AI and IoT for Smart Manufacturing – Practices and Standards

Yan Lu (Keywords: AI-Based Methods; Intelligent and Flexible Manufacturing)

Smart Manufacturing represents a new way of making goodsand providing services for high customization at near massproduction cost, by using real time data that can improvedecision making in the value chains of manufacturing. Thisis obtained by the intensive use of digital technology,including Internet of Things (IoT) and artificialintelligence (AI), to integrate products, productionsystems and business activities through their life cyclesand value chains, and increasing decentralized decisionmaking. The objectives of this workshop is to bring smartmanufacturing stakeholders, including manufacturers,vendors, standards developers and researchers together topresent the cutting edge smart manufacturing technology,tools and use cases for production and manufacturingsystems, especially those utilizing IoT and AI. Specifically:

1)      The role of AI and IoT in smart manufacturing:overview of theory and technology
2)      Current practice and applications of AI and IoT inmanufacturing
3)      The existing and missing standards that enables theadoption of AI and IoT for smart manufacturing.
4)      Automation with AI and robots and manufacturingjobs

This full day workshop on AI and IoT for smartmanufacturing has a focus on practices. The first part willbe led by Prof. Barton with an overview of the topic area.The second part will be led by an industry colleague todiscuss current status of AI applications in industryautomation and manufacturing systems. The third part willfocus on how standards facilitate the application of AI andIoT in manufacturing. Finally, we would like to have adiscussion on the social impact of AI/Robot/Automation onmanufacturing.
Top

Deep Learning for Intelligent Manufacturing

Ruqiang Yan, Xuefeng Chen, Weihua Li, Kunpeng Zhu (Keywords: Big-Data and Data Mining; Intelligent and Flexible Manufacturing; Manufacturing, Maintenance and Supply Chains)

With increased complexity of modern manufacturing systems,exponential growth of data has been seen in manufacturing industry. Efficient utilization of those big data would provide intelligence to manufacturing machines and processes, thus helping produce high quality products with increased productivity, while at the same time reducing manufacturing costs.  Within the field of data analytics, machine learning is one of methods used to devise complex models and algorithms that lend themselves to derive knowledge from the data. As a branch of machine learning, deep learning attempts to model high level representations behind data and classify(predict) patterns via stacking multiple layers of information processing modules in hierarchical architectures, which has shown great potential for better decision making to enhance the state of manufacturing, especially in the big data era.
Top

Robotic Assembly – Recent Advancements and Opportunities for Challenging R&D

Joe Falco, Elena Messina, Maximo A. Roa  (Keywords: Assembly; Sensor-based Control; Manipulation Planning)

https://www.nist.gov/news-events/events/2018/08/robotic-assembly-recent-advancements-and-opportunities-challenging-rd

A new class of robots called collaborative robots or Co-Bots are designed to safely work alongside human workers in manufacturing environments.  These robots are equipped with force sensing and/or compliance through series elastic actuator technologies in order to limit forces and prevent injury to humans working in their proximity. Next generation end-effector technologies such as fully-actuated and under-actuated robotic hands with advanced force control, in-hand manipulation capabilities and built in compliance are mainstream within the research community. These new technologies as well as machine learning/artificial intelligence techniques and simplified programming interfaces show promise as new ways for tackling the small parts assembly problem of trending low-volume, high-mix production operations. This workshop will help identify the challenges associated with implementing robotic assembly by first exploring the application space through presentations by leading experts in the automotive, aerospace, and consumer goods manufacturing sectors.     In addition, keynote presentations and a poster session will highlight work underway that is already addressing the challenges in this application space.      Finally, tools to benchmark research progress in mechanical assembly that are designed with reference to existing design-for-assembly (DFA) methods will be presented.The discussion period will be used to identify key research areas needed to address the low-volume, high-mix, small parts assembly problem.   Although the focus will be on assembly applications, many of the same challenges and solutions are relevant to other domains, such as service robotics.
Top