Interval multiple-output soft sensors development with capacity control for wastewater treatment applications: A comparative study

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 广州中国科学院沈阳自动化研究所分所

	Interval multiple-output soft sensors development with capacity control for wastewater treatment applications: A comparative study
	Huang DP(黄道平); Xiao HJ(肖红军); Ba, Bingxin ; Li, Xianxiang ; Liu, Jian; Liu YQ(刘乙奇)
刊名	CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
	2019
卷号	184 页码:82-93
关键词	Soft-sensors Multi-output Capacity control Wastewater Uncertainty
ISSN号	0169-7439
产权排序	2
英文摘要	Soft-sensor is the most common strategy to predict hard-to-measure variables in the wastewater treatment processes. However, existence of a large number of hard-to-measure variables always renders a generic single-output soft-sensor inadequate. This study developed multi-output soft-sensors using Multivariate Linear Regression model (MLR), Multivariate Relevant Vector Machine (MRVM) and Multivariate Gaussian Processes Regression (MGPR) models aiming to predict multiple hard-to-measure variables simultaneously and to capture the joint distribution of the response variables. This, in turn, ensures that the proposed soft-sensors are not just able to obtain prediction values, but also to indicate the credibility of information for hard-to-measure quantities. To further compromise the computational overhead of multi-output soft-sensors, improved Variable Importance in Projection (VIP) and Least Absolute Shrinkage and Selection Operator (Lasso) are proposed to reduce the dimensions of data, thereby alleviating the complexity of predicted models. The proposed methodologies were firstly demonstrated by applying the design algorithm to a wastewater plant (WWTP) simulated with the wellestablished model, BSM1, then extended to a full-scale WWTP with data collecting from the field. Results showed that the proposed strategy significantly improved the prediction performance.
资助项目	National Natural Science Foundation of China[61873096] ; National Natural Science Foundation of China[61673181] ; National Natural Science Foundation of China[61533002] ; National Natural Science Foundation of China[61803086] ; Science and Technology Planning Project of Guangdong Province, China[2016A020221007] ; Technology Innovation Special Fund of Foshan, China[2014AG10018] ; Science and Technology Program of Guangzhou, China[201804010256] ; Fundamental Research Funds for the central Universities, SCUT[2017MS053]
WOS关键词	VARIABLE SELECTION ; PLS ; REGRESSION ; MODEL
WOS研究方向	Automation & Control Systems ; Chemistry ; Computer Science ; Instruments & Instrumentation ; Mathematics
语种	英语
WOS记录号	WOS:000456903800008
资助机构	National Natural Science Foundation of China ; Science and Technology Planning Project of Guangdong Province, China ; Technology Innovation Special Fund of Foshan, China ; Science and Technology Program of Guangzhou, China ; Fundamental Research Funds for the central Universities, SCUT
内容类型	期刊论文
源URL	[http://ir.sia.cn/handle/173321/24136]
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 & Engineering, South China University of Technology, Wushan Road, Guang Zhou, 510640, Chinales R China 2.School of Automtion, Foshan University, Jiangwan Road, Fo Shan, 528000, China 3.ShenYang Institute of of Automation, GuangZhou, Chinese Academy of Sciences, Hai Bin Road, Guang Zhou, 511458, China
推荐引用方式 GB/T 7714	Huang DP,Xiao HJ,Ba, Bingxin,et al. Interval multiple-output soft sensors development with capacity control for wastewater treatment applications: A comparative study[J]. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS,2019,184:82-93.
APA	Huang DP,Xiao HJ,Ba, Bingxin,Li, Xianxiang,Liu, Jian,&Liu YQ.(2019).Interval multiple-output soft sensors development with capacity control for wastewater treatment applications: A comparative study.CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS,184,82-93.
MLA	Huang DP,et al."Interval multiple-output soft sensors development with capacity control for wastewater treatment applications: A comparative study".CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 184(2019):82-93.