Stable data-driven manufacturing decision making by introducing causal relationships for high dimensional data
Gao, Xiaoyu ORCID: 0000-0001-5625-3654 , Zhao, Zhiwei, Li, Yingguang and Liu, Changqing (2024) Stable data-driven manufacturing decision making by introducing causal relationships for high dimensional data. IEEE Transactions on Industrial Informatics. ISSN 1551-3203 (Print), 1941-0050 (Online) (In Press)
PDF (AAM)
47836_GAO_Stable_data-driven_manufacturing_decision_making_by_introducing_causal_relationships_for_high_dimensional_data.pdf - Accepted Version Restricted to Repository staff only Download (4MB) | Request a copy |
Abstract
In digital manufacturing, data-driven methods are promising to revolutionize various decision-making processes. However, the relationships between variables in high- dimensional data of data-driven decision-making methods are only correlations. Important causal relationships and knowledge between process variables are not considered. Therefore, existing data-driven systems are instable, which could result in unreliable and dangerous decisions. To establish a stable decision-making model for complex processes with high-dimensional data, a causal-based decision-making framework combined causal relationships and knowledge between key manufacturing variables was proposed. The causal relationships between State, Decision and Objective data was established in form of direct acyclic graph forming by breaking an unexcepted loop between variables using a Shadow Objective variable. Then, causal knowledge of high-dimensional state was introduced to the neural network, forming a stable decision-making model. Compared with data-driven methods used in robotics and manufacturing scenarios, the proposed framework provided better and stable decisions particularly in noised environments.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | manufacturing decision-making; data-driven; causal relationship; causal loop |
Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
Faculty / School / Research Centre / Research Group: | Faculty of Engineering & Science > School of Engineering (ENG) Faculty of Engineering & Science |
Last Modified: | 10 Sep 2024 12:08 |
URI: | http://gala.gre.ac.uk/id/eprint/47836 |
Actions (login required)
View Item |
Downloads
Downloads per month over past year