Advanced manufacturing, is a group of manufacturing activities that use advanced technologies, cutting-edge materials, automation, and computation to manufacture new products and to improve manufacturing methods of existing products. Advanced manufacturing provides a capability to produce customized and complex products, while reducing both production time and cost. To ensure the quality and reliability of products, most advanced manufacturing systems are equipped with hundreds of sensors that are used to collect quality-related data such as the part dimensions, strength, etc. This results in a tremendous amount of data (namely, Big Data) that provide unique opportunities for improving advanced manufacturing systems. This EArly-Grant for Exploratory Research (EAGER) award supports fundamental research that enhances existing knowledge for the development of new analytical methods for Big Data that help improve the quality of manufactured products. The results of this research will have a significant impact on a variety of high profile application domains including automotive, aerospace, defense, biomedical, and medical by, preventing catastrophic failures, reducing scrap and rework costs, and improving product quality, all of which increase customer satisfaction and aid in economic growth.
The use of statistical methods for improving manufacturing processes has been extensively studied and various techniques have been developed in this area. However, most existing methods fail to effectively analyze the big manufacturing process data due to their complex structure, high-volume, and high sampling rates. To address these issues, this research will propose and validate a new framework that enables modeling and analysis of Big Data in real-time by exploiting and integrating statistical learning, optimization, advanced computing, and manufacturing principles. The research team will develop a set of nonparametric methods for real-time sensing and measurement of Big Data, effective data compression, and process monitoring, change detection, and diagnosis.
