MGCHMO: A dynamic differential human memory optimization with Cauchy and Gauss mutation for solving engineering problems

The Human Memory Optimization (HMO) algorithm is a newly released metaheuristic algorithm based on humans in 2023, which can effectively solve most optimization problems. However, when dealing with complex optimization problems, HMO has limitations such as insufficient convergence accuracy and susceptibility to local optimal solutions. To this end, we integrated chaotic mapping, Cauchy mutation, Gaussian mutation, differential mutation, and parameter dynamic adjustment strategies into the original algorithm and developed an enhanced MGCHMO algorithm. Firstly, in the initialization phase of the MGCHMO, the Tent mapping chaotic mapping mechanism is introduced to enhance the diversity and search ability of the initial population through the traversal and randomness characteristics of chaos. Secondly, in the memory generation phase, we added the Cauchy mutation strategy, which effectively expanded the search range of the algorithm, helped the algorithm escape from local optima, and explored a broader solution space. Then, during the recall phase, Gaussian mutation and differential mutation are added. Among them, Gaussian mutation enables the algorithm to perform more refined searches within a local range. Differential mutation, on the other hand, guides the algorithm to explore towards a more optimal solution through the information of individual differences. Finally, the parameters of the algorithm are dynamically adjusted to enhance its optimization performance, ensuring that the algorithm maintains optimal search performance at different phases, thereby accelerating the convergence process and improving the quality of the solution.

To verify the optimization performance of MGCHMO, we conducted a series of detailed performance experiments on three different test sets: CEC2017, CEC2020, and CEC2022. The results showed that MGCHMO has higher convergence and stability. In addition, we tested the applicability of MGCHMO on 30 engineering examples, topology optimization design, aerospace orbit optimization, and curve shape optimization, and the results further demonstrated the significant application capability and feasibility of MGCHMO.