Research

Research Projects

Cognitive Computing in Cyber Manufacturing

Recent advancements in low-cost sensing and communication technology provide unprecedented opportunities to synchronize manufacturing facility to the cyber computational space. The new paradigm of cyber manufacturing system (CMS) is a convergence of interconnectivity and intelligence to form adaptable and resilient processes in the factory of future. In this project, we we rethink not only how we accelerate machine learning algorithms in hardware but also redesign algorithms using strategies that more closely model the human brain to achieve real-time performance with high efficiency and robustness in CMS.

Cognitive Computing in Cyber Manufacturing

 

Collective Intelligence in Advanced Manufacturing

The increasing digitalization in advanced manufacturing has accelerated the information flow. Technologies such as Cyber-Physical Systems (CPS), Industrial Internet of Things (IIoT), and Artificial Intelligence (AI) are bringing an extensive added value into Industry 4.0 value chains. AI and Machine learning, especially supervised learning, has been shown successful and valuable for many applications in cyber manufacturing. Supervised machine learning requires labeled data for training a machine learner.  Given a limited budget, complex dependencies, sparsity between informative instances, deciding what to annotate can be challenging. In this research, we target at developing a new query strategy to select data for annotation.

Collective Intelligence in Advanced Manufacturing

 

Multi-scale and In-situ Quality Assurance in Additive Manufacturing

The ability of metal additive manufacturing (AM) to produce intricate geometry parts (e.g., lattice structures and internal channels) from hard-to-process materials (e.g., Ti-6Al-4V and 17-4PH alloys) manifests the potential to revolutionize manufacturing. However, repeatability and product quality remain imposing barriers towards scaling metal AM to production environments. Given the layer-by-layer nature of the process, an anomaly in a layer due to dimensional accuracy, layer morphology, mechanical and metallurgical defects, if not averted, will be permanently sealed in by subsequent layers and deteriorate the builds strength and fatigue life. In this research, we focus on developing models for monitoring and control, system diagnostics and prognostics, and quality and reliability improvement.

Multi-scale and In-situ Quality Assurance in Additive Manufacturing