This paper is a contribution to the research which aims to provide an efficient optimization algorithm for job-shop scheduling problems with multi-purpose machines or MPMJSP. To meet its objective, this paper proposes a new variant of particle swarm optimization algorithm, called GLN-PSO C, which is an extension of the standard particle swarm optimization algorithm that uses multiple social learning topologies in its evolutionary process. GLN-PSOC is a metaheuristic that can be applied to many types of optimization problems, where MPMJSP is one of these types. To apply GLN-PSOC in MPMJSP, a procedure to map the position of particle into the solution of MPMJSP is proposed. Throughout this paper, GLN-PSOC combined with this procedure is named MPMJSP-PSO. The performance of MPMJSP-PSO is evaluated on well-known benchmark instances, and the numerical results show that MPMJSP-PSO performs well in terms of solution quality and that new best known solutions were found in some instances of the test problems. © World Scientific Publishing Co. & Operational Research Society of Singapore.