Slime Mould Algorithm-based mutated Chaotic Local Search for global optimization and engineering applications

Swarm intelligence has gained increasing interest, with the Slime Mould Algorithm (SMA) standing out as a promising yet convergence-prone metaheuristic. To address this limitation, we propose an improved variant, called mSMACLS, which integrates a mutated Chaotic Local Search (mCLS) strategy into SMA. The mCLS mechanism selectively perturbs dimensions of the global best solution using chaotic sequences, enhancing local exploitation while maintaining global exploration. We evaluate 10 chaotic maps to identify the most effective configuration and conduct extensive experiments on 23 standard benchmark functions and 10 more complex optimization problems. The proposed algorithm is further validated on 15 challenging benchmark problems from the CEC2017 competition on constrained single-objective optimization. Results show that the Logistic chaotic map provides the best performance within the mCLS framework. Overall, mSMACLS consistently outperforms six well-known metaheuristics across most test cases, demonstrating improved convergence speed and solution quality. Finally, the algorithm’s applicability is tested on 3 real-world engineering design problems, and the results were very encouraging.