Skip to main content

Upscaling Product development Simulation Capabilities exploiting Artificial inteLligence for Electrified vehicles



Website containing all the publishable information related to the project. This deliverable belongs to Task 7.2. In the deliverable the main website functions will be described

Corresponding load cases for the full vehicle models to be used within the project

Definition of the load cases for the previous specified vehicles models. This deliverable will be obtained in task 5.1.

Reduced order models for aerodynamic performance prediction

This delievrable will describe the steps taken to define the reduced order models that will be obtained when the task2.2 is completed.

Requirements for setting up a reduced order model of a battery to be used in a full vehicle crash simulation

List of the requirements for the ROM of the battery that will be used in the full vehicle crash simulation. This deliverable will result from T5.1.

Requirements for setting up a reduced order model of a full vehicle model with parametrized boundary conditions

List of the requirements to define the ROM of the full vehicle according to the desired accuracy. This deliverable belongs to T5.1.

Requirements for setting up an AI model to improve parallelization of the solver

Report of the requirements for the AI model so that the solver can be parallelized his deliverable belongs to Task 53

Requirements for aerothermal simulations reduced order model

"This report will list the requirements for the variables necessary to perform the ""offline"" phase to generate the AI/ROM models. This is in terms of which variables, the size of the dataset and the characteristics to obtain the desired accuracy in every case. This deliverable results from Task 2.1. "

Potential for ML-based acceleration in finite volume

Report of the solver algorithm review and further acceleration potential assessment, focusing on the pressure correction step for the acceleration efforts. This deliverable is a result of ST1.1.1.

Assessment of reduced order models for aerodynamic performance prediction

Report on the validation process of the previously defined reduced order models used for higher fidelity data. This deliverable results from Task 2.3.

Validated tool to handle and rationalize aerodynamic data from heterogeneous sources

This report will describe the tool implemented for dealing with all types of aerodynamic data coming from different sources and in different formats. This deliverable results from Task 2.4.

Searching for OpenAIRE data...


Application of Physics Informed Machine Learning model for correcting RANS modeled Reynolds Stress Anisotropy

Author(s): Bhanu Prakash, Charalampos Tsimis, Enric Aramburu
Published in: 2020
Publisher: IDIADA

AI Enhanced Methods for Virtual Prediction of Short Circuit in Full Vehicle Crash Scenarios

Author(s): Alexandre Dumon, Michael Andres, Stefano Menegazzi, Christoph Breitfuss, Cristian Jimenez, Francisco Chinesta, Fatima Daim, Alain Tramecon
Published in: SAE Technical Paper Series, 2020
Publisher: SAE International
DOI: 10.4271/2020-01-0950