Ford Global Technolgoies, LLC

Beverly Joyce Becker

Gregory Allen Kaepp

Nanxin Wang

Hassen Hammoud

Chi-Chin Wu

Han C Wang

Zhengyu Lei

Keming Chen

Fang Liu

Yan Xue

A method () for cascading system level target to component level design objectives using machine learning and design synthesis techniques. The method () of the present invention uses machine learning techniques to build () surrogate models from given system targets (). The method then employs design synthesis methods to determine () a range of component level design objectives for the given system level targets using the surrogate models. The range of component level design objectives is fed back () to one of the surrogate models to determine () the component design objectives.

Method for cascading vehicle system targets to component level design objectives

A method is disclosed for determining the correctness of proposed values or data for engineering parameters. The method incorporates the use of a server side computer and a client side computer connected to each other via an electronic network. The method includes the steps of obtaining a knowledge base of data. The knowledge base is stored on the server side computer. Proposed values or data are generated at the client side computer using an applet. The proposed data is then transmitted over the network from the client side computer to the server side network. The proposed data is then compared against the knowledge base of data using a servlet designed to invoke and utilize computers other than the server side computer that may have rules or facts necessary to test the proposed data. The results are prepared and then transmitted from the server side computer to the client side computer. The client side computer does not require a proprietary application to be resident therein. It merely requires a web browser to access and utilize all of the information resident in the knowledge base stored in the server side computer.

Method for serving engineering rules on a network through servlet and applet

An adaptive CAD system, comprising: (a) gathering data consisting of at least one of (i) human generated information and techniques, and (ii) machine generated information and rules; (b) processing the gathered data by instructions to produce processed knowledge containing script without a product or part design; (c) recursively editing the processed knowledge to continuously improve the script to form an executable part design, such processing being carried out by inputting into the editing process at least one of (i) recently learned data, (ii) associative techniques, relations and features, and (iii) knowledge-based rules and instructions and (d) inputting the history of step (c) into processed knowledge, such inputting creating captured improvement criteria, that is iteratively and recursively feeding back into either the recursive editing process or into processing of step (b) to effect evolvement of an executable design form.

Intelligent CAD process

Growing community of inventors

Harper Woods, MI, United States of America

Beverly Joyce Becker