An integrated approach for aircraft turbofan engine fault detection based on data mining techniques

• Published in: Expert systems 2019-04, Vol.36 (2), p.n/a
• Main Authors: Gharoun, Hassan, Keramati, Abbas, Nasiri, Mohammad Mahdi, Azadeh, Ali
• Format: Article
• Language: English
• Subjects: Aircraft; Aircraft detection; aircraft engine; Aircraft engines; Airplane engines; Algorithms; artificial neural network; Data mining; exhaust gas temperature; Exhaust gases; Expert systems; Fault detection; Gas temperature; Health; one‐class SVM; Support vector machines; Turbofan engines
• ISSN: 0266-4720; 1468-0394
• DOI: 10.1111/exsy.12370

The present study proposes an algorithm for fault detection in terms of condition‐based maintenance with data mining techniques. The proposed algorithm is applied on an aircraft turbofan engine using flight data and consists of two main sections. In the first section, the relationship between engine exhaust gas temperature (EGT) as the main engine health monitoring criterion and other operational and environmental parameters of the engine was modelled using the data‐driven models. In the second section, a data set including EGT residuals, that is, the difference between the actual EGT of the system and the EGT estimated by the developed model in the health conditions of the engine, was created. Finally, faults occurring in each flight were detected based on the identification of abnormal events by a one‐class support vector machine trained by the health condition EGT residual data set. The results indicated that the proposed algorithm was an effective approach for inspecting aircraft engine conditions and detecting faults, with no need for technical knowledge on the interior characteristics of the aircraft engine.