Making costly manufacturing smart with transfer learning under limited data: A case study on composites autoclave processing. (April 2021)

• Record Type: Journal Article
• Authors: Ramezankhani, Milad; Crawford, Bryn; Narayan, Apurva; Voggenreiter, Heinz; Seethaler, Rudolf; Milani, Abbas S.
• Is Part Of: Journal of manufacturing systems. Volume 59(2021)
• Page Start: 345
• Page End: 354
• Publication Date: 2021-04
• Subjects: Intelligent manufacturing -- Transfer learning -- Limited data -- Autoclave processing -- Aerospace composites; Manufacturing processes -- Periodicals; Production engineering -- Data processing -- Periodicals; Robots, Industrial -- Periodicals; Production, Technique de la -- Informatique -- Périodiques; Robots industriels -- Périodiques; Electronic journals; 670.42
• DOI: 10.1016/j.jmsy.2021.02.015
• Languages: English
• ISSNs: 0278-6125

Abstract

Highlights: Transfer learning immunes model's performance against shifts in the dynamic operational settings of smart manufacturing. Transfer learning delivers robust and reliable predictions for manufacturing applications under limited data. Sequential unfreezing proved to be an integral part of transfer learning in mitigating the effect of catastrophic forgetting. The data from a historical autoclave curing process can be used for learning a new cure cycle setting with limited data. Abstract: The integration of advanced manufacturing processes with ground-breaking Artificial Intelligence methods continue to provide unprecedented opportunities towards modern cyber-physical manufacturing processes, known as smart manufacturing or Industry 4.0. However, the "smartness" level of such approaches closely depends on the degree to which the implemented predictive models can handle uncertainties and production data shifts in the factory over time. In the case of change in a manufacturing process configuration with no sufficient new data, conventional Machine Learning (ML) models often tend to perform poorly. In this article, a transfer learning (TL) framework is proposed to tackle the aforementioned issue in modeling smart manufacturing. Namely, the proposed TL framework is able to adapt to probable shifts in the production process design and deliver accurate predictions without the need to re-train the model. Armed with sequential unfreezing and early stopping methods, the model demonstrated the ability to avoid catastrophic forgetting in the presence of severely limited data. Through the exemplified industry-focused case study on autoclave composite processing, the model yielded a drastic (88%) improvement in the generalization accuracy compared to the conventional learning, while reducing the computational and temporal cost by 56%.