A Revised KDD Procedure for the Modeling of Continuous Production in Powder Processing

In this paper, a revised Knowledge Discovery in Databases (KDD) procedure is proposed, which is designed especially for data mining in powder processing and other types of continuous production. The revised KDD procedure includes data preprocessing, feature engineering, machine learning and model ev...

Full description

Saved in:
Bibliographic Details
Main Authors: Vernickel, K., Weber, J., Li, X., Berg, J., Reinhart, G.
Format: Conference Proceeding
Language:English
Subjects:
KDD
Machine Learning
Powder Processing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a revised Knowledge Discovery in Databases (KDD) procedure is proposed, which is designed especially for data mining in powder processing and other types of continuous production. The revised KDD procedure includes data preprocessing, feature engineering, machine learning and model evaluation. The proposed methods are implemented and evaluated using a dataset from a fluidized bed opposed jet mill. The evaluation results show that the machine learning model can accurately predict the product quality in this scenario and capture the internal relations between processing parameters and product quality.
ISSN:2157-362X
DOI:10.1109/IEEM44572.2019.8978828