,
Assistant Professor, Kalinga University , Naya Raipur, Chhattisgarh , India
Assistant Professor, Kalinga University , Naya Raipur, Chhattisgarh , India
Predictive maintenance has become an important factor in improving the reliability and efficiency of industrial robots in the evolving environment of smart manufacturing. The proposed paper is a predictive maintenance framework based on AI to be implemented to multi-sensor industrial robots that will be used in a smart manufacturing setting. The point is to be able to develop a model that will combine multiple sensor data (e.g., temperature, vibration, force, and acoustic signals) with sophisticated machine learning models to anticipate possible problems in robotic systems. Early warning of mechanical failures can be achieved through sensor fusion and AI methods, enabling the framework to identify problems in the machine at an early stage and implement corrective measures in time to reduce downtime. The deep learning model was a hybrid between a convolutional neural network (CNNs) and a long short-term memory (LSTM) network, where time-series sensor data was processed and equipment malfunctions predicted. The model was trained and tested on a real-world dataset (smart factory), which is sensor readings of industrial robots. The findings indicate that the method has got an accuracy rate of 92.5% in failure prediction and is better than the traditional methods in accuracy and recall. Moreover, the system provides real-time health information for the robot, greatly reducing the cost and time required for unscheduled maintenance. The paper will end with a discussion of the implications of using AI to integrate predictive maintenance in smart manufacturing and define future directions of the model in the context of various industrial configurations in order to increase its scale and applicability.
This is an open access article distributed under the Creative Commons Attribution Non-Commercial License (CC BY-NC) License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
0
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.