Online Training Course

What is the difference between AI, Machine Learning, and Deep Learning?

What are "Physics-Informed Neural Networks" (PINNs)?

How does this course help with simulation speed?

Fundamentals of AI/ML for Simulation Engineers

15 - 18 June 2026 | Online | 4 hours each day

1:00pm (London) | 2:00pm (Berlin) | 3:00pm (Helsinki)
5:00am (Los Angeles) | 8:00am (New York)
6:30pm (New-Delhi) | 10:00pm (Tokyo)

Course language: English

Designed to provide a strong understanding of AI/ML fundamentals and practical skills in integrating Artificial Intelligence (AI), this comprehensive training course focuses on AI for Simulation Engineering

The course provides a technical roadmap for integrating Machine Learning (ML) and Deep Learning into engineering workflows. Participants will progress from foundational Machine Learning (ML) principles to Deep Learning architectures, including a good theoretical and practical grounding in Physics-Informed Neural Networks (PINNs). Participants will also master reduced-order and surrogate modelling for accelerating and optimizing design cycles.

Consisting of two parts, the course is software-agnostic, prioritizing methodologies and techniques that can be applied across various computational platforms.

Part 1: An interactive lecture that introduces the theory and mathematical background behind artificial intelligence.

Part 2: Hands-on exercises, where participants learn how to create their own Deep Learning models.

Key Learning Outcomes

• Physics-Driven AI: Developing PINNs that integrate physical laws into loss functions.
• Predictive Modelling: Utilizing Reduced Order Models to replace computationally expensive simulations.
• Data Engineering: Mastery of Feature Selection, Dimension Reduction, and Active Sampling.
• Model Quality & Ethics: Strategies for preventing Overfitting, managing Model Bias, and addressing Model Aging.
• AI-Guided DoE (Design of Experiments): Achieving richer design-space understanding with fewer high-fidelity simulations.

Detailed Course Program:

Day 1

Introductory Example: Modelling Compressor Parameters

• Problem Description
• Comparison between AI and traditional solution

An Overview of Example Applications in Research

• Simulation Acceleration
• Reduced Order Models

Definitions

• The definition of AI
• The difference between AI, Machine Learning, and Deep Learning

Overview of Machine Learning methods

• The basic principles behind all Machine Learning methods
• Learning Paradigms (Supervised, Unsupervised, Reinforcement Learning)
• Supervised Algorithms:
  - Random Forest Regression
  - Gradient Boosting
  - Support Vector Machines
• Classification and Logistic Regression
• How to handle non-numerical data

Foundations of Deep Learning

• How Neurons Form the Hypothesis Function
• Activation Functions
• Deep Learning Regression
• Model Training
• Forward Pass and Backpropagation
• Loss Functions
• Optimizers for Deep Learning
• Measuring Model Quality
• Overfitting
• Data Split
• Layer Types
• Neuron Architecture
• Physics Informed Neural Networks
• Surrogate Modelling

Day 2

Practical Exercises

• Building a Deep Learning Model for sensitivity analysis
• Building a Physics Informed Neural Network

Day 3 and day 4

Example project for a deep learning surrogate model for design optimization

Creating machine learning models from scratch

• A high-level overview of creating machine learning models
• Reviewing available data and setting a goal
• Data preparation
• The importance of the training, test, validation split
• Setting the model architecture
• Choosing optimization algorithms and loss functions
• Creating PINNs
• Evaluating model performance
• Overview of MLOps
• An overview of tools to create machine learning models
• Open-source libraries (TensorFlow vs. PyTorch)
• Application software

Project preparation

• Reviewing available data
• Using a preliminary exploratory data analysis to gauge the feasibility of the ML project
• Defining a modelling target
• Working in tandem with a simulation project

Data preparation

• Data transformation: File formats and making data trainable
• Data cleaning
• Handling classes and text with vectorization
• Dimension reduction
• Feature selection
• Feature Engineering

Sampling

• Introduction to data sampling
• Statistical sampling methods
• Active sampling
• Sampling errors

Measuring model performance and validity

• Performance measures for ML models

Consuming the machine learning model

• Predictive Tasks
• Design optimization

Limitations of machine learning models

• Model biases
• Limitations of interpolation and extrapolation
• Model aging



PSE Competencies addressed by this training course

OPTpr7
Understanding of at least one of the -modern- methods of search strategy such as Neural Networks, Genetic Algorithms, etc. | Advanced
OPTco34
Describe the method of Genetic Algorithms. | Standard
OPTco35
Explain the process of Neural Network based optimization. | Standard
OPTco36
Describe the training phase of a Neural Network. | Standard
OPTkn10
List which Artificial Intelligence based approaches that your system uses. | Standard
PROB-v2-22
Describe surrogate model type methods for stochastic calculations | | Advanced - This one is looking for AI and ML methods to be explained

T​rainer

M​ax Kassera (yasAI)
Max Kassera studied mechanical engineering with a minor in economics at the University of Kaiserslautern-Landau, where he first applied machine learning and artificial intelligence to turbocharger design in 2017. After graduating, he was awarded two German government grants to develop AI software for mechanical engineering, which led to the incorporation of yasAI in 2022. With yasAI, Max began training engineers in applying AI to simulation projects with a focus on simulations and fluid mechanics.

FAQ

Organisation

Duration
4 hours each day - course starts each day:

• 1:00pm (London)
• 2:00pm (Berlin)
• 3:00pm (Helsinki)
• 5:00am (Los Angeles)
• 8:00am (New York)
• 6:30pm (New-Delhi)
• 10:00pm (Tokio)

Login phase from 30 min before session starts.

Language
English

Course Fee
Non NAFEMS members: 1.600 Euro / person*
NAFEMS member: 1.250 Euro / person*
Included in the fees are digital course notes and a certificate.
* plus VAT if applicable.
Please note - unpaid registrations will be cancelled one week prior to the event start date unless previous contact has been made with our Accounts Department or the course organiser. If not, then our cancellation policy will be enforced. If required, the cancellation policy can be viewed on the event page on our website.

NAFEMS membership fees (company)
A standard NAFEMS site membership costs 1,365 Euro per year, an academic site and entry membership costs 855 Euro per year.

Cancellation Policy

Course cancellation by NAFEMS
If there aren't enough participants, we reserve the right to cancel the course a week before the start date. The course can also be cancelled in cases of presenter illness or force majeure. In these cases, the course fees will be returned.

Organisation / Contact
NAFEMS
e-mail: roger.oswald@nafems.org

Accreditation Policy

The course is agreed and under control of NAFEMS Education and Training Working Group (ETWG).