A multi-skilled workforce optimisation in maintenance logistics networks by multi-thread simulated annealing algorithms

Abstract

The sustainability of service and manufacturing operations rely heavily on the availability of equipment and assets. High availability of assets can be achieved with effective maintenance strategies. In this direction, we study a multi-skilled workforce planning problem to establish a resilient maintenance service network for high-value assets. We improve the efficiency of the maintenance network by optimising the workforce capacity in repair shops and achieving workforce heterogeneity by cross-training. As a solution strategy, we develop a two-stage iterative heuristic algorithm. At the first stage, the set of all feasible cross-training policies is effectively and systematically searched via a state-of-art multi-thread simulated annealing (MTSA) metaheuristic to find a policy(ies) that achieves the minimum cost. Further, the developed MTSA algorithm is enhanced with the multi-neighbourhood feature to escape from local optimality and implemented via parallel programming techniques. In the second stage, workforce capacity and spare parts inventory levels are optimised for the cross-training policy found at the first stage by a queuing approximation and a greedy heuristic. The MTSA obtains the lowest cost in 91 cases out of 128 compared to genetic algorithm (GA), variable neighbourhood search (VNS), an improved single-thread simulated annealing algorithm (SA) and integer programming-based clustering (IPBC) algorithms.

Keywords:

• maintenance logistics
• repair shop
• cross-training
• multi-thread simulated annealing
• queuing approximation
• parallel programming

Disclosure statement

No potential conflict of interest was reported by the author(s).

Supplemental data

Supplemental data for this article can be accessed at https://doi.org/10.1080/00207543.2020.1735665.

Notes

1 All computer codes for developed algorithms are available at: https://github.com/mahiratmis/mtsa

2 From now on we use server instead of workforce to be consistent.

3 Fixed values of decision variables will be over-lined by bar $\overline{}$ notation.

4 See Appendix 2 for the proof.

5 All input and output datasets used are available at: https://github.com/mahiratmis/mtsa.

6 We provide optimality gap results for all cases as a supplementary material.