TY - GEN
T1 - Achieving Cognitive Intelligence for Sustainable Advanced Manufacturing
AU - Ituarte, Iñigo Flores
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
PY - 2024
Y1 - 2024
N2 - Sustainable manufacturing is a global imperative, requiring the convergence of materials, manufacturing processes, and engineering design. Manufacturing plays a vital role in the global economy; however, it contributes detrimentally to 20% of carbon emissions. Laser-based advanced manufacturing, primarily additive manufacturing (AM), holds promise for sustainable production despite challenges like cost-effectiveness, energy efficiency, and process stability. The challenge lies in effectively studying critical parameters and incorporating new materials, sensing technologies, advanced modeling, and prediction methods into the manufacturing process’s waste-free and defect-free monitoring and optimization. This research focuses on developing research recommendations in three areas. First, (i) justifying the importance of developing Free and Open-Source Hardware (FOSH) laser-based AM infrastructure to facilitate research exploration, data-sharing, and open research. Second, (ii) exploring the concepts and theories towards integrated data-driven “perceptual intelligence,” model-driven “computational intelligence,” and integrated artificial intelligence methods to achieve cognitive capabilities with explainability and generalizability. Third, (iii) one case study on melt pool monitoring in metal-based AM showcases novel capabilities and limitations in real-time process monitoring using data-driven modeling. Regardless of the complexity and multidisciplinary nature of achieving cognitive intelligence in manufacturing processes, this endeavor will revolutionize advanced manufacturing process modeling and optimization, enabling more sustainable manufacturing processes.
AB - Sustainable manufacturing is a global imperative, requiring the convergence of materials, manufacturing processes, and engineering design. Manufacturing plays a vital role in the global economy; however, it contributes detrimentally to 20% of carbon emissions. Laser-based advanced manufacturing, primarily additive manufacturing (AM), holds promise for sustainable production despite challenges like cost-effectiveness, energy efficiency, and process stability. The challenge lies in effectively studying critical parameters and incorporating new materials, sensing technologies, advanced modeling, and prediction methods into the manufacturing process’s waste-free and defect-free monitoring and optimization. This research focuses on developing research recommendations in three areas. First, (i) justifying the importance of developing Free and Open-Source Hardware (FOSH) laser-based AM infrastructure to facilitate research exploration, data-sharing, and open research. Second, (ii) exploring the concepts and theories towards integrated data-driven “perceptual intelligence,” model-driven “computational intelligence,” and integrated artificial intelligence methods to achieve cognitive capabilities with explainability and generalizability. Third, (iii) one case study on melt pool monitoring in metal-based AM showcases novel capabilities and limitations in real-time process monitoring using data-driven modeling. Regardless of the complexity and multidisciplinary nature of achieving cognitive intelligence in manufacturing processes, this endeavor will revolutionize advanced manufacturing process modeling and optimization, enabling more sustainable manufacturing processes.
KW - Additive Manufacturing
KW - Artificial Intelligence
KW - Sustainable Manufacturing
U2 - 10.1007/978-3-031-74485-3_4
DO - 10.1007/978-3-031-74485-3_4
M3 - Conference contribution
AN - SCOPUS:85213295378
SN - 9783031744846
T3 - Lecture Notes in Mechanical Engineering
SP - 28
EP - 39
BT - Flexible Automation and Intelligent Manufacturing
A2 - Wang, Yi-Chi
A2 - Chan, Siu Hang
A2 - Wang, Zih-Huei
PB - Springer
T2 - International Conference on Flexible Automation and Intelligent Manufacturing
Y2 - 23 June 2024 through 26 June 2024
ER -