An Encoder-Decoder Based Approach for Anomaly Detection with Application in Additive Manufacturing
An Encoder-Decoder Based Approach for Anomaly Detection with Application in Additive Manufacturing
复制标题
DOI：
10.1109/icmla.2019.00171
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Baihong Jin;Yingshui Tan;A. Nettekoven;Yuxin Chen;U. Topcu;Yisong Yue;A. Sangiovanni-Vincentelli
中科院分区：
文献类型：
--
作者：
Baihong Jin;Yingshui Tan;A. Nettekoven;Yuxin Chen;U. Topcu;Yisong Yue;A. Sangiovanni-Vincentelli
我们提出了一种新的无监督深度学习方法，该方法利用编码器-解码器架构来检测工业制造过程中收集的顺序传感器数据中的异常。我们的方法的目的不仅是检测是否存在一个异常在给定的时间步，但也要预测接下来会发生什么（顺序）的过程。我们在从真实世界的增材制造（AM）测试平台收集的数据集上展示了我们的方法。该数据集包含在正常条件和合成异常情况下收集的红外（IR）图像。我们表明，我们的编码器-解码器模型是能够识别注入的异常，在现代AM制造过程中，在一个无监督的方式。此外，我们的方法还提供了有关制造过程中测试台温度不均匀性的提示，这在实验之前是未知的。
We present a novel unsupervised deep learning approach that utilizes an encoder-decoder architecture for detecting anomalies in sequential sensor data collected during industrial manufacturing. Our approach is designed to not only detect whether there exists an anomaly at a given time step, but also to predict what will happen next in the (sequential) process. We demonstrate our approach on a dataset collected from a real-world Additive Manufacturing (AM) testbed. The dataset contains infrared (IR) images collected under both normal conditions and synthetic anomalies. We show that our encoder-decoder model is able to identify the injected anomalies in a modern AM manufacturing process in an unsupervised fashion. In addition, our approach also gives hints about the temperature non-uniformity of the testbed during manufacturing, which was not previously known prior to the experiment.