Fault detection and isolation for engine under closed-loop control

Fault detection and isolation (FDI) have become one of the most important aspects of automobile design. Fault detection and isolation for engine open loop system was investigated in many research. In fact, the simulation results obtained from engine open loop system do not reflect the real situation for automotive engine. In the practice the engine works as closed-loop control system. In this paper, a new FDI scheme is developed for automotive engines under closed-loop control system. Test the method using closed-loop system has been done. The method uses an independent radial basis function (RBF) neural network model to model engine dynamics, and the modeling errors are used to form the basis for residual generation. Furthermore, another RBF network is used as a fault classifier to isolate occurred fault from other possible faults in the system. The performance of the developed scheme is assessed using an engine benchmark, the Mean Value Engine Model (MVEM) with Matlab/Simulink. Six faults have been simulated on the MVEM, including four sensor faults, one component fault and one actuator fault. The simulation results show that all the simulated faults can be clearly detected and isolated in dynamic conditions throughout the engine operating range.