A new data analytics framework emphasising preprocessing of data to generate insights into complex manufacturing systems

Abstract

Recent emphasis has been placed on improving the processes in manufacturing by employing early detection or fault prediction within production lines. Whilst companies are increasingly including sensors to record observations and measurements, this brings challenges in interpretation as standard approaches do not highlight the presence of unknown relationships. To address this, we have proposed a new data analytics framework for predicting faults in a large-scale manufacturing system and validated it using both a publicly available Bosch manufacturing dataset with a focus on preprocessing of the data and the open-source SECOM industrial dataset. This paper is an extension to the work presented at International Conference on Intelligent Manufacturing and Internet of Things. The additional material includes a detailed focus on feature selection and the various approaches for identifying important features in the data, an updated framework methodology and description, an extension of XGBoost to allow this model to be used for prediction/classification and a comparison for classification with a Random Forest, tree-based model. The framework was used to explore two public manufacturing datasets and successfully identified the most influential features related to product failure in each production line data.