Industrial manufacturing companies face the challenge of adapting to increasingly complex demands, especially with the influx of online ordering. One case of this is in the underperformance of end-effectors, limiting the adaptability of robotic arms in manufacturing functionality. To create proper gripper adaptability, intelligent gripper design is required to improve the sensibility and processing capability of the end-effectors. This will allow for grippers to perform effective decision-making and optimize production. This paper suggests a methodology that includes a step-by-step design process for an intelligent gripper and discusses how to develop intelligence utilizing key components of Industry 4.0 (Internet of Things, machine learning, and cloud manufacturing). This method was analyzed in a case study of a low-level intelligent vacuum gripper design. The methodology will be beneficial to intelligent gripper design from multiple levels of intelligence, creating a guide for engineers to follow to effectively design intelligent gripper solutions for their systems.

Industry 4.0 is considering a new industrial revolution with important advanced manufacturing paradigms connected. This paper explores the capture of tacit knowledge using digital tools and a robotic mechatronic case study. Digital manufacturing tools have been used to simulate complex human-robot interactions, and it is important to capture said tacit knowledge to create next generation automation systems. This research uses a tacit knowledge lifecycle to capture key mechatronics experiences using a digital twin. The research hypothesis is that capturing mechatronic tacit knowledge through digital twins could support the creation of a new and more complex next generation automation system.