Convolutional-Based Encoder–Decoder Network for Time Series Anomaly Detection during the Milling of 16MnCr5

Machine learning methods have widely been applied to detect anomalies in machine and cutting tool behavior during lathe or milling. However, detecting the workpiece itself not received same attention by researchers. In this article, authors present a publicly available multivariate time series dataset which was recorded milling of 16MnCr5. Due artificially introduced, realistic workpiece, can be for anomaly detection. By using convolutional autoencoder as first model, good results location were achieved. Furthermore, tools with two different diameters where used led eligible transfer learning. The objective article is provide researchers real-world process suitable modern research topics such detection