Prediction of Motorcycle Suspension Stroke through Dynamic Neural Networks

Electronic instrumentation and sensors are extensively adopted on board of vehicles to prevent the road accidents and improve the overall driving experience. On the other hand, the development of fault detection strategies are usually carried out in order to limit the direct impact of electronics on the vehicle cost. To this aim the employment of the analytical redundancy of measurement information should be preferred. As an example of the systematic approach, the software sensor for the rear suspension of the two-wheeled vehicles is designed focusing on recurrent Artificial Neural Networks able to predict the dynamic behavior. Experimental results concerning with a typically adopted instrumentation set show the rear suspension elongation can be correctly estimated. They disclose the possibility of setting-up an effective Instrument Fault Detection and Isolation scheme based on the real-time adoption of the proposed software sensor in order to improve the system reliability.