Interpretable multi-task learning for product quality prediction with attention mechanism

Cheng Han Yeh, Yao Chung Fan, Wen-Chih Peng

研究成果: Conference contribution同行評審

9 引文 斯高帕斯(Scopus)

摘要

In this paper, we investigate the problem of mining multivariate time series data generated from sensors mounted on manufacturing stations for early product quality prediction. In addition to accurate quality prediction, another crucial requirement for industrial production scenarios is model interpretability, i.e., to understand the significance of an individual time series with respect to the final quality. Aiming at the goals, this paper proposes a multi-task learning model with an encoder-decoder architecture augmented by the matrix factorization technique and the attention mechanism. Our model design brings two major advantages. First, by jointly considering the input multivariate time series reconstruction task and the quality prediction in a multi-task learning model, the performance of the quality prediction task is boosted. Second, by incorporating the matrix factorization technique, we enable the proposed model to pay/learn attentions on the component of the multivariate time series rather than on the time axis. With the attention on components, the correlation between a sensor reading and a final quality measure can be quantized to improve the model interpretability. Comprehensive performance evaluation on real data sets is conducted. The experimental results validate that strengths of the proposed model on quality prediction and model interpretability.

原文English
主出版物標題Proceedings - 2019 IEEE 35th International Conference on Data Engineering, ICDE 2019
發行者IEEE Computer Society
頁面1910-1921
頁數12
ISBN(電子)9781538674741
DOIs
出版狀態Published - 4月 2019
事件35th IEEE International Conference on Data Engineering, ICDE 2019 - Macau, China
持續時間: 8 4月 201911 4月 2019

出版系列

名字Proceedings - International Conference on Data Engineering
2019-April
ISSN(列印)1084-4627

Conference

Conference35th IEEE International Conference on Data Engineering, ICDE 2019
國家/地區China
城市Macau
期間8/04/1911/04/19

指紋

深入研究「Interpretable multi-task learning for product quality prediction with attention mechanism」主題。共同形成了獨特的指紋。

引用此