Practicability study on the suitability of artificial, neural networks for the approximation of unknown steering torques

• Published in: Vehicle system dynamics Vol. 54; no. 10; pp. 1362 - 1383
• Main Authors: Van Ende, K. T. R., Schaare, D., Kaste, J., Küçükay, F., Henze, R., Kallmeyer, F. K.
• Format: Journal Article
• Language: English
• Published: Taylor & Francis 02.10.2016
• Subjects: Approximation; Artificial neural networks; Computer simulation; Dynamical systems; Levenberg-Marquardt method; Networks; Neural networks; Nonlinear dynamics; steer-by-wire; Steering; steering torque; Training
• ISSN: 0042-3114; 1744-5159
• DOI: 10.1080/00423114.2016.1202987

For steer-by-wire systems, the steering feedback must be generated artificially due to the system characteristics. Classical control concepts require operating-point driven optimisations as well as increased calibration efforts in order to adequately simulate the steering torque in all driving states. Artificial neural networks (ANNs) are an innovative control concept; they are capable of learning arbitrary non-linear correlations without complex knowledge of physical dependencies. The present study investigates the suitability of neural networks for approximating unknown steering torques. To ensure robust processing of arbitrary data, network training with a sufficient volume of training data is required, that represents the relation between the input and target values in a wide range. The data were recorded in the course of various test drives. In this research, a variety of network topologies were trained, analysed and evaluated. Though the fundamental suitability of ANNs for the present control task was demonstrated.