SCALABLE ANALYTICS PLATFORM FOR MACHINE LEARNING IN SMART PRODUCTION SYSTEM

Abstract

The rapid advancement of Industry 4.0 has led to the integration of smart production systems with advanced data analytics and machine learning techniques. Modern manufacturing environments generate massive volumes of data from sensors, machines, and production processes, making it essential to develop scalable analytics platforms for efficient data processing and decision-making. This project proposes a scalable analytics platform for machine learning in smart production systems to enhance operational efficiency, predictive maintenance, and real-time monitoring. The proposed system integrates data collection from industrial IoT devices, followed by preprocessing and storage in distributed systems such as Hadoop or cloud-based platforms. Machine learning algorithms are applied to analyze production data and identify patterns related to equipment performance, fault detection, and process optimization. The platform supports scalable data processing using technologies such as Apache Spark and distributed computing frameworks, enabling real-time and batch analytics. The system provides visualization dashboards to monitor production metrics and predictive insights, helping industries make informed decisions. Performance is evaluated based on scalability, processing speed, and prediction accuracy. Experimental results demonstrate that the platform efficiently handles large-scale data and improves production efficiency through intelligent analytics. This approach enables industries to adopt smart manufacturing practices, reduce downtime, and enhance productivity, making it a valuable solution for modern industrial environments.