|
Maintenance workforce optimisation in a process industry using differential evolution |
|---|---|
| รหัสดีโอไอ | |
| Creator | Sunday Ayoola Oke |
| Title | Maintenance workforce optimisation in a process industry using differential evolution |
| Contributor | Desmond Eseoghene Ighravwe, Kazeem Adekunle Adebiyi |
| Publisher | Asia-Pacific Journal of Science and Technology |
| Publication Year | 2562 |
| Journal Title | Asia-Pacific Journal of Science and Technology |
| Journal Vol. | 24 |
| Journal No. | 1 |
| Page no. | 1-26 |
| Keyword | Maintenance costs, production volume, meta-heuristics, process industry, weighted additive fuzzy goal programming |
| URL Website | https://www.tci-thaijo.org/index.php/APST/index |
| Website title | https://www.tci-thaijo.org/index.php/APST/article/view/55442 |
| ISSN | 2539-6293 |
| Abstract | In the past few years, differential evolution (DE) algorithms have been applied to solve system optimisation problems. Optimisation of workforce variables is a necessary requirement to make maintenance workforce planning. Since the effective control and monitoring of major system losses is tied to maintenance, the competent historical performance and potential of DE to optimise maintenance workforce variables has strongly inspired this work. The workforce optimisation structure depends on computations involving the following performance parameter: Production line availability, workforce size changes, cost of service rate improvement, workforce bonuses as well as penalty costs and then cost of spare parts. The developed framework used DE algorithm to optimise workforce including production and maintenance variables in an integrated framework. The model incorporates nonlinear integer model and weighted additive fuzzy goal programming model. The DE algorithm was used in generating Pareto solution for maintenance and production variables. The reliability as well as the effectiveness of the presented method was verified using practical real-life data from a process industry operating in a developing country. The obtained results showed that DE algorithm can generate accurate results with a fast convergence rate and good stability as genetic algorithm and particle swarm optimisation algorithm. The study could be replicated in other process industries such as drinks manufacturing. |
