Data-driven minimization of pump operating and maintenance cost

Zijun Zhang; Xiaofei He; Andrew Kusiak

doi:10.1016/j.engappai.2015.01.003

Data-driven minimization of pump operating and maintenance cost

Zijun Zhang^*, Xiaofei He, Andrew Kusiak

^*Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

21 Citations (Scopus)

Abstract

A data-driven model for scheduling pumps in a wastewater treatment process is proposed. The objective is to minimize the cost of pump operations and maintenance. A neural network algorithm is applied to model performance of the pumps using the data collected at a municipal wastewater treatment plant. The discrete-state Markov process is utilized to develop a model of maintenance decisions. The developed pump performance and maintenance models are integrated into a scheduling model. A hierarchical particle swarm optimization algorithm is designed to solve the proposed scheduling model. The concepts developed in this paper are illustrated with two case studies.

Original language	English
Pages (from-to)	37-46
Journal	Engineering Applications of Artificial Intelligence
Volume	40
Online published	4 Feb 2015
DOIs	https://doi.org/10.1016/j.engappai.2015.01.003
Publication status	Published - Apr 2015

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 6 Clean Water and Sanitation
SDG 11 Sustainable Cities and Communities

Research Keywords

Cost optimization
Data mining
Energy savings
Particle swarm optimization
Pump system
Scheduling

Access Output

10.1016/j.engappai.2015.01.003

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{dabe648018154f1587dbfb741608423c,

title = "Data-driven minimization of pump operating and maintenance cost",

abstract = "A data-driven model for scheduling pumps in a wastewater treatment process is proposed. The objective is to minimize the cost of pump operations and maintenance. A neural network algorithm is applied to model performance of the pumps using the data collected at a municipal wastewater treatment plant. The discrete-state Markov process is utilized to develop a model of maintenance decisions. The developed pump performance and maintenance models are integrated into a scheduling model. A hierarchical particle swarm optimization algorithm is designed to solve the proposed scheduling model. The concepts developed in this paper are illustrated with two case studies.",

keywords = "Cost optimization, Data mining, Energy savings, Particle swarm optimization, Pump system, Scheduling",

author = "Zijun Zhang and Xiaofei He and Andrew Kusiak",

year = "2015",

month = apr,

doi = "10.1016/j.engappai.2015.01.003",

language = "English",

volume = "40",

pages = "37--46",

journal = "Engineering Applications of Artificial Intelligence",

issn = "0952-1976",

publisher = "Elsevier Ltd.",

}

TY - JOUR

T1 - Data-driven minimization of pump operating and maintenance cost

AU - Zhang, Zijun

AU - He, Xiaofei

AU - Kusiak, Andrew

PY - 2015/4

Y1 - 2015/4

N2 - A data-driven model for scheduling pumps in a wastewater treatment process is proposed. The objective is to minimize the cost of pump operations and maintenance. A neural network algorithm is applied to model performance of the pumps using the data collected at a municipal wastewater treatment plant. The discrete-state Markov process is utilized to develop a model of maintenance decisions. The developed pump performance and maintenance models are integrated into a scheduling model. A hierarchical particle swarm optimization algorithm is designed to solve the proposed scheduling model. The concepts developed in this paper are illustrated with two case studies.

AB - A data-driven model for scheduling pumps in a wastewater treatment process is proposed. The objective is to minimize the cost of pump operations and maintenance. A neural network algorithm is applied to model performance of the pumps using the data collected at a municipal wastewater treatment plant. The discrete-state Markov process is utilized to develop a model of maintenance decisions. The developed pump performance and maintenance models are integrated into a scheduling model. A hierarchical particle swarm optimization algorithm is designed to solve the proposed scheduling model. The concepts developed in this paper are illustrated with two case studies.

KW - Cost optimization

KW - Data mining

KW - Energy savings

KW - Particle swarm optimization

KW - Pump system

KW - Scheduling

UR - http://www.scopus.com/inward/record.url?scp=84923373021&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84923373021&origin=recordpage

U2 - 10.1016/j.engappai.2015.01.003

DO - 10.1016/j.engappai.2015.01.003

M3 - RGC 21 - Publication in refereed journal

SN - 0952-1976

VL - 40

SP - 37

EP - 46

JO - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

ER -

Data-driven minimization of pump operating and maintenance cost

Abstract

UN SDGs

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

ECS: Scheduling Power Production of Hybrid Power Systems with Data Mining and Computational Intelligence

Cite this

Data-driven minimization of pump operating and maintenance cost

Abstract

UN SDGs

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

ECS: Scheduling Power Production of Hybrid Power Systems with Data Mining and Computational Intelligence

Cite this