Warped Time Series Anomaly Detection
This addresses anomaly detection for systems with repetitive behavior, like industrial production lines, but is incremental as it builds on existing Dynamic Time Warping methods.
The paper tackles the problem of detecting anomalies in time series with repetitive but temporally distorted cycles, such as in industrial robots, by developing WETSAND, a three-stage method that segments cycles, computes a prototype using a GPU-based barycenter algorithm, and scores anomalies with Dynamic Time Warping variants, showing it scales to large signals, works with little data, and outperforms general-purpose approaches like autoencoders.
This paper addresses the problem of detecting time series outliers, focusing on systems with repetitive behavior, such as industrial robots operating on production lines.Notable challenges arise from the fact that a task performed multiple times may exhibit different duration in each repetition and that the time series reported by the sensors are irregularly sampled because of data gaps. The anomaly detection approach presented in this paper consists of three stages.The first stage identifies the repetitive cycles in the lengthy time series and segments them into individual time series corresponding to one task cycle, while accounting for possible temporal distortions.The second stage computes a prototype for the cycles using a GPU-based barycenter algorithm, specifically tailored for very large time series.The third stage uses the prototype to detect abnormal cycles by computing an anomaly score for each cycle.The overall approach, named WarpEd Time Series ANomaly Detection (WETSAND), makes use of the Dynamic Time Warping algorithm and its variants because they are suited to the distorted nature of the time series.The experiments show that \wetsand scales to large signals, computes human-friendly prototypes, works with very little data, and outperforms some general purpose anomaly detection approaches such as autoencoders.