Acoustic signal-based misfire detection in internal combustion engines using machine learning techniques

Salehi, Fahime; Moosavian, Ashkan; Hashemi Daryan, Jafar; Moqtaderi, Hamed

doi:10.22034/er.2026.2076337.1107

Acoustic signal-based misfire detection in internal combustion engines using machine learning techniques

Articles in Press

Document Type : Original Article

Authors

Fahime Salehi ¹

Ashkan Moosavian ²

Jafar Hashemi Daryan ³

Hamed Moqtaderi ⁴

¹ MSc Student, Department of Mechanical Engineering, Faculty of Engineering, Alzahra University.

² Assistant Prof., Department of Mechanical Engineering, National University of Skills, Tehran, Iran

³ Test and validation development head, IranKhodro Powertrain Company (IPCo), Tehran, Iran.

⁴ Assistant Prof., Department of Mechanical Engineering, Alzahra University, Tehran, Iran

10.22034/er.2026.2076337.1107

Abstract

The This research focuses on detecting misfire in a four-cylinder four-stroke gasoline engine inside an acoustic engine test cell using audio signal processing. This research proposes a smart solution by combining signal processing techniques and artificial neural networks. Misfire was created by fuel injection cut off for each cylinder at a constant speed of 760 rpm, and the audio signals were recorded under controlled acoustic conditions. FFT, MFCC and STFT techniques were used for feature extraction. The results showed that the artificial neural network and the one-dimensional convolutional neural network with features extracted from the fast Fourier transform achieved accuracies of 98.40% and 99.36%, respectively. Also, the two-dimensional convolutional neural network using features extracted from the short-time Fourier transform achieved an accuracy of 99.71%. These results show that the proposed methods, especially the use of two-dimensional convolutional neural networks, have a very good performance in identifying the healthy and faulty state of the engine and can serve as an effective tool for real-time monitoring and fault diagnosis of gasoline engines.

Keywords

Engine Fault detection

Misfiring

Acoustic Signal

Machine learning

Subjects