Abstract:
One essential part of automated diagnosis systems for SI engines is due to elements of air path system. The faults occur in this subsystem can result in deviation of air-fuel ratio, which causes increased emissions due to incomplete combustion, misfire and especially loss of power and drivability problems. In this article, a model-based diagnosis system for air-path of an SI engine is constructed. Thus, an adiabatic nonlinear four-state dynamic model of an SI engine is utilized for fault simulations. In the next step, a diagnosis system is designed in the framework of Multilayer Perceptron (MLP) Artificial Neural Network (ANN) classifier. Simulation results show that the constructed diagnosis system for six fault modes considering all three kinds of common faults is applied effectively. In this paper, the Manifold Air Temperature (MAT) sensor, Fuel Injector (FAG) and Throttle Actuator (THAG) faults which comparatively have been evaluated less than other elements in previous relative neural network based works, are also taken into account. As another remarkable aspect of this work, all classes of faults are diagnosed in their full possible over reading (positive) and under reading (negative) ranges.