Home
Tutorials
Learn more about the Altair HyperWorks suite of products with interactive tutorials.
PhysicsAI Tutorials
Create .json Files
Tutorial Level: Intermediate In this tutorial, you will generate .json files for training a PhysicsAI model on custom outputs/KPIs from a .csv file summarizing the KPIs of the entire dataset.

Welcome
What's New
View new features for Altair HyperWorks 2025.1.
Get Started
Learn the basics and discover the workspace.
Tutorials
Learn more about the Altair HyperWorks suite of products with interactive tutorials.
- Video Tutorials
- Tips and Tricks Videos
- HyperMesh Tutorials
- HyperView Tutorials
- HyperGraph Tutorials
- MotionView Tutorials
- PhysicsAI Tutorials
  - Create .json Files
    Tutorial Level: Intermediate In this tutorial, you will generate .json files for training a PhysicsAI model on custom outputs/KPIs from a .csv file summarizing the KPIs of the entire dataset.
  - Custom Inputs: Global Hook
    Tutorial Level: Advanced In this tutorial, you will use custom global input variables (such as varying material properties, global boundary conditions, and so on) for training.
  - Custom Inputs: Nodal Hook
    Tutorial Level: Advanced In this tutorial, you will use custom nodal input variables (such as varying nodal and elemental forces, boundary loads, and so on) for training.
  - Custom Outputs/KPIs in PhysicsAI Models
    Tutorial Level: Beginner In this tutorial, you will learn the procedure for using your own knowledge point indicators (KPIs) as responses in PhysicsAI.
  - Train Your Own Model
    Tutorial Level: Beginner In this tutorial, you will use PhysicsAI to train your own model.
  - Transfer Learning in PhysicsAI
    Tutorial Level: Intermediate In this tutorial, you will be guided through the process of using transfer learning in PhysicsAI with a provided pre-trained model and datasets by taking two routes: using transfer learning and training a model from scratch.
  - Use PhysicsAI for Test Data
    Tutorial Level: Advanced In this tutorial, you will train a PhysicsAI model without simulation results.
  - Use PhysicsAI in HyperStudy
    Explore the HyperStudy tutorials to learn more about using PhysicsAI in HyperStudy.
  - Use SER Architecture for Training on KPIs
    Tutorial Level: Advanced In this tutorial, you will use the Shape Encoding Regressor (SER) architecture to predict KPIs.
- Publishing and Reporting Tutorials
Startup Procedures and Customizations
Start and configure the applications.
Tool Finder
View a list of deprecated panels and their newer, equivalent workflows.
Manage Files and Data
Create, open, import, and save models.
Sessions and Report Templates
Set up sessions and create report templates.
Interface with External Products
Solver interfaces supported in HyperMesh.
Entities and Solver Interfaces
A solver interface is made up of a template and a FE-input reader.
Browsers
Browsers provide a structured view of model data, which you can use to review, modify, create, and manage the contents of a model. In addition to visualization, browsers offer features like search, filtering, and sorting, which enhance your ability to navigate and interact with the model data.
Sketching
Create and edit 2D parametric sketch geometry.
Topology
Create, edit, and cleanup geometry.
FE Geometry
FE geometry is topology on top of mesh, meaning CAD and mesh exist as a single entity. The purpose of FE geometry is to add vertices, edges, surfaces, and solids on FE models which have no CAD geometry.
Meshing and Elements
Explore the different types of mesh you can create in HyperMesh and create and edit 0D, 1D, 2D, and 3D elements.
Model Build and Assembly
Create, organize and manage parts and subsystems.
Composites
HyperMesh composites modeling.
Connectors
Create connections between parts of your model.
Morph
Rapidly change the shape of the FE mesh without severely sacrificing the mesh quality.
Skeleton Modeling
Create a reduced ordered model to facilitate optimization at the concept phase.
Design Space
Workflow to support topology optimization model build and setup.
Optimization
Setup an Optimization in HyperMesh.
Design Explorer
Multi-disciplinary design exploration and optimization tools.
Validate
Validate the model built before running solver analysis.
Analyze
Models require loads and boundary conditions in order to represent the various physics and/or physical equivalents to bench and in-use testing.
Axisymmetry
Reduce a full 3D model with axisymmetric surfaces while accounting for imperfections.
Concept Modeling
Tools and workflows that are dedicated to rapidly creating new parts for specific use cases, or amending existing parts. The current capabilities are focused on stiffening parts.
Crash and Safety
Tools used for crash and safety analysis.
Airbag
Use airbag folder utilities and export a resulting airbag in a Radioss deck.
Aerospace
Essential utility tools developed using HyperMesh-Tcl.
Aeroelasticity
Import an aeroelastic finite element model with Nastran Bulk Data format.
Certification
Framework to plug certification methods to assess margin of safety from the model and result information.
PhysicsAI
Use PhysicsAI to build fast predictive models from CAE data. PhysicsAI can be trained on data with any physics or remeshing and without design variables.
Results Data in HyperMesh and HyperView
Results data can be post-processed using both HyperMesh and HyperView.
Developer
The Developer ribbon contains tools for automation and customization.
Plot Data in HyperMesh and HyperGraph
Plot data can be post-processed using both HyperMesh and HyperGraph.
Multibody Modeling in MotionView
MotionView is a general pre-processor for Multibody Dynamics.
Media Files in MediaView
MediaView plays video files, displays static images, tracks objects, and measures distances.
Tabulate Results in TableView
Use TableView to create an Excel-like spreadsheet.
Text Files in TextView
TextView math scripts reference vector data from HyperGraph windows to automate data processing and data summary.
Publishing and Reporting
Create, define, and export reports.

View All Altair HyperWorks Help

Create .json Files

Tutorial Level: Intermediate In this tutorial, you will generate .json files for training a PhysicsAI model on custom outputs/KPIs from a .csv file summarizing the KPIs of the entire dataset.

These .json files should be created prior to creating a dataset inside PhysicsAI and you are free to use the method of your choice. The KPIs need to be supplied through .json files in addition to the solver result files (.h3d, .odb, and so on) or solver input decks (.fem, .rad, and so on) in the same subdirectory and have the same name (for example, A.h3d and A.json, B.h3d and B.json, and so on).

For information on using custom outputs during training, see the Custom Outputs/KPIs in PhysicsAI Models tutorial.

Before you begin, copy the file(s) used in this tutorial to your working directory.

creating_jsons.zip

Note:

Unzip the project creating_jsons.zip and inspect the contents:

collected_data.csv is a comma separated file which contains a summary of the relative file paths of the various .h3d files and the corresponding KPIs.
physicsai_csvtojson.py is a python script that reads the .csv file above and generates .json files in the same relative location as the .h3d files listed in the .csv.
run_000XX_beam.h3d files provided in different locations within the attached folder.

In this tutorial, you will:

Update a .csv file with your KPIs.
Generate .json files corresponding to each of the provided .h3d files.

Create Files

In this step, you will create .json files which contain the KPIs corresponding to the .h3d files.

Open the collected_data.csv file.
This file summarizes the relative locations of the different .h3d files provided. Also, the KPI values corresponding to each .h3d file are listed in the columns with an appropriate header. Anyone can edit this file to add or remove KPIs.
Figure 1. KPI Summary Contained in the CSV File
Verify the relative path to the .h3d file is correctly input in the first column and that each .h3d has all the KPIs defined.
Run the physicsai_csvtojson.py file.
This file generates the .json files which contain the KPIs in a structured format. Each .json file has the same name as the corresponding .h3d file except that the extension is .json.
Figure 2. Example .json File