Automotive Internal-Combustion-Engine Fault Detection and Classification Using Artificial Neural Network Techniques

In this paper, an engine fault detection and classification technique using vibration data in the crank angle domain is presented. These data are used in conjunction with artificial neural networks (ANNs), which are applied to detect faults in a four-stroke gasoline engine built for experimentation. A comparative study is provided between the popular backpropagation (BP) method, the Levenberg–Marquardt (LM) method, the quasi-Newton (QN) method, the extended Kalman filter (EKF), and the smooth variable structure filter (SVSF). The SVSF is a relatively new estimation strategy, based on the sliding mode concept. It has been formulated to efficiently train ANNs and is consequently referred to as the SVSF-ANN. The accuracy of the proposed method is compared with the standard accuracy of the Kalman-based filters and the popular BP algorithms in an effort to validate the SVSF-ANN performance and application to engine fault detection and classification. The customizable fault diagnostic system is able to detect known engine faults with various degrees of severity, such as defective lash adjuster, piston chirp (PC), and chain tensioner (CT) problems. The technique can be used at any dealership or assembly plant to considerably reduce warranty costs for the company and manufacturer.

I. Introduction

IN the last three decades, a range of artificial intelligence (AI) algorithms have been developed and applied to pattern classification problems. Among these, artificial neural networks (ANNs) have been prevalent as they are adaptive and show exceptional nonlinear input–output mapping ability [1]. ANNs are information processing models inspired by the human brain. The human brain has over 100 billion neurons that communicate with each other using chemical and electrical signals. ANNs are a mathematical rendition of neurons that communicate with one another and learn from experience. Training of an ANN is achieved using data sets that represents a specific input–output mapping. It is typically implemented in applications such as automatic vehicle control [2], pattern recognition [3], [4], function approximation, and robotic applications [5].