Semi-Active suspension control needs to measure the relative velocity of the wheels respect to the vehicle body to regulate the damping forces. Linear potentiometers are the most used sensors in racing for linearity and simplicity, but they suffer of wear and tear and aging higher than the other sensors involved in the control loop. As a consequence, to save the efficiency and the effectiveness of the suspension control strategy, an Instrument Fault Detection (IFD) system able to detect the faults occurring on such a sensor should be adopted. . In this framework, the paper proposes a IFD scheme based on the analytical redundancy existing among the quantity measured by the rear suspension sensor and the other quantities involved in a typical suspension control loop. In other words, the fault detection is made by comparing the actual sensor output with the expected one provided by a "soft" sensor. In particular, the soft sensor has been implemented by suitably designing and tuning a Nonlinear Auto-Regressive with eXogenous inputs (NARX) network which is able to take into account for the system nonlinearity. Experimental results have proven the good promptness and reliability of the scheme in detecting also "small faults" (e.g. due to slight variations of the input/output sensor curve).
|Titolo:||ANN-based IFD in motorcycle rear suspension|
|Data di pubblicazione:||2017|
|Appare nelle tipologie:||4.1.2 Proceedings con ISBN|