Международный журнал достижений в области технологий
Открытый доступ

Абстрактный

IC Engine Fault diagnosis Using ROC

M.R.Parate, S.N.Dandare

Advanced methods of supervision fault detection and fault diagnosis become increasingly important for many technical processes, for the improvement of reliability, safety and efficiency. This especially important for safety related processes in aircraft, trains, automobiles, power plants and chemical plants. The classical approaches are limited for checking of some measurable output variables and does not provide a deeper insight and usually do not allow a fault diagnosis. The proposed system has model-based approach for fault diagnosis of IC engine using audio signals from engine. The audio signals are captured from the engine using microphone and are processed using MATLAB to find characteristics parameters of the signals. Artificial Neural Network is used to identify the fault in IC engine, the Receiver operating characteristic (ROC) analysis is used to obtain the most appropriate transfer function for the ANN and it also provides the most comprehensive description of diagnostic accuracy which is used to diagnose the faults in IC Engine.