Autoconfiguration of a Vibration-Based Anomaly Detection System with Sparse a-priori Knowledge Using Autoencoder Networks
Autoconfiguration of a Vibration-Based Anomaly Detection System with Sparse a-priori Knowledge Using Autoencoder Networks
复制标题
DOI：
10.1007/978-3-662-62138-7_52
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
J. Hillenbrand;J. Fleischer
中科院分区：
文献类型：
--
作者：
J. Hillenbrand;J. Fleischer
本文提出了一种方法，机器部件监督很少或没有先验知识的机器，操作条件和磨损行为。提出了一种基于自动编码器网络和聚类的无监督学习方法的混合方法，用于识别机器状态和可能的故障前异常。为了科普信息稀疏性，无监督方法的模型参数是根据数据分布和物理动机自动推导的。该方法在人工引入的轴承故障数据集上进行了验证。聚类结果表明，该方法在振动数据状态监测中具有普遍适用性。
This paper presents a method for machine component supervision with little to none prior knowledge of the machine, operating conditions and wear behavior. A hybrid approach based on unsupervised learning methods, consisting of an autoencoder network and clustering, to identify machine states and possible failure preceding anomalies is proposed. In order to cope with information sparsity, the model parameters of the unsupervised methods are derived automatically based on data distribution and a physical motivation. The approach was validated on a dataset of artificially introduced bearing faults. The gained clustering results show a general usability of the approach for condition monitoring with vibration data.