Learning Adaptive Semi-Supervised Multi-Output Soft-Sensors with Co-Training of Heterogeneous Models | |
Li, Dong1; Huang DP(黄道平)1; Yu GP(于广平)2; Liu YQ(刘乙奇)1 | |
刊名 | IEEE Access |
2020 | |
卷号 | 8页码:46493-46504 |
关键词 | Soft-sensors, semi-supervised co-training, multi-output recursive partial least square (RPLS) long short-term memory recurrent neural network (LSTM) |
ISSN号 | 2169-3536 |
产权排序 | 2 |
英文摘要 | Soft-sensors are widely utilized for predictions of important but hard-to-measure variables in industrial processes. However, significant variations, process uncertainties, negative influence of external environment and insufficient use of unlabeled data always cause the attenuation of prediction performance. Thus, this paper proposed an adaptive semi-supervised multi-output soft-sensor by co-training recursive heterogeneous models. In the proposed strategy, a linear multi-output model, called recursive partial least square (MRPLS), and a nonlinear multi-output, called long short-term memory recurrent neural network (MLSTM), are co-trained to deal with inefficient use of label data adaptively. Ensemble of both models are not only able to address the linear and nonlinear hybrid behaviors in different time scale, but also able to deal with multiple tasks learning issues. In addition, the model proposed an odd-even grouping strategy to equalize two parts of the labeled data, which is able to capture the global variations of a process. To validate the prediction performance of the proposed soft-sensor, it was verified through a simulation benchmark platform (BSM1) and a real sewage treatment plant (UCI database). The results meant that co-training MRPLS-MLSTM achieved better performance compared with other existing co-training models in terms of the hard-to-measure variables. |
资助项目 | National Natural Science Foundation of China[61873096] ; National Natural Science Foundation of China[61673181] ; Science and Technology Program of Guangzhou, China[201804010256] |
WOS关键词 | REGRESSION ; FRAMEWORK ; PLS |
WOS研究方向 | Computer Science ; Engineering ; Telecommunications |
语种 | 英语 |
WOS记录号 | WOS:000524577400005 |
资助机构 | National Natural Science Foundation of China under Grant 61873096 and Grant 61673181 ; Science and Technology Program of Guangzhou, China, under Grant 201804010256 |
内容类型 | 期刊论文 |
源URL | [http://ir.sia.cn/handle/173321/26639] |
专题 | 沈阳自动化研究所_广州中国科学院沈阳自动化研究所分所 |
通讯作者 | Liu YQ(刘乙奇) |
作者单位 | 1.School of Automation Science and Engineering, South China University of Technology, Guangzhou 510640, China 2.Chinese Academy of Sciences, Shenyang Institute of Automation, Guangzhou 511458, China |
推荐引用方式 GB/T 7714 | Li, Dong,Huang DP,Yu GP,et al. Learning Adaptive Semi-Supervised Multi-Output Soft-Sensors with Co-Training of Heterogeneous Models[J]. IEEE Access,2020,8:46493-46504. |
APA | Li, Dong,Huang DP,Yu GP,&Liu YQ.(2020).Learning Adaptive Semi-Supervised Multi-Output Soft-Sensors with Co-Training of Heterogeneous Models.IEEE Access,8,46493-46504. |
MLA | Li, Dong,et al."Learning Adaptive Semi-Supervised Multi-Output Soft-Sensors with Co-Training of Heterogeneous Models".IEEE Access 8(2020):46493-46504. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论