A novel hybrid fick's law algorithm-quasi oppositional-based learning algorithm for solving constrained mechanical design problems

Abstract

In this article, a recently developed physics-based Fick's law optimization algorithm is utilized to solve engineering optimization challenges. The performance of the algorithm is further improved by incorporating quasi-oppositional-based techniques at the programming level. The modified algorithm was applied to optimize the rolling element bearing system, robot gripper, planetary gear system, and hydrostatic thrust bearing, along with shape optimization of the vehicle bracket system. Accordingly, the algorithm realizes promising statistical results compared to the rest of the well-known algorithms. Furthermore, the required number of iterations was comparatively less required to attain the global optimum solution. Moreover, deviations in the results were the least even when other optimizers provided better or more competitive results. This being said that this optimization algorithm can be adopted for a critical and wide range of industrial and real-world challenges optimization.