Dassault Systemes Simulia Corp.

Subham Sett

Alexander Jacobus Maria Van Der Velden

Victor George Oancea

Manoj Kumar Mohanram Chinnakonda

Jing Bi

Prabhav Saraswat

Juan Antonio Hurtado

Jiang Yao

A method includes simulating a process, with computer-based software, to produce virtual data about the process; identifying process parameters for a real-world version of the process; providing a real-world sensor to sense a parameter associated with the real-world version of the process; receiving sensor readings from the real-world sensor while the real-world version is being performed; and training a machine-learning software model to predict a behavior of the real-world sensor based on the virtual data about the process, the process parameters, and the sensor readings.

Machine learning based on virtual (V) and real (R) data

The present invention relates to a method and corresponding system for modeling a musculo-skeletal system. An embodiment of the method of the invention begins by scaling and positioning a musculo-skeletal model to correspond with motion capture data of a subject. Next, kinematically consistent motion data is generated from the motion capture data and then an inverse dynamic analysis of the musculo-skeletal model is performed using the generated kinematically consistent motion data, such that at least one analysis result is generated. The musculo-skeletal model is then updated to correspond with the at least one analysis result of the inverse dynamic analysis. Finally, the muscle activation of the updated musculo-skeletal model is optimized by determining at least one muscle force using the updated musculo-skeletal model, and by further updating the updated musculo-skeletal model to correspond with the determined at least one muscle force.

Musculo-skeletal modeling using finite element analysis, process integration, and design optimization

Growing community of inventors

Providence, RI, United States of America

Subham Sett