DescriptionMiniaturization, low-cost sensors, advances in wireless communication, and the inherent rise of IoT help to make manufacturing processes, post-production services, and supply chains transparent to both manufacturers and customers. Demand fluctuation, along with the requirements of high product quality, low cost, and mass customization lead to an increase in manufacturing complexity of factories. The relationships and interactions among the system's elements (i.e. , products, humans, robots, environments, machines, tools, etc.) along with the stochastic nature of the system, characterized by unpredictability (sourced from varying demand, component and communication failures, human decision making and control) make the mathematical modeling of a manufacturing system challenging. To make sense of big data obtained from production processes, we need advanced data analytics methods from machine learning and complexity science, including approaches such as information theory, chaos theory, and non-linear theory, to model a manufacturing system's complexity.
The objectives of this workshop are twofold: (1) to get a common understanding of emerging technologies that contribute to building future factories and products (e.g. , agile manufacturing, cognitive robots and cognitive products, digital twin and digital shadow), and (2) to identify prominent scenarios that can be realized to demonstrate advantages of complexity-theoretical viewpoint on manufactural complexity.
|Period||20 Apr 2018|
|Degree of Recognition||Local|