Information systems research

11 Model-Based Controlling Approaches for Manufacturing Processes

Reinforcement learning-based adaptive control strategies for sustainable production systems

Abstract. The need to achieve sustainable production has become an urgent necessity in the conditions of stricter environmental requirements and the rise in the cost of energy worldwide. The classical proportionalintegralderivative controllers and linear Model Predictive Controllers are conventional model-based control strategies that by nature rely on precise process models and fixed optimization horizons and hence are not well suited to the dynamic, non-linear, and complex nature of the modern production environment. The current paper suggests a new adaptive control system based on Reinforcement Learning (RL), where the overall production system is optimized and controlled to achieve Sustainable Production Systems, with the multi-objective rewarding function, which aims to minimize the Overall Equipment Effectiveness (OEE), defect rate, specific energy consumption, and carbon dioxide emissions, and a physics-informed Digital Twin safety filter that stops unsafe policy execution in training and deployment. The proposed framework is evaluated on a multi-machine flexible manufacturing cell benchmark, which includes CNC milling, turning, and robotic assembly, and yields an OEE of 93.6, a defect rate of 0.9, a decrease in specific energy consumption of 27.8, and a decrease in CO 2 emissions of 23.4 compared to PID baseline controllers. Experiments with ablation prove all the above-mentioned in the necessity of each of the architectural constituents, and the Pareto frontier analysis proves that the proposed SAC agent is the best in the OEE-versus-energy trade-off space compared to all of the competing methods.

Stability- and Safety-Guaranteed Artificial Intelligence: Enhancing Renewable-Dominated Power System Operation and Control

As renewable energy becomes the dominant generation resource in modern power systems, system stability and safety pose critical challenges due to increased uncertainty, reduced inertia, and escalating system complexity. Artificial intelligence (AI) provides unprecedented capabilities for real-time control, predictive optimization, and adaptive decision making, yet its adoption in safety-critical power system applications is hampered by concerns over robustness, interpretability, and the absence of formal guarantees. This article outlines how stability- and safety-guaranteed AI approaches can bridge this gap to enable reliable integration of renewables. In this article, we review emerging methods that embed physics, control theory, and optimization constraints in AI models for power systems, discuss advances in certifiable robustness and Lyapunov-based learning, and chart the path for deployment in renewable-dominated grids. The article concludes with policy, regulatory, and research recommendations for ensuring that AI not only accelerates the clean energy transition but also preserves resilience and trust in critical infrastructure.

Multi-Agent System-driven Digital Twins for predictive maintenance: architectures, technologies and open research challenges

This systematic review explores the intersection between Multi-Agent Systems and Digital Twins, with a particular focus on predictive maintenance applications in resource-constrained contexts and reveals that, despite significant progress, no existing system offers an integrated embedded-distributed hierarchical solution that simultaneously meets the requirements of Industry 5.0.

Artificial Intelligence as Effectiveness Enabler of Dynamic Reconfiguration of Systems Architecture in Industry 5.0

Industrial operations increasingly face high-stakes decisions that involve people, data streams, simulations, and control systems. Urgent sessions often require external expertise, retrieval of documents and live telemetry, running what-if simulations, and verifying safety constraints. These scenarios highlight the need for secure interoperability, explainable decision support, and human-in-the-loop control. This paper presents a proposal of a technology-agnostic reference architecture that builds on Industry 4.0 frameworks by incorporating the human-centric, resilient, and sustainable principles of Industry 5.0. Its intelligent layer enables the new approach to human involvement in the process, facilitating meaningful human–machine collaboration. The proposed research provides a practical and conceptual framework for systems engineers, industrial software architects, and operations managers seeking to transition legacy operational plants into human-aligned ecosystems. Its feasibility is evaluated through a simulation-based underground mining testbed, where heterogeneous data sources and communication protocols are integrated into a common operational environment. The proof of concept shows how telemetry, data storage, machine learning models, and operator feedback can be combined to support auditable, explainable, and human-contestable industrial decisions, demonstrating the classification accuracy, remaining useful life forecasting capabilities, and enhanced recommendation precision enabled by iterative operator feedback loops.

An AI-Driven Integrated Framework for Construction, Operation, And Grid Optimization of Battery Energy Storage Systems

The rapid expansion of renewable energy systems has intensified the need for advanced Battery Energy Storage Systems (BESS) capable of supporting grid stability, operational efficiency, and resilient infrastructure development. This paper proposes an AI-driven integrated framework for the construction, operation, and grid optimization of BESS, addressing limitations in existing fragmented approaches that treat design, control, and grid interaction as isolated processes. The proposed next-generation architecture introduces a multi-layered system that unifies construction design, digital monitoring, artificial intelligence optimization, and grid integration into a cohesive framework. The construction layer emphasizes modular design principles and advanced thermal safety systems to enhance scalability, reliability, and lifecycle performance. The digital layer incorporates real-time monitoring and digital twin models, enabling continuous system representation, predictive simulation, and performance tracking. The AI layer leverages machine learning algorithms for predictive dispatch, fault detection, and adaptive control, ensuring efficient energy utilization and proactive system maintenance. The grid layer focuses on frequency regulation and voltage stabilization, enabling seamless integration with renewable energy sources and enhancing overall grid resilience. A key contribution of this study is the development of a holistic BESS architecture that integrates AI into construction-informed design, allowing operational insights to influence structural and system configurations. This bidirectional interaction between design and operation improves system optimization and reduces long-term operational risks. Furthermore, the framework establishes a foundation for smart grid resilience by enabling real-time decision-making, automated control, and adaptive response to grid disturbances. The proposed model advances the field by providing a unified approach to BESS deployment, offering practical implications for energy providers, infrastructure developers, and policymakers seeking to enhance sustainability and reliability in modern power systems.