Adaptive optimal control allocation using Lagrangian neural networks for stability control of a 4WS–4WD electric vehicle

Murat Demirci, Metin Gokasan

Research output: Contribution to journalArticlepeer-review

30 Citations (Scopus)

Abstract

This study involves a layered vehicle dynamics control system, which is composed of an adaptive optimal control allocation method using Lagrangian neural networks for optimal distribution of tyre forces and the sliding mode yaw moment observer for robust control of yaw dynamics. The proposed optimal control allocation method eliminates the requirement of solving optimization problem in every time step and it is a convergent and stability guaranteed solution for the optimal tyre force distribution problem. The aim in the sliding mode yaw moment observer is to force the vehicle to track a reference vehicle dynamic behaviour by estimating the equivalent input extended disturbance, which is the required stabilizing virtual yaw moment. The proposed layered stability control scheme has been tested on a four-wheel drive–four-wheel steer electric Fiat Doblo Van, which is modelled in CarSim. Both the sliding mode disturbance observer and the optimal control allocation methods are the first known applications to the stability control problem of road vehicles.

Original languageEnglish
Pages (from-to)1139-1151
Number of pages13
JournalTransactions of the Institute of Measurement and Control
Volume35
Issue number8
DOIs
Publication statusPublished - Dec 2013

Keywords

  • Lagrangian neural networks
  • optimal control allocation
  • sliding mode control
  • vehicle dynamics control
  • yaw moment observer

Fingerprint

Dive into the research topics of 'Adaptive optimal control allocation using Lagrangian neural networks for stability control of a 4WS–4WD electric vehicle'. Together they form a unique fingerprint.

Cite this