The Journal of Engine Research

The Journal of Engine Research

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

Document Type : Original Article

Authors
Fahime Salehi 1
Ashkan Moosavian 2
Jafar Hashemi Daryan 3
Hamed Moqtaderi 1
1 Department of Mechanical Engineering, Faculty of Engineering, Alzahra University, Tehran, Iran
2 Department of Mechanical Engineering, Technical and Vocational University (TVU), Tehran, Iran
3 Irankhodro Powertrain Company (IPCo), Tehran, Iran
10.22034/er.2026.2076337.1107
Abstract
This study investigates misfire detection in a four-cylinder, four-stroke gasoline engine by combining acoustic signal processing techniques with artificial neural networks. Misfires were induced by sequentially cutting fuel injection for each cylinder while the engine operated at a constant speed of 760rpm, and the resulting acoustic signals were captured under controlled test-cell conditions. Fast Fourier Transform (FFT), Mel-Frequency Cepstral Coefficients (MFCC), and Short-Time Fourier Transform (STFT) techniques were applied for feature extraction. The findings indicate that the artificial neural network (ANN) and the one-dimensional convolutional neural network (1D-CNN), when using FFT-derived features, achieved accuracies of 98.40% and 99.36%, respectively. Additionally, the two-dimensional convolutional neural network (2D-CNN), utilizing features extracted from the STFT, achieved an accuracy of 99.71%. These results demonstrate that the proposed methods—particularly the 2D-CNN perform exceptionally well in distinguishing between healthy and misfiring engine states, proving to be an effective approach for the real-time monitoring and fault diagnosis of gasoline engines.
Keywords
Engine Fault Detection
Misfire Detection
Acoustic Signal
Machine Learning
Convolutional Neural Network
[1] Tang L, Tian H, Huang H, Shi S, Ji Q. A survey of mechanical fault diagnosis based on audio signal analysis. Measurement. 2023 Oct 1;220:113294. doi: 10.1016/j.measurement.2023.113294
[2] Goli Karimabadi A, Ghassabzadeh Saryazdi M, Ohadi A, Moosavian A. Diagnosing the clearance fault of the camshaft in the hot test stage at the end of the production line by using of audio signal processing. NDT Technology. 2024 Feb 20;3(4):41-9. doi: 10.30494/jndt.2024.471587.1147
[3] Jafarian K, Mobin M, Jafari-Marandi R, Rabiei E. Misfire and valve clearance faults detection in the combustion engines based on a multi-sensor vibration signal monitoring. Measurement. 2018 Nov 1;128:527-36. doi: 10.1016/j.measurement.2018.04.062
[4] Firmino JL, Neto JM, Oliveira AG, Silva JC, Mishina KV, Rodrigues MC. Misfire detection of an internal combustion engine based on vibration and acoustic analysis. Journal of the Brazilian Society of Mechanical Sciences and Engineering. 2021 Jul;43(7):336. doi: 10.1007/s40430-021-03052-y
[5] de V. Lima TL, Filho AC, Belo FA, Souto FV, Silva TC, Mishina KV, Rodrigues MC. Noninvasive methods for fault detection and isolation in internal combustion engines based on chaos analysis. Sensors. 2021 Oct 19;21(20):6925. doi: 10.3390/s21206925
[6] Rodrigues NF, Brito AV, Ramos JG, Mishina KD, Belo FA, Lima Filho AC. Misfire detection in automotive engines using a smartphone through wavelet and chaos analysis. Sensors. 2022 Jul 6;22(14):5077. doi: 10.3390/s22145077
[7] Terwilliger AM, Siegel JE. Improving misfire fault diagnosis with cascading architectures via acoustic vehicle characterization. Sensors. 2022 Oct 12;22(20):7736. doi: 10.3390/s22207736
[8] bin Md Sharib MK, bin Abu Bakar E, bin Hawary AF, Akhtar MN, Abdullah MN. Adaptive system on engine misfire and knocking features for IC engine. Materials Today: Proceedings. 2023 Apr 18. doi: 10.1016/j.matpr.2023.03.677
[9] Li W, Liu X, Wang D, Lu W, Yuan B, Qin C, Cheng Y, Căleanu C. MITDCNN: A multi-modal input Transformer-based deep convolutional neural network for misfire signal detection in highnoise diesel engines. Expert Systems with Applications. 2024 Mar 15;238:121797. doi: 10.1016/j.eswa.2023.121797
[10] Yazdi MH, Aliyari-Shoorehdeli M, Moosavian A. Convolutional transformer approach for engine spark plug fault diagnosis using acoustic signal. The Journal of Engine Research. 2024;70(4):56-68. doi: 10.22034/ER.2024.2025036.1036
[11] Karabacak YE. Condition monitoring of internal combustion engines with vibration signals and fault detection by using machine learning techniques. International Journal of Automotive Engineering and Technologies. 2024 Dec 12;13(4):191-200. doi: 10.18245/ijaet.1251886
[12] Li Z, Qin Z, Luo W, Ling X. Gasoline engine misfire fault diagnosis method based on improved YOLOv8. Electronics. 2024 Jul 9;13(14):2688. doi: 10.3390/electronics13142688
[13] Yu F, Huang Y, Chen G, Yang X, Du C, Gong Y. Engine Misfire Fault Detection Based on the Channel Attention Convolutional Model. Computers, Materials & Continua. 2025 Jan 1;82(1). doi: 10.32604/cmc.2024.058051
[14] Isa MM, Ngatiman NA, Ahmad MI, Saad SM, Nuawi MZ. Monitoring Valve and Spark Plug Failures using Z-Freq Statistical Analysis. Journal of Acoustics and Vibration Research. 2025 Jun 30;3(1):14-21.
[15] Huang Y, Zou A, Xu K, Yan B, Hua C, Dong D. Misfire Fault Diagnosis in Multi-Cylinder Internal Combustion Engine with Multi-Input Neural Networks. 2025. Available at SSRN 4965428. doi: 10.2139/ssrn.4965428
[16] Zheng T, Zhang Y, Li Y, Shi L. Real-time combustion torque estimation and dynamic misfire fault diagnosis in gasoline engine. Mechanical Systems and Signal Processing. 2019 Jul 1;126:521-35. doi: 10.1016/j.ymssp.2019.02.048
[17] Gourisaria MK, Agrawal R, Sahni M, Singh PK. Comparative analysis of audio classification with MFCC and STFT features using machine learning techniques. Discover Internet of Things. 2024 Jan 3;4(1):1. doi: 10.1007/s43926-023-00049-y
[18] Mishra M, Srivastava M. A view of artificial neural network. In2014 international conference on advances in engineering & technology research (ICAETR-2014) 2014 Aug 1 (pp. 1-3). IEEE. doi: 10.1109/ICAETR.2014.7012785
[19] Wang H, Liu C, Du W, Wang S. Intelligent diagnosis of rotating machinery based on optimized adaptive learning dictionary and 1DCNN. Applied Sciences. 2021 Nov 30;11(23):11325. doi: 10.3390/app112311325
The Journal of Engine Research
Volume 72, Issue 4 - Serial Number 81
English Paper
Winter 2026
Pages 1-20

  • Receive Date 21 November 2025
  • Revise Date 01 December 2025
  • Accept Date 28 April 2026