Machine learning and IoT based Predictive Maintenance for the industrial motors for sustained Automation in the power plant Industry

Abstract

The purpose of this research is to develop novel framework based on advanced tools, including machine learning and the Internet of Things and self-attention mechanisms. Traditional and advanced tools were used in the data-driven predictive maintenance mechanism and served as a basis for comparing the tools. At the power plant, thirty-four datasets were collected to monitor three industrial motors continuously. The tools’ predictive ability was analysed using conceptualized features from the sensory data , and the management strategy remained dependent on the network. The study results show that each tool performs at high-performing levels because each exceeded 75% of the performance metric. The study results indicated that the proposed framework gave a consistent high-performance metric, 86.4%, in all the ten experimental scenarios used . The rate determination was attributed to the choice of the long short-term memory architecture, the self-attention mechanisms, and the optimization techniques. The choice of using mean squared logarithmic error also contributed to the outcomes because these tools yield high-performance scores. In addition to these, the test of the forecasting models chosen also influenced this performance. This study’s findings show that this framework is reliable in predicting pending failure equipment and developing relevant management strategies in industrial motors failure. It was found that the use of advanced tools in the development of the framework was a crucial aspect. Scaled tools and optimization techniques are of crucial importance in predictive management in equipment failure as they assist the frameworks in identifying ideal features from the sensory data. It should also be noted that the choice of a loss-function model is also important in the predictability of framework..