Integrating Deep Learning with MES-ERP Systems for Real-Time Production Optimization and Resource Allocation in Smart Manufacturing

Authors: Sudheer Panyaram

DOI: https://doi.org/10.37082/IJIRMPS.v10.i3.232554

Short DOI: https://doi.org/

Country: USA

Full-text Research PDF File:   View   |   Download

Abstract: The integration of Deep Learning (DL) into Manufacturing Execution Systems (MES) and Enterprise Resource Planning (ERP) systems would greatly affect the development of smart manufacturing, therefore giving transformational powers for efficient resource allocation and real-time production optimisation. Data-driven insights, predictive maintenance, dynamic scheduling, and proactive decision-making help DL models including Recurrent Neural Networks (RNNs), Convolutional Neural Networks (CNNs), and Reinforcement Learning (RL) agents learn from enormous volumes of historical and real-time sensor data, uncover hidden patterns, and adapt to manufacturing environments unlike conventional rule-based approaches. By forecasting equipment failures and material shortages, DL improves MES response; at the same time, it guides ERP decisions including procurement, labour allocation, and energy control when integrated with MES, which controls shop-floor control, and ERP, which supervises enterprise-level planning. These models can close the loop between data collecting, analytics, and execution. Autoencoders and transformers also assist by mimicking challenging events and spotting system behaviour issues. With this combined DL-MES-ERP architecture real-time feedback and self-optimization is achievable using edge computing and cloud platforms for scalable, low-latency inference. The results show observable benefits in general equipment effectiveness (OEE), lower unplanned downtime, better inventory control, and more production agility using industrial simulations. Emphasising important DL techniques especially suited for smart factory use-cases, the paper investigates the performance of modular integration frameworks. Among the topics addressed are data heterogeneity, model generalisation, cybersecurity concerns, and human-machine collaboration. Ultimately, our work underlines the significance of DL in producing autonomous, adaptable, robust cyber-physical production systems resistant against increasing complexity and demand unpredictability. The integration of Deep Learning (DL) techniques with Manufacturing Execution Systems (MES) and Enterprise Resource Planning (ERP) systems is investigated in order to enhance real-time production optimisation and resource allocation in smart manufacturing environments. Data-driven intelligence obtained from networked systems allows manufacturers to achieve predictive capabilities, adaptive planning, and autonomous control. By offering an architecture for integration, evaluations of primary deep learning models relevant to manufacturing data, and results showing better use of resources, lower downtime, and improved production efficiency, the research proves the architecture using case studies and simulations.

Keywords:

Paper Id: 232554

Published On: 2022-05-06

Published In: Volume 10, Issue 3, May-June 2022

Share this