Gradient Optimizer Algorithm with Hybrid Deep Learning Based Failure Detection and Classification in the Industrial Environment

• Published in: Computer modeling in engineering & sciences Vol. 138; no. 2; pp. 1341 - 1364
• Main Authors: Zarouan, Mohamed, Mehedi, Ibrahim M., Latif, Shaikh Abdul, Rana, Md. Masud
• Format: Journal Article
• Language: English
• Published: Henderson Tech Science Press 2024
• Subjects: Algorithms; Classification; Continuous wavelet transform; Deep learning; Failure detection; Fault detection; Fault diagnosis; Industrial applications; Industry 4.0; Machine learning; Modernization; Rotating machinery; Rotating machines; Wavelet transforms
• ISSN: 1526-1506; 1526-1492; 1526-1506
• DOI: 10.32604/cmes.2023.030037

Failure detection is an essential task in industrial systems for preventing costly downtime and ensuring the seamless operation of the system. Current industrial processes are getting smarter with the emergence of Industry 4.0. Specifically, various modernized industrial processes have been equipped with quite a few sensors to collect process-based data to find faults arising or prevailing in processes along with monitoring the status of processes. Fault diagnosis of rotating machines serves a main role in the engineering field and industrial production. Due to the disadvantages of existing fault, diagnosis approaches, which greatly depend on professional experience and human knowledge, intellectual fault diagnosis based on deep learning (DL) has attracted the researcher’s interest. DL reaches the desired fault classification and automatic feature learning. Therefore, this article designs a Gradient Optimizer Algorithm with Hybrid Deep Learning-based Failure Detection and Classification (GOAHDL-FDC) in the industrial environment. The presented GOAHDL-FDC technique initially applies continuous wavelet transform (CWT) for preprocessing the actual vibrational signals of the rotating machinery. Next, the residual network (ResNet18) model was exploited for the extraction of features from the vibration signals which are then fed into the HDL model for automated fault detection. Finally, the GOA-based hyperparameter tuning is performed to adjust the parameter values of the HDL model accurately. The experimental result analysis of the GOAHDL-FDC algorithm takes place using a series of simulations and the experimentation outcomes highlight the better results of the GOAHDL-FDC technique under different aspects.