Big data mining for smart additive manufacturing: novel methods and future perspectives
ECAS-ENBIS Webinar
Big data mining for smart additive manufacturing: novel methods and future perspectives
Speaker: Marco Grasso, Bianca Maria Colosimo (Department of Mechanical Engineering, Politecnico di Milano, Via La Masa 1, 20156, Milan, Italy)
Chair: Davide Cacciarelli (Imperial College London, UK)
Date: 11th April 2025, at 16:00-17:00 CET
Abstract:
The rapid evolution of digital industry paradigms is transforming the landscape of modern production, enabling new opportunities and challenges in the field of quality data mining, modelling and monitoring. A key enabling technology at the core of this transition is additive manufacturing (AM), which unlocks unprecedented levels of data volume, variety, velocity and veracity for in-line and in-situ inspection and process monitoring. By leveraging such big data availability, industry can tackle specific challenges and barriers imposed by continuously evolving needs and requirements for advanced product performance. In this framework, the integration of new machine learning and artificial intelligence (AI) capabilities has emerged as one of most promising research fields to aid the industrial development of smart and zero-defect manufacturing solutions.
The talk addresses the integration of big data analytics within the Industry 4.0 ecosystems to enable fully autonomous and intelligent AM systems. Novel in-situ monitoring solutions and real industrial applications across different sectors illustrate the transformative potential of big data mining in reducing costs, anticipating anomaly detection, improving product quality, and accelerating innovation in AM. The talk present cutting-edge research developments and results, and it highlights opportunities and perspectives for future deployment in real industrial environments.
For example, wearable devices allow collecting data at an individual level, which can be used to propose an unseen degree of personalization for a broad domain of applications, such as the adaptive automatic control of a setting. This can be done using RL: depending on sensor data (state) some setting of the wearable device must be automatically piloted (action) in such a way that the user does not interact often with its device (reward).
Keywords: in-situ monitoring; big data; machine learning; artificial intelligence; additive manufacturing.
Bio:
Marco Grasso is Associate Professor. He got both his MSc in Aerospace Engineering and his PhD in Mechanical Engineering at Politecnico di Milano. He spent periods as visiting scholar at the Hong Kong University of Science and Technology and at Nanyang Technical University, Singapore.
His main area of expertise is quality data modelling and monitoring in the field of Industry 4.0 and Additive Manufacturing, with a focus on smart manufacturing solutions for in-line/in-situ process monitoring of big data, sensor signals and video-image data.
He is Associate Editor of Progress in Additive Manufacturing, and he served as Guest Editor for other international journals. He was among the recipients of the 2023 ASQ Brumbaugh Award.
