Data-Driven Process Monitoring for Knowledge Discovery: Local and Global Structures

Document Type

Article

Publication Date

1-1-2023

Abstract

In industrial processes, the amount of raw data generated can add complexity in the analysis and understanding of the process dynamics. Being able to properly interpret this data can help improve plant operation. A platform is introduced for monitoring of industrial processes and optimization of the model-building process. FASTMAN-JMP (FAST MANual Data Manipulation implemented in JMP [1]) is a tool developed in Python to apply various data mining and machine learning techniques quickly and easily to better understand valuable patterns and hidden trends in process data. It is shown that local and global structures in the data set can be visualized and related to actual process operations though the identification of the variables responsible for the separation between selected given clusters. Furthermore, adequate comparisons of these algorithms can be difficult, having different loss functions with many parameters. We aim to decipher these algorithms, and how they work in the context of industrial data. Results are presented for an industrial case study of a pyrolysis reactor.

Publication Source (Journal or Book title)

Computer Aided Chemical Engineering

First Page

1809

Last Page

1815

This document is currently not available here.

Share

COinS