【摘要】 针对标准樽海鞘群算法存在的计算精度不足、易陷入局部停滞等缺陷，提出一种多策略融合的樽海鞘群算法。在初始化阶段，引入线性同余法随机发生器；利用野马算法优化樽海鞘领导者位置；采用金豺算法改进樽海鞘种群追随机制。通过测试函数寻优对比实验，证明多策略融合的樽海鞘群算法相比于其他智能算法在鲁棒性与稳定性方面均有显著提升。将多策略融合的樽海鞘群算法应用到含瓦斯煤破裂过程信号特征识别，实验结果表明：提出的含瓦斯煤破裂过程信号特征识别模型具有更好的表现，准确率可达93.33%,相比其他识别模型，识别率更高。更多还原

【Abstract】 Aiming at the shortcomings of salp swarm algorithms, such as insufficient calculation accuracy and ease to fall into local optimum, an improved salp swarm algorithm with multi-strategy integtation is proposed. In the initialization stage, the linear congruence random generators is introduced. The wild horse optimization algorithm is used for improving the leader’s position, and the following mechanism of salp swarm algorithm is improved by using golden jackal optimization. Through the comparison of test function optimization experiments, it is proved that the improved salp swarm algorithm based on multi-strategy integration has a significant improvement in robustness and stability compared with other intelligent algorithms. The improved salp swarm algorithm with multi-strategy integration is applied to the signal feature identification of the gas bearing coal fracture process. The experimental results show that the proposed signal feature identification model of the gas bearing coal fracture process has a better performance, with an accuracy rate of 93.33%. Compared with other identification models, the identification rate is higher.更多还原