Unsupervised Anomaly Detection in Process-Complex Industrial Time Series: A Real-World Case Study
For practitioners deploying anomaly detection in real industrial settings with heterogeneous processes, this work provides a comparative evaluation showing that autoencoders, especially temporal convolutional ones, are necessary to handle such complexity.
This empirical study evaluates anomaly detection methods on a complex industrial time-series dataset with pronounced process-induced variability. Temporal convolutional autoencoders achieve the most robust performance, outperforming Isolation Forest and other autoencoder variants.
Industrial time-series data from real production environments exhibits substantially higher complexity than commonly used benchmark datasets, primarily due to heterogeneous, multi-stage operational processes. As a result, anomaly detection methods validated under simplified conditions often fail to generalize to industrial settings. This work presents an empirical study on a unique dataset collected from fully operational industrial machinery, explicitly capturing pronounced process-induced variability. We evaluate which model classes are capable of capturing this complexity, starting with a classical Isolation Forest baseline and extending to multiple autoencoder architectures. Experimental results show that Isolation Forest is insufficient for modeling the non-periodic, multi-scale dynamics present in the data, whereas autoencoders consistently perform better. Among them, temporal convolutional autoencoders achieve the most robust performance, while recurrent and variational variants require more careful tuning.