An Encoder-Decoder Based Approach for Anomaly Detection with Application in Additive Manufacturing

07/26/2019
by   Baihong Jin, et al.
8

We present a novel unsupervised deep learning approach that utilizes the encoder-decoder architecture for detecting anomalies in sequential sensor data collected during industrial manufacturing. Our approach is designed not only to 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 testbed. The dataset contains images collected under both normal conditions and synthetic anomalies. We show that the encoder-decoder model is able to identify the injected anomalies in a modern manufacturing process in an unsupervised fashion. In addition, it also gives hints about the temperature non-uniformity of the testbed during manufacturing, which is what we are not aware of before doing the experiment.

READ FULL TEXT

page 2

page 5

page 6

research
08/30/2022

Denoising Architecture for Unsupervised Anomaly Detection in Time-Series

Anomalies in time-series provide insights of critical scenarios across a...
research
07/01/2016

LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection

Mechanical devices such as engines, vehicles, aircrafts, etc., are typic...
research
03/21/2022

AnoViT: Unsupervised Anomaly Detection and Localization with Vision Transformer-based Encoder-Decoder

Image anomaly detection problems aim to determine whether an image is ab...
research
06/19/2023

Machine Learning for Real-Time Anomaly Detection in Optical Networks

This work proposes a real-time anomaly detection scheme that leverages t...
research
06/19/2020

Manifolds for Unsupervised Visual Anomaly Detection

Anomalies are by definition rare, thus labeled examples are very limited...
research
06/13/2022

Anomaly Detection and Inter-Sensor Transfer Learning on Smart Manufacturing Datasets

Smart manufacturing systems are being deployed at a growing rate because...
research
06/19/2019

VizADS-B: Analyzing Sequences of ADS-B Images Using Explainable Convolutional LSTM Encoder-Decoder to Detect Cyber Attacks

The purpose of the automatic dependent surveillance broadcast (ADS-B) te...

Please sign up or login with your details

Forgot password? Click here to reset