Skip Navigation
Small Business Innovation Research/Small Business Tech Transfer

Drag &Drop, Multiphysics & Neural Net-based Lab-on-Chip Optimization Software, Phase I

Completed Technology Project

Project Description

Drag &Drop, Multiphysics & Neural Net-based Lab-on-Chip Optimization Software, Phase I
The overall objective of this project is to develop a drag and drop, component library (fluidic lego) based, system simulation and optimization software for entire lab-on-chip systems. Current approaches for biochip system design are either very inefficient (trial-and-error based) or time-consuming (high-fidelity simulation-based). The proposed tool will benefit the biochip community by tremendously shortening design optimization times (minutes). Representation of complex, interacting physico-chemical processes of a biochip in a system design tool is a formidable challenge. Our innovative solution seeks to use state-of-the-art high-fidelity simulations to develop and train Artificial Neural Network (ANN) based models for different components of a biochip. The Phase I effort will focus on proof-of-concept by (a) Development of multiphysics simulation-based ANN models for typical components of a biochip; (b) Demonstration of capabilities of the developed ANN model through optimization of a micromixing biochip. In Phase II, we will further develop and refine ANN models to account for additional multiphysics effects (electrokinetics, biochemistry, etc.) and dynamic response. The final product will feature a comprehensive library of components along with a user-friendly graphical user interface. CFDRC is the technology leader in multiphysics simulations for the biochip industry, and very well placed to successfully undertake this challenging task. More »

Primary U.S. Work Locations and Key Partners

Light bulb

Suggest an Edit

Recommend changes and additions to this project record.

This is a historic project that was completed before the creation of TechPort on October 1, 2012. Available data has been included. This record may contain less data than currently active projects.