摘要
将卷积神经网络引入风机故障检测领域,设计了一种一维卷积神经网络的结构,并和Soft-Max分类器相结合构造了一种双层智能诊断架构。一维卷积神经网络用于行星齿轮箱数据的特征提取,Soft-Max分类器对提取的特征进行分类。与传统智能算法相比,该方法具有训练样本少,可直接使用原始数据训练网络;计算效率高,可以适应实时诊断的需要。试验结果证明,该方法可以有效地诊断出不同工况下的行星齿轮箱中的齿轮故障。
The convolutional neural network was introduced into the field of fan fault detection for the first time,a new method based on one dimensional convolution neural network( CNNs) and Soft-Max classifier was proposed,which was applied to the fault diagnosis of gearbox planetary gear under different operating conditions. The structure of the network was a double layer structure,the improved convolutional neural network was used for feature extraction,and the Soft-Max classifier was used to classify the health status of the signal. Compared with the traditional intelligent algorithm,this method had the advantages of fewer training samples,direct training of network with raw data,high computational efficiency,and it can meet the needs of real-time diagnosis. The data of multi operating conditions are fused and verified by experiments. The experimental results showed that the method can effectively diagnose the gear faults in planetary gear box under different working conditions.
作者
李东东
王浩
杨帆
郑小霞
周文磊
邹胜华
LI Dongdong;Hao;YANGFan;ZHENG Xiaoxia;ZHOUWenlei;ZOUShenghua(School of Electrical Engineering,Shanghai University of Electric of Power,Shanghai 200090,China;Shanghai Higher Institution Engineering Research Center of High Efficiency ElShanghai 200090,China;School of Atomation Engineering,Shanghai University of Electric of Power,Shanghai 200090,China;Jilin Power Supply Company,State Grid,Jilin 132000,China;Nortlieast of Jiangxi Power Supply Branch,State Grid,Leping 333300,China)
出处
《电机与控制应用》
2018年第6期80-87,108,共9页
Electric machines & control application
基金
国家自然科学基金项目(51407114
51507098)
上海市科学技术委员会资助项目(13DZ2251900
10DZ2273400)
上海市"曙光计划"资助项目(15SG50)