摘要
针对带式输送机电动滚筒故障状态难以识别,造成诊断精度不高的问题,提出了一种改进沙猫群优化算法(ISCSO)、变分模态分解(VMD)和门控循环单元(GRU)相结合的带式输送机电动滚筒故障诊断模型。在沙猫优化算法(SCSO)中引入Logistic-tent混沌映射、螺旋搜索、麻雀警戒机制改进算法。使用改进的SCSO优化VMD获得音频信号的固有模态函数(IMF)分量,再基于Pearson相关系数与复合缩放排列熵(CZPE)筛选并计算有效IMF分量的CZPE值进行特征重构,提升GRU的诊断精度。同时利用ISCSO算法对GRU网络参数进行优化。通过实验对比,结果表明ISCSO-VMD-GRU模型故障诊断准确率达到99.69%,相较于其他模型性能提升效果显著。
Aiming at the problem that the fault state of the electric roller of the belt conveyor is difficult to identify,resulting in low diagnosis accuracy,an improved sand cat swarm optimization algorithm(ISCSO),variational mode decomposition(VMD)and gated loop unit(GRU)are proposed.Combined fault diagnosis model of belt conveyor electric roller.The improved algorithm of Logistic-tent chaotic mapping,spiral search,and sparrow alert mechanism is introduced into the Sand Cat Optimization Algorithm(SCSO).Use the improved SCSO to optimize VMD to obtain the intrinsic mode function(IMF)component of the audio signal,and then filter and calculate the CZPE value of the effective IMF component based on Pearson correlation coefficient and composite scaling permutation entropy(CZPE)for feature reconstruction to improve the diagnosis of GRU accuracy.At the same time,the ISCSO algorithm is used to optimize the GRU network parameters.Through experimental comparison,the results show that the fault diagnosis accuracy of the ISCSO-VMD-GRU model reaches 99.69%,which has a significant performance improvement compared to other models.
作者
许南南
李敬兆
叶桐舟
XU Nannan;LI Jingzhao;YE Tongzhou(School of Electrical and Information Engineering,Anhui University of Science and Technology,Huainan Anhui 232000,China;School of Mechanical Engineering,Anhui University of Science and Technology,Huainan Anhui 232000,China)
出处
《佳木斯大学学报（自然科学版）》
CAS
2024年第5期51-56,共6页
Journal of Jiamusi University：Natural Science Edition
基金
国家自然科学基金项目(52374154)
淮南市科技计划项目(2021A243)。
