MACHINE FAULT DETECTION BASED ON AUDIO SIGNAL ANALYSIS USING A DEEP LEARNING TECHNIQUE

Minh-Tuan Nguyen; Van-Duong Vuong

Minh-Tuan Nguyen Hung Yen University of Technology and Education
Van-Duong Vuong Hung Yen University of Technology and Education

Keywords: fault detection, deep learning, convolution neural network, ResNet-18, audio signal, Mel-spectrogram

Abstract

Condition monitoring and fault detection in machinery are critical components of industrial maintenance, as they identify and predict potentially hazardous issues before their eventuality, which may result in significant damage or delay. The latest advancements in machine learning and deep learning have made it possible to utilize target audio signals for this task. Audio-based development is a non-invasive, economical, and readily exploitable method that may be used in real-time. This paper proposes a fault detection procedure for computer fans through audio signals. The audio signals are captured from normal and faulty fans. Based on the Fast Fourier transform, these signals are preprocessed and extracted as a Mel-spectrogram. Some deep learning models perform the classification task from input data of features extracted from audio signals. Experimental results show that the ResNet-18 gives the highest accuracy of 100% with different datasets, including noisy and non-noise datasets, and an accuracy of 98.9% when mixing these two datasets. This result can be applied to machine fault detection.

References

J. Hou, X. Lu, Y. Zhong, W. He, D. Zhao, and F. Zhou, ‘A comprehensive review of mechanical fault diagnosis methods based on convolutional neural network’, Feb. 01, 2024, EXTRICA. doi: 10.21595/jve.2023.23391.

M. Yurdakul and S. Tasdemir, ‘Acoustic Signal Analysis with Deep Neural Network for Detecting Fault Diagnosis in Industrial Machines’, arXiv preprint arXiv:2312.01062, 2023.

M. T. Nguyen and J. H. Huang, ‘Fault detection in water pumps based on sound analysis using a deep learning technique’. Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering, vol. 236, no. 2, pp. 298–307, 2022.

N. Sai Dhanush and P. S. Ambika, ‘Bearing Fault Diagnosis Using Machine Learning and Deep Learning Techniques’, in Congress on Intelligent Systems, Springer, 2023, pp. 309–321.

A. Senanayaka, P. Lee, N. Lee, C. Dickerson, A. Netchaev, and S. Mun, ‘Enhancing the accuracy of machinery fault diagnosis through fault source isolation of complex mixture of industrial sound signals’. The International Journal of Advanced Manufacturing Technology, 2024, pp. 1–16.

D. Michelsanti et al., ‘An overview of deep-learning-based audio-visual speech enhancement and separation’. IEEE/ACM Trans Audio Speech Lang Process, 2021, vol. 29, pp. 1368–1396.

H. Purwins, B. Li, T. Virtanen, J. Schlüter, S.-Y. Chang, and T. Sainath, ‘Deep learning for audio signal processing’. IEEE J Sel Top Signal Process, 2019, vol. 13, no. 2, pp. 206–219.

H. Purohit et al., ‘MIMII Dataset: Sound dataset for malfunctioning industrial machine investigation and inspection’, arXiv preprint arXiv:1909.09347, 2019.

S. Kiranyaz et al., ‘Exploring Sound vs Vibration for Robust Fault Detection on Rotating Machinery’, IEEE Sens J, 2024.

C.-J. Chang, C.-C. Chen, and B.-H. Chen, ‘Bearing Fault Diagnosis Based on an Advanced Method: ID-CNN-LSTM’, in 2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI), IEEE, 2023, pp. 63–66.

J. He, P. Wu, Y. Tong, X. Zhang, M. Lei, and J. Gao, ‘Bearing fault diagnosis via improved one-dimensional multi-scale dilated CNN’. Sensors, 2021, vol. 21, no. 21, p. 7319.

M.-T. Nguyen, T.-P. Nguyen, and T.-V. Tran, ‘Automatically Abnormal Detection for Radiator Fans Through Sound Signals Using a Deep Learning Technique’, in International Conference on Material, Machines and Methods for Sustainable Development, Springer, 2022, pp. 271–278.

C. Constantinescu and R. Brad, ‘An Overview on Sound Features in Time and Frequency Domain’. International Journal of Advanced Statistics and IT&C for Economics and Life Sciences, 2023, vol. 13, no. 1, pp. 45–58.

M. T. Nguyen, W. W. Lin, and J. H. Huang, ‘Heart sound classification using deep learning techniques based on log-mel spectrogram’. Circuits Syst Signal Process, 2023, vol. 42, no. 1, pp. 344–360.

A. Safonova, G. Ghazaryan, S. Stiller, M. Main-Knorn, C. Nendel, and M. Ryo, ‘Ten deep learning techniques to address small data problems with remote sensing’. International Journal of Applied Earth Observation and Geoinformation, 2023, vol. 125, p. 103569.

A. Krizhevsky, I. Sutskever, and G. E. Hinton, ‘Imagenet classification with deep convolutional neural networks’. Adv Neural Inf Process Syst, 2012, vol. 25.

K. Simonyan and A. Zisserman, ‘Very deep convolutional networks for large-scale image recognition’, arXiv preprint arXiv:1409.1556, 2014.

C. Szegedy et al., ‘Going deeper with convolutions’, in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1–9.

K. He, X. Zhang, S. Ren, and J. Sun, ‘Deep residual learning for image recognition’, in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.

F. Chollet, ‘Xception: Deep learning with depthwise separable convolutions’, in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 1251–1258.

G. Naidu, T. Zuva, and E. M. Sibanda, ‘A review of evaluation metrics in machine learning algorithms’, in Computer Science On-line Conference, Springer, 2023, pp. 15–25.

R. Mohammed, J. Rawashdeh, and M. Abdullah, ‘Machine learning with oversampling and undersampling techniques: overview study and experimental results’, in 2020 11th international conference on information and communication systems (ICICS), IEEE, 2020, pp. 243–248.

M. Iqbal and A. K. Madan, ‘CNC machine-bearing fault detection based on convolutional neural network using vibration and acoustic signal’. Journal of Vibration Engineering & Technologies, 2022, vol. 10, no. 5, pp. 1613–1621.

M.-T. Nguyen and J.-H. Huang, ‘Snore detection using convolution neural networks and data augmentation’, in International Conference on Advanced Mechanical Engineering, Automation and Sustainable Development, Springer, 2021, pp. 99–104.