Fault Diagnosis and Fault-Tolerant Control for Manifold Absolute Pressure Sensor(MAP) of Diesel Engine Based on Elman Network Observer

Yingmin Wang

Abstract


Fault diagnosis (FD) and fault-tolerant control (FTC) of automotive diesel engines are important for efficient repair and maintenance. The construction of an accurate model for a diesel engine intake system is difficult due to its strong nonlinearity, and bias fault and precision degradation fault of Manifold Absolute Pressure Sensor (MAP) of diesel engine can’t be diagnosed easily using model-based methods. In this paper, a FD-FTC system is developed for the diesel engine intake system. The system is based on Elman neural network observer, and active fault-tolerant control strategies are constructed. A short analysis reveals Elman neural network observer is suitable to prediction of the intake pressure of diesel engine, which is more accurate than BP network. In this FD-FTC system, four types of MAP failures are considered, complete failure fault, bias fault, precision degradation fault and drift fault. The simulations of the proposed FD-FTC system on a validated experimental intake system diesel engine model, show good results for MAP failures.

Keywords


Neural networks, Diesel engine, Intake system, Threshold, Fault diagnosis, Fault-tolerant control.

Full Text: PDF