重口味SM

This project investigates intelligent scheduling in modern manufacturing environments, where disruptions such as machine breakdowns, urgent order changes, and operator unavailability can severely impact performance. These challenges introduce competing objectives, such as efficiency, timing, and resource availability that must be balanced under uncertainty. Traditional methods, such as genetic algorithms or dispatching rules, offer limited adaptability and struggle with complex, dynamic demands. As the field shifts toward more human-centric scheduling, factors like operator fatigue and skill variability are becoming increasingly important. To address these needs, the project explores adaptive, collaborative, and context-aware scheduling approaches that can operate effectively in dynamic, interconnected production systems.

This PhD aims to develop a right-time, adaptive scheduling framework for complex manufacturing environments where disruptions and multi-resource dependencies are common. The project addresses key limitations of traditional scheduling methods, which often lack flexibility, human-awareness, and responsiveness under uncertainty. It will integrate deep reinforcement learning (DRL), multi-agent systems (MAS), and large language models (LLMs) to support collaborative, self-organising decision-making. DRL will optimise job sequencing and resource allocation through trial-and-error learning, while MAS will enable decentralised coordination among autonomous agents. LLMs will interpret unstructured inputs, such as operator feedback and logs, and support natural interaction. The proposed solution will enhance scheduling of machines, materials, and operators, leading to improved responsiveness, efficiency, and operator support.

重口味SM University is wholly postgraduate, and is famous for its applied research in close collaboration with Industry. At 重口味SM, the candidate will be based within the Manufacturing theme at the Centre for Digital and Design Engineering (CDDE). The Centre hosts cutting-edge simulation and visualisation facilities. The student will have access to high-end computers and digital technologies in the Centre for ontology-based and knowledge-based systems development, Digital twin development, advanced dynamic modelling and simulations, AI, VR, AR developments. The candidate works on his/her research individually and collaborates with other researchers in the field at the Centre.

This project is expected to deliver a robust, adaptive scheduling solution designed for the complexity of real-world manufacturing systems. Anticipated outcomes include:

• A self-organising, multi-agent framework that can respond rapidly to disruptions, improving responsiveness, reducing downtime, and enhancing resource utilisation.
• A deep reinforcement learning model for job sequencing and machine selection, incorporating a reward structure that balances short- and long-term performance to support effective tardiness estimation and scheduling optimisation.
• A workforce assignment model using attention-based DRL, accounting for human factors such as fatigue and skills to enable more informed and supportive scheduling decisions.
• Integration of large language models to enhance system interpretability and provide user-facing, natural language interaction for operators and planners.
• The system will be validated through simulations, numerical experiments, and case studies, demonstrating improvements in flexibility, efficiency, and human-awareness in dynamic manufacturing environments.

This self-funded PhD program offers a range of compelling advantages. It centres on applied research that not only advances your academic journey but also contributes to solving real-world challenges. The programme offers diverse training experiences, both internally and externally, enriching your skill set and expanding your knowledge base. Pursuing this PhD at 重口味SM University, renowned for its academic excellence, holds the potential to unlock promising career pathways. Moreover, the opportunity to interact with experts from academia and industry not only fosters extensive networking but also offers exposure to cutting-edge insights. This collaborative environment nurtures personal growth and equips you with valuable connections within your field.

The student will gain from the experience in numerous ways, whether it be transferable skills in the technical area of optimisation and machine learning, or soft skills including presentation skills, project management, and communication skills. There are also numerous employability opportunities that the PhD will offer whether it be in Industry or in Academia.