According to the imbalance between exploration and exploitation, susceptibility to local optima, and low search efficiency of metaheuristic algorithms, a hybrid slime mould genetic algorithm based on spatial attenuation self-diffusion mechanism if presented. The algorithm uses genetic algorithm as the basic structure, and guides individuals to search in the solution space by recombining features through three operations: selection, crossover, and mutation. Firstly, it introduces oscillation-contraction mechanism with characteristics of both positive-negative feedback and random walking as crossover operators to enhance both global and local search capabilities. Secondly, a self-diffusion mechanism based on spatial decay is proposed as a mutation operator. This mechanism guides the diffusion motion using a spatial scale which decreases over the algorithm's lifecycle, promoting diversity in the early stages and effective exploration of neighborhood information in the later stages. Finally, a discriminative control strategy is introduced to adaptively adjust the algorithm's parameters based on the distribution deviation of the population fitness. This strategy helps balance the exploration and exploitation capabilities of the algorithm. To validate the algorithm's performance, experiments are conducted on two publicly available benchmark test sets: IEEE CEC2017 and IEEE CEC2021. The results demonstrate that the proposed algorithm effectively balances exploration and exploitation capabilities and exhibits superior optimization performance compared with other 23 different types of algorithms.

针对目前常见的元启发式算法面临勘探与开发不平衡、优化性能不稳定等问题, 提出一种基于空间衰减自扩散机制的黏菌遗传混合算法SMAGA, 以遗传算法为基准结构, 通过选择、交叉和变异3项操作重组特征引导个体在解空间内搜索。SMAGA首先设计具有正负反馈和随机游走特性的振荡收缩机制作为交叉算子, 用来增强算法的全局搜索能力和局部搜索能力。然后, 提出一种基于空间衰减的自扩散机制作为算法的变异算子。该机制使用随算法生命周期衰减的空间尺度, 引导自身进行扩散运动, 在算法前期增强多样性, 在算法后期有效挖掘可行解的邻域信息。最后, 提出一种判别式控制策略, 根据群体适应度的分布偏差, 自适应地调整算法的参数, 进而平衡算法的勘探能力和开发能力。为验证算法的性能, 分别在IEEE CEC2017和IEEE CEC2021基准测试集上展开实验, 结果表明, 与其他23种不同类型算法相比, 所提算法能够有效地平衡算法的勘探能力和开发能力, 至少存在1个数量级的优化精度差异, 有望高效地解决复杂优化问题。