Forecasting Industrial Aging Processes with Machine Learning Methods
This work addresses maintenance scheduling for industrial plants, offering incremental improvements by comparing data-driven models to existing mechanistic approaches.
The paper tackled the problem of predicting industrial aging processes to enable proactive maintenance, and found that recurrent neural networks achieved near-perfect predictions on larger datasets and maintained good performance on smaller datasets with domain shifts, while simpler models only performed comparably on smaller datasets.
Accurately predicting industrial aging processes makes it possible to schedule maintenance events further in advance, ensuring a cost-efficient and reliable operation of the plant. So far, these degradation processes were usually described by mechanistic or simple empirical prediction models. In this paper, we evaluate a wider range of data-driven models, comparing some traditional stateless models (linear and kernel ridge regression, feed-forward neural networks) to more complex recurrent neural networks (echo state networks and LSTMs). We first examine how much historical data is needed to train each of the models on a synthetic dataset with known dynamics. Next, the models are tested on real-world data from a large scale chemical plant. Our results show that recurrent models produce near perfect predictions when trained on larger datasets, and maintain a good performance even when trained on smaller datasets with domain shifts, while the simpler models only performed comparably on the smaller datasets.