Attenuating the Wheel Speed Sensor Errors Based on Resilient Back Propagation Neural Network

Wheel speed is a very important control signal in modern car control systems. The quality of the processed wheel speed determines the performance of these systems. However, the quality of the signal is not so good due to manufacturing tolerances or wear and tear of the sensor. In this paper a method to compensate for the mechanical inaccuracy of the sensor is presented. We train Resilient Back Propagation (RPROP) neural network by utilizing large amounts of sensor angular errors to correct the wheel speed. The results by simulation show that it's effective and has high quality of anti-noisy.

[1]  Fredrik Gustafsson,et al.  Indirect Tire Pressure Monitoring using Sensor Fusion , 2002 .

[2]  Niclas Persson,et al.  Event Based Sampling with Application to Spectral Estimation , 2002 .

[3]  Liu Feng,et al.  Applying Improved BP Neural Network In Underwater Targets Recognition , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[4]  W. Hernandez.  Improving the response of wheel speed sensors by using robust and optimal signal processing techniques , 2005, Proceedings of the IEEE International Symposium on Industrial Electronics, 2005. ISIE 2005..

[5]  Martin T. Hagan,et al.  Neural network design , 1995 .