DOI: 10.1016/j.watres.2017.10.053
Scopus记录号: 2-s2.0-85032687422
论文题名: Predicting influent biochemical oxygen demand: Balancing energy demand and risk management
作者: Zhu J.-J. ; Kang L. ; Anderson P.R.
刊名: Water Research
ISSN: 431354
出版年: 2018
卷: 128 起始页码: 304
结束页码: 313
语种: 英语
英文关键词: Biochemical oxygen demand (BOD)
; Decision making
; Energy saving
; Risk management
; Soft sensor
; Wastewater
Scopus关键词: Biochemical oxygen demand
; Decision making
; Effluents
; Energy conservation
; Energy utilization
; Forecasting
; Linear regression
; Neural networks
; Oxygen
; Risk management
; Wastewater
; Wastewater reclamation
; Water treatment plants
; Biochemical oxygen demands (BOD)
; Compromise programming
; Multiple linear regressions
; Operational reliability
; Real-time process control
; Reduce energy consumption
; Soft sensors
; Water reclamation plants
; Process control
; ammonia
; oxygen
; oxygen
; water
; accuracy assessment
; artificial neural network
; biochemical oxygen demand
; concentration (composition)
; decision making
; energy conservation
; energy use
; prediction
; regression analysis
; risk assessment
; sensor
; water treatment plant
; accuracy
; Article
; biochemical oxygen demand
; concentration (parameters)
; controlled study
; energy balance
; energy cost
; environmental reclamation
; prediction
; priority journal
; process control
; risk management
; artificial neural network
; evaluation study
; forecasting
; procedures
; reproducibility
; risk management
; water management
; Biological Oxygen Demand Analysis
; Forecasting
; Neural Networks (Computer)
; Oxygen
; Reproducibility of Results
; Risk Management
; Water
; Water Purification
英文摘要: Ready access to comprehensive influent information can help water reclamation plant (WRP) operators implement better real-time process controls, provide operational reliability and reduce energy consumption. The five-day biochemical oxygen demand (BOD5), a critical parameter for WRP process control, is expensive and difficult to measure using hard-sensors. An alternative approach based on a soft-sensor methodology shows promise, but can be problematic when used to predict high BOD5 values. Underestimating high BOD5 concentrations for process control could result in an insufficient amount of aeration, increasing the risk of an effluent violation. To address this issue, we tested a hierarchical hybrid soft-sensor approach involving multiple linear regression, artificial neural networks (ANN), and compromise programming. While this hybrid approach results in a slight decrease in overall prediction accuracy relative to the approach based on ANN only, the underestimation percentage is substantially lower (37% vs. 61%) for predictions of carbonaceous BOD5 (CBOD5) concentrations higher than the long-term average value. The hybrid approach is also flexible and can be adjusted depending on the relative importance between energy savings and managing the risk of an effluent violation. © 2017 Elsevier Ltd Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/113158
Appears in Collections: 气候减缓与适应
There are no files associated with this item.
作者单位: Department of Civil, Architectural and Environmental Engineering, Illinois Institute of Technology, Chicago, IL 60616-3793, United States; Department of Applied Mathematics, Illinois Institute of Technology, Chicago, IL 60616-3793, United States
Recommended Citation:
Zhu J.-J.,Kang L.,Anderson P.R.. Predicting influent biochemical oxygen demand: Balancing energy demand and risk management[J]. Water Research,2018-01-01,128