Battery management system and vehicle

Abstract

The present invention provides a battery management system and a vehicle, and relates to the technical field of vehicle power management. The system includes: an isolated power supply module, a processor, a CAN communication module, and a wake-up module; the isolated power supply module is used to provide isolated power to the CAN communication module; the CAN communication module is used to connect to an external CAN communication module through a CANH signal line and a CANL signal line, and receive external information of the external CAN communication module; the wake-up module receives a differential signal between the CANH signal line and the CANL signal line, and the input end of the wake-up module is also used to receive an external wake-up signal from an external wake-up source, and the output end of the wake-up module is connected to the input end of the processor, and is used to output an internal wake-up signal to the processor according to the differential signal and / or the external wake-up signal; the processor is used to process external information, and control the opening and closing of the isolated power supply module according to the external information and the internal wake-up signal. The present invention can solve the problems of the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle power management, and in particular to a battery management system and a vehicle. Background Art

[0002] Battery Management System (BMS) is an electronic system used to monitor and manage rechargeable batteries. It is widely used in electric vehicles, energy storage systems, portable electronic devices and other fields. It plays a vital role in ensuring that the batteries used in these applications are both efficient and safe.

[0003] As more and more electric controllers are installed in automobiles, such as motor controllers, TBOX, electronic transmissions, and electronic instruments, the existing communication methods and circuit designs of battery management systems are not conducive to managing multiple electric controllers, which can easily lead to problems such as high power consumption, difficulty in awakening, and low safety of the battery management system. Summary of the invention

[0004] The present invention aims to solve at least one of the above problems.

[0005] To solve the above problems, in a first aspect, the present invention provides a battery management system for managing a battery pack, comprising: an isolation power module, a processor, a CAN communication module and a wake-up module;

[0006] The input end of the isolated power supply module is connected to the battery pack, the output end of the isolated power supply module is connected to the CAN communication module, and the isolated power supply module is used to provide isolated power to the CAN communication module;

[0007] The CAN communication module is used to connect to an external CAN communication module through a CANH signal line and a CANL signal line to receive external information of the external CAN communication module;

[0008] The input end of the wake-up module is respectively connected to the CANH signal line and the CANL signal line, and is used to receive the differential signal between the CANH signal line and the CANL signal line. The input end of the wake-up module is also used to connect to an external wake-up source, and is used to receive an external wake-up signal from the external wake-up source. The output end of the wake-up module is connected to the input end of the processor, and is used to output an internal wake-up signal to the processor according to the differential signal and / or the external wake-up signal.

[0009] The input end of the processor is connected to the CAN communication module for receiving the external information. The output end of the processor is connected to the enable pin of the isolated power supply module for controlling the start and stop of the isolated power supply module according to the external information and the internal wake-up signal. The battery pack is also connected to the power supply end of the processor for supplying power to the processor.

[0010] Optionally, the battery management system further includes an analog front-end acquisition chip and an analog front-end protection chip, a first end of the analog front-end acquisition chip and the analog front-end protection chip are both connected to the battery pack, and a second end of the analog front-end acquisition chip is connected to the processor;

[0011] The analog front-end acquisition chip is used to collect the working data of the battery pack, control the charging and discharging circuit of the battery pack according to the working data, and transmit the working data to the processor;

[0012] The analog front-end protection chip is used to collect the working data and control the charging and discharging circuit of the battery pack according to the working data.

[0013] Optionally, the wake-up module includes an optocoupler, the input end of the optocoupler is respectively connected to the CANH signal line and the CANL signal line, the input end of the optocoupler is connected to the processor, and the optocoupler is used to receive the differential signal and convert the differential signal into the internal wake-up signal.

[0014] Optionally, the battery management system also includes a voltage stabilizing module, the input end of the voltage stabilizing module is connected to the battery pack, the output end of the voltage stabilizing module is respectively connected to the input end of the isolation power supply module and the power supply end of the processor, and the voltage stabilizing module is used to convert the voltage of the battery pack into a stable voltage.

[0015] Optionally, the CAN communication module includes a CAN communication chip and an isolation communication chip;

[0016] The CAN communication chip is used to connect to the external CAN communication module through the CANH signal line and the CANL signal line to receive the external information;

[0017] The isolation communication chip is connected to the CAN communication chip and the processor respectively, and is used to protect the external information and transmit the external information to the processor.

[0018] Optionally, the battery management system further includes a storage module, the storage module is connected to the processor via SPI communication, and the storage module is used to store processing data of the processor.

[0019] Optionally, the battery management system also includes a battery evaluation module, which is connected to the battery pack and the processor, respectively, and is used to obtain the working data, determine the load state of the battery pack based on the working data, and collect health data of the battery pack, and predict the health state of the battery pack based on the working data and the health data.

[0020] Optionally, the battery assessment module includes an acquisition unit and a health status assessment model;

[0021] The acquisition unit is used to acquire the health data;

[0022] The health status assessment model is used to predict the health status based on the work data and the health data.

[0023] Optionally, the health status assessment model includes an input layer, a feature extraction layer, a multimodal fusion layer, an attention layer, a recurrent layer, and an output layer;

[0024] The input layer is used to obtain the working data and the health data, wherein the health data includes vibration data and sound data;

[0025] The feature extraction layer includes a first convolution layer, a second convolution layer and a third convolution layer, wherein the first convolution layer is used to extract the working time feature of the working data; the second convolution layer is used to extract the vibration frequency feature of the vibration data; and the third convolution layer is used to extract the sound frequency feature of the sound data;

[0026] The multimodal fusion layer includes a feature fusion layer and a fully connected layer. The feature fusion layer is used to fuse the working time feature, the vibration frequency feature and the sound frequency feature to generate a multimodal fusion feature. The fully connected layer is used to integrate the multimodal fusion features to generate high-level low-dimensional features.

[0027] The attention layer is based on an attention mechanism, and is used to convert the high-level low-dimensional features into importance features;

[0028] The cyclic layer is used to extract the long-term dependency of the importance feature, and cyclically stack the long-term dependency to generate a time series feature;

[0029] The output layer is used to map the time series features to generate the health status.

[0030] In a second aspect, the present invention provides a vehicle, comprising the battery management system as described above.

[0031] The battery management system and vehicle of the present invention have the following beneficial effects:

[0032] First, by providing isolated power to the CAN communication module through the isolated power module, the battery pack and the CAN communication module can be electrically isolated, which improves the safety of the system, prevents potential damage to sensitive electronic components caused by high voltage electricity, and reduces the possibility of electromagnetic interference. Secondly, the CANH signal line and CANL signal line of the CAN communication module are connected to the external CAN communication module, and based on the automatic bus arbitration mechanism of the CAN communication module, it can exchange data efficiently and stably with external electrical controllers, such as motor controllers, TBOX, electronic transmissions, and electronic instruments, which is more conducive to multi-controller communication. Then, the differential signal between the CANH signal line and the CANL signal line is received by the wake-up module, and the processor can be awakened after the differential signal reaches a certain threshold, so as to achieve more flexible response to different working states. At the same time, the wake-up module also receives the external wake-up signal of the external wake-up source, so as to achieve multi-wake-up source wake-up of the processor and solve the problem of wake-up difficulty. Finally, by processing external information and internal wake-up signals through the processor, the battery management system can enter "sleep mode" or "working mode" at any time. When the processor enters "sleep mode" according to external information, the output end of the processor is connected to the enable pin of the isolated power module to realize the function of shutting down the isolated power module, thereby reducing the power consumption of the battery management system in sleep mode and solving the problem of high power consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 One of the structural schematic diagrams of the battery management system provided by an embodiment of the present invention;

[0034] Figure 2 A second structural diagram of a battery management system provided by an embodiment of the present invention;

[0035] Figure 3 A circuit diagram of a wake-up module provided in an embodiment of the present invention;

[0036] Figure 4 A third structural diagram of a battery management system provided by an embodiment of the present invention;

[0037] Figure 5 A fourth structural diagram of a battery management system provided by an embodiment of the present invention;

[0038] Figure 6 A fifth structural diagram of a battery management system provided by an embodiment of the present invention;

[0039] Figure 7 A sixth structural diagram of a battery management system provided by an embodiment of the present invention;

[0040] Figure 8 A schematic diagram of the structure of a health status assessment model provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be interpreted as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0042] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0043] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to"; the term "based on" means "based at least in part on"; the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "optional embodiments". The relevant definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc. mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0044] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0045] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

[0046] In view of the problems existing in the above-mentioned related technologies, this embodiment provides a battery management system and a vehicle.

[0047] like Figure 1 As shown, a battery management system provided by an embodiment of the present invention is applied to manage a battery pack, and includes: an isolation power module, a processor, a CAN communication module and a wake-up module.

[0048] Specifically, a battery management system provided by an embodiment of the present invention is applied to a battery pack to manage and control the battery pack, while receiving signals from external signal sources, such as an external CAN communication module and an external wake-up source, so as to achieve management and control of the battery pack.

[0049] The input end of the isolated power supply module is connected to the battery pack, the output end of the isolated power supply module is connected to the CAN communication module, and the isolated power supply module is used to provide isolated power to the CAN communication module.

[0050] Specifically, the isolated power module is powered by a battery pack and converts the power of the battery pack into an isolated power supply to achieve electrical isolation and ensure the power safety of the CAN communication module. Exemplarily, the isolated power module can use an isolated power chip to achieve the electrical isolation function.

[0051] The CAN communication module is used to connect to an external CAN communication module through a CANH signal line and a CANL signal line to receive external information from the external CAN communication module.

[0052] Specifically, the CANH signal line and the CANL signal line are two signal lines in the Controller Area Network (CAN) bus. The external CAN communication module includes devices such as motor controllers, TBOX, electronic transmissions, and electronic instruments. By connecting to the external CAN communication module through the CANH signal line and the CANL signal line and receiving external information from the external CAN communication module, the anti-interference ability can be improved, long-distance transmission can be achieved, and fast and reliable data exchange can be achieved. It also supports multi-master mode, that is, multiple nodes are allowed to send messages at the same time, and it has an automatic arbitration mechanism, which can improve the integration of the battery management system.

[0053] The input end of the wake-up module is respectively connected to the CANH signal line and the CANL signal line, and is used to receive the differential signal between the CANH signal line and the CANL signal line. The input end of the wake-up module is also used to connect to an external wake-up source, and is used to receive an external wake-up signal from the external wake-up source. The output end of the wake-up module is connected to the input end of the processor, and is used to output an internal wake-up signal to the processor according to the differential signal and / or the external wake-up signal.

[0054] Specifically, the input end of the wake-up module is connected to the CANH signal line and the CANL signal line respectively, receives the differential signal between the CANH signal line and the CANL signal line, and generates an internal wake-up signal when the differential signal reaches a preset threshold, thereby waking up the processor in the dormant state. In addition, the input end of the wake-up module is also used to connect to an external wake-up source, receive an external wake-up signal from the external wake-up source, realize multiple wake-up sources to wake up the processor, ensure the reliability of the wake-up processor, and thus improve the integration of the battery management system.

[0055] The input end of the processor is connected to the CAN communication module for receiving the external information. The output end of the processor is connected to the enable pin of the isolated power supply module for controlling the start and stop of the isolated power supply module according to the external information and the internal wake-up signal. The battery pack is also connected to the power supply end of the processor for supplying power to the processor.

[0056] Specifically, the battery pack is also connected to the input end of the processor to supply power to the processor, that is, the power supply of the processor comes from the battery pack. The processor is used to receive and process external information, and send corresponding processing information to other modules of the battery management system and the external CAN communication module. The output end of the processor is connected to the enable pin of the isolated power supply module. When in sleep mode, the processor can turn off the isolated power supply module to reduce power consumption in the sleep state. When awakened, the isolated power supply module is turned on to work normally. Therefore, the versatility of the processor can be achieved, thereby improving the integration of the battery management system.

[0057] In this embodiment, first, by providing an isolated power supply to the CAN communication module through the isolated power supply module, the electrical isolation between the battery pack and the CAN communication module can be achieved, the safety of the system is improved, the potential damage to sensitive electronic components caused by high voltage electricity is prevented, and the possibility of electromagnetic interference is reduced, thereby improving the integration of the battery management system. Secondly, by connecting the CANH signal line and the CANL signal line of the CAN communication module to the external CAN communication module, and based on the automatic bus arbitration mechanism of the CAN communication module, it can be used with external electrical controllers, such as motor controllers, TBOX, electronic transmissions, and electronic instruments. Efficient and stable data exchange is carried out, which is more conducive to multi-controller communication, thereby improving the integration of the battery management system. Then, by receiving the differential signal between the CANH signal line and the CANL signal line through the wake-up module, the processor can be awakened after the differential signal reaches a certain threshold, and a more flexible response to different working states is achieved. At the same time, the wake-up module also receives an external wake-up signal from an external wake-up source, realizing a multi-wake-up source wake-up processor, solving the problem of wake-up difficulty, thereby improving the integration of the battery management system. Finally, by processing external information and internal wake-up signals through the processor, the battery management system can enter "sleep mode" or "working mode" at any time. When the processor enters "sleep mode" according to external information, the output end of the processor is connected to the enable pin of the isolation power module to realize the function of shutting down the isolation power module, thereby reducing the power consumption of the battery management system in sleep mode, solving the problem of high power consumption, and thus improving the integration of the battery management system.

[0058] Optionally, the battery management system further includes an analog front-end acquisition chip and an analog front-end protection chip, a first end of the analog front-end acquisition chip and the analog front-end protection chip are both connected to the battery pack, and a second end of the analog front-end acquisition chip is connected to the processor;

[0059] The analog front-end acquisition chip is used to collect the working data of the battery pack, control the charging and discharging circuit of the battery pack according to the working data, and transmit the working data to the processor;

[0060] The analog front-end protection chip is used to collect the working data and control the charging and discharging circuit of the battery pack according to the working data.

[0061] Specifically, Figure 2As shown, the battery management system also includes an analog front-end acquisition chip and an analog front-end protection chip, both of which are connected to the battery pack, and the analog front-end acquisition chip is also connected to the processor; the working data includes the single cell voltage of the battery pack, the current of the battery pack, and the temperature of the battery pack. The analog front-end acquisition chip communicates with the processor through IIC, so that the processor can read the working data, and process, analyze, store, and evaluate the working data to determine the use status, health status, and fault status of the battery pack. In addition, the analog front-end acquisition chip can also independently protect the battery pack, for example, cutting off the charge and discharge circuit, that is, cutting off the charge and discharge MOS. The analog front-end protection chip is also used to collect working data, but unlike the analog front-end acquisition chip, the analog front-end protection chip is not connected to the processor, and the analog front-end protection chip works independently. It determines that the battery pack has a fault such as over-voltage, over-voltage, over-current, etc., and it will independently and actively protect it without the participation of any other modules. Exemplarily, the protection threshold of the analog front-end acquisition chip is higher than that of the analog front-end protection chip. For example, the overvoltage protection of the analog front-end acquisition chip is 4250mV, and the overvoltage protection of the analog front-end protection chip is 4220mV. If the analog front-end acquisition chip triggers the protection, it means that the analog front-end protection chip fails, and it is considered that the battery pack has a fault. In general, if either the analog front-end acquisition chip or the analog front-end protection chip fails, the other can still work. This greatly improves the redundancy of protection and greatly improves safety.

[0062] Optionally, the wake-up module includes an optocoupler, the input end of the optocoupler is respectively connected to the CANH signal line and the CANL signal line, the input end of the optocoupler is connected to the processor, and the optocoupler is used to receive the differential signal and convert the differential signal into the internal wake-up signal.

[0063] Specifically, the wake-up circuit diagram of the wake-up module is as follows: Figure 3As shown, the wake-up module includes an optocoupler, and the first pin of the optocoupler is connected to the CANH signal line, and a first resistor R1 is provided between the first pin and the CANH signal line, the second pin of the optocoupler is connected to the CANL signal line, the third pin of the optocoupler is connected to the processor input terminal, the third pin of the optocoupler is connected to the second resistor R2 and the first capacitor C1, and the second resistor R2 and the first capacitor C1 are both grounded, and the fourth pin of the optocoupler is connected to the 3.3V power supply line of the processor MCU. Since the first pin of the optocoupler is connected to the CANH signal line and the second pin of the optocoupler is connected to the CANL signal line, when there is a message on the CAN bus, the voltage difference between the CANH signal line and the CANL signal line can reach a maximum of about 2.5V, that is, a differential signal, which causes the third pin and the fourth pin of the optocoupler to be turned on. Since the fourth pin is 3.3V, when it is turned on, the third pin is also pulled up to about 3V. At this time, the rising edge signal of about 3V is an internal wake-up signal, which can be used to wake up the processor. Although the existing processor has a built-in wake-up function, the processor still needs to keep running when it is in sleep mode, which consumes too much power. The wake-up module of this embodiment can work independently to wake up the processor, and can power off and put all modules on the CAN communication channel, such as the CAN communication module, into sleep mode, thereby greatly reducing power consumption.

[0064] Optionally, the battery management system also includes a voltage stabilizing module, the input end of the voltage stabilizing module is connected to the battery pack, the output end of the voltage stabilizing module is respectively connected to the input end of the isolation power supply module and the power supply end of the processor, and the voltage stabilizing module is used to convert the voltage of the battery pack into a stable voltage.

[0065] Specifically, Figure 4 As shown, the battery management system also includes a voltage stabilizing module, the input end of the voltage stabilizing module is connected to the battery pack, the output end of the voltage stabilizing module is connected to the isolation power module and the processor respectively, and the voltage stabilizing module is used to convert the voltage of the battery pack into a stable voltage. The voltage stabilizing module can use a low dropout linear regulator (LDO) and set a multi-stage buck structure to ensure that the voltage of the battery pack is converted into a stable voltage required by other modules. For example, a three-stage buck structure can be set, the first-stage buck structure converts 40V into 20V, the second-stage buck structure converts 20V into 5V, and the third-stage buck structure converts 5V into 3.3V to adapt to the working voltage of other modules.

[0066] Optionally, the CAN communication module includes a CAN communication chip and an isolation communication chip;

[0067] The CAN communication chip is used to connect to the external CAN communication module through the CANH signal line and the CANL signal line to receive the external information;

[0068] The isolation communication chip is connected to the CAN communication chip and the processor respectively, and is used to protect the external information and transmit the external information to the processor.

[0069] Specifically, Figure 5 As shown, the CAN communication module includes a CAN communication chip and an isolation communication chip; the CAN communication chip is used to connect to an external CAN communication module through the CANH signal line and the CANL signal line to receive external information; the isolation communication chip is connected to the CAN communication chip and the processor respectively, and is used to protect and transmit external information to the processor. In addition, the isolation communication chip can change the reference ground of the processor communication, that is, through the isolation communication chip, the processor can communicate with a new, independent "zero point" or "reference point". This new reference ground is separated from the grounding on the battery side, which can reduce the impact of electromagnetic interference from the battery side on the communication signal. Even if there is voltage fluctuation or noise on the battery side, it will not directly affect the communication quality on the processor side. If a fault occurs on the battery side, such as a short circuit, the isolation communication chip can prevent the fault from spreading to the processor side, protecting the key control circuit.

[0070] Optionally, the battery management system further includes a storage module, the storage module is connected to the processor via SPI communication, and the storage module is used to store processing data of the processor.

[0071] Specifically, Figure 6 As shown, the battery management system also includes a storage module, which is connected to the processor via SPI communication, and the storage module is used to store the processing data of the processor. Exemplarily, the storage module can use a 128Mbit flash chip. During operation, the processor will send various processing data to the storage module via SPI communication. Storage strategies include power-on storage, periodic storage, snapshot storage, and file management. In the storage strategy, an average of one piece of data is stored every 2 minutes, and one piece of data is 85 bytes. The external flash is 16Mbytes, so a total of 197,379 pieces of data can be stored. If it runs for an average of 4 hours a day, 120 pieces of data are stored every day. The storage module can store a total of 1,645 days of data, which is suitable for most application environments.

[0072] Optionally, the battery management system also includes a battery evaluation module, which is connected to the battery pack and the processor, respectively, and is used to obtain the working data, determine the load state of the battery pack based on the working data, and collect health data of the battery pack, and predict the health state of the battery pack based on the working data and the health data.

[0073] Specifically, Figure 7As shown, the battery management system also includes a battery evaluation module, which is connected to the battery pack and the processor respectively, for obtaining working data, determining the load state of the battery pack according to the working data, and collecting the health data of the battery pack, and predicting the health state of the battery pack according to the working data and the health data. Exemplarily, a deep learning algorithm, such as a long short-term memory network, a convolutional neural network, and an optimization algorithm, can be used to build a more accurate load state model. By collecting a large amount of working data in actual use, including parameters such as temperature, voltage, and current, the training model identifies complex nonlinear relationships to determine the load state of the battery pack; the load state of the battery pack can also be calculated using mathematical empirical formulas. Exemplarily, a deep learning algorithm, such as a long short-term memory network, a convolutional neural network, and an optimization algorithm, can be used to build a more accurate health state model. By collecting a large amount of working data and health data in actual use, including parameters such as temperature, voltage, current, vibration, and sound, the training model identifies complex nonlinear relationships to determine the health state of the battery pack.

[0074] Optionally, the battery assessment module includes an acquisition unit and a health status assessment model;

[0075] The acquisition unit is used to acquire the health data;

[0076] The health status assessment model is used to predict the health status based on the work data and the health data.

[0077] Specifically, the battery evaluation module includes an acquisition unit and a health status evaluation model; the acquisition unit uses sensors, such as vibration sensors, sound sensors, etc., to acquire health data; the health status evaluation model is used to predict the health status based on the working data and health data. In addition, the neural network model can be trained first, and the training data can be collected. The neural network model can be trained by setting the loss function and optimizer to obtain a high-precision health status evaluation model, and in the subsequent use process, an adaptive learning mechanism can be set to allow the model to be fine-tuned according to the latest data to adapt to the changes in the battery over time and continuously optimize the accuracy of the model.

[0078] Optionally, the health status assessment model includes an input layer, a feature extraction layer, a multimodal fusion layer, an attention layer, a recurrent layer, and an output layer;

[0079] The input layer is used to obtain the working data and the health data, wherein the health data includes vibration data and sound data;

[0080] The feature extraction layer includes a first convolution layer, a second convolution layer and a third convolution layer, wherein the first convolution layer is used to extract the working time feature of the working data; the second convolution layer is used to extract the vibration frequency feature of the vibration data; and the third convolution layer is used to extract the sound frequency feature of the sound data;

[0081] The multimodal fusion layer includes a feature fusion layer and a fully connected layer. The feature fusion layer is used to fuse the working time feature, the vibration frequency feature and the sound frequency feature to generate a multimodal fusion feature. The fully connected layer is used to integrate the multimodal fusion features to generate high-level low-dimensional features.

[0082] The attention layer is based on an attention mechanism, and is used to convert the high-level low-dimensional features into importance features;

[0083] The cyclic layer is used to extract the long-term dependency of the importance feature, and cyclically stack the long-term dependency to generate a time series feature;

[0084] The output layer is used to map the time series features to generate the health status.

[0085] Specifically, Figure 8As shown in FIG. 1 , the health status assessment model includes an input layer, a feature extraction layer, a multimodal fusion layer, an attention layer, a loop layer, and an output layer; the input layer is used to obtain work data and health data, wherein the health data includes vibration data and sound data. The input layer sorts the obtained work data and health data in time series, performs data preprocessing, and standardizes or normalizes the input data to ensure that different sensor data are on the same scale. At the same time, the sliding window technology can be used to convert the original time series into a subsequence of fixed length, which is convenient for subsequent feature extraction of the time dimension. The feature extraction layer includes a first convolution layer, a second convolution layer, and a third convolution layer. The first convolution layer is used to extract the working time features of the work data; the second convolution layer is used to extract the vibration frequency features of the vibration data; and the third convolution layer is used to extract the sound frequency features of the sound data. The first convolution layer, the second convolution layer, and the third convolution layer are all one-dimensional convolution layers. The difference is that since the first convolution layer, the second convolution layer, and the third convolution layer process different types of data, the number of convolution kernels set inside them is also different. For example, when processing vibration signals, more convolution kernels are required to capture features in different frequency ranges. Exemplarily, a maximum pooling layer can be set after the first convolutional layer, the second convolutional layer, and the third convolutional layer to achieve dimensionality reduction, thereby improving computational efficiency. The multimodal fusion layer includes a feature fusion layer and a fully connected layer. The feature fusion layer is used to fuse working time features, vibration frequency features, and sound frequency features to generate multimodal fusion features; the fully connected layer integrates multimodal fusion features to generate high-level low-dimensional features; the feature fusion layer fuses the working time features, vibration frequency features, and sound frequency features of different modes into multimodal fusion features, and then integrates the multimodal features through the fully connected layer. Through its internal weight matrix and activation function, nonlinear feature transformation can be performed. This transformation helps to capture the complex interactive relationship between different modal features, so that the model can learn the interactive relationship between different modalities. Among them, multiple fully connected layers can be set, and all fully connected layers are connected in sequence to further integrate multimodal features. The attention layer is based on the attention mechanism and is used to convert high-level low-dimensional features into importance features. The attention layer uses an attention mechanism, such as a self-attention mechanism, which allows the model to automatically learn which modes are more important in the current state, so that the model can dynamically focus on important time points in the time dimension to obtain importance features. The recurrent layer is used to extract the long-term dependencies of the importance features, and cyclically stack the long-term dependencies to generate time series features; the recurrent layer can use an LSTM network to capture the long-term dependencies in the time series, and cyclically stack the long-term dependencies to generate time series features. The output layer is used to map the time series features and generate the health status. The output layer uses a Sigmoid activation function to limit the output between 0 and 1 to represent the health status of the battery.

[0086] Another embodiment of the present invention provides a vehicle, comprising the battery management system as described above.

[0087] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc. In the present application, the unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment of the present invention. In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0088] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. A battery management system, used for managing battery packs, characterized in that: include: Isolate the power supply module, processor, CAN communication module and wake-up module; The input end of the isolated power supply module is connected to the battery pack, the output end of the isolated power supply module is connected to the CAN communication module, and the isolated power supply module is used to provide isolated power to the CAN communication module; The CAN communication module is used to connect to an external CAN communication module through a CANH signal line and a CANL signal line to receive external information of the external CAN communication module; The input end of the wake-up module is respectively connected to the CANH signal line and the CANL signal line, and is used to receive the differential signal between the CANH signal line and the CANL signal line. The input end of the wake-up module is also used to connect to an external wake-up source, and is used to receive an external wake-up signal from the external wake-up source. The output end of the wake-up module is connected to the input end of the processor, and is used to output an internal wake-up signal to the processor according to the differential signal and / or the external wake-up signal. The input end of the processor is connected to the CAN communication module for receiving the external information, the output end of the processor is connected to the enable pin of the isolated power module for controlling the start and stop of the isolated power module according to the external information and the internal wake-up signal, and the battery pack is also connected to the power supply end of the processor for supplying power to the processor; The battery management system further includes an analog front-end acquisition chip and an analog front-end protection chip, wherein a first end of the analog front-end acquisition chip and the analog front-end protection chip are both connected to the battery pack, and a second end of the analog front-end acquisition chip is connected to the processor; The analog front-end acquisition chip is used to collect the working data of the battery pack, control the charging and discharging circuit of the battery pack according to the working data, and transmit the working data to the processor; The analog front-end protection chip is used to collect the working data and control the charging and discharging circuit of the battery pack according to the working data; The battery management system further includes a battery evaluation module, which is connected to the battery pack and the processor respectively, and is used to obtain the working data, determine the load state of the battery pack according to the working data, and collect health data of the battery pack, and predict the health state of the battery pack according to the working data and the health data; The battery evaluation module includes an acquisition unit and a health status evaluation model; The acquisition unit is used to acquire the health data; The health status assessment model is used to predict the health status according to the work data and the health data; The health status assessment model includes an input layer, a feature extraction layer, a multimodal fusion layer, an attention layer, a loop layer, and an output layer; The input layer is used to obtain the working data and the health data, wherein the health data includes vibration data and sound data; The feature extraction layer includes a first convolution layer, a second convolution layer and a third convolution layer, wherein the first convolution layer is used to extract the working time feature of the working data; the second convolution layer is used to extract the vibration frequency feature of the vibration data; and the third convolution layer is used to extract the sound frequency feature of the sound data; The multimodal fusion layer includes a feature fusion layer and a fully connected layer. The feature fusion layer is used to fuse the working time feature, the vibration frequency feature and the sound frequency feature to generate a multimodal fusion feature. The fully connected layer is used to integrate the multimodal fusion features to generate high-level low-dimensional features. The attention layer is based on the self-attention mechanism in the attention mechanism, and is used to convert the high-level low-dimensional features into importance features; The circulation layer adopts an LSTM network to extract the long-term dependency of the importance feature, and cyclically stack the long-term dependency to generate time series features; The output layer uses a Sigmoid activation function to map the time series features and generate the health status.

2. The battery management system according to claim 1, characterized in that: The wake-up module includes an optocoupler, the input end of the optocoupler is respectively connected to the CANH signal line and the CANL signal line, the input end of the optocoupler is connected to the processor, and the optocoupler is used to receive the differential signal and convert the differential signal into the internal wake-up signal.

3. The battery management system according to claim 1, characterized in that: The battery management system also includes a voltage stabilizing module, the input end of the voltage stabilizing module is connected to the battery pack, the output end of the voltage stabilizing module is respectively connected to the input end of the isolation power supply module and the power supply end of the processor, and the voltage stabilizing module is used to convert the voltage of the battery pack into a stable voltage.

4. The battery management system according to claim 1, characterized in that: The CAN communication module includes a CAN communication chip and an isolation communication chip; The CAN communication chip is used to connect to the external CAN communication module through the CANH signal line and the CANL signal line to receive the external information; The isolation communication chip is connected to the CAN communication chip and the processor respectively, and is used to protect the external information and transmit the external information to the processor.

5. The battery management system according to claim 1, characterized in that: The battery management system also includes a storage module, which is connected to the processor via SPI communication, and is used to store processing data of the processor.

6. A vehicle, characterized in that: Comprising a battery management system as described in any one of claims 1-5.

Images