An enhanced reliability-oriented workforce planning model for process industry using combined fuzzy goal programming and differential evolution approach

• Main Authors: D. E. Ighravwe, S. A. Oke, K. A. Adebiyi
• Format: Article
• Language: English
• Published: Islamic Azad University 2017-08-01
• Series: Journal of Industrial Engineering International
• Subjects: Returns-on-workforce investment; Fuzzy goal programming; Meta-heuristics; Maintenance workforce planning; Manufacturing system
• Online Access: http://link.springer.com/article/10.1007/s40092-017-0223-9
• ISSN: 1735-5702; 2251-712X

Abstract This paper draws on the “human reliability” concept as a structure for gaining insight into the maintenance workforce assessment in a process industry. Human reliability hinges on developing the reliability of humans to a threshold that guides the maintenance workforce to execute accurate decisions within the limits of resources and time allocations. This concept offers a worthwhile point of deviation to encompass three elegant adjustments to literature model in terms of maintenance time, workforce performance and return-on-workforce investments. These fully explain the results of our influence. The presented structure breaks new grounds in maintenance workforce theory and practice from a number of perspectives. First, we have successfully implemented fuzzy goal programming (FGP) and differential evolution (DE) techniques for the solution of optimisation problem in maintenance of a process plant for the first time. The results obtained in this work showed better quality of solution from the DE algorithm compared with those of genetic algorithm and particle swarm optimisation algorithm, thus expressing superiority of the proposed procedure over them. Second, the analytical discourse, which was framed on stochastic theory, focusing on specific application to a process plant in Nigeria is a novelty. The work provides more insights into maintenance workforce planning during overhaul rework and overtime maintenance activities in manufacturing systems and demonstrated capacity in generating substantially helpful information for practice.