Go back    Home Solutions Computational Intelligence and Data Science framework and the KadiAI interface

Computational Intelligence and Data Science framework and the KadiAI interface (CIDS and KadiAI)

Authors: Arnd Koeppe

Keywords: machine learning, artificial intelligence, neural networks, active learning, mechanics, materials science

CIDS is a framework for Artificial Intelligence (AI) and Machine Learning (ML) for engineering, materials, and natural sciences applications. It combines models, functions, and pipelines from libraries such as tensorflow/keras, sklearn, scipy, and pandas to build modular, flexible, and reproducible AI models.

The interface KadiAI integrates AI tools, such as CIDS, seamlessly into Kadi workflows and interacts with Kadi's repositories and data management features.


Publications

Explainable Artificial Intelligence for Mechanics: Physics-Explaining Neural Networks for Constitutive Models

Koeppe A, Bamer F, Selzer M, Nestler B, Markert B - Frontiers in Materials - 2022


High-fidelity simulations and data-driven insights on rate-governing phases in duplex and triplex systems during isotropic normal grain growth

Amos P, Koeppe A, Perumal R, Nestler B - Physical Review Materials - 2022


Mechanics 4.0

Koeppe A, Hesser D, Mundt M, Bamer F, Selzer M, Markert B - Handbook Industry 4.0 - 2022


Machine Learning Assisted Design of Experiments for Solid State Electrolyte Lithium Aluminum Titanium Phosphate

Zhao Y, Schiffmann N, Koeppe A, Brandt N, Bucharsky E, Schell K, Selzer M, Nestler B - Frontiers in Materials - 2022


An artificial intelligence approach to model nonlinear continua by intelligent meta‐elements

Koeppe A, Bamer F, Markert B - PAMM - 2021


Workflow concepts to model nonlinear mechanics with computational intelligence

Koeppe A, Bamer F, Selzer M, Nestler B, Markert B - PAMM - 2021


Tiefes Lernen in der Finite-Elemente-Methode

Koeppe A - Dissertation - 2021


Estimation of Gait Mechanics Based on Simulated and Measured IMU Data Using an Artificial Neural Network

Mundt M, Koeppe A, David S, Witter T, Bamer F, Potthast W, Markert B - Frontiers in Bioengineering and Biotechnology - 2020


An efficient Monte Carlo strategy for elasto-plastic structures based on recurrent neural networks

Koeppe A, Bamer F, Markert B - Acta Mechanica - 2019


Efficient numerical modeling of 3D-printed lattice-cell structures using neural networks

Koeppe A, Hernandez Padilla C, Voshage M, Schleifenbaum J, Markert B - Manufacturing Letters - 2018


License
Apache 2.0

Other solutions related to Computational Intelligence and Data Science framework and the KadiAI interface in Helmholtz Imaging CONNECT:

Solution
Karlsruhe Data Infrastructure for Materials Science (Kadi4Mat)

Kadi4Mat is the Karlsruhe Data Infrastructure for Materials Science, an open source software for managing research data. The goal of this project is to combine the ability to manage and exchange data, the repository, with …


Helmholtz Imaging spinning wheel

Please wait, your data is processed

Please wait, your data is processed