Neural network control of seat vibrations of a non-linear full vehicle model using PMSM

In this paper, the dynamic behaviour of a non-linear eight degrees of freedom vehicle model having active suspensions and passenger seat using Permanent Magnet Synchronous Motor (PMSM) controlled by a Neural Network (NN) controller is examined. A robust NN structure is established by using principle design data from the Matlab diagrams of system functions. In the NN structure, Fast Back-Propagation Algorithm (FBA) is employed. The user inputs a set of 16 variables while the output from the NN consists of f"1-f"1"6 non-linear functions. Further, the PMSM controller is also determined using the same NN structure. Various tests of the NN structure demonstrated that the model is able to give highly sensitive outputs for vibration condition, even using a more restricted input data set. The non-linearity occurs due to dry friction on the dampers. The vehicle body and the passenger seat using PMSM are fully controlled at the same time. The time responses of the non-linear vehicle model due to road disturbance and the frequency responses are obtained. Finally, uncontrolled and controlled cases are compared. It is seen that seat vibrations of a non-linear full vehicle model are controlled by a NN-based system with almost zero error between desired and achieved outputs.

[1]  Paul H. Calamai,et al.  Application of genetic algorithms to the design optimization of an active vehicle suspension system , 1998 .

[2]  Aleksander Hac.  Optimal Linear Preview Control of Active Vehicle Suspension , 1992 .

[3]  J. K. Hedrick,et al.  A model following sliding mode controller for semi-active suspension systems with MR dampers , 2001, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

[4]  Ilya V. Kolmanovsky,et al.  Predictive energy management of a power-split hybrid electric vehicle , 2009, 2009 American Control Conference.

[5]  Subhash Rakheja,et al.  An Analytical and Experimental Investigation of the Driver-Seat-Suspension System , 1994 .

[6]  Anastasios N. Venetsanopoulos,et al.  Artificial neural networks - learning algorithms, performance evaluation, and applications , 1992, The Kluwer international series in engineering and computer science.

[7]  J. K. Hedrick,et al.  Alternative Control Laws for Automotive Active Suspensions , 1989 .

[8]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[9]  Jong Hyeon Park,et al.  Decentralized Variable Structure Control of Vehicle Active Suspensions. , 2000 .

[10]  George Juraj Stein,et al.  ACTIVE VIBRATION CONTROL SYSTEM FOR THE DRIVER'S SEAT FOR OFF- ROAD VEHICLES , 1991 .

[11]  Dean Karnopp,et al.  Optimal Performance of Variable Component Suspensions , 1988 .

[12]  Dae Sung Joo,et al.  Sliding mode neural network inference fuzzy logic control for active suspension systems , 2002, IEEE Trans. Fuzzy Syst..

[13]  Andrew G. Alleyne,et al.  Application of Nonlinear Control Theory to Electronically Controlled Suspensions , 1993 .

[14]  Theodorus J.A. de Vries,et al.  Linear motor motion control using a learning feedworward controller , 1997 .

[15]  Anastasios N. Venetsanopoulos,et al.  Fast learning algorithms for neural networks , 1992 .

[16]  David Crolla,et al.  ACTIVE SUSPENSION CONTROL; PERFORMANCE COMPARISONS USING CONTROL LAWS APPLIED TO A FULL VEHICLE MODEL , 1991 .

[17]  Toshio Yoshimura,et al.  CONSTRUCTION OF AN ACTIVE SUSPENSION SYSTEM OF A QUARTER CAR MODEL USING THE CONCEPT OF SLIDING MODE CONTROL , 2001 .

[18]  Rahmi Guclu.  Logicno mehko krmiljenje aktivnega vzmetenja brez upada njegove zračnosti , 2004 .

[19]  Davorin David Hrovat.  Applications of Optimal Control to Advanced Automotive Suspension Design , 1993 .

[20]  Rahmi Guclu.  Fuzzy Logic Control of Seat Vibrations of a Non-Linear Full Vehicle Model , 2005 .