Tandem Connectionist Anomaly Detection: Use of Faulty Vibration Signals in Feature Representation Learning
Tandem Connectionist Anomaly Detection: Use of Faulty Vibration Signals in Feature Representation Learning
复制标题
串联联结异常检测：在特征表示学习中使用错误振动信号
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Tetsuji Ogawa
中科院分区：
文献类型：
--
作者：
T. Hasegawa;Jun Ogata;M. Murakawa;Tetsuji Ogawa
提出了一种有效利用故障状态数据的方法，以实现对旋转机械的鲁棒、准确的数据驱动异常（故障）检测。虽然在训练过程中使用故障数据通常可以提高异常检测系统的性能，但很难在目标机器上获得足够的样本来训练故障或缺陷。因此，我们利用来自非目标（不同类型）机器的现有数据进行特征表示学习，以改进目标机器的异常检测。具体来说，深度神经网络（dnn）被训练来区分非目标机器的正常和故障状态，用于提取特征。然后将提取的特征作为基于高斯混合模型（GMMs）的异常检测器的输入。这种结构被称为DNN/GMM串联连接异常检测。使用实际风力涡轮机部件的振动信号进行的实验比较表明，开发的串联连接系统比现有系统产生了显著的改进，并且表示学习在机器类型的差异方面表现良好。
An effective use of faulty-state data is proposed to achieve robust, accurate data-driven anomaly (fault) detection for rotating machine. Although using faulty data in the training process generally can improve the performance of anomaly detection system, it is rare to obtain enough samples to train failures or defects on a target machine. We therefore utilize the existing data from non-target (different-type) machines for feature representation learning to improve anomaly detection for the target machine. Specifically, deep neural networks (DNNs) that are trained to discriminate the normal and faulty states of the non-target machines are used to extract features. The extracted features are then taken as inputs to an anomaly detector based on Gaussian mixture models (GMMs). This architecture is called DNN/GMM tandem connectionist anomaly detection. Experimental comparisons using vibration signals from actual wind turbine components demonstrated that the developed tandem connectionist system yielded significant improvements over existing systems, and that the representation learning performed robustly with respect to differences in machine types.
影响因子：
8.7
作者：
P. Cross;Xiandong Ma
通讯作者：
P. Cross;Xiandong Ma