Coordinated Supervisory Control System for Smart Manufacturing

University Of Virginia Main Campus, Charlottesville VA

Investigators

Abstract

This project will support fundamental research in smart manufacturing processes and systems, promoting the progress of science as well as national prosperity. Recent advancements in sensors, information, communication, and robotics technologies have driven better ways of doing manufacturing. Modern manufacturing systems are equipped with multiple sensors, communication devices, and material handling robots that operate alongside other autonomous machines and human coworkers/supervisors. However, the full potential of these technological advances in improving production efficiency and quality has not been realized. This is because manufacturing systems are inherently stochastic and nonlinear, and there is a lack of theoretical and technical understanding of real-time model-based prediction of manufacturing performance and production control. This research will establish novel data-enabled models for predicting manufacturing system performance under uncertainty and adaptive, robust, and scalable control and coordination algorithms for production control. The new knowledge will provide manufacturers with a rigorous quantitative tool for real-time monitoring and control of the complex manufacturing systems. The results of this research will contribute to both the theory and the practice of smart manufacturing and will be very useful to the entire U.S. manufacturing sector for maximizing productivity and economic benefit. This research incorporates goals with industrial needs, helps broaden the participation of underrepresented groups in research, and enhances engineering education. This research will fill the knowledge gap via the integrated study of production dynamics and multiple robots material dispatching decisions to address their interactions in real-time, which is significant for manufacturing systems efficiency. The research approach will be a novel combination of dynamic systems modeling of material flow through production processes along with dynamic multirobot task assignment under uncertainty for optimizing production performance metrics. The research team aims to: a) establish a data-enabled mathematical framework to describe real-time manufacturing systems with dynamic production and multirobot operations to enhance the understanding of dynamic manufacturing processes and systems; and b) establish the scientific and technological foundation in adaptive control and decentralized decision making for multirobot system working with machines/humans. The Coordinated Supervisory Control System is based on the holistic view of physical system analysis, advanced data-driven modeling, and adaptive control. The methodology is transformable to other dynamic systems with distributed sensors and data, such as transportation, supply chain, and health care management. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.