10–14 Sept 2023
Europe/Madrid timezone

Machine Learning Applications for Monitoring and Troubleshooting Chemical and Process Industries

Not scheduled
20m
Machine learning

Speakers

Dr Mattia Vallerio (Solvay SA) Francisco Navarro (Imperial College)

Description

Typically, machine learning (ML) and artificial intelligence (AI) applications tend to focus on examples that are not relevant to process engineers.

In this talk, industrial data science fundamentals will be explained and linked with commonly-known examples in process engineering, followed by two common industrial applications using state-of-art ML techniques.

First, will discuss what open-source packages can be used to connect to industrial historians (Aspentech IP.21 and OSIsoft PI). Then we will cover AutoML and ExplainableAI Python packages that are commonly used in industry. Among them, We will show how Predictor Explainer (JMP+Python) automates the screening of process variables both for continuous and batch process data.

Classification Both methodology and application
Keywords continuous data, batch data, industry, open-source

Primary authors

Dr Mattia Vallerio (Solvay SA) Dr Carlos Perez-Galvan (Solvay SA) Francisco Navarro (Imperial College)

Presentation materials

There are no materials yet.