.png){kind=icon}
返回
FIGAN: A Missing Industrial Data Imputation Method Customized for Soft Sensor Application
.png){kind=icon}
PRE
AI
DOI：10.1109/TASE.2021.3132037.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Missing data is quite common in the industrial field, resulting in problems in downstream applications, as most data driven methods used in these applications rely on complete and high-quality dataset to build a high-quality model. Existing methods deal with missing data individually regardless of its downstream application, treating all variables equally without considering their different roles in the downstream application. This would affect imputation performance for key variables, thus deteriorating the accuracy of the downstream model. A considerable challenge is how to refine the missing data imputation task. In this paper, a new method termed fine-tuned imputation GAN (FIGAN) is designed to achieve customized data imputation for industrial soft sensor. The major contribution of the paper lies in two aspects: 1) different from the original imputation GAN (GAIN) which treats all variables equally, FIGAN is guided by a soft sensor module so as to achieve customized data imputation by performing improved data imputation on quality-related variables. Enhanced accuracy for the final industrial soft sensor would be possible; 2) in addition, since labels of the soft sensor might also have missing data, a soft sensor with pseudo labeling is designed to conquer the problem with data imputation and label prediction being optimized interactively. Case studies on a converter steelmaking process and a penicillin fermentation process show the feasibility of the proposed FIGAN. It is noted that such customized imputation could be readily transferred to other downstream applications with missing data.
Keyword:
Soft sensors
Data models
Generative adversarial networks
Generators
Training
Task analysis
Probabilistic logic
Industrial process
data imputation
soft sensor
generative adversarial network
semi-supervised learning
期刊
IF:
6.4
论文数:
5.1K
被引数:
1.6W
机构
引用论文
Cold exposure as a potentiating factor of pineal actions in nonhibernating mammals.png)
Cryobiology
CryobiologyIF0
PREAI
分享收藏Spatial imputation for air pollutants data sets via low rank matrix completion algorithm通过低秩矩阵完成算法对空气污染物数据集进行空间插补
OAAI
OAAI分享收藏SLC25A13 Gene Analysis in Citrin Deficiency: Sixteen Novel Mutations in East Asian Patients, and the Mutation Distribution in a Large Pediatric Cohort in ChinaPLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏
查看更多内容