matrix are extracted with twin structures to find out the shared semantic information between the automotive battery voltage and the internal battery voltage local feature matrix under each set of the corresponding channel dimension in the two sets, that is, to mine the common features between them. By clarifying these common characteristics, we can have a deeper understanding of the common characteristics of the vehicle battery and the internal battery in the same dimension in terms of voltage performance, which can provide key basis for subsequent understanding of the internal battery status and determining whether the internal battery needs to be charged.

[0061] Specifically, in the embodiment of the present application, the battery voltage semantic compensation text subunit is used to: perform semantic compensation decoding based on a large language on each of the automobile battery-internal battery voltage fine-grained local shared semantic feature matrices in the set of the automobile battery-internal battery voltage fine-grained local shared semantic feature matrices to obtain a set of automobile battery-internal battery voltage semantic compensation text descriptions. This process can be expressed as:

[0062] T i =LLM{S i}

[0063] Among them, S i Yes F 1i and F 2i The car battery-internal battery voltage fine-grained local shared semantic feature matrix between them, LLM is the semantic compensation decoding operation, T i For S i Corresponding car battery-internal battery voltage semantic compensation text description;

[0064] Each automobile battery-internal battery voltage semantic compensation text description in the set of automobile battery-internal battery voltage semantic compensation text description is subjected to text convolution semantic encoding to obtain a set of automobile battery-internal battery voltage semantic compensation text feature matrices. This process can be expressed as:

[0065] M i =TextCNN{T i}

[0066] Among them, T i For S i Corresponding car battery-internal battery voltage semantic compensation text description, TextCNN is text convolutional coding, M i For S i Corresponding car battery-internal battery voltage semantic compensation text feature matrix.

[0067] It should be understood that by performing semantic compensation decoding based on the big language for each of the car battery-internal battery voltage fine-grained local shared semantic feature matrices in the set of the car battery-internal battery voltage fine-grained local shared semantic feature matrices, the powerful language understanding and generation capabilities of the big language model can be used to generate corresponding semantic representations based on the feature information in the car battery-internal battery voltage fine-grained local shared semantic feature matrix, which is conducive to increasing the interpretability and comprehensibility of the input features. At the same time, the big language model can also use its own stored knowledge to supplement the input information and enhance the semantic richness of the features, which helps to have a more comprehensive understanding of the relationship between the car battery and the internal battery voltage, their respective state performance, etc. Next, text convolution semantic encoding is performed on each vehicle battery-internal battery voltage semantic compensation text description in the set of the vehicle battery-internal battery voltage semantic compensation text description to achieve semantic feature alignment of each vehicle battery-internal battery voltage semantic compensation text description. This can make it more convenient to subsequently apply the semantic compensation information contained in the vehicle battery-internal battery voltage semantic compensation text description to the obtained vehicle battery-internal battery voltage fine-grained local shared semantic feature matrix, thereby further expanding and deepening the understanding of the battery voltage status.

[0068] Specifically, in the embodiment of the present application, the battery voltage feature aggregation subunit is used to: perform fine-grained semantic interaction compensation on each corresponding group of automobile battery-internal battery voltage fine-grained local shared semantic feature matrices and automobile battery-internal battery voltage semantic compensation text feature matrices in the set of the automobile battery-internal battery voltage fine-grained local shared semantic feature matrices and the set of the automobile battery-internal battery voltage semantic compensation text feature matrices to obtain a set of automobile battery-internal battery voltage local interaction fine-grained semantic reinforcement feature matrices. The process can be expressed as:

[0069]

[0070] Among them, S i Yes F 1i and F 2i The car battery-internal battery voltage fine-grained local shared semantic feature matrix, M i T M i The transposed matrix of For matrix multiplication, D is the i The scale is the matrix width multiplied by the matrix height, softmax(·) is the softmax function, α and β are weighting coefficients, S bi is the i-th automobile battery-internal battery voltage local interaction fine-grained semantic reinforcement feature matrix in the set of automobile battery-internal battery voltage local interaction fine-grained semantic reinforcement feature matrices;

[0071] The set of the fine-grained semantic reinforcement feature matrices of the local interaction between the vehicle battery and the internal battery voltage is aggregated along the channel dimension to obtain the semantic interaction encoding feature map of the time series space domain of the vehicle battery and the internal battery voltage. This process can be expressed as:

[0072] F f =couple{S b1 ,S b2 ,...,S bi ,...,S bn}

[0073] Among them, S b1 , S b2 , S bi and S bn are the first, second, i-th and n-th vehicle battery-internal battery voltage local interaction fine-grained semantic reinforcement feature matrices in the set of vehicle battery-internal battery voltage local interaction fine-grained semantic reinforcement feature matrices, n is the number of feature matrices in the set of vehicle battery-internal battery voltage local interaction fine-grained semantic reinforcement feature matrices, couple{·,·,...,·} is the aggregation of the set of feature matrices along the channel dimension, F f It is the semantic interaction encoding feature map of the automobile battery-internal battery voltage time series space domain.

[0074] It should be understood that by performing fine-grained semantic interaction compensation on each corresponding group of the fine-grained local shared semantic feature matrix of the automobile battery-internal battery voltage and the semantic compensation text feature matrix of the automobile battery-internal battery voltage in the set of the automobile battery-internal battery voltage fine-grained local shared semantic feature matrix and the automobile battery-internal battery voltage semantic compensation text feature matrix, the fine-grained shared semantic features between the automobile battery voltage time-series spatial domain feature map and the internal battery voltage time-series spatial domain feature map and the semantic compensation features between the automobile battery voltage time-series spatial domain feature map and the internal battery voltage time-series spatial domain feature map can be realized. The interaction at the fine-grained level can improve the integrity of the fine-grained interaction of the two feature maps. Finally, the set of the automobile battery-internal battery voltage local interaction fine-grained semantic reinforcement feature matrix is ​​aggregated along the channel dimension to obtain the automobile battery-internal battery voltage time-series spatial domain semantic interaction encoding feature map. In this way, it is helpful to promote the feature information previously mined and strengthened at the fine-grained level from the local level to a feature level with a more global perspective, so as to better grasp the overall semantic interaction information of the automobile battery and the internal battery voltage in the time and space domains.

[0075] In the embodiment of the present application, the control result generating unit 133 is used to obtain a control result based on the semantic interaction coding feature of the automobile battery-internal battery voltage time series space domain, and control the charge and discharge control module based on the control result. Specifically, Figure 5 FIG. 1 is a block diagram of a control result generating unit in a vehicle emergency starting power supply control system according to an embodiment of the present application. Figure 5 As shown, the control result generating unit 133 includes: an internal battery charging judging subunit 1331, used for obtaining the control result by passing the vehicle battery-internal battery voltage time-series space domain semantic interaction encoding feature map through a classifier-based charging mode controller, and the control result is used to indicate whether the internal battery of the vehicle emergency power supply is charged; a charging control result responding subunit 1332, used for responding to the control result that the internal battery of the vehicle emergency power supply is charged, and the MCU control module controls the charging and discharging control module to charge the internal battery of the vehicle emergency power supply.

[0076] In an embodiment of the present application, the internal battery charging judgment subunit 1331 is used to obtain the control result by passing the vehicle battery-internal battery voltage time-series space domain semantic interaction encoding feature map through a classifier-based charging mode controller, and the control result is used to indicate whether the internal battery of the vehicle emergency power supply is charged. Specifically, in an embodiment of the present application, the internal battery charging judgment subunit is used to: expand each car battery-internal battery voltage time-series space domain semantic interaction coding feature matrix in the car battery-internal battery voltage time-series space domain semantic interaction coding feature map into a one-dimensional feature vector according to a row vector or a column vector, and then cascade to obtain a charging control classification feature vector; use the fully connected layer of the classifier to fully connect the charging control classification feature vector to obtain a charging control fully connected coding feature vector; input the charging control fully connected coding feature vector into the Softmax classification function of the classifier to obtain the probability value of the car battery-internal battery voltage time-series space domain semantic interaction coding feature map belonging to each classification label, and the classification label includes a value for indicating that the internal battery of the car emergency power supply needs to be charged and a value for indicating that the internal battery of the car emergency power supply does not need to be charged; the classification label corresponding to the largest of the probability values ​​is determined as the control result.

[0077] It should be understood that the vehicle battery-internal battery voltage time series space domain semantic interaction encoding feature map contains rich battery status information. In order to map this abstract and complex feature representation to a specific charging decision (i.e., control result), it is necessary to input the vehicle battery-internal battery voltage time series space domain semantic interaction encoding feature map into a charging mode controller based on a classifier. Specifically, a classifier is a machine learning model that can analyze and judge according to the characteristics of the input data and map it to different categories. It is trained with a large amount of labeled data, which includes different voltage time series data of vehicle batteries and internal batteries and corresponding charging decisions. During the training process, the classifier continuously adjusts its own parameters (weights and biases, etc.) to minimize the error between the predicted results and the actual labeled results. After the training is completed, when a new vehicle battery-internal battery voltage time series space domain semantic interaction encoding feature map is input, the classifier analyzes and judges the feature map according to the learned mode and parameters, and outputs the corresponding charging decision result, that is, whether to charge the internal battery of the vehicle emergency power supply, so that the charging of the internal battery of the emergency power supply can be accurately controlled.

[0078] Here, considering that the automobile battery voltage time-series spatial domain feature map and the internal battery voltage time-series spatial domain feature map respectively represent the image semantic features of the time-series recursive map of the automobile battery voltage and the internal battery voltage of the automobile emergency power supply, when performing global interaction encoding based on cross-domain fine-grained features, due to the cross-domain fine-grained semantic interaction differences caused by the image semantic feature distribution differences caused by the time-series distribution differences of the data sources, the automobile battery-internal battery voltage time-series spatial domain semantic interaction coding feature map will have probabilistic convergence and divergence based on different feature coding interactivity, thereby affecting the accuracy of the control results obtained by the classifier-based charging mode controller.

[0079] Preferably, the vehicle battery-internal battery voltage time series space domain semantic interaction encoding feature map is passed through a classifier-based charging mode controller to obtain a control result, including:

[0080] Determine the automobile battery-internal battery voltage time series space domain semantic interaction coding feature map obtained by the charging mode controller based on the classifier. The automobile battery-internal battery voltage time series space domain semantic interaction coding distribution probability value p represents the probability value of charging the internal battery of the automobile emergency power supply;

[0081] The automobile battery-internal battery voltage time series space domain semantic interaction coding feature map is normalized to the maximum value to obtain the automobile battery-internal battery voltage time series space domain semantic interaction coding probability feature map F;

[0082] The power function of each eigenvalue of the vehicle battery-internal battery voltage time series space domain semantic interaction coding probability feature map is calculated with one minus the distribution probability value of the vehicle battery-internal battery voltage time series space domain semantic interaction coding, and the power function of each eigenvalue of the vehicle battery-internal battery voltage time series space domain semantic interaction coding probability feature map is used as an exponent to obtain a first vehicle battery-internal battery voltage time series space domain semantic interaction coding convergence feature map. The process can be expressed as:

[0083] F1=F ⊙(1-p)

[0084] Among them, F represents the probability feature map of the semantic interaction coding of the vehicle battery-internal battery voltage in the time series space domain, p represents the distribution probability value of the semantic interaction coding of the vehicle battery-internal battery voltage in the time series space domain, ⊙ represents the multiplication by position, F ⊙(1-p) represents a power function that calculates each eigenvalue in F with one minus p as the exponent, and F1 represents the first vehicle battery-internal battery voltage time series space domain semantic interaction coding convergence feature map;

[0085] The power function of each eigenvalue of the point difference feature map between the unit feature map and the probability feature map of the semantic interaction coding in the time series space domain of the vehicle battery-internal battery voltage is calculated with the distribution probability value of the semantic interaction coding in the time series space domain of the vehicle battery-internal battery voltage as an exponent to obtain a second convergence feature map of the semantic interaction coding in the time series space domain of the vehicle battery-internal battery voltage. The process can be expressed as:

[0086]

[0087] Wherein, F represents the semantic interaction coding probability feature map of the vehicle battery-internal battery voltage temporal space domain, p represents the distribution probability value of the semantic interaction coding of the vehicle battery-internal battery voltage temporal space domain, F I represents the unit feature map, and ⊙ represent point-by-point subtraction and point-by-point multiplication, respectively. Indicates that F is calculated with p as the exponent I The power function of each eigenvalue of the feature map obtained by subtracting the feature map from point F, F2 represents the second car battery-internal battery voltage time series space domain semantic interaction coding convergence feature map;

[0088] The automobile battery-internal battery voltage time series space domain semantic interaction coding probability feature map is multiplied by a difference value minus the automobile battery-internal battery voltage time series space domain semantic interaction coding distribution probability value to obtain a first automobile battery-internal battery voltage time series space domain semantic interaction coding limited feature map. The process can be expressed as:

[0089] F3=F⊙(1-p)

[0090] Among them, F represents the probability feature map of the semantic interaction coding of the vehicle battery-internal battery voltage in the time series space domain, p represents the distribution probability value of the semantic interaction coding of the vehicle battery-internal battery voltage in the time series space domain, ⊙ represents the multiplication by position point, and F3 represents the limited feature map of the semantic interaction coding of the first vehicle battery-internal battery voltage in the time series space domain;

[0091] The point difference feature map is multiplied by the automobile battery-internal battery voltage time series space domain semantic interaction coding distribution probability value to obtain a second automobile battery-internal battery voltage time series space domain semantic interaction coding limited feature map. The process can be expressed as:

[0092]

[0093] Wherein, F represents the semantic interaction coding probability feature map of the vehicle battery-internal battery voltage temporal space domain, p represents the distribution probability value of the semantic interaction coding of the vehicle battery-internal battery voltage temporal space domain, F I represents the unit feature map, and ⊙ represent position point subtraction and position point multiplication respectively, and F4 represents the second vehicle battery-internal battery voltage time series space domain semantic interaction coding limited feature map;

[0094] After dot-multiplying the first vehicle battery-internal battery voltage time series space domain semantic interaction coding convergence feature map with the second vehicle battery-internal battery voltage time series space domain semantic interaction coding convergence feature map, dot-multiplying the first vehicle battery-internal battery voltage time series space domain semantic interaction coding limit feature map and the second vehicle battery-internal battery voltage time series space domain semantic interaction coding limit feature map to obtain an optimized vehicle battery-internal battery voltage time series space domain semantic interaction coding feature map. The process can be expressed as:

[0095]

[0096] Among them, F1 represents the first car battery-internal battery voltage time series space domain semantic interaction coding convergence feature map, F2 represents the second car battery-internal battery voltage time series space domain semantic interaction coding convergence feature map, F3 represents the first car battery-internal battery voltage time series space domain semantic interaction coding limit feature map, and ⊙ represent point-by-point addition and point-by-point multiplication, respectively; F4 represents the second vehicle battery-internal battery voltage time series space domain semantic interaction coding limited feature map; and F' represents the optimized vehicle battery-internal battery voltage time series space domain semantic interaction coding feature map;

[0097] The optimized automobile battery-internal battery voltage time series space domain semantic interaction encoding feature map is input into the classifier-based charging mode controller to obtain the control result.

[0098] That is, by using the cross entropy form power series of the regression analysis probability of the vehicle battery-internal battery voltage time series space domain semantic interaction coding feature map as the probability distribution convergence limit, the class probability convergence approximation of the vehicle battery-internal battery voltage time series space domain semantic interaction coding feature map is performed on the basis of the combination of the feature set distribution and the probability density distribution of the vehicle battery-internal battery voltage time series space domain semantic interaction coding feature map, so as to avoid the fatal potential divergence of the vehicle battery-internal battery voltage time series space domain semantic interaction coding feature map. Under the premise of conservative convergence control, the probability distribution cross entropy of the vehicle battery-internal battery voltage time series space domain semantic interaction coding feature map is further used as the objective function to guide the limited recovery strategy, so as to achieve the common agility of the convergence of the probability convergence and divergence of the vehicle battery-internal battery voltage time series space domain semantic interaction coding feature map to the probability density distribution space, and improve the accuracy of the control result obtained by the vehicle battery-internal battery voltage time series space domain semantic interaction coding feature map through the classifier-based charging mode controller.

[0099] In the embodiment of the present application, the charging control result response subunit 1332 is used to respond to the control result of charging the internal battery of the automobile emergency power supply, and the MCU control module controls the charge and discharge control module to charge the internal battery of the automobile emergency power supply. In this way, it can ensure that the automobile emergency power supply is always in the best state, improve the system reliability and safety, and through this reasonable charging operation, it is also helpful to extend the service life of the internal battery of the automobile emergency power supply and maintain its good performance.

[0100] In summary, the MCU control module is clearly explained, and it uses a data analysis and processing algorithm based on deep learning to recursively process the automotive battery voltage timing data and the internal battery voltage timing data of the automotive emergency power supply and extract spatial domain features, so as to intelligently judge whether to charge the internal battery of the automotive emergency power supply and control the charging and discharging control module based on the fine-grained spatial semantic interaction representation between the automotive battery voltage timing spatial domain features and the internal battery voltage timing spatial domain features. In this way, it is possible to capture subtle patterns and trends in voltage changes, and dynamically adjust the charging strategy to ensure optimal performance in various usage scenarios. This not only enhances the flexibility of the system, but also solves the problem that the fixed threshold method cannot cope with environmental changes, thereby effectively protecting battery performance and extending its service life.

[0101] In an embodiment of the present application, the charge and discharge control module 140 is used to determine whether to charge the internal battery of the automobile emergency power supply based on the control result. It should be understood that the automobile emergency starting power supply is used as a backup power guarantee for the vehicle. Its core function is to quickly and reliably provide starting power when the car battery is low or fails, so that the vehicle can operate normally. The charge and discharge control module can accurately charge the internal battery of the automobile emergency power supply according to the control result generated by the MCU control module. For example, after the vehicle has been parked for a long time, the battery of the car battery is reduced due to natural discharge and other reasons. The charge and discharge control module starts the charging procedure for the internal battery according to the control result to ensure that the internal battery has sufficient power, which greatly improves the success rate and reliability of the vehicle emergency start.

[0102] In summary, the automobile emergency starting power supply control system 100 based on the embodiment of the present application is explained, which first collects the voltage timing data of the automobile battery and the internal battery of the automobile emergency power supply, and then transmits these voltage timing data to the MCU control module, and the MCU control module conducts in-depth analysis of these voltage timing data to obtain corresponding control results, and according to this control result, performs charging or discharging operations on the automobile battery or the internal battery of the automobile emergency power supply. In this way, real-time monitoring and intelligent management of the status of the automobile battery and the internal battery of the automobile emergency power supply can be achieved, which is conducive to improving the reliability and practicality of the automobile emergency power supply at critical moments, and thus can provide strong guarantee for the normal operation of the automobile.

[0103] In an embodiment of the present application, a vehicle emergency starting power supply control method is also provided, which is used to execute the vehicle emergency starting power supply control system as described above. Figure 6 FIG. 1 is a flow chart of a method for controlling an automobile emergency starting power supply according to an embodiment of the present application. Figure 6 As shown, in the automobile emergency starting power supply control method, it includes: S110, recursively processing the automobile battery voltage timing data and the internal battery voltage timing data of the automobile emergency power supply and extracting spatial domain features to obtain the automobile battery voltage timing spatial domain features and the internal battery voltage timing spatial domain features; S120, performing fine-grained spatial domain interaction coding on the automobile battery voltage timing spatial domain features and the internal battery voltage timing spatial domain features to obtain automobile battery-internal battery voltage timing spatial domain semantic interaction coding features; S130, obtaining a control result based on the automobile battery-internal battery voltage timing spatial domain semantic interaction coding features, and controlling the charge and discharge control module based on the control result.

[0104] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned automobile emergency starting power supply control method have been referred to above. Figures 1 to 5The description of the automobile emergency starting power supply control system has been introduced in detail, and therefore, its repeated description will be omitted.

[0105] In summary, the automobile emergency starting power supply control method based on the embodiment of the present application is explained, which first collects the voltage timing data of the automobile battery and the internal battery of the automobile emergency power supply, and then transmits these voltage timing data to the MCU control module, and the MCU control module conducts in-depth analysis of these voltage timing data to obtain corresponding control results, and based on this control result, performs charging or discharging operations on the automobile battery or the internal battery of the automobile emergency power supply. In this way, real-time monitoring and intelligent management of the status of the automobile battery and the internal battery of the automobile emergency power supply can be achieved, which is conducive to improving the reliability and practicality of the automobile emergency power supply at critical moments, and thus can provide strong guarantees for the normal operation of the automobile.

Claims

1. An automobile emergency starting power supply control system, characterized in that: include: Voltage detection module, used to collect vehicle battery voltage timing data and internal battery voltage timing data of vehicle emergency power supply; A data transmission module, used to transmit the vehicle battery voltage timing data and the internal battery voltage timing data of the vehicle emergency power supply to the MCU control module; The MCU control module is used to analyze the vehicle battery voltage timing data and the internal battery voltage timing data of the vehicle emergency power supply to obtain a control result; A charge and discharge control module is used to determine whether to charge the internal battery of the automobile emergency power supply based on the control result; wherein the MCU control module includes: A battery voltage timing analysis unit, used for recursively processing the vehicle battery voltage timing data and the internal battery voltage timing data of the vehicle emergency power supply and extracting spatial domain features to obtain vehicle battery voltage timing spatial domain features and internal battery voltage timing spatial domain features; A car battery-internal voltage interaction unit, used for performing fine-grained spatial domain interaction encoding on the car battery voltage temporal spatial domain features and the internal battery voltage temporal spatial domain features to obtain a car battery-internal battery voltage temporal spatial domain semantic interaction encoding feature; The control result generating unit is used to obtain the control result based on the semantic interaction coding feature of the automobile battery-internal battery voltage time series space domain, and control the charge and discharge control module based on the control result.

2. The automobile emergency starting power supply control system according to claim 1, characterized in that: The battery voltage timing analysis unit comprises: A battery voltage timing data recursive graph calculation subunit, used to calculate the recursive graphs of the vehicle battery voltage timing data and the internal battery voltage timing data of the vehicle emergency power supply to obtain a vehicle battery voltage timing recursive graph and an internal battery voltage timing recursive graph; The battery voltage time series space domain feature extraction subunit is used to pass the automobile battery voltage time series recursive graph and the internal battery voltage time series recursive graph through the voltage time series space domain feature extractor based on MCNN to obtain the automobile battery voltage time series space domain feature graph as the automobile battery voltage time series space domain feature and the internal battery voltage time series space domain feature graph as the internal battery voltage time series space domain feature.

3. The automobile emergency starting power supply control system according to claim 2 is characterized in that: The automobile battery-internal voltage interaction unit comprises: A battery voltage shared feature interaction subunit is used to perform feature decomposition on the vehicle battery voltage time series spatial domain feature graph and the internal battery voltage time series spatial domain feature graph, and calculate the shared semantic features between the decomposed set of vehicle battery voltage time series local spatial domain semantic feature matrices and the set of internal battery voltage time series local spatial domain semantic feature matrices to obtain a set of vehicle battery-internal battery voltage fine-grained local shared semantic feature matrices; A battery voltage semantic compensation text subunit is used to calculate the semantic compensation text features of each automobile battery-internal battery voltage fine-grained local shared semantic feature matrix in the set of automobile battery-internal battery voltage fine-grained local shared semantic feature matrices to obtain a set of automobile battery-internal battery voltage semantic compensation text feature matrices; The battery voltage feature aggregation subunit is used to perform weighted aggregation on the set of the automobile battery-internal battery voltage fine-grained local shared semantic feature matrices based on the set of the automobile battery-internal battery voltage semantic compensation text feature matrices to obtain a automobile battery-internal battery voltage temporal space domain semantic interaction coding feature map as the automobile battery-internal battery voltage temporal space domain semantic interaction coding feature.

4. The automobile emergency starting power supply control system according to claim 3 is characterized in that: The battery voltage sharing feature interaction subunit is used to: Performing feature decomposition on the vehicle battery voltage time series space domain feature graph and the internal battery voltage time series space domain feature graph along the channel dimension of the vehicle battery voltage time series space domain feature graph and the internal battery voltage time series space domain feature graph to obtain a set of the vehicle battery voltage time series local space domain semantic feature matrices and a set of the internal battery voltage time series local space domain semantic feature matrices; For each group of corresponding channel dimensions in the set of the automobile battery voltage timing local spatial domain semantic feature matrices and the set of the internal battery voltage timing local spatial domain semantic feature matrices, a twin structure shared semantic feature extraction is performed to obtain the set of automobile battery-internal battery voltage fine-grained local shared semantic feature matrices.

5. The automobile emergency starting power supply control system according to claim 4, characterized in that: The battery voltage semantic compensation text subunit is used to: Performing semantic compensation decoding based on a large language on each of the automobile battery-internal battery voltage fine-grained local shared semantic feature matrices in the set of the automobile battery-internal battery voltage fine-grained local shared semantic feature matrices to obtain a set of automobile battery-internal battery voltage semantic compensation text descriptions; Each automobile battery-internal battery voltage semantic compensation text description in the set of automobile battery-internal battery voltage semantic compensation text description is subjected to text convolution semantic coding to obtain a set of automobile battery-internal battery voltage semantic compensation text feature matrices.

6. The automobile emergency starting power supply control system according to claim 5, characterized in that: The battery voltage characteristic aggregation subunit is used to: Performing fine-grained semantic interaction compensation on each corresponding group of automobile battery-internal battery voltage fine-grained local shared semantic feature matrices and automobile battery-internal battery voltage semantic compensation text feature matrices in the set of the automobile battery-internal battery voltage fine-grained local shared semantic feature matrices and the set of the automobile battery-internal battery voltage semantic compensation text feature matrices to obtain a set of automobile battery-internal battery voltage local interactive fine-grained semantic reinforcement feature matrices; The set of the fine-grained semantic reinforcement feature matrices of the local interaction between the vehicle battery and the internal battery voltage is aggregated along the channel dimension to obtain the temporal spatial domain semantic interaction encoding feature map of the vehicle battery and the internal battery voltage.

7. The automobile emergency starting power supply control system according to claim 6, characterized in that: The control result generating unit comprises: The internal battery charging judgment subunit is used to pass the vehicle battery-internal battery voltage time series space domain semantic interaction coding feature map through the classifier-based charging mode controller to obtain the control result, and the control result is used to indicate whether to charge the internal battery of the vehicle emergency power supply; The charging control result response subunit is used to respond to the control result of charging the internal battery of the automobile emergency power supply, and the MCU control module controls the charge and discharge control module to charge the internal battery of the automobile emergency power supply.

8. The automobile emergency starting power supply control system according to claim 7, characterized in that: The internal battery charging judgment subunit is used for: Expand each automobile battery-internal battery voltage time series space domain semantic interaction coding feature matrix in the automobile battery-internal battery voltage time series space domain semantic interaction coding feature map into a one-dimensional feature vector according to a row vector or a column vector, and then cascade them to obtain a charging control classification feature vector; Using the fully connected layer of the classifier to perform fully connected encoding on the charging control classification feature vector to obtain a charging control fully connected encoding feature vector; Input the charging control fully connected encoding feature vector into the Softmax classification function of the classifier to obtain the probability value of the vehicle battery-internal battery voltage time series space domain semantic interaction encoding feature map belonging to each classification label, wherein the classification label includes a label indicating that the internal battery of the vehicle emergency power supply needs to be charged and a label indicating that the internal battery of the vehicle emergency power supply does not need to be charged; The classification label corresponding to the largest probability value among the probability values ​​is determined as the control result.

9. A method for controlling an automobile emergency starting power supply, used to execute the automobile emergency starting power supply control system as claimed in claim 1, characterized in that: The automobile emergency starting power supply control method comprises: Recursively processing the automobile battery voltage time series data and the internal battery voltage time series data of the automobile emergency power supply and extracting spatial domain features to obtain automobile battery voltage time series spatial domain features and internal battery voltage time series spatial domain features; Performing fine-grained spatial domain interaction coding on the automotive battery voltage temporal spatial domain features and the internal battery voltage temporal spatial domain features to obtain automotive battery-internal battery voltage temporal spatial domain semantic interaction coding features; Based on the semantic interaction coding characteristics of the automobile battery-internal battery voltage time series space domain, a control result is obtained, and based on the control result, the charge and discharge control module is controlled.

10. The automobile emergency starting power supply control method according to claim 9, characterized in that: Recursively processing the automobile battery voltage time series data and the internal battery voltage time series data of the automobile emergency power supply and extracting spatial domain features to obtain automobile battery voltage time series spatial domain features and internal battery voltage time series spatial domain features, including: Respectively calculating the recursive graphs of the automobile battery voltage timing data and the internal battery voltage timing data of the automobile emergency power supply to obtain an automobile battery voltage timing recursive graph and an internal battery voltage timing recursive graph; The automobile battery voltage timing recursive graph and the internal battery voltage timing recursive graph are passed through a voltage timing spatial domain feature extractor based on MCNN to obtain an automobile battery voltage timing spatial domain feature graph as the automobile battery voltage timing spatial domain feature and an internal battery voltage timing spatial domain feature graph as the internal battery voltage timing spatial domain feature.

Images