Deep Learning with LPC and Wavelet Algorithms for Driving Fault Diagnosis

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 18; p. 7072
• Main Authors: Gong, Cihun-Siyong Alex, Su, Chih-Hui Simon, Liu, Yuan-En, Guu, De-Yu, Chen, Yu-Hua
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.09.2022; MDPI
• Subjects: Acoustics; Algorithms; Artificial intelligence; Automobiles; Big Data; convolutional neural network (CNN); Data analysis; Data mining; Datasets; Deep learning; deep neural network (DNN); Failure; Fault diagnosis; Internet of Things; linear predictive coefficient (LPC); Machine learning; machine learning (ML); Neural networks; Repair & maintenance; Sensors; vehicle early fault diagnosis; Vehicles; Voice recognition; wavelet transform (WT); Wavelet transforms; Taiwan
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22187072

Vehicle fault detection and diagnosis (VFDD) along with predictive maintenance (PdM) are indispensable for early diagnosis in order to prevent severe accidents due to mechanical malfunction in urban environments. This paper proposes an early voiceprint driving fault identification system using machine learning algorithms for classification. Previous studies have examined driving fault identification, but less attention has focused on using voiceprint features to locate corresponding faults. This research uses 43 different common vehicle mechanical malfunction condition voiceprint signals to construct the dataset. These datasets were filtered by linear predictive coefficient (LPC) and wavelet transform(WT). After the original voiceprint fault sounds were filtered and obtained the main fault characteristics, the deep neural network (DNN), convolutional neural network (CNN), and long short-term memory (LSTM) architectures are used for identification. The experimental results show that the accuracy of the CNN algorithm is the best for the LPC dataset. In addition, for the wavelet dataset, DNN has the best performance in terms of identification performance and training time. After cross-comparison of experimental results, the wavelet algorithm combined with DNN can improve the identification accuracy by up to 16.57% compared with other deep learning algorithms and reduce the model training time by up to 21.5% compared with other algorithms. Realizing the cross-comparison of recognition results through various machine learning methods, it is possible for the vehicle to proactively remind the driver of the real-time potential hazard of vehicle machinery failure.