Westinghouse Electric Corporation

Imagars LLC

Peter K Liaw

William G Clark, Jr

Baldur Andrew Steingrimsson

Anand Kulkarni

John J Herald

Xuesong Fan

Duckbong Kim

This invention presents an innovative framework for the application of machine learning for identification of alloys or composites with desired properties of interest. For each output property of interest, we identify the corresponding driving (input) factors. These input factors may include the material composition, heat treatment, process, microstructure, temperature, strain rate, environment or testing mode. Our framework assumes selection of optimization technique suitable for the application at hand and data available, starting with simple linear, or quadratic, regression analysis. We present a physics-based model for predicting the ultimate tensile strength, a model that accounts for physical dependencies, and factors in the underlying physics as a priori information. In case an artificial neural network is deemed suitable, we suggest employing custom kernel functions consistent with the underlying physics, for the purpose of attaining tighter coupling, better prediction, and extracting the most out of the—usually limited—input data available.

Machine learning to accelerate alloy design

A process for removing paint by high pressure waterjet blasting of painted surfaces wherein the waterjet comprises a ferrofluid or other liquid containing tiny magnetic particles suspended therein. The particles may be in colloidal suspension or be suspended by agitation and are preferably polymer coated. The liquid-magnetic particle mixture lends itself to electromagnetic process control, run-off maintenance and waste processing capabilities. Thereby, the process can employ process control and waste remediation options.

Pressurized ferrofluid paint removal system using an electromagnet and

Growing community of inventors

Knoxville, TN, United States of America

Peter K Liaw