Structural optimization using multi-objective modified adaptive symbiotic organisms search

Multiple objective structural optimization is a challenging problem in which suitable optimization methods are needed to find optimal solutions. Therefore, to answer such problems effectively, a multi-objective modified adaptive symbiotic organisms search (MOMASOS) with two modified phases is planned along with a normal line method as an archiving technique for designing of structures. The proposed algorithm consists of two separate improved phases including adaptive mutualism and modified parasitism phases. The probabilistic nature of mutualism phase of MOSOS lets design variables to have higher exploration and higher exploitation simultaneously. As search advances, a stability between the global search and a local search has a significant effect on the solutions. Therefore, an adaptive mutualism phase is added to the offer MOASOS. Also, the parasitism phase of MOSOS offers over exploration which is a major issue of this phase. The over exploration results in higher computational cost since the majority of the new solutions gets rejected due to inferior objective functional values. In consideration of this issue, the parasitism phase is upgraded to a modified parasitism phase to increase the possibility of getting improved solutions. In addition, the proposed changes are comparatively simple and do not need an extra parameter setting for MOSOS. For the truss problems, mass minimization and maximization of nodal deflection are considered as objective functions, elemental stresses are considered as behavior constraints and (discrete) elemental sections are considered as side constraints. Five truss optimization problems validate the applicability of the considered meta-heuristics to solve complex engineering. Also, four constrained benchmark engineering design problems are solved to demonstrate the effectiveness of MOMASOS. The results confirmed that the proposed adaptive mutualism phase and modified parasitism phase with a normal line method as an archiving technique provide superior and competitive results than the former obtained results. (C) 2019 Elsevier Ltd. All rights reserved.