Material-Adaptive Anomaly Detection Using Property-Concatenated Transfer Learning in Wire Arc Additive Manufacturing

• Published in: International journal of precision engineering and manufacturing 2024-02, Vol.25 (2), p.383-408
• Main Authors: Shin, Seung-Jun, Lee, Ju-Hong, Jadhav, Sainand, Kim, Duck Bong
• Format: Article
• Language: English
• Subjects: Additive manufacturing; Anomalies; Artificial neural networks; Data acquisition; Datasets; Engineering; Gas tungsten arc welding; Image acquisition; Industrial and Production Engineering; Low carbon steels; Machine learning; Manufacturing; Material properties; Materials Science; Melt pools; Regular Paper; Stainless steels; Wire
• ISSN: 2234-7593; 2005-4602
• DOI: 10.1007/s12541-023-00924-2

Wire arc additive manufacturing is a promising additive manufacturing process because of its high deposition rate, and material diversity. However, the low quality of melted parts is a critical issue, owing to the difficulty in establishing design rules for process–structure–property–performance. Previous studies have resolved this challenge by deriving anomaly detection models for quality monitoring and have largely relied on machine learning by training melt pool image data. Acquiring sufficient data is a key to obtaining reliable models in machine learning; however, an issue arises from concerning the cost intensiveness in high-cost materials. We propose a material-adaptive anomaly detection method to detect balling defects in a target material using property-concatenated transfer learning. First, transfer learing is applied to derive convolutional neural network (CNN)-based models from a source material and transfer them to a target material, wherein data are insufficient and machine learning rarely achieves high performance. Second, material properties are concatenated on transfer learning as additional features onto image features, contrary to typical transfer learning where CNNs only extract image features. We perform experiments in a gas tungsten arc welding system with low-carbon steel (LCS), stainless steel (STS), and inconel (INC) materials. Our models achieve best classification accuracies of 82.95%, 89.47%, and 84.22% when transferring from LCS to STS, LCS to INC, and STS to INC, respectively, compared with 78.03%, 86.37%, and 73.63% obtained using typical transfer learning. The proposed method can effectively resolve the data scarcity by model transfer from sufficient datasets in low-cost materials to rare datasets in high-cost materials. Moreover, it outperforms typical transfer learning because material properties are learned as manufacturing-knowledge features, accounting for melting and hardening characteristics of materials.