Channa argus optimizer for solving numerical optimization and engineering problems.

In this study, we introduce the Channa Argus Optimizer (CAO), a novel swarm-based meta-heuristic algorithm that draws inspiration from the distinctive hunting and escaping behavior observed in Channa Arguses in the natural world. The CAO algorithm mainly emulates the hunting and escaping behavior of Chinna Argus to realize a tradeoff between exploitation and exploration in the solution space and discourage premature convergence. The competitiveness and effectiveness of CAO are validated utilizing 29 typical CEC2017 and 10 CEC2020 unconstrained benchmarks and 5 real-world constrained optimization mechanical engineering issues. The CAO algorithm was tested on CEC2017 and CEC2020 functions and compared with 7 algorithms to evaluate performance. In addition, the CAO algorithm is tested on the CEC2017 benchmark functions with dimensions of 10-D, 30-D, 50-D, and 100-D. It is then compared and evaluated against other algorithms, using the Wilcoxon rank-sum test and Friedman mean rank. Finally, the CAO algorithm is utilized to tackle five intricate engineering problems to show its robustness. These results have demonstrated the effectiveness and potential of the CAO algorithm, yielding outstanding results and ranking first among other algorithms.