Understanding and Preparing Data of Industrial Processes for Machine Learning Applications
This addresses a critical data preprocessing bottleneck for machine learning applications in industrial settings, though it appears incremental as it builds on existing imputation methods.
The paper tackles the challenge of handling large proportions of missing values in industrial data, such as from sensor unavailability in steel production, by presenting a technique that utilizes all available data without removing observations, as demonstrated with real-world data.
Industrial applications of machine learning face unique challenges due to the nature of raw industry data. Preprocessing and preparing raw industrial data for machine learning applications is a demanding task that often takes more time and work than the actual modeling process itself and poses additional challenges. This paper addresses one of those challenges, specifically, the challenge of missing values due to sensor unavailability at different production units of nonlinear production lines. In cases where only a small proportion of the data is missing, those missing values can often be imputed. In cases of large proportions of missing data, imputing is often not feasible, and removing observations containing missing values is often the only option. This paper presents a technique, that allows to utilize all of the available data without the need of removing large amounts of observations where data is only partially available. We do not only discuss the principal idea of the presented method, but also show different possible implementations that can be applied depending on the data at hand. Finally, we demonstrate the application of the presented method with data from a steel production plant.