Preprocessing-Free Gear Fault Diagnosis Using Small Datasets With Deep Convolutional Neural Network-Based Transfer Learning
Preprocessing-Free Gear Fault Diagnosis Using Small Datasets With Deep Convolutional Neural Network-Based Transfer Learning
复制标题
DOI：
10.1109/access.2018.2837621
复制
发表时间：
2018-01-01
期刊：
影响因子：
3.9
通讯作者：
Tang, Jiong
中科院分区：
文献类型：
--
作者：
Cao, Pei;Zhang, Shengli;Tang, Jiong
齿轮传动的早期诊断一直是一个重大的挑战，因为齿轮故障主要发生在微观结构甚至材料水平，但它们的影响只能在系统水平上间接观察。齿轮故障诊断系统的性能在很大程度上取决于所提取的特征和随后应用的分类器。传统的故障相关特征提取和识别是基于领域专家知识，通过数据预处理，这是特定于系统的，可能不容易推广。另一方面，尽管最近基于深度神经网络的方法具有自适应特征提取和固有分类的特点，但它们通常需要大量的训练数据。针对这些问题，本文提出了一种基于深度卷积神经网络的迁移学习方法。拟议的迁移学习架构由两部分组成;第一部分由预训练的深度神经网络构建，用于从输入中自动提取特征，第二部分是一个完全连接的阶段，用于对需要训练的特征进行分类使用齿轮故障实验数据。使用基准齿轮系统的实验数据的案例分析表明，该方法不仅娱乐预处理自由自适应特征提取，而且只需要一个小的训练数据集。
Early diagnosis of gear transmission has been a significant challenge, because gear faults occur primarily at microstructure or even material level but their effects can only be observed indirectly at a system level. The performance of a gear fault diagnosis system depends significantly on the features extracted and the classifier subsequently applied. Traditionally, fault-related features are extracted and identified based on domain expertise through data preprocessing which are system-specific and may not be easily generalized. On the other hand, although recently the deep neural networks based approaches featuring adaptive feature extractions and inherent classifications have attracted attention, they usually require a substantial set of training data. Aiming at tackling these issues, this paper presents a deep convolutional neural network-based transfer learning approach. The proposed transfer learning architecture consists of two parts; the first part is constructed with a pre-trained deep neural network that serves to extract the features automatically from the input, and the second part is a fully connected stage to classify the features that needs to be trained using gear fault experimental data. Case analyses using experimental data from a benchmark gear system indicate that the proposed approach not only entertains preprocessing free adaptive feature extractions, but also requires only a small set of training data.