Vision

With the arrival of the fourth Industrial Revolution marked by emerging technological breakthroughs such as High-Speed Wireless Communication, Cyber-physical Systems, Big Data, Artificial Intelligence (AI), Virtual Reality (VR), and Additive Manufacturing (AM), our society and the way we work and live will be reshaped radically. Along with this revolution, engineering designers will need to cope with new challenges in product and systems design. Massive amounts of data are generated by humans and machines from which valuable insights can be extracted to support design and manufacturing processes (data-driven design). Smart products tend to work collectively rather than in isolation (connectivity). Design methods for small-scale projects may not apply to the design of complex products or systems (complexity). Therefore, innovative theory, methods, and tools adapted to the design and manufacturing of next-generation products and systems, especially in aviation industry, are needed. The vision for the DSD Lab is to develop data-driven and simulation-based approaches to support innovative design and manufacturing under connectivity and complexity by integrating methods rooted in design science, data science, and systems engineering.


Main areas

1. Data-driven Design and Manufacturing

Today massive amounts of human and machine-generated data have become accessible from which valuable insights for product design and manufacturing can be extracted. There is a need to systematically collect and utilize various forms of data to support the design and manufacturing activities for aviation products and systems. The objective of this topic area is to develop data-driven approaches to support innovative design and manufacturing, including what data should be collected, how to collect them and utilize them, and how to validate these approaches. Key techniques include natural language processing, ontology engineering, domain knowledge-based machine learning and multi-objective optimization. Potential applications of this research include user-centered design for electric vehicles, data-driven high-efficient supply chain and inventory systems for manufacturing, etc.


2. Design of Intelligent Interconnected Product Systems

With the advances in high-speed wireless communication, AI and Cloud Computing, intelligent interconnected product systems (e.g., swarm of robots), are gradually becoming a part of modern life. These systems are promising in undertaking complex or dangerous missions such as delivering packages to far-off locations, checking the structural integrity of skyscrapers, etc. Compared to products working in isolation, interconnected product systems are more powerful and robust due to their distributed and simultaneous working abilities. However, interconnected product systems are often self-organized and need to adapt to highly dynamic and uncertain contexts. The performance of such systems is often impaired by battery or fuel constraints while working remotely. The objective of this research topic is to develop a simulation-based approach to configure product attributes in an interconnected product system optimally such that the system can complete predefined missions while consuming minimal resources (e.g., quantity of members in the system, energy consumption). Key techniques include dynamics simulation, agent-based learning, reinforcement learning, etc. Potential applications of this research include the design and simulation of drone networks used in logistics system, industrial robot system, etc.


3. Collaborative Decision Making in Design of Complex Systems

A successful product design usually requires the collaborative efforts of multiple participants from various backgrounds, especially in the design of complex products or systems. Thanks to the technological advances in virtual reality and high-speed Internet, teamwork in engineering design has been extended into cyber space where designers can cooperate remotely as virtual and distributed teams and individual decision making also evolves into collaborative decision making. It is important to investigate how to make engineering decisions collaboratively in the design of complex products and systems, as designers under such contexts may behave and communicate differently than in small in-person teams. The objective of this research topic is to develop a simulation-based approach to model and simulate collaborative decision making in the design of complex products and systems. Key techniques include human behavioral experiments, crowdsourcing, network analysis and robust design optimization. Potential applications of this research include optimal resource allocation and decision making in the design of large-scale engineering projects (e.g., large aircrafts, urban infrastructures).



Current Projects