The invention relates to the field of automobile control, in particular to a side slip angle estimation method based on Transform and extended Kalman filtering, which comprises the following steps: S1, designing a vehicle active excitation control input curve, and constructing an off-line training data set with high working condition coverage of a Transform neural network; s2, inputting the data set in the step S1 into a Transform neural network to obtain a vehicle side slip angle pseudo measurement value and a relative error prediction value thereof; s3, designing an adaptive extended Kalman filtering algorithm based on the seven-degree-of-freedom vehicle dynamics model; and S4, based on the side slip angle pseudo measurement value and the relative error prediction value in the S2, the process of expanding the Kalman filtering algorithm in the S3 and the mean value and the variance of the measurement noise are self-adapted, and the estimation of the vehicle side slip angle is realized. Compared with the prior art, the method comprehensively considers the robustness based on a model estimation algorithm and the generalization based on a neural network estimation algorithm, and has great significance in improving the accuracy of side slip angle estimation and ensuring the robustness.
本发明涉及汽车控制领域,尤其是涉及一种基于Transformer和扩展卡尔曼滤波的质心侧偏角估计方法,包括以下步骤:S1、设计车辆主动激励控制输入曲线,构建Transformer神经网络工况高覆盖度的离线训练数据集;S2、将步骤S1中的数据集输入Transformer神经网络中,获得车辆质心侧偏角伪测量值及其相对误差预测值;S3、基于七自由度车辆动力学模型,设计自适应扩展卡尔曼滤波算法;S4、基于S2中质心侧偏角伪测量值和相对误差预测值自适应S3中扩展卡尔曼滤波算法的过程和测量噪声的均值及方差,实现车辆质心侧偏角的估计。与现有技术相比,本发明综合考虑了基于模型估计算法的鲁棒性和基于神经网络估计算法的泛化性,对于提高质心侧偏角估计的准确性同时保证其鲁棒性具有重大意义。
Transform and extended Kalman filtering-based side slip angle estimation method
一种基于Transformer和扩展卡尔曼滤波的质心侧偏角估计方法
2024-08-27
Patent
Electronic Resource
Chinese
IPC: | 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 / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
Vehicle Side Slip Angle Estimation Using Stiffness-Update Method and Extend Kalman Filter
Springer Verlag | 2020
|Vehicle Side Slip Angle Estimation Using Stiffness-Update Method and Extend Kalman Filter
British Library Conference Proceedings | 2021
|A variable structure adaptive extended Kalman filter for vehicle slip angle estimation
Online Contents | 2011
|A variable structure adaptive extended Kalman filter for vehicle slip angle estimation
Tema Archive | 2011
|