Smart Manufacturing: MLOps-Enabled Event-Driven Architecture for Enhanced Control in Steel Production

2025-11-19

AI Summary

To address high energy consumption, significant product quality fluctuations, and severe process inefficiencies in steel induction furnace heating, this paper proposes an intelligent control method integrating digital twin technology with MLOps-driven deep reinforcement learning (DRL). Real-time multi-source industrial data are acquired via edge computing and microservices architecture to construct a high-fidelity digital twin. An event-driven data-closed-loop system enables the DRL agent to autonomously map physical-virtual states and dynamically optimize heating power setpoints. The key innovation lies in embedding the MLOps paradigm into the industrial control loop, enabling continuous model training, deployment, and monitoring. Experimental results demonstrate a 12.3% reduction in energy consumption, a 27.6% decrease in overheating/underheating defect rates, improved energy efficiency and product consistency, and cross-production-line scalability. This work establishes a reusable, scalable paradigm for intelligent automation in process industries.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Machine Learning: Hardware-aware ML
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We explore a Digital Twin-Based Approach for Smart Manufacturing to improve Sustainability, Efficiency, and Cost-Effectiveness for a steel production plant. Our system is based on a micro-service edge-compute platform that ingests real-time sensor data from the process into a digital twin over a converged network infrastructure. We implement agile machine learning-based control loops in the digital twin to optimize induction furnace heating, enhance operational quality, and reduce process waste. Key to our approach is a Deep Reinforcement learning-based agent used in our machine learning operation (MLOps) driven system to autonomously correlate the system state with its digital twin to identify correction actions that aim to optimize power settings for the plant. We present the theoretical basis, architectural details, and practical implications of our approach to reduce manufacturing waste and increase production quality. We design the system for flexibility so that our scalable event-driven architecture can be adapted to various industrial applications. With this research, we propose a pivotal step towards the transformation of traditional processes into intelligent systems, aligning with sustainability goals and emphasizing the role of MLOps in shaping the future of data-driven manufacturing.

Problem

• Optimizing induction furnace heating using digital twin technology
• Reducing process waste through machine learning control loops
• Enhancing operational quality with MLOps-driven autonomous systems

Innovation

• Digital Twin-Based Approach for Smart Manufacturing
• Micro-service edge-compute platform with real-time data
• Deep Reinforcement learning agent in MLOps system