Abstract: To overcome the shortcomings of slow convergence speed, low precision and local optimum for the Dung Beetle Optimizer (DBO) algorithm, dung beetle optimizer algorithm with restricted reverse learning and Cauchy-Gauss variation (SI-DBO) was proposed in this paper. Firstly, Circle mapping was used to initialize the population to make the distribution of the population more uniform and diverse, which improved the convergence speed and optimization accuracy of the algorithm. Secondly, restricted reverse learning was used to update the location of dung beetles to improve their search ability. Finally, the Cauchy-Gauss variation strategy was used to help the population escape from the local optimal location and find the global optimal location. To verify the performance of SI-DBO, simulation experiments were carried out on the test functions and Wilcoxon rank sum test was performed on the experimental results. The algorithm was also used to solve the robot gripper problem. Experimental results show that the SI-DBO achieves higher optimization accuracy and convergence speed than the improved dung beetle optimizer (BWDBO) and Sparrow Search Algorithm (SSA) for the test functions. Meanwhile, the SI-DBO performs better than the Particle Swarm Optimization (PSO) for the robot gripper problem, indicating desirable optimization performance and engineering practicability of the SI-DBO.

Key words: dung beetle optimizer algorithm, restricted reverse learning, Cauchy-Gauss variation, Wilcoxon rank sum test, robot gripper problem

摘要： 针对蜣螂优化（DBO）算法中存在收敛速度慢，精度不高，容易陷入局部最优的问题，提出了一种融入限制反向学习与柯西-高斯变异的蜣螂优化算法（SI-DBO）。首先，用Circle映射初始化种群使种群的分布更加的均匀和具有多样性，该策略提升算法的收敛速度和寻优精度。其次，使用限制反向学习的方式来对蜣螂的位置进行更新，来提升蜣螂的搜索能力。最后，使用柯西-高斯变异策略来帮助种群逃逸出局部最佳位置，寻找全局最佳位置。为了验证SI-DBO的性能，在测试函数上进行了仿真实验并对实验结果进行了Wilcoxon秩和检验，还将该算法用于求解机器人夹持器问题。实验结果表明与改进后的蜣螂优化算法（BWDBO），麻雀搜索算法（SSA）相比，SI-DBO算法在测试函数上均获得了较高的寻优精度和收敛速度，同时在求解机器人夹持器问题时SI-DBO算法效果优于粒子群优化算法（PSO），从而验证了SI-DBO算法具有更好的寻优性能和工程实用性。

关键词: 蜣螂优化算法, 限制反向学习, 柯西-高斯变异, Wilcoxon秩和检验, 机器人夹持器问题