Intelligent control system and method for new energy automobile air suspension shock absorber

Abstract

The invention provides an intelligent control system and method for an air suspension shock absorber of a new energy automobile, and relates to the field of intelligent control of the new energy automobile, and the intelligent control method comprises the following steps: carrying out data integration and time sequence feature coding on a set of vehicle state data by adopting a data processing technology based on deep learning; aggregation and parameter correlation are carried out on the time sequence characteristics of the vehicle state data, so that the pressure value of the air spring is intelligently predicted based on the global-local semantic mapping enhanced representation of the time sequence correlation coding characteristics of the aggregated and correlated vehicle state parameters; and the pressure value of the air spring is adaptively adjusted according to the comparison with the real-time parameters. In this way, the pressure of the air spring can be dynamically adjusted in real time, and the driving experience and the driving safety can be improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent control of new energy vehicles, and more specifically, to an intelligent control system and method for an air suspension shock absorber of a new energy vehicle. Background Art

[0002] As the automotive industry is rapidly developing towards intelligence and electrification, new energy vehicles have become the focus of the market. As one of the core components, air suspension shock absorbers can adjust the vehicle height and suspension hardness by adjusting the pressure of the air spring to adapt to various road conditions and load conditions.

[0003] However, traditional air suspension systems mainly rely on fixed parameter settings or simple feedback mechanisms. On the one hand, fixed parameter settings cannot adapt to changing road conditions and load conditions, resulting in poor suspension performance; on the other hand, simple feedback mechanisms are slow to respond, and it is difficult to adjust the pressure of the air spring in time when faced with complex driving behaviors such as sudden acceleration and braking, as well as sudden road conditions such as potholes and speed bumps. This limitation severely restricts the system's dynamic adjustment capabilities and overall performance improvement, affecting the optimization of the driving experience and driving safety.

[0004] Therefore, an intelligent control solution for the air suspension shock absorber of a new energy vehicle is desired. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an intelligent control system and method for an air suspension shock absorber of a new energy vehicle.

[0006] According to one aspect of the present application, an intelligent control system for an air suspension shock absorber of a new energy vehicle is provided, which includes: A vehicle status data acquisition module, used to acquire vehicle status data collected by a sensor component deployed in a new energy vehicle to obtain a set of vehicle status data, wherein the sensor component includes an acceleration sensor, a vehicle speed sensor, a height sensor, and a vibration frequency sensor, and the vehicle status data includes a vehicle acceleration value, a vehicle speed value, a vehicle height value, and a vehicle vibration frequency value; A vehicle state time series feature extraction module, used for performing data regularization and time series feature extraction on the set of vehicle state data to obtain a vehicle acceleration time series correlation feature implicit coding vector, a vehicle speed time series correlation feature implicit coding vector, a vehicle height time series change feature implicit coding vector and a vehicle vibration frequency time series correlation feature implicit coding vector; A vehicle state parameter association module, used for performing multi-dimensional time series association on the vehicle acceleration time series association feature implicit coding vector, the vehicle speed time series association feature implicit coding vector, the vehicle height time series change feature implicit coding vector and the vehicle vibration frequency time series association feature implicit coding vector to obtain a time series association coding feature map between vehicle state parameters; A vehicle state parameter temporal correlation enhancement module is used to perform global-local vehicle state semantic mapping enhancement on the vehicle state parameter temporal correlation coding feature map to obtain an enhanced vehicle state parameter temporal correlation coding feature map; The pressure value adjustment module is used to adjust the pressure value of the air spring based on the enhanced time series correlation coding characteristic diagram between vehicle state parameters.

[0007] According to another aspect of the present application, there is provided an intelligent control method for an air suspension shock absorber of a new energy vehicle, comprising: Acquire vehicle status data collected by a sensor component deployed in a new energy vehicle to obtain a set of vehicle status data, wherein the sensor component includes an acceleration sensor, a vehicle speed sensor, a height sensor, and a vibration frequency sensor, and the vehicle status data includes a vehicle acceleration value, a vehicle speed value, a vehicle height value, and a vehicle vibration frequency value; Performing data regularization and time series feature extraction on the set of vehicle state data to obtain an implicit coding vector of vehicle acceleration time series correlation features, an implicit coding vector of vehicle speed time series correlation features, an implicit coding vector of vehicle height time series change features, and an implicit coding vector of vehicle vibration frequency time series correlation features; Performing multi-dimensional time series correlation on the vehicle acceleration time series correlation feature implicit coding vector, the vehicle speed time series correlation feature implicit coding vector, the vehicle height time series change feature implicit coding vector and the vehicle vibration frequency time series correlation feature implicit coding vector to obtain a time series correlation coding feature map between vehicle state parameters; Performing global-local vehicle state semantic mapping enhancement on the vehicle state parameter temporal correlation coding feature map to obtain an enhanced vehicle state parameter temporal correlation coding feature map; Based on the enhanced time series correlation coding characteristic diagram between vehicle state parameters, the pressure value of the air spring is adjusted.

[0008] Compared with the prior art, the intelligent control system and method of the air suspension shock absorber of a new energy vehicle provided by the present application uses a data processing technology based on deep learning to integrate data and encode time series features of a collection of vehicle state data, and then aggregates and associates the time series features of each vehicle state data with parameters, thereby intelligently predicting the pressure value of the air spring based on the global-local semantic mapping enhanced representation of the time series association encoding features between the aggregated and associated vehicle state parameters, and adaptively adjusting the pressure value of the air spring by comparing it with the real-time parameters. In this way, real-time dynamic adjustment of the air spring pressure can be achieved, which helps to improve the driving experience and driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] 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: Figure 1 This is a system block diagram of an intelligent control system for an air suspension shock absorber of a new energy vehicle according to an embodiment of the present application.

[0010] Figure 2 The present invention is a block diagram of a vehicle state time series feature extraction module in an intelligent control system of an air suspension shock absorber for a new energy vehicle according to an embodiment of the present application.

[0011] Figure 3 The present invention is a block diagram of a vehicle state parameter association module in an intelligent control system of an air suspension shock absorber for a new energy vehicle according to an embodiment of the present application.

[0012] Figure 4 The present invention is a block diagram of a vehicle state parameter timing correlation enhancement module in an intelligent control system of an air suspension shock absorber of a new energy vehicle according to an embodiment of the present application.

[0013] Figure 5 The present invention is a flowchart of an intelligent control method for an air suspension shock absorber of a new energy vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0014] 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.

[0015] As the automotive industry accelerates its development towards intelligence and electrification, new energy vehicles have become the focus of market attention. As one of the key components, air suspension shock absorbers can not only adjust the height of the vehicle by adjusting the pressure of the air spring, but also change the hardness of the suspension to adapt to various road conditions and load requirements.

[0016] However, traditional air suspension systems usually rely on fixed parameter settings or relatively simple feedback adjustment mechanisms. On the one hand, fixed parameter settings are difficult to flexibly respond to complex and changing road conditions and load conditions, resulting in suspension performance that is difficult to achieve ideal conditions; on the other hand, simple feedback adjustments have the problem of slow response speed, especially in violent driving behaviors such as sudden acceleration and braking, as well as in dealing with emergencies such as potholes and speed bumps. It is difficult to adjust the pressure of the air spring in time. These deficiencies significantly limit the system's dynamic response capabilities and overall performance improvements, which not only hinders the optimization of driving comfort, but also has a certain impact on driving safety.

[0017] In response to the above technical problems, the technical concept of the present application is to obtain the vehicle status data collected by the sensor components deployed in the new energy vehicle to obtain a set of vehicle status data (vehicle acceleration value, vehicle speed value, vehicle height value and vehicle vibration frequency value), and use data analysis and feature analysis technology based on deep learning to perform data integration and time series feature encoding of the set of vehicle status data. Then, the time series features of each vehicle status data are aggregated and associated between parameters, so as to intelligently predict the pressure value of the air spring based on the global-local semantic mapping enhanced representation of the time series association encoding features between the aggregated and associated vehicle status parameters, and adjust the pressure value of the air spring adaptively by comparing it with the real-time parameters. The present application enables the system to respond quickly to complex road conditions and driving behaviors through real-time data collection and processing capabilities, and realizes real-time dynamic adjustment of the air spring pressure, thereby significantly improving driving comfort, reducing bumps, and providing a smoother driving experience to improve driving safety.

[0018] Figure 1 : is a system block diagram of an intelligent control system of an air suspension shock absorber for a new energy vehicle according to an embodiment of the present application. Figure 1As shown, in the intelligent control system 100 of the air suspension shock absorber of the new energy vehicle, it includes: a vehicle state data acquisition module 110, which is used to obtain the vehicle state data collected by the sensor component deployed in the new energy vehicle to obtain a set of vehicle state data, wherein the sensor component includes an acceleration sensor, a vehicle speed sensor, a height sensor and a vibration frequency sensor, and the vehicle state data includes a vehicle acceleration value, a vehicle speed value, a vehicle height value and a vehicle vibration frequency value; a vehicle state time series feature extraction module 120, which is used to perform data regularization and time series feature extraction on the set of vehicle state data to obtain a vehicle acceleration time series correlation feature implicit coding vector, a vehicle speed time series correlation feature implicit coding vector, a vehicle height time series change feature implicit coding vector and a vehicle vibration frequency value. The vehicle state parameter association module 130 is used to perform multi-dimensional time series association on the vehicle acceleration time series association feature implicit coding vector, the vehicle speed time series association feature implicit coding vector, the vehicle height time series change feature implicit coding vector and the vehicle vibration frequency time series association feature implicit coding vector to obtain a vehicle state parameter time series association coding feature map; the vehicle state parameter time series association enhancement module 140 is used to perform global-local vehicle state semantic mapping enhancement on the vehicle state parameter time series association coding feature map to obtain an enhanced vehicle state parameter time series association coding feature map; the pressure value adjustment module 150 is used to adjust the pressure value of the air spring based on the enhanced vehicle state parameter time series association coding feature map.

[0019] In the embodiment of the present application, the vehicle state data acquisition module 110 is used to obtain the vehicle state data collected by the sensor assembly deployed in the new energy vehicle to obtain a set of vehicle state data, wherein the sensor assembly includes an acceleration sensor, a vehicle speed sensor, a height sensor and a vibration frequency sensor, and the vehicle state data includes a vehicle acceleration value, a vehicle speed value, a vehicle height value and a vehicle vibration frequency value. It should be understood that the acceleration value can reflect the dynamic behaviors of the vehicle such as acceleration, deceleration, sudden acceleration and sudden braking. During sudden acceleration, the center of gravity of the vehicle moves backward, and the air suspension system needs to adjust the air spring pressure to maintain the balance and stability of the vehicle body to avoid excessive rise of the front of the vehicle; during sudden braking, the center of gravity of the vehicle moves forward, and the appropriate air spring pressure can prevent the front of the vehicle from sinking excessively, ensuring the handling performance and safety of the vehicle. Different vehicle speeds will also affect the vehicle's requirements for the air suspension system. When driving at high speeds, the vehicle needs a harder suspension to improve stability and reduce the shaking and roll of the vehicle body; while when driving at low speeds, a relatively soft suspension can provide better comfort and absorb bumps on the road. The vehicle height value reflects the ground clearance of the vehicle and the posture of the vehicle body. When the vehicle passes through different road conditions, such as raised speed bumps, potholes, etc., the height of the vehicle will change. By obtaining the vehicle height value, the intelligent control system can determine the current road condition of the vehicle. For example, when the height of the vehicle suddenly drops, it may be that it encounters a pothole. At this time, it is necessary to increase the pressure of the air spring to cushion the impact and protect the vehicle and passengers; when the height of the vehicle rises, it may be that it passes through a bump. The system can adjust the pressure appropriately to restore the normal body posture. In addition, the vehicle height value is also related to the load of the vehicle. When fully loaded, the height of the vehicle will decrease, and the air spring pressure needs to be adjusted accordingly to maintain a suitable suspension state. The vibration frequency value can reflect the flatness of the road surface and the working state of the vehicle suspension system. Different road conditions will produce vibrations of different frequencies. For example, rough roads will cause the vehicle to produce high-frequency vibrations, while flat roads have lower vibration frequencies. By obtaining the vehicle vibration frequency value, the intelligent control system can understand the condition of the road surface. For high-frequency vibration roads, increasing the pressure of the air spring can increase the stiffness of the suspension and reduce the vibration of the vehicle; for low-frequency vibration roads, the pressure can be appropriately reduced to improve comfort. In general, the vehicle status data obtained are the basic basis for adjusting the air spring pressure value. By analyzing the obtained vehicle status data, we can understand the actual operating status of the vehicle and make corresponding adjustments to the air spring pressure value based on this to adapt to the ever-changing road conditions and driving conditions, ensuring the best driving experience and driving safety.

[0020] The following is a detailed description of a specific implementation process of "obtaining vehicle status data collected by sensor components deployed in new energy vehicles to obtain a collection of vehicle status data": The first is the selection and installation of the sensor. In order to accurately measure the acceleration changes of the vehicle during driving, a high-precision, fast-response three-axis acceleration sensor such as ADXL345 is often used. It can accurately sense the acceleration of the vehicle in the three directions of X, Y, and Z. The range selection needs to be based on the actual use scenario of the vehicle, generally determined in ±2g, ±4g, ±8g or ±16g to adapt to the acceleration changes under different driving conditions such as sudden acceleration and sudden braking. When installing, it should be firmly placed near the center of gravity of the vehicle chassis and fixed with bolts or special glue. Be sure to ensure the correct installation direction so that its coordinate axis is strictly consistent with the front, back, left, right, and up and down directions of the vehicle to avoid measurement errors caused by improper installation. The selection of the speed sensor should not be ignored either. The magnetoelectric speed sensor has a lower cost and is suitable for ordinary models; while the Hall-type speed sensor has higher accuracy and strong anti-interference ability, and is widely used in new energy vehicles with strict requirements for speed measurement. When installing the speed sensor, the common installation location is the vehicle's transmission output shaft or the wheel hub. If it is installed on the transmission output shaft, make sure that the gear of the sensor is properly meshed with the gear ring on the output shaft; if it is installed on the wheel hub, make sure that the gap between the sensor and the hub is within the specified range of 0.5-2mm to ensure the accuracy of the measurement. The selection of height sensors can consider potentiometer or photoelectric. The potentiometer height sensor has a simple structure and low cost, while the photoelectric height sensor has high accuracy and good reliability. For example, Omron's photoelectric height sensor can provide accurate height measurement data. The height sensor is generally installed in the vehicle's suspension system, such as near the shock absorber or control arm. During the installation process, pay special attention to its position and angle. Only in this way can the travel change of the suspension be accurately measured, and then the height information of the vehicle can be accurately reflected. Vibration frequency sensors mostly use piezoelectric vibration sensors, which have the advantages of high sensitivity and fast response speed, and can accurately capture the vibration frequency of the vehicle. When installing, install it tightly on the key parts of the vehicle, such as the engine, chassis or body, to ensure that the sensor is in full contact with the measured part to effectively obtain the vibration signal.

[0021] After the sensor is installed, the data acquisition phase begins. The signals output by the acceleration sensor are divided into two types: analog and digital. The analog signal needs to be converted into a digital signal with the help of an analog-to-digital converter (ADC) before subsequent processing; the digital signal can be directly transmitted to the data acquisition module. The vehicle speed sensor outputs a pulse signal, and the vehicle speed can be calculated by measuring the frequency or period of the pulse. The signal output by the height sensor may be a voltage signal or a digital signal, which needs to be processed accordingly according to the sensor type. The vibration frequency sensor outputs an electrical signal related to the vibration frequency, which also needs to be properly processed and converted. The data acquisition work is completed by microcontrollers (such as Arduino, STM32, etc.), which are responsible for receiving the signals of each sensor and performing preliminary processing and storage. In this process, the sampling frequency needs to be set reasonably. For acceleration and vibration frequency data, the sampling frequency is generally set at 100Hz-1000Hz, which can effectively capture its rapid changes; for vehicle speed and height data, the sampling frequency is relatively low, and can be set at 10Hz-50Hz.

[0022] Then the collected data needs to be transmitted and stored. Data transmission can be done by wired or wireless means. CAN bus is commonly used for wired transmission. CAN bus has become a common choice for internal vehicle data transmission due to its high reliability and strong anti-interference ability. Wireless transmission can use Bluetooth, Wi-Fi, 4G / 5G and other technologies to achieve remote real-time data transmission. To ensure data security and integrity, data needs to be encoded and encrypted during transmission. After the data is transmitted to the vehicle's central processor or remote server, it will be stored in a database. The choice of database should be based on actual needs and data characteristics. Relational databases (such as MySQL, Oracle, etc.) and non-relational databases (such as MongoDB, Redis, etc.) have their own advantages. Reasonable organization and management of stored data will help subsequent data processing and analysis.

[0023] Finally, data preprocessing and quality control are performed. When preprocessing data, filtering methods are often used to remove noise and interference signals. Mean filtering, median filtering, Kalman filtering, etc. are all commonly used methods. For example, using Kalman filtering on acceleration data can significantly reduce measurement errors and improve data accuracy. At the same time, the data is normalized to unify the data collected by different sensors to the same scale range for subsequent analysis and model training. In terms of quality control, strict quality checks must be performed on the collected data to determine the validity of the data, such as checking whether the vehicle speed data is within a reasonable range and whether the acceleration data has abnormal fluctuations. For invalid or abnormal data, it is necessary to mark and eliminate them, and take corresponding measures to repair or supplement them to ensure that the data quality is reliable, so as to provide a solid guarantee for the subsequent intelligent control results obtained based on these data analyses.

[0024] In the embodiment of the present application, the vehicle state time series feature extraction module 120 is used to perform data regularization and time series feature extraction on the set of vehicle state data to obtain the vehicle acceleration time series associated feature implicit coding vector, the vehicle speed time series associated feature implicit coding vector, the vehicle height time series change feature implicit coding vector and the vehicle vibration frequency time series associated feature implicit coding vector. Specifically, Figure 2 FIG. 1 is a block diagram of a vehicle state time series feature extraction module in an intelligent control system of an air suspension shock absorber of a new energy vehicle according to an embodiment of the present application. Figure 2 As shown, the vehicle state time series feature extraction module 120 includes: a vehicle state data splitting and regularization unit 121, which is used to split the set of vehicle state data according to the parameter sample dimension, and regularize the split data according to the time dimension to obtain the time series of vehicle acceleration values, the time series of vehicle speed values, the time series of vehicle height values ​​and the time series of vehicle vibration frequency values; a vehicle state time series feature generation unit 122, which is used to perform time series feature extraction based on one-dimensional convolution on the time series of vehicle acceleration values, the time series of vehicle speed values, the time series of vehicle height values ​​and the time series of vehicle vibration frequency values ​​to obtain the vehicle acceleration time series associated feature implicit coding vector, the vehicle speed time series associated feature implicit coding vector, the vehicle height time series change feature implicit coding vector and the vehicle vibration frequency time series associated feature implicit coding vector.

[0025] In an embodiment of the present application, the vehicle state data splitting and regularizing unit 121 is used to split the set of the vehicle state data according to the parameter sample dimension, and regularize the split data according to the time dimension to obtain the time series of vehicle acceleration values, the time series of vehicle speed values, the time series of vehicle height values, and the time series of vehicle vibration frequency values. Accordingly, considering different vehicle state parameters, such as acceleration, speed, height, and vibration frequency, each of them has a unique physical meaning and change law, and in order to be able to observe and analyze these different types of parameters separately, in order to deeply understand the characteristics of each parameter. In the technical solution of the present application, the set of the vehicle state data is split according to the parameter sample dimension, and the split data is regularized according to the time dimension to obtain the time series of vehicle acceleration values, the time series of vehicle speed values, the time series of vehicle height values, and the time series of vehicle vibration frequency values. In this way, the characteristics of each parameter in the time dimension can be mined. For example, from the time series of vehicle speed values, it is possible to discover the vehicle's driving speed patterns at different times of the day, or the speed change trend during long-distance driving; from the time series of vehicle vibration frequency, it is possible to identify the periodic changes in vibration frequency under specific road conditions. These characteristics are critical for understanding the vehicle's driving behavior and operating conditions.

[0026] In an embodiment of the present application, the vehicle state time series feature generation unit 122 is used to perform time series feature extraction based on one-dimensional convolution on the time series of the vehicle acceleration value, the time series of the vehicle speed value, the time series of the vehicle height value, and the time series of the vehicle vibration frequency value, respectively, to obtain the vehicle acceleration time series associated feature implicit coding vector, the vehicle speed time series associated feature implicit coding vector, the vehicle height time series change feature implicit coding vector, and the vehicle vibration frequency time series associated feature implicit coding vector. It should be understood that in order to further capture and refine the time series feature information of each vehicle state parameter in the time dimension, in the technical solution of the present application, the time series of the vehicle acceleration value, the time series of the vehicle speed value, the time series of the vehicle height value and the time series of the vehicle vibration frequency value are respectively subjected to time series feature extraction based on one-dimensional convolution to slide the convolution kernel on the time series, automatically extract local features in the data, and capture local dependencies of the data in the time dimension, such as the change pattern of the vehicle's acceleration in a short period of time, the instantaneous fluctuation of the speed, etc., to obtain the implicit coding vector of the vehicle acceleration time series correlation feature, the implicit coding vector of the vehicle speed time series correlation feature, the implicit coding vector of the vehicle height time series change feature and the implicit coding vector of the vehicle vibration frequency time series correlation feature.

[0027] In the embodiment of the present application, the vehicle state parameter association module 130 is used to perform multi-dimensional time series association on the vehicle acceleration time series association feature implicit coding vector, the vehicle speed time series association feature implicit coding vector, the vehicle height time series change feature implicit coding vector and the vehicle vibration frequency time series association feature implicit coding vector to obtain a time series association coding feature map between vehicle state parameters. Specifically, Figure 3 FIG. 1 is a block diagram of a vehicle state parameter association module in an intelligent control system of an air suspension shock absorber of a new energy vehicle according to an embodiment of the present application. Figure 3 As shown, the vehicle state parameter association module 130 includes: a vehicle state feature multi-dimensional aggregation coding unit 131, which is used to perform vehicle state feature multi-dimensional aggregation coding on the vehicle acceleration time series association feature implicit coding vector, the vehicle speed time series association feature implicit coding vector, the vehicle height time series change feature implicit coding vector and the vehicle vibration frequency time series association feature implicit coding vector to obtain a vehicle state multi-dimensional time series aggregation matrix; a vehicle state parameter time series association coding feature generation unit 132, which is used to input the vehicle state multi-dimensional time series aggregation matrix into a vehicle state parameter time series association feature extractor based on a two-dimensional convolutional neural network to obtain the vehicle state parameter time series association coding feature map.

[0028] In the embodiment of the present application, the vehicle state feature multi-dimensional aggregation coding unit 131 is used to perform vehicle state feature multi-dimensional aggregation coding on the vehicle acceleration time series correlation feature implicit coding vector, the vehicle speed time series correlation feature implicit coding vector, the vehicle height time series change feature implicit coding vector and the vehicle vibration frequency time series correlation feature implicit coding vector to obtain a vehicle state multi-dimensional time series aggregation matrix. Accordingly, considering that there are complex time series correlation relationships between various vehicle parameters, for example, changes in vehicle speed may affect the vehicle vibration frequency, and are also associated with changes in vehicle height (such as when passing through undulating roads), therefore, in order to discover the synergy and mutual influence patterns between different parameter features to more accurately reflect the actual operating conditions of the vehicle, the present application performs vehicle state feature multi-dimensional aggregation coding on the vehicle acceleration time series correlation feature implicit coding vector, the vehicle speed time series correlation feature implicit coding vector, the vehicle height time series change feature implicit coding vector and the vehicle vibration frequency time series correlation feature implicit coding vector to integrate these feature information from different dimensions together to form a more comprehensive and integrated vehicle state description, thereby obtaining a vehicle state multi-dimensional time series aggregation matrix. In particular, in a specific embodiment of the present application, the vehicle acceleration timing-related characteristic implicit coding vector, the vehicle speed timing-related characteristic implicit coding vector, the vehicle height timing-related characteristic implicit coding vector and the vehicle vibration frequency timing-related characteristic implicit coding vector are arranged in a matrix to obtain the vehicle state multi-dimensional timing-series aggregation matrix.

[0029] In the embodiment of the present application, the vehicle state parameter temporal correlation coding feature generating unit 132 is used to input the vehicle state multi-dimensional temporal aggregation matrix into the vehicle state parameter correlation feature extractor based on the two-dimensional convolutional neural network to obtain the vehicle state parameter temporal correlation coding feature map. It should be understood that in order to mine the mutual correlation and influence relationship of each vehicle parameter in the time dimension, the present application obtains the vehicle state parameter temporal correlation coding feature map by inputting the vehicle state multi-dimensional temporal aggregation matrix into the vehicle state parameter correlation feature extractor based on the two-dimensional convolutional neural network. A person of ordinary skill in the art should know that a two-dimensional convolutional neural network (2D-CNN) is good at processing data with a two-dimensional spatial structure and can process row and column information in the matrix at the same time. By using the multi-dimensional temporal aggregation matrix as the input of the 2D-CNN, the advantages of the 2D-CNN in processing such structured data can be fully utilized to mine the potential relationship between rows and columns in the matrix, that is, the complex association between different parameters and the same parameter at different time points. In this way, feature extraction can be performed in the two-dimensional space of the parameter dimension and the time dimension, so as to more comprehensively and deeply mine the correlation characteristics between the vehicle state parameters. For example, it can simultaneously capture the correlation pattern between the change in vehicle acceleration within a certain time period and the change in vehicle height within the same time period, providing an intuitive basis for further understanding the vehicle's operating status.

[0030] In the embodiment of the present application, the vehicle state parameter temporal correlation enhancement module 140 is used to perform global-local vehicle state semantic mapping enhancement on the vehicle state parameter temporal correlation coding feature map to obtain an enhanced vehicle state parameter temporal correlation coding feature map. Specifically, Figure 4 FIG. 1 is a block diagram of a vehicle state parameter timing correlation enhancement module in an intelligent control system of an air suspension shock absorber of a new energy vehicle according to an embodiment of the present application. Figure 4As shown, the vehicle state parameter temporal association enhancement module 140 includes: a vehicle state feature global key semantic information extraction unit 141, which is used to input the vehicle state parameter temporal association coding feature map into the global key semantic information extraction network to obtain the global temporal key semantic information coding vector between the vehicle state parameters; a to-be-processed feature window determination unit 142, which is used to extract the channel feature vector between the vehicle state parameters to be processed from the vehicle state parameter temporal association coding feature map, and determine the vehicle state local neighborhood semantic association window of the channel feature vector between the vehicle state parameters to be processed; a semantic mapping guidance factor calculation unit 143, which is used to calculate the vehicle state local neighborhood semantic association window corresponding to the channel feature vector between the vehicle state parameters to be processed A key semantic information encoding vector is obtained, and a semantic comparison analysis is performed on the local key semantic information encoding vector of the vehicle state and the global temporal key semantic information encoding vector between the vehicle state parameters to determine the vehicle state semantic mapping guidance factor of the channel feature vector between the vehicle state parameters to be processed; an enhanced channel feature generating unit 144 between the vehicle state parameters to be processed is used to modulate the channel feature vector between the vehicle state parameters to be processed based on the vehicle state semantic mapping guidance factor to obtain an enhanced channel feature vector between the vehicle state parameters to be processed, wherein the enhanced channel feature vector between the vehicle state parameters to be processed is the channel feature vector of the pixel position (i, j) of the enhanced vehicle state parameter temporal association encoding feature map.

[0031] It should be understood that the vehicle operation status is a complex system, which includes both overall trends and long-term patterns, as well as local instantaneous changes and detailed features. However, when traditional convolutional neural networks process the temporal correlation coding feature map between vehicle state parameters, due to the limited receptive field, it is difficult to effectively model long-distance dependencies and accurately extract global semantic background information. In addition, the analysis of vehicle state parameters requires high fine-grained information expression of local features. However, when the convolution operation captures the local semantics of the vehicle state, information dilution is prone to occur, resulting in insufficient expression of some subtle changes (such as slight changes in vehicle vibration frequency, highly variable edge features, etc.). Therefore, the present application introduces a global-local vehicle state semantic mapping enhancement mechanism to enhance the temporal correlation coding feature map between the vehicle state parameters to obtain an enhanced temporal correlation coding feature map between vehicle state parameters. In particular, the mechanism integrates the collaborative modeling of global semantics and local semantics, fuses the global semantic background information with the local feature details, constructs a mapping guidance factor, and uses this factor to modulate and enhance each channel in the feature space, thereby generating features with higher task relevance and stronger expressiveness, so as to enhance the understanding of the overall operating status of the vehicle.

[0032] Specifically, the temporal correlation coding feature map between the vehicle state parameters needs to be first input into the global key semantic information extraction network to obtain the global temporal key semantic information coding vector between the vehicle state parameters. The above process can be expressed as: ;in, is a time series correlation coding characteristic diagram between the vehicle state parameters, is the set of real numbers, and They are The height and width of each feature matrix along the channel dimension, yes The number of channels, is the feature decomposition operation, and They are The first, second, and third and The temporal correlation encoding feature vector between vehicle state parameters, and They are The corresponding weight matrix and bias vector, is matrix multiplication, is the rating vector, is the first in the set of significant factors of temporal correlation between vehicle state parameters. The significant factor of temporal correlation between vehicle state parameters, is the normalization function, is the number of vectors in the set of temporal correlation encoding feature vectors between vehicle state parameters, It is the global temporal key semantic information encoding vector between vehicle state parameters.

[0033] It should be understood that in the vehicle operation state, there are long-distance dependencies between vehicle state parameters (such as acceleration, speed, height, and vibration frequency) at different times. For example, during the acceleration process of the vehicle, from the beginning of acceleration to reaching a stable speed, the changes in the acceleration value and the speed value in this process are continuous and interrelated, and this correlation may span a long time series. The global key semantic information extraction network can capture these long-distance dependencies from the temporal correlation encoding feature map between vehicle state parameters. It uniformly encodes the entire feature space by constructing a global semantic template, so that the network can focus on the potential connections between different vehicle parameters at different times, so as to more accurately understand the changing trend of the vehicle operation state. Moreover, the global key semantic information extraction network can not only expand the receptive field through its special construction and operation, but also model the potential dependencies across pixels and feature channels. Specifically, in the temporal correlation encoding feature map between vehicle state parameters, there may be complex dependencies between different pixels (representing different times or different parameter values) and different feature channels (representing different vehicle state parameters). The network can mine these latent dependencies, for example, discovering the hidden connection between changes in vehicle vibration frequency and vehicle speed and height, thereby gaining a deeper understanding of the nature of the vehicle's operating state and providing stronger support for optimizing the control of the suspension system.

[0034] Specifically, in the embodiment of the present application, the feature window determination unit to be processed is used to extract the channel feature vector between the vehicle state parameters at the pixel position (i, j) from the temporal correlation coding feature map between the vehicle state parameters as the channel feature vector between the vehicle state parameters to be processed. The process can be expressed by the formula: ;in, yes The channel feature vector of the vehicle state parameters at pixel position (i, j) in , is the channel feature vector between the vehicle state parameters to be processed; Based on the characteristic distribution characteristics of the channel feature vector between the vehicle state parameters to be processed, the vehicle state local neighborhood semantic association window of the channel feature vector between the vehicle state parameters to be processed is determined, wherein the channel feature vector between the vehicle state parameters to be processed is located at the center of the vehicle state local neighborhood semantic association window. The process can be expressed by the formula: ;in, is the channel feature vector between the vehicle state parameters to be processed, For calculation The square of the Euclidean norm of is the logarithmic function value with base 2, is rounded up, is the center position value of the channel feature vector between the vehicle state parameters to be processed in the vehicle state local neighborhood semantic association window, is the size of the local neighborhood semantic association window of the vehicle state.

[0035] It should be understood that the time series correlation coding feature map between vehicle state parameters contains various information about the vehicle's operating status, presented in the form of pixels. By extracting the channel feature vector between vehicle state parameters at pixel position (i, j) as the channel feature vector between vehicle state parameters to be processed, it is possible to focus on the local feature details in the vehicle's operating status, which is conducive to subsequent more refined analysis. It should be noted that in this step, the channel feature vector between vehicle state parameters to be processed is the channel feature vector of any pixel position in the time series correlation coding feature map between vehicle state parameters.

[0036] Accordingly, considering that in the entire vehicle state analysis process, the previous steps have processed the temporal correlation encoding feature map between vehicle state parameters from a global perspective, and obtained some global semantic information. However, to understand the vehicle state more finely, it is necessary to transition from the global to the local. The channel feature vector between the vehicle state parameters to be processed represents the local information of the vehicle state at a specific location. Determining the local neighborhood semantic association window of the vehicle state by analyzing its feature distribution characteristics is the key operation to achieve this transition from the global to the local. That is, accurately determining the local neighborhood semantic association window of the vehicle state can enable the model to more accurately capture the local semantic association between the vehicle state parameters. Specifically, the local neighborhood semantic association window of the vehicle state focuses on high semantic correlation points, so that the model can have a deeper understanding of the state of the vehicle at a specific location and time, avoiding interference from irrelevant information. It is worth mentioning that the determination of the local neighborhood semantic association window of the vehicle state is closely related to the ideas of regional dependency modeling and information reduction. In areas where the feature distribution is relatively concentrated and the semantic correlation is strong, the window range can be appropriately narrowed to focus on key information; in areas where the feature distribution is relatively dispersed and more contextual information needs to be considered, the window range can be expanded. For example, when the vehicle is in a stable driving state, the changes in relevant parameters are relatively small, and the receptive field can be smaller; when the vehicle encounters complex road conditions or performs intense driving operations, the parameters change greatly, and the receptive field can be expanded accordingly to better capture changes in the vehicle state.

[0037] Specifically, in an embodiment of the present application, the semantic mapping guidance factor calculation unit includes: a vehicle state local key semantic information extraction subunit, which is used to input the channel feature vectors between all vehicle state parameters in the local neighborhood semantic association window of the vehicle state into a local neighborhood association semantic information extraction network to obtain the vehicle state local key semantic information encoding vector corresponding to the channel feature vector between the vehicle state parameters to be processed; a vehicle state semantic mapping guidance factor calculation subunit, which is used to determine the vehicle state semantic mapping guidance factor of the channel feature vector between the vehicle state parameters to be processed based on the semantic comparison analysis between the global temporal key semantic information encoding vector between the vehicle state parameters and the vehicle state local key semantic information encoding vector corresponding to the channel feature vector between the vehicle state parameters to be processed.

[0038] More specifically, in the embodiment of the present application, the vehicle state local key semantic information extraction subunit is used to input all vehicle state parameter channel feature vectors in the vehicle state local neighborhood semantic association window into the local neighborhood association semantic information extraction network to obtain the vehicle state local key semantic information encoding vector corresponding to the vehicle state parameter channel feature vector to be processed. The above process can be expressed as: ;in, is the center position value of the channel feature vector between the vehicle state parameters to be processed in the vehicle state local neighborhood semantic association window, is the channel feature vector between vehicle state parameters at pixel position (k, l) in the local neighborhood semantic association window of the vehicle state, yes The corresponding vehicle state local key semantic information encoding vector.

[0039] It should be understood that the channel feature vectors in the local neighborhood semantic association window of the vehicle state cover a large amount of fine-grained semantic data, such as small changes in various state parameters of the vehicle in a short period of time. The local neighborhood association semantic information extraction network can accurately identify and extract key semantic information that is highly related to the feature points to be processed. For example, when a vehicle passes through a speed bump, the network can accurately extract information related to the sharp change in vibration frequency, the instantaneous change in vehicle height, and the short-term fluctuation in acceleration from many feature vectors. This information is crucial for judging the specific state of the vehicle at this time. Moreover, in actual data processing, not all information in the association window is of substantial help in understanding the vehicle state of the feature points to be processed, and it contains a lot of redundant semantic information. Through the built-in correlation measurement mechanism of the local neighborhood association semantic information extraction network, this information can be screened to exclude those contents that are not very relevant to the current feature points to be processed, thereby avoiding these redundant information from interfering with subsequent analysis.

[0040] More specifically, in the embodiment of the present application, the vehicle state semantic mapping guidance factor calculation subunit is used to: based on the channel feature vector between the vehicle state parameters to be processed, perform semantic interaction optimization based on the intrinsic-diagonal dual mediation on the vehicle state local key semantic information encoding vector corresponding to the channel feature vector between the vehicle state parameters to be processed to obtain the optimized vehicle state local key semantic information encoding vector of the channel feature vector between the vehicle state parameters to be processed. The process can be expressed by the formula: ;in, represents matrix multiplication, is a vector and The correlation matrix of is a matrix The diagonal vector composed of the diagonal elements of is a matrix The eigenvalues ​​of eigenvectors are yes The corresponding optimized vehicle state local key semantic information encoding vector, It is added by position point; The Mahalanobis distance between the global temporal key semantic information encoding vector between the vehicle state parameters and the optimized vehicle state local key semantic information encoding vector of the channel feature vector between the vehicle state parameters to be processed is calculated as the vehicle state semantic mapping guidance factor of the channel feature vector between the vehicle state parameters to be processed. The process can be expressed by the formula: ;in, yes The corresponding optimized vehicle state local key semantic information encoding vector, is the global temporal key semantic information encoding vector between vehicle state parameters, yes and The inverse matrix of the covariance matrix between is the transpose operation, yes and The vehicle state semantic mapping guidance factor between them.

[0041] Here, for the vehicle state local key semantic information encoding vector obtained by local semantic information extraction, the interaction between entities with similar semantic neighborhood types in the local semantic interaction system, that is, the vehicle state local key semantic information encoding vector and the channel feature vector between the vehicle state parameters to be processed, can be further characterized based on the concept of homomorphic phase, that is, the vehicle state local key semantic information encoding vector with similar semantic neighborhood window association is driven by the semantic similarity of the channel feature vector between the vehicle state parameters to be processed, so that the vehicle state local key semantic information encoding vector and the channel feature vector between the vehicle state parameters to be processed with similar attributes are more inclined to form a feature entity association. Specifically, the diagonal vector and the eigenvector of the association representation between the vehicle state local key semantic information encoding vector and the channel feature vector between the vehicle state parameters to be processed are used as the mediated mediation effect representation and the targeted mediation effect representation respectively, so as to represent the indirect influence of the association semantic similarity on the target variable through the mediation variable through the mediation effect modeling, so as to perform local semantic logic mediation inference through the homomorphic phase semantic network structure, and further improve the subsequent semantic mapping alignment.

[0042] It should be understood that by calculating the Mahalanobis distance between the global temporal key semantic information encoding vector between vehicle state parameters and the optimized vehicle state local key semantic information encoding vector of the channel feature vector between the vehicle state parameters to be processed, the semantic mapping relationship of the channel feature vector to be processed in the global context can be clarified. Specifically, the global temporal key semantic information encoding vector between vehicle state parameters represents the overall trend and long-term pattern of the vehicle state, which is a description of the vehicle state from a macro perspective; while the optimized vehicle state local key semantic information encoding vector focuses on the local detail information of the feature points to be processed. The calculation of the Mahalanobis distance can measure the difference and degree of association between the two, so as to determine the position and meaning of the local features in the global semantic context. This step is similar to the idea of ​​feature alignment. The global semantics provides a reference framework for the local semantics, so that the local features can be compared and analyzed in the global context. In general, the semantic comparison operation (implemented by calculating the Mahalanobis distance) not only strengthens the global consistency of the vehicle state feature expression, but also retains the local personalized details. It generates a specific vehicle state semantic mapping guidance factor in the form of semantic mapping, which can provide the core basis for the subsequent final vehicle state feature enhancement operation.

[0043] Finally, based on the vehicle state semantic mapping guidance factor, the channel feature vector between the vehicle state parameters to be processed is modulated to obtain the enhanced channel feature vector between the vehicle state parameters to be processed, wherein the enhanced channel feature vector between the vehicle state parameters to be processed is the channel feature vector of the pixel position (i, j) of the enhanced vehicle state parameter temporal correlation coding feature map. The above process can be expressed by the formula: ;in, is the channel feature vector between the vehicle state parameters to be processed, yes and The vehicle state semantic mapping guidance factor between is the channel feature vector of the pixel position (i, j) in the enhanced vehicle state parameter temporal correlation coding feature map, that is, The enhanced channel feature vector between the vehicle state parameters to be processed is obtained by modulation.

[0044] It should be understood that the importance of different channel features in the original vehicle state parameter temporal correlation coding feature map for describing the vehicle operating state is not exactly the same, and the priority of each channel feature will change under different driving scenarios and task requirements. The vehicle state semantic mapping guidance factor reflects the degree of correlation and difference between the channel feature vector between the vehicle state parameters to be processed and the global semantics. Based on this factor, when the channel feature vector between the vehicle state parameters to be processed is modulated by a multiplicative adjustment method, the weight of the channel feature can be adjusted according to its fit with the global semantics. This will increase the feature weight of the more critical channel in the original feature map for accurately judging the vehicle state and adjusting the suspension, while the weight of other relatively minor channel features will be reduced accordingly, so that the model can focus more on important feature information during specific processing. Furthermore, by adjusting the channel feature vectors between the vehicle state parameters to be processed in the original vehicle state parameter temporal association coding feature map based on the vehicle state semantic mapping guidance factor, the semantic information carried by each channel feature can be more accurately expressed and enhanced, thereby further enriching the representation capability of the enhanced vehicle state parameter temporal association coding feature map composed of it, so that the enhanced feature map can more comprehensively and meticulously describe the vehicle's operating status, thereby providing strong support for subsequent accurate judgment of the vehicle's actual needs and corresponding control decisions.

[0045] In the embodiment of the present application, the pressure value adjustment module 150 is used to adjust the pressure value of the air spring based on the enhanced time series correlation coding feature map between vehicle state parameters. Specifically, in the embodiment of the present application, the pressure value adjustment module is used to: input the enhanced time series correlation coding feature map between vehicle state parameters into the model prediction controller to obtain suspension optimization parameters, and the suspension optimization parameters include the pressure value of the air spring; send the suspension optimization parameters to the actuator layer, and the actuator layer sends a control instruction to the air spring based on the comparison between the suspension optimization parameters and the suspension real-time parameters to adjust the pressure value of the air spring.

[0046] It should be understood that the enhanced time-series correlation coding feature map between vehicle state parameters is input into the model predictive controller to obtain the suspension optimization parameters, that is, the enhanced time-series correlation coding feature map between vehicle state parameters is decoded using the time-series correlation coding feature map between vehicle state parameters to intelligently predict the pressure value of the air spring. In particular, the model predictive controller usually analyzes and calculates the input feature map based on a certain mathematical model and algorithm. The enhanced feature map provides the model with rich semantic information, allowing the model to better learn and understand the relationship between the vehicle state and the suspension parameters. By analyzing these features, the model can predict the suspension optimization parameters that best suit the current vehicle state based on its internal algorithms and rules. In a specific embodiment of the present application, the enhanced vehicle state parameter temporal correlation coding feature map is input into a model predictive controller to obtain suspension optimization parameters, and the suspension optimization parameters include the pressure value of the air spring, including: multiplying the decoding weight matrix of the model predictive controller with each feature matrix of the enhanced vehicle state parameter temporal correlation coding feature map along the channel dimension to obtain the decoded enhanced vehicle state parameter temporal correlation coding feature map, and accumulating and summing the feature values ​​of all positions of the decoded enhanced vehicle state parameter temporal correlation coding feature map to obtain the suspension optimization parameters.

[0047] Then, the suspension optimization parameters are sent to the actuator layer, and the actuator layer sends a control instruction to the air spring to adjust the pressure value of the air spring based on the comparison between the suspension optimization parameters and the suspension real-time parameters. It should be understood that the operating conditions during vehicle driving are complex and changeable, and the actual suspension real-time parameters will continue to fluctuate. Comparing the suspension optimization parameters with the suspension real-time parameters can monitor the difference between the current state and the ideal state of the system in real time, so that the actuator layer can accurately determine the deviation between the current air spring pressure and the ideal pressure, and then issue accurate control instructions to achieve precise adjustment of the air spring pressure value to meet the driving needs of the vehicle under various complex road conditions.

[0048] The following is a detailed description of a specific implementation process of "sending the suspension optimization parameters to the actuator layer, and the actuator layer sending a control instruction to the air spring to adjust the pressure value of the air spring based on the comparison between the suspension optimization parameters and the suspension real-time parameters": First, the calculated suspension optimization parameters are reliably transmitted to the actuator layer through the efficient data transmission network inside the vehicle, such as the Controller Area Network bus. The Controller Area Network bus has the advantages of high reliability and strong anti-interference ability, which can ensure that data is not lost or erroneous during transmission, so that the actuator layer can accurately receive the suspension optimization parameters.

[0049] While receiving the suspension optimization parameters, the actuator layer also continuously obtains the real-time parameters of the suspension. The vehicle is equipped with a variety of sensors to monitor these real-time parameters. The pressure sensor is responsible for accurately measuring the actual pressure of the air spring. It can sense the subtle changes in the internal pressure of the air spring in real time and convert these physical quantities into electrical signal outputs; the displacement sensor focuses on monitoring position information closely related to the suspension state, such as the degree of compression or extension of the suspension. This information helps to fully understand the real-time working conditions of the suspension. These sensors collect data at a very high frequency and transmit the collected data to the actuator layer in a timely manner through a dedicated data transmission line.

[0050] The core component inside the actuator layer, the control unit, is the key to processing and decision-making. The control unit is usually composed of a powerful microprocessor, which has a complex and sophisticated control algorithm program pre-programmed inside. When the control unit receives the suspension optimization parameters and real-time parameters, it will immediately start the comparison operation. Taking the air spring pressure as an example, the control unit will accurately calculate the difference between the current actual air spring pressure and the ideal air spring pressure, and will also analyze the trend of pressure changes to determine whether the pressure is continuously rising, falling or remaining stable.

[0051] In order to achieve precise control, the control unit will generate control instructions based on the preset control logic and algorithm rules. Among them, the PID control algorithm (proportional-integral-differential control) plays an important role in this process. The PID control algorithm comprehensively considers the current error (the difference between the actual pressure and the ideal pressure), the integral of the error (reflecting the accumulation of errors over a period of time in the past) and the differential of the error (reflecting the rate of change of the error). Through the reasonable adjustment and calculation of these three parameters, the PID algorithm can output a suitable control signal. When the current pressure of the air spring is lower than the ideal air spring pressure value, the PID algorithm will output a control signal that increases the pressure according to the calculation results; conversely, when the pressure is too high, the output control signal will cause the pressure to decrease.

[0052] After the control instruction is generated, the next step is execution. The actuator layer amplifies the control signal through a drive circuit such as a power amplifier. Because the signal power output by the control unit is often small and cannot directly drive the actuator to work, a power amplifier is required to amplify the signal to a sufficient strength. The actuator mainly includes key components such as solenoid valves and air pumps. When the control instruction requires an increase in the air spring pressure, the signal amplified by the power amplifier will drive the solenoid valve to open and start the air pump at the same time. The air pump begins to fill the air spring with gas, and as the gas is continuously injected, the pressure of the air spring gradually increases. In this process, the pressure sensor continuously monitors the pressure changes and feeds back the new pressure data to the control unit of the actuator layer in real time. The control unit will continuously adjust the control instruction based on these feedback data to ensure that the air spring pressure can quickly and accurately approach the ideal air spring pressure value. If the pressure rises too fast or exceeds the ideal air spring pressure value, the control unit will adjust the control instruction in time to reduce the working intensity of the air pump or close the solenoid valve to prevent excessive pressure.

[0053] Conversely, when the air spring pressure needs to be reduced, the control command will cause the solenoid valve to open a specific exhaust channel to allow the gas in the air spring to be discharged. During the exhaust process, the pressure sensor also monitors the pressure changes in real time, and the control unit adjusts the opening of the solenoid valve in real time according to the feedback data to achieve precise control of the pressure drop speed and ensure that the pressure is steadily reduced to the ideal air spring pressure value.

[0054] During the entire adjustment process, a tight closed-loop control system is formed between the actuator layer and the sensor. The sensor continuously provides real-time data to the actuator layer, which analyzes and makes decisions based on these data and ideal parameters, generates control instructions and adjusts the action of the actuator, thereby achieving dynamic and precise adjustment of the air spring pressure.

[0055] In summary, the intelligent control system 100 of the air suspension shock absorber of a new energy vehicle based on the embodiment of the present application is explained, which uses a data processing technology based on deep learning to integrate data and encode time series features of a set of vehicle state data, and then aggregates and associates the time series features of each vehicle state data, so as to intelligently predict the pressure value of the air spring based on the global-local semantic mapping enhanced representation of the time series association encoding features between the aggregated and associated vehicle state parameters, and adjust the pressure value of the air spring adaptively by comparing it with the real-time parameters. In this way, the real-time dynamic adjustment of the air spring pressure can be achieved, which helps to improve the driving experience and driving safety.

[0056] Figure 5 Flow chart of the intelligent control method of the air suspension shock absorber of a new energy vehicle according to an embodiment of the present application. Figure 5As shown, in the intelligent control method of the air suspension shock absorber of the new energy vehicle, it includes: S110, acquiring the vehicle state data collected by the sensor component deployed in the new energy vehicle to obtain a set of vehicle state data, the sensor component includes an acceleration sensor, a vehicle speed sensor, a height sensor and a vibration frequency sensor, and the vehicle state data includes a vehicle acceleration value, a vehicle speed value, a vehicle height value and a vehicle vibration frequency value; S120, performing data regularization and time series feature extraction on the set of vehicle state data to obtain a vehicle acceleration time series correlation feature implicit coding vector, a vehicle speed time series correlation feature implicit coding vector, a vehicle height time series change feature implicit coding vector and a vehicle An implicit coding vector of a timing correlation feature of vibration frequency; S130, performing multi-dimensional timing correlation on the implicit coding vector of the timing correlation feature of vehicle acceleration, the implicit coding vector of the timing correlation feature of vehicle speed, the implicit coding vector of the timing change feature of vehicle height and the implicit coding vector of the timing correlation feature of vehicle vibration frequency to obtain a timing correlation coding feature map between vehicle state parameters; S140, performing global-local vehicle state semantic mapping enhancement on the timing correlation coding feature map between vehicle state parameters to obtain an enhanced timing correlation coding feature map between vehicle state parameters; S150, adjusting the pressure value of the air spring based on the enhanced timing correlation coding feature map between vehicle state parameters.

[0057] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned intelligent control method for the air suspension shock absorber of the new energy vehicle have been referred to above. Figures 1 to 4 The description of the intelligent control system of the air suspension shock absorber of the new energy vehicle has been introduced in detail, and therefore, its repeated description will be omitted.

[0058] In summary, the intelligent control method of the air suspension shock absorber of a new energy vehicle based on the embodiment of the present application is explained, which uses a data processing technology based on deep learning to integrate the data and encode the time series features of the vehicle state data set, and then aggregates and associates the time series features of each vehicle state data, so as to intelligently predict the pressure value of the air spring based on the global-local semantic mapping enhanced representation of the time series association encoding features between the aggregated and associated vehicle state parameters, and adjust the pressure value of the air spring adaptively by comparing it with the real-time parameters. In this way, the real-time dynamic adjustment of the air spring pressure can be achieved, which helps to improve the driving experience and driving safety.

Claims

1. An intelligent control system for an air suspension shock absorber of a new energy vehicle, characterized in that: include: A vehicle status data acquisition module, used to acquire vehicle status data collected by a sensor component deployed in a new energy vehicle to obtain a set of vehicle status data, wherein the sensor component includes an acceleration sensor, a vehicle speed sensor, a height sensor, and a vibration frequency sensor, and the vehicle status data includes a vehicle acceleration value, a vehicle speed value, a vehicle height value, and a vehicle vibration frequency value; A vehicle state time series feature extraction module, used for performing data regularization and time series feature extraction on the set of vehicle state data to obtain a vehicle acceleration time series correlation feature implicit coding vector, a vehicle speed time series correlation feature implicit coding vector, a vehicle height time series change feature implicit coding vector and a vehicle vibration frequency time series correlation feature implicit coding vector; A vehicle state parameter association module, used for performing multi-dimensional time series association on the vehicle acceleration time series association feature implicit coding vector, the vehicle speed time series association feature implicit coding vector, the vehicle height time series change feature implicit coding vector and the vehicle vibration frequency time series association feature implicit coding vector to obtain a time series association coding feature map between vehicle state parameters; A vehicle state parameter temporal correlation enhancement module is used to perform global-local vehicle state semantic mapping enhancement on the vehicle state parameter temporal correlation coding feature map to obtain an enhanced vehicle state parameter temporal correlation coding feature map; The pressure value adjustment module is used to adjust the pressure value of the air spring based on the enhanced time series correlation coding characteristic diagram between vehicle state parameters.

2. The intelligent control system of the air suspension shock absorber of the new energy vehicle according to claim 1 is characterized in that: The vehicle state time series feature extraction module comprises: A vehicle status data splitting and regularization unit is used to split the set of vehicle status data according to the parameter sample dimension, and regularize the split data according to the time dimension to obtain a time series of vehicle acceleration values, a time series of vehicle speed values, a time series of vehicle height values, and a time series of vehicle vibration frequency values; The vehicle state time series feature generation unit is used to perform time series feature extraction based on one-dimensional convolution on the time series of the vehicle acceleration value, the time series of the vehicle speed value, the time series of the vehicle height value and the time series of the vehicle vibration frequency value to obtain the vehicle acceleration time series associated feature implicit coding vector, the vehicle speed time series associated feature implicit coding vector, the vehicle height time series change feature implicit coding vector and the vehicle vibration frequency time series associated feature implicit coding vector.

3. The intelligent control system of the air suspension shock absorber of the new energy vehicle according to claim 2 is characterized in that: The vehicle state parameter association module includes: A vehicle state feature multi-dimensional aggregation coding unit, used for performing vehicle state feature multi-dimensional aggregation coding on the vehicle acceleration time series associated feature implicit coding vector, the vehicle speed time series associated feature implicit coding vector, the vehicle height time series change feature implicit coding vector and the vehicle vibration frequency time series associated feature implicit coding vector to obtain a vehicle state multi-dimensional time series aggregation matrix; The vehicle state parameter temporal correlation coding feature generation unit is used to input the vehicle state multi-dimensional temporal aggregation matrix into the vehicle state parameter temporal correlation feature extractor based on the two-dimensional convolutional neural network to obtain the vehicle state parameter temporal correlation coding feature map.

4. The intelligent control system of the air suspension shock absorber of the new energy vehicle according to claim 3 is characterized in that: The vehicle state parameter time series correlation enhancement module includes: A vehicle state feature global key semantic information extraction unit, used for inputting the temporal correlation coding feature map between vehicle state parameters into a global key semantic information extraction network to obtain a global temporal key semantic information coding vector between vehicle state parameters; A feature window determination unit to be processed is used to extract a channel feature vector between vehicle state parameters to be processed from the temporal correlation coding feature map between vehicle state parameters, and determine a vehicle state local neighborhood semantic association window of the channel feature vector between vehicle state parameters to be processed; A semantic mapping guidance factor calculation unit is used to calculate the vehicle state local key semantic information coding vector corresponding to the channel feature vector between the vehicle state parameters to be processed, and perform semantic comparison analysis on the vehicle state local key semantic information coding vector and the global temporal key semantic information coding vector between the vehicle state parameters to determine the vehicle state semantic mapping guidance factor of the channel feature vector between the vehicle state parameters to be processed; The enhanced channel feature generation unit between the vehicle state parameters to be processed is used to modulate the channel feature vector between the vehicle state parameters to be processed based on the vehicle state semantic mapping guidance factor to obtain the enhanced channel feature vector between the vehicle state parameters to be processed, wherein the enhanced channel feature vector between the vehicle state parameters to be processed is the channel feature vector of the pixel position (i, j) of the enhanced vehicle state parameter temporal association coding feature map.

5. The intelligent control system of the air suspension shock absorber of the new energy vehicle according to claim 4 is characterized in that: The to-be-processed feature window determination unit is used to: Extracting the channel feature vector between vehicle state parameters at pixel position (i, j) from the time series correlation coding feature map between vehicle state parameters as the channel feature vector between vehicle state parameters to be processed; Based on the characteristic distribution characteristics of the channel feature vector between the vehicle state parameters to be processed, the vehicle state local neighborhood semantic association window of the channel feature vector between the vehicle state parameters to be processed is determined, wherein the channel feature vector between the vehicle state parameters to be processed is located at the center position of the vehicle state local neighborhood semantic association window.

6. The intelligent control system of the air suspension shock absorber of the new energy vehicle according to claim 5 is characterized in that: The semantic mapping guidance factor calculation unit includes: A vehicle state local key semantic information extraction subunit is used to input all vehicle state parameter channel feature vectors in the vehicle state local neighborhood semantic association window into a local neighborhood association semantic information extraction network to obtain the vehicle state local key semantic information encoding vector corresponding to the vehicle state parameter channel feature vector to be processed; The vehicle state semantic mapping guidance factor calculation subunit is used to determine the vehicle state semantic mapping guidance factor of the channel feature vector between the vehicle state parameters to be processed based on the semantic comparison analysis between the global temporal key semantic information encoding vector between the vehicle state parameters and the vehicle state local key semantic information encoding vector corresponding to the channel feature vector between the vehicle state parameters to be processed.

7. The intelligent control system of the air suspension shock absorber of the new energy vehicle according to claim 6 is characterized in that: The vehicle state semantic mapping guidance factor calculation subunit is used to: Based on the channel feature vector between the vehicle state parameters to be processed, the vehicle state local key semantic information encoding vector corresponding to the channel feature vector between the vehicle state parameters to be processed is subjected to semantic interaction optimization based on the intrinsic-diagonal dual mediation to obtain the optimized vehicle state local key semantic information encoding vector of the channel feature vector between the vehicle state parameters to be processed; The Mahalanobis distance between the global temporal key semantic information encoding vector between the vehicle state parameters and the optimized vehicle state local key semantic information encoding vector of the channel feature vector between the vehicle state parameters to be processed is calculated as the vehicle state semantic mapping guidance factor of the channel feature vector between the vehicle state parameters to be processed.

8. The intelligent control system of the air suspension shock absorber of the new energy vehicle according to claim 7 is characterized in that: The pressure value adjustment module is used to: Inputting the enhanced time series correlation coding feature map between vehicle state parameters into a model predictive controller to obtain suspension optimization parameters, wherein the suspension optimization parameters include the pressure value of the air spring; The suspension optimization parameters are sent to an actuator layer, and the actuator layer sends a control instruction to the air spring to adjust the pressure value of the air spring based on a comparison between the suspension optimization parameters and the suspension real-time parameters.

9. An intelligent control method for an air suspension shock absorber of a new energy vehicle, characterized in that: include: Acquire vehicle status data collected by a sensor component deployed in a new energy vehicle to obtain a set of vehicle status data, wherein the sensor component includes an acceleration sensor, a vehicle speed sensor, a height sensor, and a vibration frequency sensor, and the vehicle status data includes a vehicle acceleration value, a vehicle speed value, a vehicle height value, and a vehicle vibration frequency value; Performing data regularization and time series feature extraction on the set of vehicle state data to obtain an implicit coding vector of vehicle acceleration time series correlation features, an implicit coding vector of vehicle speed time series correlation features, an implicit coding vector of vehicle height time series change features, and an implicit coding vector of vehicle vibration frequency time series correlation features; Performing multi-dimensional time series correlation on the vehicle acceleration time series correlation feature implicit coding vector, the vehicle speed time series correlation feature implicit coding vector, the vehicle height time series change feature implicit coding vector and the vehicle vibration frequency time series correlation feature implicit coding vector to obtain a time series correlation coding feature map between vehicle state parameters; Performing global-local vehicle state semantic mapping enhancement on the vehicle state parameter temporal correlation coding feature map to obtain an enhanced vehicle state parameter temporal correlation coding feature map; Based on the enhanced time series correlation coding characteristic diagram between vehicle state parameters, the pressure value of the air spring is adjusted.

10. The intelligent control method of the air suspension shock absorber of the new energy vehicle according to claim 9, characterized in that: Adjusting the pressure value of the air spring based on the enhanced vehicle state parameter temporal correlation coding characteristic diagram includes: Inputting the enhanced vehicle state parameter temporal correlation coding feature map into a model predictive controller to obtain suspension optimization parameters, wherein the suspension optimization parameters include the pressure value of the air spring; The suspension optimization parameters are sent to an actuator layer, and the actuator layer sends a control instruction to the air spring to adjust the pressure value of the air spring based on a comparison between the suspension optimization parameters and the suspension real-time parameters.

Images