Detection of plugged injectors in a gasoline engine system using a neural fuzzy scheme

Abstract

An incorrect fuel mixture or the use of inappropriate fuel additives may cause the injectors of a gasoline engine to become restricted, or the needles of the injectors to become stuck. In such an event, the injectors fail to spray normally or may even fail to function at all. Accordingly, this study develops a plugged-injector fault diagnosis system based upon a neural fuzzy scheme. Based upon knowledge of the engine speed, throttle position, injection duration, and vibration frequency, the fuzzy scheme is capable of diagnosing three distinct plugged-injector fault scenarios, namely one permanently plugged injector, two permanently plugged injectors, and one or two temporarily plugged injectors respectively. In addition, a group-injection fault diagnosis system is also developed with the ability to classify further two-plugged-injector fault scenarios as either group-injection faults or ungroup-injection faults. The experimental results confirm the ability of the two systems to diagnose correctly one- and two-plugged-injector faults. Furthermore, it is shown that the neural fuzzy plugged-injector diagnosis scheme provides a more accurate and reliable diagnosis than a polynomial-based approach for the two-plugged-injector fault scenario. Overall, the neural fuzzy schemes proposed in this study provide an efficient and practical means of diagnosing injector faults in gasoline engine systems.