Ontology-guided attribute learning to accelerate certification for developing new printing processes

Abstract

Identifying printing defects is vital for process certification, especially with evolving printing technologies. However, this task proves challenging, especially for micro-level defects necessitating microscopy, which presents a scalability barrier for manufacturing. To address this challenge, we propose an attribute learning methodology inspired by human learning, which identifies shared attributes among seen and unseen objects. First, it extracts defect class embeddings from an engineering-guided defect ontology. Then, attribute learning identifies the combination of attributes for defect estimation. This approach enables it to recognize previously unseen defects by identifying shared attributes, even those not included in the training dataset. The research formulates a joint optimization problem for learning and fine-tuning class embedding and ontology and solves it by integrating natural language processing, metaheuristics for exploration and exploitation, and stochastic gradient descent. In a case study involving a direct-ink-writing process for creating nanocomposites, this methodology was used to learn new defects not found in the training data using the optimized ontology. Compared to traditional zero-shot learning, this ontology-based approach significantly improves class embedding, outperforming transfer learning in one-shot and two-shot learning scenarios. This research represents an early effort to learn new defect concepts, potentially reducing the need for extensive measurements in defect identification.

Keywords:

• Additive manufacturing
• attribute learning
• ontology
• Defect identification
• process certification

Data availability statement

The data and code used in this study is here (https://github.com/FAMU-FSU-IME/Ontology-guided-Attribute-Learning.git).

Additional information

Notes on contributors

Tsegai O. Yhdego

Tsegai O. Yhdego is a researcher in industrial engineering pursuing a PhD at Florida A&M University. His academic journey includes a BSc in electrical and electronics engineering (2015) from Eritrea Institute of Technology and an MSc in mechatronic engineering (2019) from The Pan African University Institute for Basic Sciences, Technology and Innovation. His research focuses on developing small-sample machine learning algorithms, specializing in ontology-based federated learning, emphasizing data security and collaborative machine learning. He has also contributed to the aviation industry, developing ML models to forecast flight delay and delay impact.

Hui Wang

Hui Wang is an associate professor of industrial engineering at the Florida A&M University-Florida State University College of Engineering and a member of the HighPerformance Materials Institute (HPMI). His research has been focused on (i) data modeling and analytics to support quality control for manufacturing processes, including small-sample learning under an interconnected environment, and (ii) optimization of manufacturing system design and supply chain. He received his PhD in industrial engineering from the University of South Florida and an MSE in mechanical engineering from the University of Michigan.

Zhibin Yu

Zhibin Yu is an associate professor of industrial engineering at the Florida A&M University-Florida State University College of Engineering and a member of the High Performance Materials Institute (HPMI). His research has been focused on nanomaterials synthesis and processing for printing electronics. He received his PhD in materials science and engineering from the University of California, Los Angeles.

Hongmei Chi

Hongmei Chi is a professor of computer and information sciences at Florida A&M University. Her research focuses on areas of applied cybersecurity, mobile health privacy, Monte Carlo and quasi-Monte Carlo, and data science. She received her PhD in computer science at Florida State University.