A novel adaptive 3-stage hybrid teaching-based differential evolution algorithm for frequency-constrained truss designs

This study proposes an adaptive 3-stage hybrid teaching-based differential evolution (ATDE) algorithm to deal with sizing and layout frequency-constrained truss designs more efficiently. The optimization process is divided into 3 stages, and suitable mutation formulae are applied adaptively in each stage. A novel operator inspired by the teaching phase of teaching learning based optimization (TLBO) is introduced in the early stage with a modified 'DE/rand/1', and two other adjusted DE formulae are appropriately executed in later stages to provide a straightforward yet better exploration-exploitation-balanced mutation scheme. A gradually-shrinking mechanism is suggested to make the mutations parameter-free as well as improve the searching ability. In addition, as the enhanced mutation phase is more likely to generate promising mutants, an elitist selection technique allowing only best individuals to survive is employed to accelerate the evolution process. Various weight minimization benchmark truss examples are performed to validate the effectiveness and robustness of the pro-posed method. Obtained results show ATDE to be more efficient than other recent advanced methods in the literature. The code of ATDE is publicly available at https://github.com/HuyMax/ATDE-Truss-Frequency.