The invention relates to an intelligent tire slip angle estimation method based on CNN-Transform, and belongs to the technical field of intelligent vehicle perception. The method comprises the following steps: S1, acquiring acceleration signals of a full-load tire under various lateral deviation working conditions by using a three-axis acceleration sensor, and performing 200Hz low-pass filtering and data 8: 2 division; s2, designing a convolutional neural network (CNN) comprising four one-dimensional convolutional layers, extracting deep features from the preprocessed signals, and reserving time sequence information in combination with position coding; s3, aggregating and enhancing the extracted features by adopting a multi-head cross attention module, filtering interference information, and highlighting key features related to the slip angle; and S4, inputting the processed test data into the trained CNN-Transformer model, and predicting the side slip angle of the tire. According to the method, by combining the advantages of CNN in local feature extraction and Transform in global feature attention capability, the precision of slip angle estimation and the robustness of the system are remarkably improved, and the method is suitable for various tire specifications and working conditions.
本发明涉及一种基于CNN‑Transformer的智能轮胎侧偏角估计方法,属于智能车辆感知技术领域。所述方法,包括:步骤S1、利用三轴加速度传感器采集满载轮胎多种侧偏工况下的加速度信号,并进行200Hz低通滤波及数据8:2划分;步骤S2、设计包含四个一维卷积层的卷积神经网络(CNN),从预处理后的信号中提取深层特征,并结合位置编码保留时序信息;步骤S3、采用多头交叉注意力模块对提取的特征进行聚合与增强,滤除干扰信息,突出与侧偏角相关的关键特征;步骤S4、将处理后的测试数据输入训练好的CNN‑Transformer模型,预测轮胎侧偏角。本发明通过结合CNN在局部特征提取与Transformer在全局特征的关注能力上的优势,显著提升了侧偏角估计的精度和系统的鲁棒性,适用于多种轮胎规格和工况条件。
CNN-Transform-based intelligent tire slip angle estimation method
一种基于CNN-Transformer的智能轮胎侧偏角估计方法
2025-04-15
Patent
Electronic Resource
Chinese
IPC: | G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion |
The tire slip angle estimation algorithm based on intelligent tire technology
SAGE Publications | 2024
|Intelligent tire slip angle prediction method based on GSA-PCA-GPR
European Patent Office | 2023
|Estimation of side slip angle using measured tire forces
Automotive engineering | 2002
|