DEVELOPMENT OF AUTONOMOUS ROBOTIC SYSTEMS FOR PRECISION MANUFACTURING USING AI-DRIVEN PREDICTIVE MAINTENANCE

Abstract

This study investigates the application of AI-driven predictive maintenance systems for autonomous robotic systems in precision manufacturing. The objective was to develop a hybrid machine learning model combining recurrent neural networks (RNN), convolutional neural networks (CNN), and support vector machines (SVM) to predict robotic system failures and enhance operational efficiency. The results demonstrated that the hybrid model outperformed individual models, achieving the highest accuracy (92.7%), precision (93.2%), recall (94.1%), and F1 score (93.6%). These findings indicate that integrating multiple machine learning algorithms significantly improves the predictive capabilities of maintenance systems in autonomous robotic systems. The research demonstrated real-time data acquisition through IoT sensors plays an essential role by maintaining ongoing monitoring for scheduling maintenance in a timely manner. Compared to classic maintenance techniques the AI-based solution shortened machine availability loss and lower maintenance expenses without compromising system dependability. Research results confirm that hybrid predictive models produce superior operational outcomes as validated by previous studies done in predictive maintenance applications.  This research joins other proof demonstrating the benefits of AI technology applications in industrial manufacturing operations which need smooth production continuity.  Future investigations need to develop predictive maintenance systems for massive manufacturing operations and introduce emerging varieties of AI technology.