Vehicle-mounted battery management and vehicle network security fused data transmission method

Abstract

The invention discloses a vehicle-mounted battery management and vehicle network security fused data transmission method, which comprises the following steps: a sending end performs data acquisition and preliminary fusion to form multi-dimensional data; based on the first neural network model and the multi-dimensional data, obtaining corresponding high-dimensional features; encrypting the high-dimensional features and then transmitting the high-dimensional features; and the receiving end obtains a final result instruction based on the second neural network model and the high-dimensional feature. Wherein the neural network model is an algorithm model with neurons as calculation units, and the neural network model is composed of a first neural network model and a second neural network model. According to the invention, the randomness of neurons is combined with a traditional encryption mode, and the correction bit and a mechanism for determining the randomness parameter based on the current timestamp are introduced, so that the security of a data transmission system is remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the field of vehicle network security, and more specifically, relates to a data transmission method integrating vehicle battery management with vehicle network security. Background Art

[0002] The current on-board battery management system (BMS) and vehicle network security system mainly rely on traditional encryption technology and data transmission protocols, and ensure that data is not stolen or tampered with during transmission through hardware encryption chips, digital signatures, and dynamic key updates. At the same time, neural computing models such as deep neural networks, convolutional neural networks (CNNs), and recurrent neural networks (RNNs) have been widely used in fields such as autonomous driving and energy management for real-time data analysis and decision support. However, these systems still have loopholes in data protection: once hackers obtain encryption keys or crack encryption algorithms, they may affect system judgments by tampering with feature mappings, and traditional protection measures are difficult to fully protect against the variability introduced by the randomness of neural network models.

[0003] During the autonomous driving process, the vehicle obtains real-time images of the surrounding environment through image sensors, and generates specific control instructions based on the vehicle status information, thereby adjusting the charging and discharging strategies of the battery modules to achieve efficient energy management. At the same time, the battery control unit collects key parameters such as temperature, voltage, current, internal resistance, SOC, SOH, etc., and transmits them to the central control unit and remote monitoring platform in real time through the vehicle network for fault diagnosis and safety linkage protection. In these scenarios, data transmission must not only ensure high speed and low latency, but also ensure that the data will not be maliciously tampered with or intercepted during transmission, thereby affecting autonomous driving decisions and battery management strategies. Summary of the invention

[0004] In order to solve the deficiencies in the prior art, the purpose of the present invention is to solve the above-mentioned defects and further propose a data transmission method that integrates on-board battery management and vehicle network security.

[0005] The present invention adopts the following technical solution.

[0006] The first aspect of the present invention discloses a data transmission method integrating vehicle-mounted battery management and vehicle network security, comprising: At the sending end, data is collected and initially integrated to form multi-dimensional data; Based on the first neural network model and the multi-dimensional data, obtaining corresponding high-dimensional features; Encrypt high-dimensional features before transmitting; The receiving end obtains the final result instruction based on the second neural network model and high-dimensional features; Among them, the neural network model is an algorithm model that uses neurons as calculation units, and the neural network model is composed of a first neural network model and a second neural network model.

[0007] Furthermore, the algorithm model using neurons as computing units is CNN, RNN or DNN.

[0008] Furthermore, the result instruction is based on data generated by the vehicle in real time and is obtained according to the output of the neural network model.

[0009] Furthermore, all neurons in the neural network algorithm are regarded as all nodes of a graph, and the connection relationship between neurons constitutes the directed edges of the graph, so the high-dimensional feature is the cut directed edges.

[0010] Furthermore, high-dimensional features are feature maps output by the intermediate layers in the neural network model.

[0011] Furthermore, in the neural network model, the input layer and the intermediate layer are arranged at the transmitting end, and the output layer is arranged at the receiving end.

[0012] Furthermore, the high-dimensional features also include check bits, which are used by the receiving end to verify whether the data is correct; wherein the sending end includes an output layer, and the check bits are obtained based on the high-dimensional features and the parameters of all randomness in the collapsed output layer.

[0013] A second aspect of the present invention discloses a data transmission system integrating vehicle-mounted battery management and vehicle network security, comprising: a vehicle-mounted battery management system and a vehicle network security system; When exchanging data between the on-board battery management system and the vehicle network security system, they serve as the sender and receiver to each other; The sending end is used for data collection and preliminary fusion to form multi-dimensional data; and based on the first neural network model and the multi-dimensional data, obtains the corresponding high-dimensional features; and encrypts the high-dimensional features and transmits them to the receiving end; The receiving end is used to obtain the final result instruction based on the second neural network model and the high-dimensional features; Among them, the neural network model is an algorithm model that uses neurons as calculation units, and the neural network model is composed of a first neural network model and a second neural network model.

[0014] The third aspect of the present invention discloses a terminal, including a processor and a storage medium; the characteristics are: The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the method described in the first aspect.

[0015] The fourth aspect of the present invention discloses a computer-readable storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0016] The beneficial effects of the present invention are that, compared with the prior art, the present invention has the following advantages: The present invention significantly improves the security of the data transmission system by combining the randomness of neurons with traditional encryption methods, introducing correction bits and a mechanism for determining randomness parameters based on the current timestamp. At the sending end, not only the feature mapping data is transmitted, but also the correction bit information is attached, so that the receiving end can verify the data integrity and ensure that even if there is randomness in the feature mapping, its actual operation results can be accurately restored. In this way, hackers not only need to perform brute force calculations when cracking encrypted data, but also must simulate the entire neural network operation process, which greatly increases the difficulty of cracking, improves the protection capabilities of the entire on-board battery management and vehicle network security system, and effectively ensures the safe and stable operation of autonomous driving and energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of a neural network model under data transmission that integrates on-board battery management and vehicle network security in an embodiment of the present invention.

[0018] Figure 2 It is a schematic diagram of a data transmission system integrating vehicle-mounted battery management and vehicle network security according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The present application is further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present application.

[0020] In the present invention, the vehicle-mounted battery management system (BMS) includes at least: battery module, battery control unit (BCU), communication interface and other modules. The battery module constitutes the basic unit of the battery pack, and each battery cell has a certain voltage and capacity. Multiple cells are composed of modules according to a certain structure, and then integrated to form an overall battery pack; the battery control unit is the core processor, responsible for collecting sensor data, running battery management algorithms, judging the status of each cell, and executing protection and balancing strategies; the communication interface transmits battery data to the vehicle network security system through CAN, LIN, Ethernet and other communication protocols to achieve data interaction and collaborative control.

[0021] The vehicle network security system includes at least: an on-board gateway module, an on-board control module, etc. The on-board gateway module serves as the data hub between the various on-board subsystems, realizing the interconnection of different networks (such as the power system network and the infotainment network), while providing basic data filtering functions; the on-board control module is used to generate precise control instructions to optimize the overall operation status of the vehicle, while encrypting the data and ensuring the safe coordination between the subsystems. During the autonomous driving process, this module can identify information such as roads, obstacles, pedestrians, etc. based on real-time image data, and intelligently adjust the control strategy based on the current power and energy status of the vehicle to achieve coordinated management of battery charging and discharging, energy recovery and power distribution. In addition, the on-board control module uses hardware or software encryption to encrypt the internal and remote data transmission of the vehicle to ensure that the data is not stolen or tampered with during the transmission process; at the same time, it realizes identity authentication between various terminal devices.

[0022] The data transmission scenarios discussed in the present invention may be: in the first scenario, during the process of autonomous driving, real-time images of the vehicle's surroundings can be obtained based on the image sensor, and the on-board control module can analyze these real-time images to obtain battery control instructions to control the battery module. For example, the battery control instructions may be: "Adjust the battery output power to 85% and activate energy regenerative braking". In the second scenario, the battery control unit can obtain key parameters such as temperature, voltage, current, internal resistance, SOC (state of charge), SOH (state of health), and generate battery abnormality data, fault codes, alarm logs and other data based on the battery control unit.

[0023] The first scenario is essentially sending the result instruction from the vehicle network security system to the BMS, while the second scenario is essentially transmitting the result instruction from the BMS to the vehicle network security system. In the prior art, the steps can be summarized as step 1 to step 3.

[0024] Step 1: At the sending end, data is collected and initially integrated to form multi-dimensional data.

[0025] Inside the transmitter, real-time status data is collected through various sensors. Usually, clock synchronization technology is required to ensure the consistency of time among data sources, and edge nodes are used to perform preliminary filtering and correction on the data to resolve security vulnerabilities caused by data loss or errors.

[0026] Step 2: Perform real-time analysis in multiple dimensions and output corresponding result instructions.

[0027] Step 2 is essentially to select a specific algorithm according to different application scenarios, and then output the result instruction to be sent to the receiving end.

[0028] For example, the first scenario involves the processing of image data, and neural network algorithms such as CNN, RNN, and DNN can usually be selected, while the second scenario often gives priority to algorithms such as decision trees, SVM, and K-NN.

[0029] It is understandable that step 1 is actually data cleaning, normalization, defect removal and other operations. And step 2 is actually based on the trained algorithm model and the multi-dimensional data of step 1 to obtain the corresponding output. These are all common knowledge and will not be repeated. In the first scenario, the multi-dimensional data can be the image data obtained by each image sensor, and the corresponding result instruction can be a battery control instruction. In the second scenario, the multi-dimensional data can be key parameters such as temperature, voltage, current, internal resistance, SOC (state of charge), SOH (state of health), and the corresponding result instruction can be battery abnormality data, fault code, alarm log and other data.

[0030] Step 3: Before sending, the result instruction needs to be encrypted.

[0031] Since the result instruction is based on the data generated by the vehicle in real time and is obtained according to the output of the neural network model, considering the real-time nature of data transmission, step 3 usually adopts a lightweight encryption algorithm (such as a hybrid solution of ECC and AES), which makes the encryption itself easy to be cracked by brute force.

[0032] This section introduces the representative neural network algorithm CNN. CNN mainly includes: input layer, middle layer (hidden layer) and output layer.

[0033] The input layer is used to receive raw data and pass it to the network in the form of vectors or tensors. Usually, the input layer does not perform complex operations, but is responsible for data format conversion and normalization to provide appropriate input for subsequent layers.

[0034] The middle layer is usually the core of CNN, and its main function is to extract features and convert data representation. The hidden layer can be further divided into different types of layers, each of which plays a specific role. These layers can usually be: convolutional layer, pooling layer, fully connected layer, etc.

[0035] The output layer is used to map the features finally extracted by the hidden layer to the output space of the target task. The structure and activation function of the output layer depend on the specific task or specific application scenario.

[0036] It is not difficult to understand that the basic structures of other neural network algorithms (such as RNN and DNN) are the same. The only difference is the way of obtaining feature maps, usually the logic of the middle layer is different.

[0037] Assuming that the algorithm selected in step 2 is a neural network algorithm, then the traditional method is essentially to encrypt the result instruction (output by the output layer) and then transmit it from the sender to the receiver in step 3.

[0038] The disadvantage of this approach is that once hackers understand the rules of encryption and crack the encryption method, they can change the resulting instructions.

[0039] Since the result instructions usually have a standardized format, hackers can easily infer the specific numerical type corresponding to each value based on the specific numerical values ​​(usually these values ​​have a stable fluctuation range).

[0040] For example, if the result instruction is cracked as [0.01; 0.02; 0.95; 0.01; 0.01], it is not difficult to infer that the result instruction is actually a prediction result containing 5 situations, among which the probability of the third situation occurring is 95%.

[0041] Understandably, the data in the result instruction has a repetitive characteristic, which means that in order to prevent the data from being tampered with during the transmission process, a check bit needs to be supplemented.

[0042] The process of adding a check digit can be summarized as follows: d2 = check(d,tm) Among them, d is the result instruction, tm should usually be the current timestamp, and d2 is the result instruction including the check bit (usually also including tm).

[0043] However, this approach is actually useless because once a hacker cracks the encryption itself, cracking the check digit again will only increase the difficulty of cracking linearly by less than double.

[0044] Based on this, the present invention proposes a data transmission method that integrates on-board battery management and vehicle network security. The core essence is to "invisibly" integrate the data to be transmitted of the on-board battery management and the vehicle network security system to achieve multi-level security protection of the data to be transmitted, including: at the sending end, data collection and preliminary fusion to form multi-dimensional data; based on the first neural network model and the multi-dimensional data, obtaining corresponding high-dimensional features; encrypting the high-dimensional features and transmitting them; at the receiving end, based on the second neural network model and the high-dimensional features, obtaining the final result instructions; wherein the neural network model is an algorithm model with neurons as calculation units, and the neural network model is composed of a first neural network model and a second neural network model.

[0045] It should be understood that the present invention is not very suitable for the second scenario. However, if the second scenario also selects a neural network algorithm such as CNN, RNN, etc., the present invention can also be applied to the second scenario.

[0046] In an embodiment of the present invention, the high-dimensional feature is preferably a feature map output by an intermediate layer.

[0047] It should be pointed out here that high-dimensional features can also be selected as an output of the intermediate layer. However, the problem with this approach is that, on the one hand, the logic of the intermediate layer is too complicated, and each neuron has a large coupling. In other words, if the intermediate layer is analyzed into convolutional layers, pooling layers, recursive layers, etc., the internal operation logic is not serial, but can be parallel, or a combination of serial and parallel, such as Figure 1 As shown. Once it is parallel, it is difficult to segment high-dimensional features. On the other hand, in further embodiments (see the content of the check bit below), how to control the parameters of partial randomness in the middle layer, that is, how to cut the middle layer, is also an extremely complex problem.

[0048] Figure 1 In the figure, modules 1 to 12 can refer to convolutional layers, pooling layers, etc.

[0049] This paragraph explains "it is difficult to segment high-dimensional features". The "segmentation" in this sentence can be compared to the concept of cut in graph theory. That is, if all neurons in the neural network algorithm are regarded as all nodes of a graph, and the connection relationship of neurons constitutes the directed edge of the graph, then high-dimensional features can only be cut directed edges. Therefore, if there are complex parallel relationships in the middle layer, it is very likely that there will be no cut directed edges.

[0050] It can be understood that the directed edge actually represents the input and output of the neuron, and the cut directed edge means that its single edge constitutes a cut of the graph.

[0051] Specifically, in Figure 1 In the example, the cut can be c1: {1->2}; c2: {8->9}, or c3: {3->4; 5->6}, but only 1->2 and 8->9 are single-edge cuts, i.e., cut directed edges. If 8->9 is selected as the cut directed edge, the first neural network model consists of 1 to 8 modules, and the second neural network model consists of 9 to 12 modules.

[0052] It is understandable that once the high-dimensional features are determined, the first neural network model and the second neural network model after splitting the neural network model must also be determined.

[0053] Furthermore, the feature map output by the middle layer must be a directed edge; accordingly, the first neural network model is the input layer and the middle layer, which are arranged at the sending end, and the second neural network model is the output layer, which is arranged at the receiving end.

[0054] The feature map (a vector) usually has a high degree of randomness, which makes it impossible to clarify the specific meaning of each element in the feature map even if the data is cracked. Most importantly, the activation function included in the output layer is a probability model (not an invertible or non-invertible computational model like matrix operations), which makes hackers feel at a loss when using brute-force cracking methods based on matrix operations. The essence of the present invention is to combine the randomness of neurons with traditional encryption methods to form a multi-level security protection structure. Unless hackers completely crack the encryption method and the neural network model, it is impossible to crack the data to be transmitted.

[0055] The expression of the output layer is specifically as follows: d = f(W * a + b) Where f is the activation function of the output layer, a is the feature map, W is the m*n weight matrix in the output layer, and b is the bias term. It can be understood that m < n, and thus an n-dimensional feature map is implemented on an m-dimensional result instruction.

[0056] The probability model is essentially a double-edged sword. If hackers tamper with the feature map, the receiving end has no way of knowing. Therefore, the data sent by the sending end should not only include the feature map itself, but also include a correction bit. When giving the correction bit, the parameter of randomness should be determined. For example, it can be based on the current timestamp, so that the parameter of randomness collapses to a specific value.

[0057] Collapse means that a parameter of randomness is determined to be a fixed value. It can be understood that in a neural network model, any randomized parameter must be determined to be a fixed value when finally participating in network calculations to ensure the uniqueness of the output result.

[0058] Assume that the feature map a is represented as the following vector [a1, a2,..., an]. Then, the original intention of the correction bit can be understood as a parity check bit or error correction code (to prevent data transmission errors), but in the scenario of the present invention, it can also essentially prevent data from being tampered with.

[0059] It can be understood that whether it is data transmission error or being tampered with, they are essentially the same, that is, the transmitted data is not the correct and true data.

[0060] To ensure the correctness and authenticity of the transmitted data, the transmitted feature map should actually also include the timestamp tm and the c check bits.

[0061] It should be noted here that c can include multiple elements (for example: c1, c2, c3...), and its positions can be scattered in the feature map. That is to say, the final transmitted feature map may look like this: [c1, a1, c2, a2, a3, c3, a4, ..., an, tm] If c = g(a, tm), where g is the pre-set verification rule agreed upon by the sender and the receiver. In other words, if c is not equal to f(a, tm), it needs to be resent.

[0062] It is understandable that the significance of introducing the timestamp tm is to ensure the randomness of the check bit c.

[0063] In summary, the high-dimensional features also include check bits, which are used by the receiving end to verify whether the data is correct. The sending end should also include an output layer, and the check bits are obtained based on the high-dimensional features and the parameters of all randomness in the collapsed output layer.

[0064] In this case, in order to crack the password, hackers not only have to perform brute force calculations, but also have to simulate the computing process of the neural network model itself, which undoubtedly greatly increases the difficulty of cracking.

[0065] Correspondingly, the present invention also discloses a data transmission system integrating vehicle-mounted battery management and vehicle network security, such as Figure 2 As shown, it includes: vehicle-mounted battery management system and vehicle network security system; When the on-board battery management system and the vehicle network security system exchange data, they act as the transmitter and receiver to each other; the transmitter is used for data collection and preliminary fusion to form multi-dimensional data; and based on the first neural network model and the multi-dimensional data, the corresponding high-dimensional features are obtained; and the high-dimensional features are encrypted and transmitted to the receiver; the receiver is used to obtain the final result instruction based on the second neural network model and the high-dimensional features; the neural network model is an algorithm model with neurons as the calculation unit, and the neural network model is composed of a first neural network model and a second neural network model.

[0066] The applicant of the present invention has made a detailed explanation and description of the implementation examples of the present invention in conjunction with the drawings in the specification. However, those skilled in the art should understand that the above implementation examples are only preferred implementation schemes of the present invention, and the detailed description is only to help readers better understand the spirit of the present invention, but not to limit the scope of protection of the present invention. On the contrary, any improvements or modifications based on the inventive spirit of the present invention should fall within the scope of protection of the present invention.

Claims

1. A data transmission method integrating vehicle battery management and vehicle network security, characterized in that: include: At the sending end, data is collected and initially integrated to form multi-dimensional data; Based on the first neural network model and the multi-dimensional data, obtaining corresponding high-dimensional features; Encrypt high-dimensional features before transmitting; The receiving end obtains the final result instruction based on the second neural network model and high-dimensional features; Among them, the neural network model is an algorithm model that uses neurons as calculation units, and the neural network model is composed of a first neural network model and a second neural network model.

2. A data transmission method integrating vehicle battery management and vehicle network security according to claim 1, characterized in that: The algorithm model that uses neurons as computing units is CNN, RNN or DNN.

3. The data transmission method for integrating vehicle battery management and vehicle network security according to claim 1 is characterized in that: The result instruction is based on data generated by the vehicle in real time and is obtained according to the output of the neural network model.

4. The data transmission method for integrating vehicle battery management and vehicle network security according to claim 1 is characterized in that: All neurons in the neural network algorithm are regarded as all the nodes of a graph. The connection relationship between neurons constitutes the directed edges of the graph, and the high-dimensional feature is the cut directed edges.

5. The data transmission method for integrating vehicle battery management and vehicle network security according to claim 4 is characterized in that: High-dimensional features are feature maps output by the intermediate layers in the neural network model.

6. A data transmission method integrating vehicle battery management and vehicle network security according to claim 5, characterized in that: In the neural network model, the input layer and the middle layer are set at the sending end, and the output layer is set at the receiving end.

7. The data transmission method for integrating vehicle battery management and vehicle network security according to claim 1 is characterized in that: The high-dimensional features also include check bits, which are used by the receiving end to verify whether the data is correct. The sending end includes an output layer, and the check bits are obtained based on the high-dimensional features and the parameters of all randomness in the collapsed output layer.

8. A data transmission system integrating vehicle battery management and vehicle network security, applied to any method of claims 1-7, characterized in that: The system includes: an on-board battery management system and a vehicle network security system; When exchanging data between the on-board battery management system and the vehicle network security system, they serve as the sender and receiver to each other; The sending end is used for data collection and preliminary fusion to form multi-dimensional data; and based on the first neural network model and the multi-dimensional data, obtains the corresponding high-dimensional features; and encrypts the high-dimensional features and transmits them to the receiving end; The receiving end is used to obtain the final result instruction based on the second neural network model and the high-dimensional features; Among them, the neural network model is an algorithm model that uses neurons as calculation units, and the neural network model is composed of a first neural network model and a second neural network model.

9. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of a data transmission method for integrating vehicle battery management and vehicle network security according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of a data transmission method for integrating vehicle-mounted battery management and vehicle network security as described in any one of claims 1 to 7 are implemented.

Images