Neural Network-Based Identification and Approximate Predictive Control of a Servo-Hydraulic Vehicle Suspension System

This paper presents multi-layer feedforward neural network-based identification and approximate predictive controller (NNAPC) for a two degree-of-freedom (DOF), quarter-car servohydraulic vehicle suspension system. The nonlinear dynamics of the servo-hydraulic actuator is incorporated in the suspension model. A suspension travel controller is developed to improve the ride comfort and handling quality of the system. A SISO neural network (NN) model based on Nonlinear AutoRegressive with eXogenous input (NARX) is developed using input-output data sets obtained from mathematical model simulation. The NN model was trained using Levenberg-Marquardt algorithm. The NNAPC was used to predict the future responses that are optimized by cost minimization. The proposed controller is compared with a constant-gain PID controller (based on Ziegler-Nichols tuning method) during suspension travel setpoint tracking in the presence of deterministic road disturbance. Simulation results demonstrate the superior performance of the NNAPC over the generic PID controller in adapting to the deterministic road disturbance.

[1]  Niels Kjølstad Poulsen,et al.  Neural Networks for Modelling and Control of Dynamic Systems: A Practitioner’s Handbook , 2000 .

[2]  Mohieddine Jelali,et al.  Hydraulic Servo-systems: Modelling, Identification and Control , 2012 .

[3]  Haiping Du,et al.  Designing H ∞/GH 2 static-output feedback controller for vehicle suspensions using linear matrix inequalities and genetic algorithms , 2008 .

[4]  Huei Peng,et al.  Adaptive robust force control for vehicle active suspensions. , 2004 .

[5]  Martin T. Hagan,et al.  An introduction to the use of neural networks in control systems , 2002 .

[6]  M.N. Taib,et al.  Selection of training data for modeling essential oil extraction system using NNARX structure , 2007, 2007 International Conference on Control, Automation and Systems.

[7]  Fan Yu,et al.  GA-BASED PID AND FUZZY LOGIC CONTROL FOR ACTIVE VEHICLE SUSPENSION SYSTEM , 2003 .

[8]  S. Baskar,et al.  Evolutionary algorithms based design of multivariable PID controller , 2009, Expert Syst. Appl..

[9]  Dingli Yu,et al.  Implementation of neural network predictive control to a multivariable chemical reactor , 2003 .

[10]  Mouleeswaran Senthil Kumar,et al.  Development of Active Suspension System for Automobiles using PID Controller , 2008 .

[11]  D. Hrovat,et al.  Survey of Advanced Suspension Developments and Related Optimal Control Applications, , 1997, Autom..

[12]  John McPhee,et al.  A design methodology for mechatronic vehicles: application of multidisciplinary optimization, multibody dynamics and genetic algorithms , 2005 .

[13]  J Darling,et al.  Control of a hydropneumatic active suspension based on a non-linear quarter-car model , 2006 .

[14]  Huei Peng,et al.  ANALYSIS OF ACTIVE SUSPENSION SYSTEMS WITH HYDRAULIC ACTUATORS , 2004 .

[15]  Charles Poussot-Vassal,et al.  Multi-objective qLPV Hinf / H2 Control of a half vehicle , 2006 .

[16]  Aidan O'Dwyer,et al.  Handbook of PI and PID controller tuning rules , 2003 .

[17]  Zhiqiang Gao,et al.  From linear to nonlinear control means: a practical progression. , 2002, ISA transactions.

[18]  YOSHIMURAToshio,et al.  Active suspension control of a one-wheel car model using single input rule modules fuzzy reasoning and a disturbance observer , 2005 .

[19]  Gary J. Balas,et al.  Road adaptive active suspension design using linear parameter-varying gain-scheduling , 2002, IEEE Trans. Control. Syst. Technol..

[20]  Honghai Liu,et al.  State of the Art in Vehicle Active Suspension Adaptive Control Systems Based on Intelligent Methodologies , 2008, IEEE Transactions on Intelligent Transportation Systems.

[21]  Nong Zhang,et al.  H∞ control of active vehicle suspensions with actuator time delay , 2007 .

[22]  Farouq S. Mjalli,et al.  Neural‐Networks‐Based Feedback Linearization versus Model Predictive Control of Continuous Alcoholic Fermentation Process , 2005 .

[23]  Tzuu-Hseng S. Li,et al.  GA-based fuzzy PI/PD controller for automotive active suspension system , 1999, IEEE Trans. Ind. Electron..

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

[25]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[26]  Péter Gáspár,et al.  Active suspension design using linear parameter varying control , 2003 .

[27]  Y. Jin,et al.  Adaptive neuron control using an integrated error approach with application to active suspensions , 2008 .

[28]  Lennart Ljung,et al.  Multiple steps prediction with nonlinear ARX models , 2004 .

[29]  Stratis Kanarachos,et al.  A neural network approach to the design of a vehicle's non-linear hybrid suspension system , 2002 .

[30]  O. A. Dahunsi,et al.  Neural network-based model predictive control of a servo-hydraulic vehicle suspension system , 2009, AFRICON 2009.

[31]  J. Renn,et al.  MODELING AND CONTROL OF A NEW 1 / 4 T SERVO-HYDRAULIC VEHICLE ACTIVE SUSPENSION SYSTEM , 2007 .

[32]  Sahin Yildirim,et al.  Vibration control of vehicle active suspension system using a new robust neural network control system , 2009, Simul. Model. Pract. Theory.

[33]  S.-J. Huang,et al.  A neural network based sliding mode controller for active vehicle suspension , 2007 .

[34]  Jih-Gau Juang,et al.  PID Control Using Presearched Genetic Algorithms for a MIMO System , 2008, IEEE Trans. Syst. Man Cybern. Part C.

[35]  Nand Kishor,et al.  Small hydro power plant identification using NNARX structure , 2005, Neural Computing & Applications.

[36]  M. K. Hada,et al.  Optimisation of an Active Suspension Force Controller using Genetic Algorithm for Random Input , 2007 .