Light-Weighted Deep Learning Model to Detect Fault in IoT-Based Industrial Equipment. (29th June 2022)

• Record Type: Journal Article
• Authors: Soni, Mukesh; Khan, Ihtiram Raza; Basir, Sameer; Chadha, Raman; Alguno, Arnold C.; Bhowmik, Tapas
• Other Names: Kumar Vijay Academic Editor.
• Is Part Of: Computational intelligence and neuroscience. Volume 2022(2022)
• Publication Date: 2022-06-29
• Subjects: Neurosciences -- Data processing -- Periodicals; Computational intelligence -- Periodicals; Computational neuroscience -- Periodicals; 612.80285
• DOI: 10.1155/2022/2455259
• Languages: English
• ISSNs: 1687-5265

Abstract

Abstract : Industry 4.0, with the widespread use of IoT, is a significant opportunity to improve the reliability of industrial equipment through problem detection. It is difficult to utilize a unified model to depict the working condition of devices in real-world industrial scenarios because of the complex and dynamic relationship between devices. The scope of this research is that it can detect equipment defects and deploys them in a natural production environment. The proposed research is describing an online detection method for system failures based on long short-term memory neural networks. In recent years, deep learning technology has taken over as the primary method for detecting faults. A neural network with a long short-term memory is used to develop an online defect detection model. Feature extraction from sensor data is done using the curve alignment method. Based on long-term memory neural networks, the fault detection model is built (LSTM). In the end, sliding window technology is used to identify and fix the problem: the model's online detection and update. The method's efficacy is demonstrated by experiments based on real data from power plant sensors.