Comparison of Transfer Learning based Additive Manufacturing Models via A Case Study
This work addresses data insufficiency in additive manufacturing modeling for researchers and practitioners, but it is incremental as it compares existing methods without introducing new ones.
The paper tackles the challenge of selecting source domains, determining target data size, and applying data preprocessing in transfer learning for additive manufacturing modeling, finding through a case study that domains with higher qualitative similarity and specific target-to-source data ratios yield better performance, with careful preprocessing balancing modeling gains.
Transfer learning (TL) based additive manufacturing (AM) modeling is an emerging field to reuse the data from historical products and mitigate the data insufficiency in modeling new products. Although some trials have been conducted recently, the inherent challenges of applying TL in AM modeling are seldom discussed, e.g., which source domain to use, how much target data is needed, and whether to apply data preprocessing techniques. This paper aims to answer those questions through a case study defined based on an open-source dataset about metal AM products. In the case study, five TL methods are integrated with decision tree regression (DTR) and artificial neural network (ANN) to construct six TL-based models, whose performances are then compared with the baseline DTR and ANN in a proposed validation framework. The comparisons are used to quantify the performance of applied TL methods and are discussed from the perspective of similarity, training data size, and data preprocessing. Finally, the source AM domain with larger qualitative similarity and a certain range of target-to-source training data size ratio are recommended. Besides, the data preprocessing should be performed carefully to balance the modeling performance and the performance improvement due to TL.