The Engineer's Impact - Min Xia

Your inside look at faculty’s research and its effect on society

In this new Q&A series, we’ll feature Western Engineering faculty members to gain a succinct overview of their research, understand its impact on society, and discover intriguing little-known facts.

Meet Mechanical and Materials Engineering Associate Professor Min Xia.

mxia-115x150Can you describe your research?

My research focuses on intelligent sensing, monitoring, and optimization of complex systems such as mechatronics systems, advanced manufacturing processes, and clean energy production systems. By using different sensing technologies, a variety of data can be obtained from the monitored complex systems. With advanced signal processing and machine learning methodologies, the information behind the data can be extracted and used to analyze the system status as well as to optimize the system output such as optimal maintenance strategies for complex machines, zero-defect and reduced energy consumption for manufacturing processes, and precise predictions of clean energy production. My research also integrates the physics of engineering systems into data-driven technologies to achieve more reliable and trustworthy solutions.

How does your research impact society in everyday life?

In the era of Industry 4.0 and the upcoming 5.0, achieving smart decision-making in the processes of many complex systems becomes crucial to enhance system efficiency and safety. Improved systems, such as manufacturing processes and clean energy production, could not only provide more affordable products but also contribute to a more sustainable society by reducing material waste, decreasing energy consumption, and lowering overall carbon emissions.

What’s an interesting, little-known fact related to your research?

Most data-driven technologies based on machine learning focus solely on finding the relationship between input and output data. Despite their good performance in applications like face recognition and natural language processing, the black-box nature of typical machine learning technologies raises concerns when dealing with critical systems, such as large industrial machines and infrastructures. It is urgent to implement the underlying physics or human expertise into data-driven models.