AI-ROMs: From Experimental Data to Real-Time Predictive Models

Course category

Standard

Level

Advanced

Duration

8 hours [4 hours for 2 days]

Time

09:00 - 13:00

Language

English

Tutor

Novella Saccenti

Description

EnginSoft, within its extensive portfolio of training courses, offers a theoretical and practical course on the creation of low computational impact mathematical-statistical models based on Reduced Order Modeling (ROM) methodologies.

The course aims to offer a theoretical and practical perspective on the application of regression and classification models in advanced numerical analysis disciplines and on the generation of predictive models using experimental data acquired from the field or generated virtually. These predictive models will be developed by applying ROM algorithms. Reduced Order Models (ROMs) offer numerous advantages, including a significant reduction in computation time and computational impact, making them easily integrable into existing design workflows. The use of Artificial Intelligence (AI) algorithms represents an advanced and innovative approach that is crucial for improving accuracy and reducing computational effort. The use of open source technologies, such as the Python programming language, allows for broad usability in all interested companies. The ability to test and modify the examples and algorithms at will makes this course transversal and easy to understand.

The primary objective of this course is to introduce participants to an easy-to-interpret modus operandi, starting from experimental data available from various sources and applying regression, classification and prediction algorithms.

Each topic consists of a theoretical part, followed by exercises.

Target Audience

The course is aimed at users (all engineers, designers, researchers) who need to:

• generate an executable 'black box' from experimental data
• reduce the computational effort of complex detailed models
• predict output in real-time
• use reduced models in system modeling

Pre-requisites

Basic knowledge of Python programming

Agenda

• Introduction to ROM
• Import experimental and/or virtual data from different sources
• A priori analysis of data and preparation of experimental data
• Introduction to the sklearn library
• Introduction to the pyMOR library
• Introduction to the pyFmi library