Sensor Fault Diagnosis for an Internal Combustion Engine Based on Neural Networks

Abstract In this paper the authors propose an approach to sensor fault diagnosis for an automotive engine based on analytical redundancy techniques. The diagnosis architecture utilizes artificial neural network models for the estimation of engine variables that can be used in the detection and isolation of incipient faults. The considered neural network models have been tuned and tested by means of an experimental setup, These models have been used to implement a fault detection and diagnosis architecture based on a NPERG scheme (Nonlinear Parity Equation Residual Generation), which has been tested with encouraging results.