Tech Tips

July 26, 2022

Stepped Variables in Optimization and Adaptive Design

In this tech tip, we introduced a concept of stepped variables started from pSeven v6.18, looking at the new type versus the already implemented continuous, discrete, and categorical variables.

Yulia Bogdanova, Application Engineer, DATADVANCE

May 7, 2022

Linear Constraint Handling in Parametric Studies in pSeven

The main idea of this study is to show how pSeven handles constraints, and what way we can use to state our problem correctly to obtain the best solution in a short time.

Yulia Bogdanova, Application Engineer, DATADVANCE

April 27, 2021

Using SHAP with pSeven Core for Sensitivity Analysis

Since pSeven 6.20, pSeven Core supports one more sensitivity analysis method — calculating SHAP (SHapley Additive exPlanations) values. This tech tip illustrates using a GTApprox model to get its SHAP values for points in a given sample.

Svetlana Chernova, Head of Software Testing, DATADVANCE

April 5, 2021

Handling Non-numerical Values in the Design Space Exploration and Predictive Modeling Studies

The ways the Design Space Exploration and Predictive Modeling tools work in situations when simulation models, approximations or initial samples return non-numerical values are described in this tech tip.

Yulia Bogdanova, Application Engineer, DATADVANCE

March 25, 2021

Integrate any Engineering Software Easily with a New Configurable and Flexible User Block

Create your own User block to integrate any CAD/CAE tool into the workflows, and include it into pSeven block library for everyday convenient use.

Alexander Dosyuk, Application Engineer, DATADVANCE

January 16, 2020

Data Fusion vs Mixture of Approximators to Handle Training Datasets of Low and High Fidelity

This tech tip demonstrates some aspects of Data Fusion tool and MoA technique capabilities to handle training datasets of low and high fidelity.

Yulia Bogdanova, Application Engineer, DATADVANCE

January 9, 2020

Automated Determination of the Validity Domain for Approximation Models

In this tech tip, we describe the usage of the InputDomainType option, which allows limiting the input design space to avoid incorrect function predictions in the area outside the training domain.

By Yulia Bogdanova, Application Engineer, DATADVANCE

November 18, 2019

Mixture of Approximators for Model Improvement

This tech tip describes the features, possible applications and benefits of the Mixture of Approximators technique available in pSeven.

By Yulia Bogdanova, Application Engineer, DATADVANCE

Contact Information

31100, Toulouse, Avenue du Général de Croutte 42

+33 (0) 5 82-95-59-68

info@datadvance.net

Blog

Stepped Variables in Optimization and Adaptive Design

Linear Constraint Handling in Parametric Studies in pSeven

Using SHAP with pSeven Core for Sensitivity Analysis

Handling Non-numerical Values in the Design Space Exploration and Predictive Modeling Studies

Integrate any Engineering Software Easily with a New Configurable and Flexible User Block

Data Fusion vs Mixture of Approximators to Handle Training Datasets of Low and High Fidelity

Automated Determination of the Validity Domain for Approximation Models

Mixture of Approximators for Model Improvement

Contact Information