Published on Thu May 05 2016

ODE - Augmented Training Improves Anomaly Detection in Sensor Data from Machines

Mohit Yadav, Pankaj Malhotra, Lovekesh Vig, K Sriram, Gautam Shroff

Machines of all kinds from vehicles to industrial equipment are increasingly instrumented with hundreds of sensors. Using such data to detect anomalousbehaviour is critical for safety and efficient maintenance. However, anomalies rarely and with great variety in such systems, so there is often insufficient data to build reliable detectors.

0
0
0
Abstract

Machines of all kinds from vehicles to industrial equipment are increasingly instrumented with hundreds of sensors. Using such data to detect anomalous behaviour is critical for safety and efficient maintenance. However, anomalies occur rarely and with great variety in such systems, so there is often insufficient anomalous data to build reliable detectors. A standard approach to mitigate this problem is to use one class methods relying only on data from normal behaviour. Unfortunately, even these approaches are more likely to fail in the scenario of a dynamical system with manual control input(s). Normal behaviour in response to novel control input(s) might look very different to the learned detector which may be incorrectly detected as anomalous. In this paper, we address this issue by modelling time-series via Ordinary Differential Equations (ODE) and utilising such an ODE model to simulate the behaviour of dynamical systems under varying control inputs. The available data is then augmented with data generated from the ODE, and the anomaly detector is retrained on this augmented dataset. Experiments demonstrate that ODE-augmented training data allows better coverage of possible control input(s) and results in learning more accurate distinctions between normal and anomalous behaviour in time-series.

Tue Oct 27 2020
Machine Learning
Smart Anomaly Detection in Sensor Systems: A Multi-Perspective Review
Anomaly detection is concerned with identifying data patterns that deviate from the expected behaviour. This is an important research problem, due to its broad set of application domains. We review state-of-the-art methods that may be employed to detect anomalies in sensor systems.
0
0
0
Mon Dec 30 2019
Machine Learning
A general anomaly detection framework for fleet-based condition monitoring of machines
Machine failures decrease up-time and can lead to extra repair costs or even human casualties and environmental pollution. Recent condition monitoring techniques use artificial intelligence in an effort to avoid time-consuming manual analysis. This work proposes an unsupervised, generic, anomaly detection framework.
0
0
0
Thu Nov 12 2020
Machine Learning
Real-World Anomaly Detection by using Digital Twin Systems and Weakly-Supervised Learning
A growing amount of monitored data in the Industry 4.0 context requires strong and reliable anomaly detection techniques. In this paper, we present novel weakly-supervised approaches to anomaly detection for industrial settings. The approaches make use of a Digital Twin to generate a training dataset.
0
0
0
Sat Aug 03 2019
Machine Learning
Developing an Unsupervised Real-time Anomaly Detection Scheme for Time Series with Multi-seasonality
On-line detection of anomalies in time series is a key technique used in robotic system monitoring, smartSensor networks and data center security. The increasing diversity of data sources and the variety of demands make this task more challenging than ever.
0
0
0
Mon Apr 09 2018
Machine Learning
Anomaly Detection for Industrial Big Data
Systems are increasingly monitored by arrays of sensors returning time-series data. An obvious use for these data is real-time systems condition monitoring and time to failure analysis.
0
0
0
Mon Aug 10 2020
Machine Learning
ARCADe: A Rapid Continual Anomaly Detector
Continual learning and anomaly detection have separately been well-studied in previous works, but their intersection remains rather unexplored. We propose an approach to train neural networks to be robust against the major challenges of this new learning problem.
0
0
0