article · Systems
Modern manufacturing facilities face challenges when attempting to model complex operations and achieve fully autonomous decision-making using digital twins. To address this, a framework has been developed for a full-duplex digital twin system tailored for autonomous process control, demonstrated through a plastic injection moulding use case. The system integrates supervised learning and deep reinforcement learning models. This dual approach facilitates the automated updating of the virtual model using operational data, whilst also driving intelligent decisions to optimise key operational metrics. The resulting architecture allows factories to enhance product quality and decrease production expenses. Overall, the findings show that this digital twin configuration achieves high-quality manufacturing outputs with minimal human intervention, demonstrating how advanced digital twins can improve the productivity, efficiency, and industrial adoption of automated manufacturing processes.
As factories seek higher efficiency and customisation, automating complex manufacturing decisions becomes essential. This work demonstrates how combining artificial intelligence with digital twins can manage physical machinery autonomously. By keeping digital representations constantly updated and optimising operations in real time, manufacturers can maintain consistent product quality and curb operational expenses without relying heavily on manual supervision.
This technology targets manufacturing operators seeking autonomous process control, specifically demonstrated in plastic injection moulding. It enables automated parameter adjustments to reduce operational costs and raise output quality with minimal manual oversight. Having been evaluated on a practical use case, the framework appears to be an applied and tested system, ready for further testing within factory production lines that require intelligent, real-time control.
AI-generated from the published abstract. Always read the original work before citing.
In the context of Industry 4.0 and smart manufacturing, production factories are increasingly focusing on process optimization, high product customization, quality improvement, cost reduction, and energy saving by implementing a new type of digital solutions that are mainly driven by Internet of Things (IoT), artificial intelligence, big data, and cloud computing. By the adoption of the cyber–physical systems (CPSs) concept, today’s factories are gaining in synergy between the physical and the cyber worlds. As a fast-spreading concept, a digital twin is considered today as a robust solution for decision-making support and optimization. Alongside these benefits, sectors are still working to adopt this technology because of the complexity of modeling manufacturing operations as digital twins. In addition, attempting to use a digital twin for fully automatic decision-making adds yet another layer of complexity. This paper presents our framework for the implementation of a full-duplex (data and decisions) specific-purpose digital twin system for autonomous process control, with plastic injection molding as a practical use-case. Our approach is based on a combination of supervised learning and deep reinforcement learning models that allows for an automated updating of the virtual representation of the system, in addition to an intelligent decision-making process for operational metrics optimization. The suggested method allows for improvements in the product quality while lowering costs. The outcomes demonstrate how the suggested structure can produce high-quality output with the least amount of human involvement. This study shows how the digital twin technology can improve the productivity and effectiveness of production processes and advances the use of the technology in the industrial sector.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/systems12020038
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
