IntelliMaint: AI-Driven Predictive Maintenance and Performance Optimization for Mechanical Systems
Authors:-V. Suvarna, Thalisetty Anusri, Kolli Satya Surya Teja, J Jyothisai, Gayatri Chakrani Palla, Malladi Venkatesh
Abstract-To enhance the accuracy of predictions and enable real-time monitoring of mechanical parts’ operational status, a deep learning model was initially developed using a convolutional neural network (CNN) structure to extract features from the mechanical components. Subsequently, another deep learning model was designed to process these extracted features through a fully connected layer for data fusion and classification, facilitating the prediction of lifespan and monitoring of health status. This trained model was then integrated with a monitoring system, creating a comprehensive solution for predicting the lifespan and tracking the health of mechanical parts. Finally, the system underwent continuous optimization and updates to improve both its prediction accuracy and real-time responsiveness, while also adapting to various operating conditions and environmental factors. The results demonstrated that the deep learning model achieved a mean absolute error (MAE) of 2.1, a root mean square error (RMSE) of 2.5, and a mean absolute percentage error (MAPE) of 10%, reflecting strong performance. This approach holds significant potential for practical application in the engineering field.
