Ontology-guided Attribute Learning to Accelerate Certification for Developing New Printing Processes
Ontology-guided Attribute Learning to Accelerate Certification for Developing New Printing Processes
复制标题
DOI：
10.1080/24725854.2023.2263786
复制
发表时间：
2023-09
影响因子：
2.6
通讯作者：
Tsegai O. Yhdego;Hongya Wang;Zhibin Yu;Hongmei Chi
中科院分区：
文献类型：
--
作者：
Tsegai O. Yhdego;Hongya Wang;Zhibin Yu;Hongmei Chi
识别印刷缺陷对于流程认证至关重要，尤其是在印刷技术不断发展的情况下。然而，这项任务具有挑战性，特别是对于需要显微镜的微观缺陷，这给制造带来了可扩展性障碍。为了应对这一挑战，我们提出了一种受人类学习启发的属性学习方法，该方法识别可见和不可见对象之间的共享属性。首先，它从工程引导的缺陷本体中提取缺陷类嵌入。然后，属性学习识别用于缺陷估计的属性组合。这种方法使其能够通过识别共享属性（甚至那些未包含在训练数据集中的属性）来识别以前未见过的缺陷。该研究提出了学习和微调类嵌入和本体的联合优化问题，并通过集成自然语言处理、探索和利用的元启发法以及随机梯度下降来解决该问题。在涉及创建纳米复合材料的直接墨水书写过程的案例研究中，该方法用于使用优化本体来学习训练数据中未发现的新缺陷。与传统的零样本学习相比，这种基于本体的方法显着改善了类嵌入，在单样本和双样本学习场景中优于迁移学习。这项研究代表了学习新缺陷概念的早期努力，有可能减少缺陷识别中大量测量的需要。
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.