Multi-objective optimisation of sewer maintenance scheduling. Issue 3 (6th May 2022)

• Record Type: Journal Article
• Authors: Draude, Sabrina; Keedwell, Ed; Kapelan, Zoran; Hiscock, Rebecca
• Is Part Of: Journal of hydroinformatics. Volume 24:Issue 3(2022)
• Page Start: 574
• Page End: 589
• Publication Date: 2022-05-06
• Subjects: multi-objective optimisation -- planned maintenance scheduling -- sewer system; Hydrology -- Data processing -- Periodicals; Geographic information systems -- Periodicals; Geographic information systems; Hydrology -- Data processing; Electronic journals; Periodicals; 551.480285
• DOI: 10.2166/hydro.2022.149
• Languages: English
• ISSNs: 1464-7141

Abstract

Abstract: Effective functioning of sewer systems is critical for the everyday life of people in the urban environment. This is achieved, among other things, by the means of regular, planned maintenance of these systems. A large water utility would normally have several maintenance teams (or crews) at their disposal who can perform related jobs at different locations in the company area and with different levels of priority. This paper presents a new methodology for the optimisation of related maintenance schedules resulting in clear prioritisation of the ordering of maintenance tasks for crews. The scheduling problem is formulated as a multi-objective optimisation problem with the following three objectives, namely the minimisation of the total maintenance cost, the minimisation of travel times of maintenance teams and the maximisation of the job's priority score, all over a pre-defined scheduling horizon. The optimisation problem is solved using the Nondominated Sorting Genetic Algorithm-II (NSGA-II) optimisation method. The results obtained from a real-life UK case study demonstrate that the new methodology can determine optimal, low-cost maintenance schedules in a computationally efficient manner when compared to the corresponding existing company schedules. Daily productivity of maintenance teams in terms of number of jobs completed improved by 26% when the methodology was applied to scheduling in the case study. Given this, the method has the potential to be applied within water utilities and the water utility Welsh Water (Dŵr Cymru Welsh Water (DCWW)) is currently implementing it into their systems. HIGHLIGHTS: A new methodology for optimised scheduling of maintenance activities in sewer systems is presented. The new methodology is capable of determining optimal, low-cost maintenance schedules that are superior to the existing ones. When compared to existing company schedules, the new methodology has increased the daily productivity of maintenance teams in terms of jobs completed daily per crew.