An Evaluation of Classification Methods for 3D Printing Time-Series Data
This is incremental work for additive manufacturing researchers, applying existing methods to new 3D printing data.
The paper tackled the problem of classifying infrared time-series data from metal 3D printing melt-pool temperatures to detect signals for predicting process outcomes, and found that Dynamic Time Warping is an effective distance measure compared to alternatives.
Additive Manufacturing presents a great application area for Machine Learning because of the vast volume of data generated and the potential to mine this data to control outcomes. In this paper we present preliminary work on classifying infrared time-series data representing melt-pool temperature in a metal 3D printing process. Our ultimate objective is to use this data to predict process outcomes (e.g. hardness, porosity, surface roughness). In the work presented here we simply show that there is a signal in this data that can be used for the classification of different components and stages of the AM process. In line with other Machine Learning research on time-series classification we use k-Nearest Neighbour classifiers. The results we present suggests that Dynamic Time Warping is an effective distance measure compared with alternatives for 3D printing data of this type.