Application of an Improved Differential Evolution Algorithm in Practical Engineering

Abstract

The differential evolution algorithm, as a simple yet effective random search algorithm, often faces challenges in terms of rapid convergence and a sharp decline in population diversity during the evolutionary process. To address this issue, an improved differential evolution algorithm, namely the multi-population collaboration improved differential evolution (MPC-DE) algorithm, is introduced in this article. The algorithm proposes a multi-population collaboration mechanism and a two-stage mutation operator. Through the multi-population collaboration mechanism, the diversity of individuals involved in mutation is effectively controlled, enhancing the algorithm's global search capability. The two-stage mutation operator efficiently balances the requirements of the exploration and exploitation stages. Additionally, a perturbation operator is introduced to enhance the algorithm's ability to escape local optima and improve stability. By conducting comprehensive comparisons with 15 well-known optimization algorithms on CEC2005 and CEC2017 test functions, MPC-DE is thoroughly evaluated in terms of solution accuracy, convergence, stability, and scalability. Furthermore, validation on 57 real-world engineering optimization problems in CEC2020 demonstrates the robustness of the MPC-DE. Experimental results reveal that, compared to other algorithms, MPC-DE exhibits superior convergence accuracy and robustness in both constrained and unconstrained optimization problems. These research findings provide strong support for the widespread applicability of multi-population collaboration in differential evolution algorithms for addressing practical engineering problems.