PREDICTIVE PRODUCTION PLANNING USING IOTENABLED ERP DATA AND MACHINE LEARNING

Abstract

The emergence of Industry 4.0 has transformed traditional manufacturing by integrating intelligent technologies such as the Internet of Things (IoT), Enterprise Resource Planning (ERP), Artificial Intelligence (AI), and Machine Learning (ML) into production environments. Manufacturing organizations are increasingly adopting IoT-enabled ERP systems to collect real-time operational data from machines, production lines, inventories, supply chains, and customer orders. Despite the availability of large volumes of industrial data, many production planning systems continue to rely on historical reports and manual scheduling techniques that fail to respond effectively to dynamic manufacturing conditions. Predictive production planning addresses this challenge by utilizing machine learning algorithms to forecast production demand, machine utilization, inventory requirements, processing times, and maintenance needs based on continuously generated ERP and IoT data. This research proposes a predictive production planning framework that integrates IoT-enabled ERP systems with advanced machine learning techniques to improve manufacturing efficiency and operational decision-making. The proposed framework collects real-time production information through IoT sensors deployed across manufacturing equipment while simultaneously extracting transactional data from ERP modules including inventory management, procurement, production scheduling, quality control, and sales forecasting. The integrated dataset undergoes preprocessing, feature engineering, normalization, and anomaly detection before being supplied to machine learning models such as Random Forest, Support Vector Machine, Gradient Boosting, XGBoost, Artificial Neural Networks, and Long Short-Term Memory (LSTM) networks for predictive analytics. The proposed framework generates accurate forecasts for production demand, machine availability, material consumption, workforce allocation, and production completion times. Intelligent optimization algorithms further utilize these predictions to develop optimal production schedules that minimize production delays, machine idle time, inventory costs, and resource wastage while maximizing throughput, equipment utilization, and customer satisfaction. Continuous feedback from IoT devices enables adaptive learning, allowing machine learning models to update production plans dynamically in response to changing shop-floor conditions. Experimental analysis demonstrates that the proposed predictive production planning framework significantly improves forecasting accuracy, production efficiency, scheduling performance, and operational flexibility compared with conventional ERP-based planning systems. The integration of IoTgenerated real-time data and machine learning enhances decision-making capabilities, supports proactive manufacturing management, and contributes to the realization of smart factory objectives. The proposed framework provides a scalable and intelligent solution suitable for discrete manufacturing, process industries, automotive production, aerospace manufacturing, electronics assembly, pharmaceutical manufacturing, and industrial automation environments