AI DRIVEN PREDICTIVE MAINTENANCE FRAMEWORK FOR MULTI-SENSOR INDUSTRIAL ROBOTS IN SMART MANUFACTURING

By

Priya Vij ,

Priya Vij

Assistant Professor, Kalinga University , Naya Raipur, Chhattisgarh , India

View authors publications

Search this author on:

PubMed | Google Scholar

Ashu Nayak

Ashu Nayak

Assistant Professor, Kalinga University , Naya Raipur, Chhattisgarh , India

View authors publications

Search this author on:

PubMed | Google Scholar

Abstract

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.

References

Citation

Copyright

Article metrics