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

Abstract

Mechanical devices such as engines, vehicles, aircrafts, etc., are typically instrumented with numerous sensors to capture the behavior and health of the machine. However, there are often external factors or variables which are not captured by sensors leading to time-series which are inherently unpredictable. For instance, manual controls and/or unmonitored environmental conditions or load may lead to inherently unpredictable time-series. Detecting anomalies in such scenarios becomes challenging using standard approaches based on mathematical models that rely on stationarity, or prediction models that utilize prediction errors to detect anomalies. We propose a Long Short Term Memory Networks based Encoder-Decoder scheme for Anomaly Detection (EncDec-AD) that learns to reconstruct 'normal' time-series behavior, and thereafter uses reconstruction error to detect anomalies. We experiment with three publicly available quasi predictable time-series datasets: power demand, space shuttle, and ECG, and two real-world engine datasets with both predictive and unpredictable behavior. We show that EncDec-AD is robust and can detect anomalies from predictable, unpredictable, periodic, aperiodic, and quasi-periodic time-series. Further, we show that EncDec-AD is able to detect anomalies from short time-series (length as small as 30) as well as long time-series (length as large as 500).

Accepted at ICML 2016 Anomaly Detection Workshop, New York, NY, USA, 2016. Reference update in this version (v2)

References in corpus (3)

• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• A Hierarchical Neural Autoencoder for Paragraphs and Documents
• ODE - Augmented Training Improves Anomaly Detection in Sensor Data from Machines

Cited by in corpus (51)

• Deep Learning for Anomaly Detection: A Survey
• Deep Learning for Time Series Anomaly Detection: A Survey
• An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Series
• Multi-Sensor Prognostics using an Unsupervised Health Index based on LSTM Encoder-Decoder
• TimeNet: Pre-trained deep recurrent neural network for time series classification
• Time Series Anomaly Detection for Cyber-Physical Systems via Neural System Identification and Bayesian Filtering
• Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets
• Developing an Unsupervised Real-time Anomaly Detection Scheme for Time Series with Multi-seasonality
• Anomaly Detection for Water Treatment System based on Neural Network with Automatic Architecture Optimization
• Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Version
• RNN-based Early Cyber-Attack Detection for the Tennessee Eastman Process
• Multivariate Time-series Anomaly Detection via Graph Attention Network
• Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals
• Neural Transformation Learning for Deep Anomaly Detection Beyond Images
• Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT
• Atrial Fibrillation Detection and ECG Classification based on CNN-BiLSTM
• WaveletAE: A Wavelet-enhanced Autoencoder for Wind Turbine Blade Icing Detection
• Autoencoder-based Condition Monitoring and Anomaly Detection Method for Rotating Machines
• ADIC: Anomaly Detection Integrated Circuit in 65nm CMOS utilizing Approximate Computing
• Graph Convolutional Networks for traffic anomaly
• Natural Language Generation with Neural Variational Models
• RSM-GAN: A Convolutional Recurrent GAN for Anomaly Detection in Contaminated Seasonal Multivariate Time Series
• Learning representations for multivariate time series with missing data using Temporal Kernelized Autoencoders
• DROCC: Deep Robust One-Class Classification
• Memory-augmented Adversarial Autoencoders for Multivariate Time-series Anomaly Detection with Deep Reconstruction and Prediction
• An Encoder-Decoder Based Approach for Anomaly Detection with Application in Additive Manufacturing
• AQEyes: Visual Analytics for Anomaly Detection and Examination of Air Quality Data
• Event2Graph: Event-driven Bipartite Graph for Multivariate Time-series Anomaly Detection
• Improving Robustness on Seasonality-Heavy Multivariate Time Series Anomaly Detection
• Anomaly Detection on Seasonal Metrics via Robust Time Series Decomposition
• PyODDS: An End-to-End Outlier Detection System
• TimeAutoML: Autonomous Representation Learning for Multivariate Irregularly Sampled Time Series
• StackVAE-G: An efficient and interpretable model for time series anomaly detection
• PyODDS: An End-to-end Outlier Detection System with Automated Machine Learning
• Time Series Data Cleaning with Regular and Irregular Time Intervals
• Dimensionality Increment of PMU Data for Anomaly Detection in Low Observability Power Systems
• Visual Analytics of Anomalous User Behaviors: A Survey
• Self-supervised learning for fast and scalable time series hyper-parameter tuning
• An Adaptive Approach for Anomaly Detector Selection and Fine-Tuning in Time Series
• Learning Competitive and Discriminative Reconstructions for Anomaly Detection
• ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information
• Sequential Adversarial Anomaly Detection for One-Class Event Data
• Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models
• A Semi-Supervised Approach for Abnormal Event Prediction on Large Operational Network Time-Series Data
• Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly Detection
• Sequential Anomaly Detection using Inverse Reinforcement Learning
• Time Series Anomaly Detection with label-free Model Selection
• Pastprop-RNN: improved predictions of the future by correcting the past
• Attention-Based Self-Supervised Feature Learning for Security Data
• Self-Supervised Encoder for Fault Prediction in Electrochemical Cells
• Reconstruct Anomaly to Normal: Adversarial Learned and Latent Vector-constrained Autoencoder for Time-series Anomaly Detection