Jin Awarded NSF CAREER Award for High Precision Micromanufacturing

Xiaoning “Sarah” Jin

Today’s advanced manufacturing technology demands greater efficiency, reliability, and precision. That’s where Mechanical and Industrial Engineering Assistant Professor Xiaoning “Sarah” Jin believes her research can play a critical role. A recent recipient of a five-year, $500K National Science Foundation (NSF) CAREER Award for “Unifying Sensing, Machine Perception and Control for High-Precision Micromanufacturing,” Jin’s goal is to develop an artificial intelligence and machine learning-assisted technology framework for high precision, advanced manufacturing processes.

With a focus on emerging products—biosensors, micro/nano-scale electronics, batteries and flexible electronics, for example—Jin’s solution is to leverage data to understand process dynamic behavior and performance in real time. This information, in turn, will improve the precision and effectiveness of process controls to meet product quality targets and make products faster, with higher throughput and minimal defects.

“Our goal is to use the abundant sensor data from complex manufacturing equipment and processes to make reasonable inferences and reveal what’s going on,” she explains. “We are trying to reveal the hidden behavior existing in high throughput, high speed processes of micro-scale device fabrication to maintain high reliability and mitigate defect rates. If there are tiny defects or errors at the beginning of a process, and you don’t have enough visibility into the process to make a timely correction, you will see a higher defect rate, which can generate significant waste in materials and energy. If we can use all available information to infer what’s happening, we can then provide proactive, adaptive action.”

The power of Big Data

Jin’s innovative approach goes beyond traditional model-based control and design using the power of sensing technologies and advanced data analytics to enable real-time decision-making for meaningful action. “Using a more data-driven approach with engineering knowledge provides us an avenue of mass production for more precise, more reliable products with more complexity and less waste, and a significant improvement in efficiency,” she says.

Under the NSF award, Jin will experimentally demonstrate and validate the framework and methods on two micromanufacturing processes—ion mill etching and roll-to-roll printing—to show the real-world impact of her research. “I want to develop a general methodology and algorithms to apply to a broader range of manufacturing processes,” she says.

Jin’s research is also coupled with STEM education and outreach activities aimed at building interest in next-generation “smart manufacturing” technologies among students at all levels and broadening the diversity of the STEM workforce. “My goal is to grow the program,” she says. “I want to help the current workforce adapt to new technology and support the education and training of future manufacturing scientists and engineers to better prepare them.”

Abstract Source: NSF


Related Faculty: Xiaoning “Sarah” Jin

Related Departments:Mechanical & Industrial Engineering