WCSE

Multi-temporal Processing Quality Prediction Based on Graph Neural Networks and Transfer Learning

Abstract—The model abstracts the complex influence relationships between parameters as graph data, uses graph neural networks to calculate the spatial information between parameters, and uses long and short term memory networks to model the complex temporal dependencies of workshop processing quality index sequences. Experimental results show that the model was achieve absolute performance improvements of 0.011, 0.001 and 2.35% compared to time series analysis methods.

Index Terms—quality prediction; graph neural networks; deep neural networks; recurrent neural networks;deep learning

Bin Yi, Jun Tang, Wenqiang Lin, Xiaohua Gao, Bing Zhou
Technology Center, China Tobacco Yunnan Industrial Co., Ltd., CHINA
Junjun Fang, Yuqi Xi
Affiliation Yuxi Cigarette Factory, Hongta Tobacco (Group) Co., Ltd., CHINA
Wenqi Li
Technology Center, China Tobacco Yunnan Industrial Co., Ltd., CHINA

[Download]

Cite: Bin Yi, Jun Tang, Wenqiang Lin, Xiaohua Gao, Bing Zhou, Junjun Fang, Yuqi Xi, Wenqi Li, "Multi-temporal Processing Quality Prediction Based on Graph Neural Networks and Transfer Learning" Proceedings of 2023 the 13th International Workshop on Computer Science and Engineering (WCSE 2023), pp. 138-145, June 16-18, 2023.