MANUFACTURING MANAGEMENT SYSTEM: CORE 2: (PRODUCT EXECUTION AND AUDIT MANAGEMENT) WITH PREDICTIVE ANALYTICS USING TENSORFLOW

Abstract

As the manufacturing industry continues to evolve, companies face increased pressure to ensure product quality, maintain operational transparency, and minimize production downtime. Traditional systems often operate reactively, resulting in inefficiencies and delayed responses. This study introduces CORE 2, a Manufacturing Management System that enhances product execution and audit management through predictive analytics powered by TensorFlow. CORE 2 is designed to deliver real-time data visibility, proactive monitoring, and audit readiness, enabling improved decision-making and quality assurance. By utilizing AI-driven predictions, the system identifies potential issues before they escalate, optimizing workflow efficiency and regulatory compliance. CORE 2 was developed using the MERN stack: MongoDB, Express.js, React.js, and Node.js, offering a responsive and scalable architecture. Predictive models were built using TensorFlow to analyze patterns in production metrics, audit logs, and performance data. These models detect risks such as production delays, quality defects, and audit inconsistencies. The Agile Scrum methodology guided the development, promoting iterative improvements through continuous feedback. The system includes modular components such as Production Tracking, Quality Control, Customer Order Information, Audit Planning, and Corrective Action Management, each deployed as a microservice. Real-time dashboards were implemented to provide intuitive insights and visualization. The integration of TensorFlow-based predictive analytics significantly improved manufacturing performance. CORE 2 enabled a proactive approach to risk detection, helping to prevent disruptions before they occurred. In audit functions, the system enhanced traceability and readiness by automating documentation and scheduling. Results also showed improved alignment with compliance requirements and more efficient corrective action management. For long-term success, the models require standardized data input and continuous training, supported by effective data governance practices. CORE 2 demonstrates that predictive analytics can shift manufacturing systems from reactive to proactive management. By leveraging AI to anticipate operational risks and audit concerns, the system enhances both quality control and compliance readiness. Future enhancements may include real-time IoT integration and expansion into other production domains. The study affirms that integrating predictive intelligence into manufacturing systems supports the transition to smarter, data-driven operations and fosters sustainable performance improvements.