%0 Journal Article
%T 直升机齿轮箱故障诊断方法<br>A New Method for Fault Diagnosis of Helicopter Gearbox
%A 李耀华
%A 王星州
%J 机械科学与技术
%D 2018
%X 为有效诊断直升机齿轮箱故障，研究建立了基于直升机齿轮箱振动信号的小波包熵ABC-BP神经网络故障诊断模型。模型以小波波包分析与信息熵分析方法为基础，提取齿轮箱振动信号的小波包熵作为神经网络的特征输入向量，引入人工蜂群优化BP神经网络，将BP神经网络的误差函数作为人工蜂群的适应度，选择适应度最优的个体参数作为神经网络的权值和阈值，不仅降低模型输入维度，还提高了诊断精度。最后基于实验数据进行了验证，结果表明该诊断模型具有较好的故障诊断效果。<br>To improve the fault diagnosis efficiency of helicopter gearbox, the information entropy and ABC-BP neural network are adopted in this paper. Combining wavelet packet and information entropy, the wavelet packet entropy of vibration signal of gearbox is extracted as the characteristic input vector of neural network, then the BP neural network is used for pattern recognition and fault classification of the characteristic parameters of gearbox, and artificial bee colony (ABC) is introduced in the optimization of BP neural network. The error function of BP neural network as the artificial bee colony fitness, individual parameters of optimal fitness degree are choose as the weights and thresholds of neural network. This method not only reduces the model input dimension, but also improves the diagnostic accuracy. Finally, the experimental results show that the diagnosis model has good effect
%K 齿轮箱
%K 小波包
%K 信息熵
%K 人工蜂群
%K BP神经网络
%K 故障诊断&lt
%K br&gt
%K gearbox
%K fault diagnosis
%K vibrations
%K information entropy
%K wavelet packet
%K neural networks
%K artificial bee colony
%K pattern recognition
%K experiments
%K efficiency
%U http://journals.nwpu.edu.cn/jxkxyjs/CN/abstract/abstract7154.shtml