College of Mechanical and Transportation Engineering, Taiyuan University of Technology
National Local Joint Engineering Laboratory of Mining Fluid Control

针对带式输送机音频数据中存在大量冗余的问题,提出了一种基于改进蜜獾算法(IHBA)优化支持向量机(SVM)的带式输送机关键音频数据识别方法。提取音频数据的梅尔频率倒谱系数作为特征;采用Tent混沌映射增加种群多样性,引入新的密度因子和黄金正弦机制来克服蜜獾算法(HBA)易陷入局部最优、收敛速度慢及寻优精度低等缺陷,并通过标准测试函数的仿真实验,验证了IHBA性能。采用IHBA优化SVM的参数,将梅尔频率倒谱系数特征输入IHBA-SVM模型中进行识别。结果表明,IHBA-SVM模型能够有效提高带式输送机关键音频数据的识别率。

To address the great redundancy in the audio data of belt conveyors, an identifying method for key audio data of belt conveyors was proposed based on the improved Honey Badger Algorithm ( IHBA) and optimized support vector machines (SVM). The Mel Frequency Cepstral Coefficients of the audio data were extracted as features; The Tent chaos mapping was used to increase population diversity, and new density factor and golden sine mechanism were introduced to overcome the defects of the Honey Badger Algorithm (HBA), such as easy to fall into local optimum, slow convergence speed, and low accuracy in finding the best solution. The performance of IHBA was verified through simulation experiments using standard test functions. The parameters of SVM were optimized by IHBA, and the Mel Frequency Cepstral Coefficients were input into the IHBA-SVM model for identification. The results show that the IHBA-SVM model can effectively improve the identification rate of key audio data from belt conveyors.

中央引导地方科技发展资金项目(YDZJSX2021A023);国家自然科学基金(52174147);山西省科技创新领军人才团队项目(202204051002003);山西省重点研发计划项目(202102100401004)

吴启航,李军霞,刘少伟,等.带式输送机关键音频数据识别研究[J].煤炭工程,2024,56(5):145-151.