A modified adaptive butterfly optimization algorithm is established with the aim of addressing the “early search blindness” and the relatively poor adaptability of the sensory modality. A normal‐distribution‐based model and a Weibull‐distribution‐based adaptive model of sensory modalities are respectively proposed for the global search process and iteration process. Among them, the Weibull‐distribution‐based adaptive model of sensory modalities is mainly manifested as the c value, that is, the adaptive change trend based on the Weibull model. The performance of the modified butterfly optimization algorithm is validated using a 14‐benchmark test function and compared with performances of some latest algorithms. The experimental results indicate that the modified algorithm performs competitively in terms of accuracy and stability. Following the experiment, the modified algorithm is further tested by running a support‐vector‐machine prediction model based on engineering data of a pipe belt conveyor's flat‐pipe/pipe‐flat transition segment. The results of the modified algorithm are then compared with test‐run outcomes of the back‐propagation prediction model and KCV‐SVM model. The results show that the prediction error is well within 10%, demonstrating the method's competence as a reliable reference for future designs of pipe belt conveyors.

中文翻译：

---

一种改进的蝶形优化算法：一种用于全局优化的自适应算法和支持向量机

建立了一种改进的自适应蝶形优化算法，以解决“早期搜索失明”和感觉模态适应性较差的问题。针对全局搜索过程和迭代过程，分别提出了一种基于正态分布的模型和一个基于威布尔分布的感觉模态自适应模型。其中，基于Weibull分布的感觉模态自适应模型主要表现为c值，即基于Weibull模型的自适应变化趋势。改进的蝶形优化算法的性能使用14基准测试函数进行了验证，并与某些最新算法的性能进行了比较。实验结果表明，改进后的算法在准确性和稳定性上具有竞争优势。实验之后，基于管带式输送机的平管/管平过渡段的工程数据运行支持向量机预测模型，进一步测试了修改后的算法。然后将修改后的算法的结果与反向传播预测模型和KCV-SVM模型的测试运行结果进行比较。结果表明，预测误差在10％以内，证明了该方法的能力，可作为未来管道输送机设计的可靠参考。然后将修改后的算法的结果与反向传播预测模型和KCV-SVM模型的测试运行结果进行比较。结果表明，预测误差在10％以内，证明了该方法的能力，可作为未来管道输送机设计的可靠参考。然后将修改后的算法的结果与反向传播预测模型和KCV-SVM模型的测试运行结果进行比较。结果表明，预测误差在10％以内，证明了该方法的能力，可作为未来管道输送机设计的可靠参考。