Detection of Fault from Acoustic Signals in Automobile Engines using Deep Learning Techniques

Authors : Fatih Alperen Erdoğan, Ayhan Küçükmanisa, Zeynep Hilal Kilimci

Pages : 148-154

Doi:10.34088/kojose.1225591

View : 84 | Download : 124

Publication Date : 2023-11-30

Article Type : Research Paper

Abstract :Detecting faults in automobile engines from sound signals is a challenging task in the production phase of automobiles. That is why it attracts engineers and researchers to handle this issue thereby applying various solutions. In this work, we propose a deep learning-based fault detection mechanism in automobile engines from different sound resources. In the dataset collection phase, various vehicle breakdown sounds are gathered from social media environments by constructing our own customized crawler. Moreover, noise addition is applied to increase the amount of data. Subsequently, raw audio files are processed at the feature extraction step employing mel-frequency cepstral coefficients. To detect the vehicle breakdown sounds, 1-D and 2-D convolutional neural networks, long short-term memory networks, artificial neural networks, and support vector machines are modeled. Experiment results show that the usage of a 1-D convolutional neural network is transcendent with 99% accuracy compared to the other techniques, especially, state-of-the-art studies are considered.
Keywords : Fault detection, automobile engines, deep learning, sound processing, convolutional neural networks