Path Enhanced Bidirectional Graph Attention Network for Quality Prediction in Multistage Manufacturing Process
| Autor: | Zhang Donghao, Zhenyu Liu, Weiqiang Jia, Hui Liu, Jianrong Tan |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
Dependency (UML)
Computer science business.industry Bidirectional search media_common.quotation_subject Deep learning Directed graph computer.software_genre Computer Science Applications Control and Systems Engineering Robustness (computer science) Path (graph theory) Graph (abstract data type) Quality (business) Artificial intelligence Data mining Electrical and Electronic Engineering business computer Information Systems media_common |
| Zdroj: | IEEE Transactions on Industrial Informatics. 18:1018-1027 |
| ISSN: | 1941-0050 1551-3203 |
| DOI: | 10.1109/tii.2021.3076803 |
| Popis: | Quality prediction, as the basis of quality control, is dedicated to predicting quality indices of the manufacturing process. In recent years, data-driven deep learning methods have received a lot of attention due to their accuracy, robustness, and convenience for the prediction of quality indices. However, the existing studies mainly focus on the quality prediction of a single machine, while ignoring dependency relationships among multiple machines in multistage manufacturing process. To tackle the above issues, a novel path enhanced bidirectional graph attention network (PGAT) is proposed in this article. PGAT models the dependencies among machines into directed graphs and introduces graph attention network to encode the dependencies. Nonetheless, it is difficult for graph neural networks to encode long-distance dependencies. Hence, dependency path information is introduced into the features of machines. Moreover, in order to solve the label noise problem that often occurs in actual industrial dataset, a masked loss function is devised. With its help, batch training with noisy labels can be achieved, which improves the training efficiency. Furthermore, experiments are conducted on a public quality prediction dataset collected from an actual production line. PGAT achieves the state-of-the-art results on this dataset, which confirms the effectiveness of PGAT. Additionally, the experimental results demonstrate the critical role of modeling dependency relationships among machines. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|