Incipient wheel fault identification in mobile robots using neural networks and nonlinear least squares

Abstract

In this paper, we present a novel method for fault identification in the case of an incipient wheel fault in mobile robots. First, a three-layer neural networks is established to estimate the deviation of the robot dynamics due to the process fault. The estimate of the faulty dynamic model is based on a combination of the nominal dynamic model and the neural network output. Then, by replacing the faulty dynamic model with its estimate value, the primary estimates of the wheel radius appear as the solutions of two quadratic equations. Next, a simple and efficient way to perform these primary estimate selections is proposed in order to eliminate undesired primary estimates. A recursive nonlinear least squares is applied in order to obtain a smooth estimate of the wheel radius. Two computer simulation examples using Matlab/Simulink show that the proposed method is very effective for incipient fault identification in the setting of both left and right wheel faults.

Keywords

Incipient fault fault identification mobile robots neural networks recursive nonlinear least squares

Get full access to this article

View all access options for this article.

References

Ding SX. Model-based fault diagnosis techniques: design schemes, algorithms and tools. Berlin, Germany: Springer, 2008.

Dixon WE, Walker ID and Dawson DM. Fault detection for wheeled mobile robots with parametric uncertainty. In: Proceedings of IEEE/ASME international conference on advanced intelligent mechatronics, vol. 1, 2001, pp.1245–1250.

Sarkar

. Supervisory fault adaptive control of a mobile robot and its application in sensor-fault accommodation. IEEE Transact Robot 2007; 23: 174–178.

Meng

Zhen

Biswas

. Hybrid fault adaptive control of a wheeled mobile robot. IEEE/ASME Transact Mechatron 2003; 8: 226–233.

Skoundrianos

Tzafestas

. Finding fault - fault diagnosis on the wheels of a mobile robot using local model neural networks. Robot Automat Magazine, IEEE 2004; 11: 83–90.

Sarkar

BHN

. Robust fault detection and isolation in mobile robot. Fault Detect Supervision Safe Techl Process 2006; 6: 20–25.

Hoang

Kang

H-J

Y-S

. Fault detection and isolation in wheeled mobile robot. Intel Comput Technol 2012; 7389: 563–569.

Hoang

Kang

H-J

. A model-based fault diagnosis scheme for wheeled mobile robots. Int J Ctrl Automat Syst 2014; 12: 1–15.

Bohn C. Parameter estimation for nonlinear systems: adaptive innovations model filters vs. adaptive extended Kalman filters. In: Proceedings of IEEE international conference on industrial technology 2000. vol. 1, pp.578–583.

10.

Pavkovic

Deur

Kolmanovsky

. Adaptive kalman filter-based load torque compensator for improved SI engine idle speed control. IEEE Transact Ctrl Syst Technol 2009; 17: 98–110.

11.

Jiang

Khorasani

Tafazoli

. Parameter estimation-based fault detection, isolation and recovery for nonlinear satellite models. IEEE Transact Ctrl Syst Technol 2008; 16: 799–808.

12.

Hartman

Bauer

Teel

. Robust finite-time parameter estimation using a hybrid systems framework. IEEE Transact Automat Ctrl 2012; 57: 2956–2962.

13.

Chengyu

Annaswamy

Kojic

. Parameter convergence in nonlinearly parameterized systems. IEEE Transact Automat Ctrl 2003; 48: 397–412.

14.

Ai-Poh

Annaswamy

Skantze

. Adaptation in the presence of a general nonlinear parameterization: an error model approach. IEEE Transact Automat Ctrl 1999; 44: 1634–1652.

15.

Adetola

Guay

. Robust adaptive MPC for constrained uncertain nonlinear systems. Int J Adapt Ctrl Signal Process 2011; 25: 155–167.

16.

Adetola

Guay

. Finite-time parameter estimation in adaptive control of nonlinear systems. IEEE Transact Automat Ctrl 2008; 53: 807–811.

17.

Reif

Gunther

Yaz

. Stochastic stability of the discrete-time extended Kalman filter. IEEE Transact Automat Ctrl 1999; 44: 714–728.

18.

Alessandri

Cuneo

Pagnan

. A recursive algorithm for nonlinear least-squares problems. Computat Optimiz Appl 2007; 38: 195–216.

19.

Bugeja

Fabri

Camilleri

. Dual adaptive dynamic control of mobile robots using neural networks. IEEE Transact Syst Man Cybernet Part B: Cybernet 2009; 39: 129–141.

20.

Fierro

Lewis

. Control of a nonholonomic mobile robot: backstepping kinematics into dynamics. J Robot Syst 1997; 1: 149–163.

21.

Lewis

Yesildirek

. Control of robot manipulators, New York: Macmillan, 1993.

22.

Van

Kang

H-J

Suh

Y-S

. A robust fault diagnosis and accommodation scheme for robot manipulators. Int J Ctrl Automat Syst 2013; 11: 377–388.

23.

Gautier

Janot

Vandanjon

. A new closed-loop output error method for parameter identification of robot dynamics. IEEE Transact Ctrl Syst Technol 2013; 21: 428–444.

24.

Sujan

Dubowsky

. An optimal information method for mobile manipulator dynamic parameter identification. IEEE/ASME Transact Mechatron 2003; 8: 215–225.

25.

Abdollahi

Talebi

Patel

. A stable neural network-based observer with application to flexible-joint manipulators. IEEE Transact Neural Network 2006; 17: 118–129.

26.

Bouchard

. New recursive-least-squares algorithms for nonlinear active control of sound and vibration using neural networks. IEEE Transact Neural Network 2001; 12: 135–147.

27.

Zhu

Chen

Príncipe

. A novel extended kernel recursive least squares algorithm. Neural Network 2012; 32: 349–357.

28.

Hasan Örkcü

. Subset selection in multiple linear regression models: A hybrid of genetic and simulated annealing algorithms. Appl Math Computat 2013; 219: 11018–11028.