A Soft Sensor with Light and Efficient Multi-scale Feature Method for Multiple Sampling Rates in Industrial Processing

doi:10.1007/s11633-022-1401-9

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	A Soft Sensor with Light and Efficient Multi-scale Feature Method for Multiple Sampling Rates in Industrial Processing
	Dezheng Wang 1; Yinglong Wang2 ; Fan Yang3 ; Liyang Xu 4; Yinong Zhang 5; Yiran Chen 2; Ning Liao 2
发表期刊	Machine Intelligence Research
ISSN	2731-538X
	2024
卷号	21 期号:2 页码:400-410
摘要	In industrial process control systems, there is overwhelming evidence corroborating the notion that economic or technical limitations result in some key variables that are very difficult to measure online. The data-driven soft sensor is an effective solution because it provides a reliable and stable online estimation of such variables. This paper employs a deep neural network with multiscale feature extraction layers to build soft sensors, which are applied to the benchmarked Tennessee-Eastman process (TEP) and a real wind farm case. The comparison of modelling results demonstrates that the multiscale feature extraction layers have the following advantages over other methods. First, the multiscale feature extraction layers significantly reduce the number of parameters compared to the other deep neural networks. Second, the multiscale feature extraction layers can powerfully extract dataset characteristics. Finally, the multiscale feature extraction layers with fully considered historical measurements can contain richer useful information and improved representation compared to traditional data-driven models.
关键词	Multi-scale, feature extractor, deep neural network (DNN), multirate sampled industrial processes, prediction
DOI	10.1007/s11633-022-1401-9
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/56046
专题	学术期刊_Machine Intelligence Research
作者单位	1.School of Automation, Southeast University, Nanjing 210096, China 2.Software and Artificial Intelligence College, Chongqing Institute of Engineering, Chongqing 400056, China 3.Beijing National Research Center for Information Science and Technology (BNRist), Department of Automation, Tsinghua University, Beijing 100084, China 4.Liangjiang International College, Chongqing University of Technology, Chongqing 401135, China 5.Smart City College, Beijing Union University, Beijing 100101, China
推荐引用方式 GB/T 7714	Dezheng Wang,Yinglong Wang,Fan Yang,et al. A Soft Sensor with Light and Efficient Multi-scale Feature Method for Multiple Sampling Rates in Industrial Processing[J]. Machine Intelligence Research,2024,21(2):400-410.
APA	Dezheng Wang.,Yinglong Wang.,Fan Yang.,Liyang Xu.,Yinong Zhang.,...&Ning Liao.(2024).A Soft Sensor with Light and Efficient Multi-scale Feature Method for Multiple Sampling Rates in Industrial Processing.Machine Intelligence Research,21(2),400-410.
MLA	Dezheng Wang,et al."A Soft Sensor with Light and Efficient Multi-scale Feature Method for Multiple Sampling Rates in Industrial Processing".Machine Intelligence Research 21.2(2024):400-410.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
MIR-2022-08-270.pdf（3208KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载