Physics based neural network for validating data

• US 20040064426A1
• Filed: 09/30/2002
• Published: 04/01/2004
• Est. Priority Date: 09/30/2002
• Status: Abandoned Application

• Current Assignee: United Technologies Corporation (Raytheon Technologies Corporation d/b/a RTX)
• Original Assignee: United Technologies Corporation (Raytheon Technologies Corporation d/b/a RTX)
• Inventors: Depold, Hans R., Sirag, David John Jr.
• Application Number:
  US10/261,237
• Publication Number:
  US 20040064426A1
• Time in Patent Office: Days
• US Class Current: 706/26
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology

Abstract

A physics based neural network (PBNN) for validating data in a physical system comprising a plurality of input nodes each receiving at least one input comprising an average measurement of a component and a standard deviation measurement of a component of the physical system and comprising a transfer function for converting the at least one input into an output, a plurality of intermediate nodes each receiving at least one output from at least one of the plurality of input nodes and comprising a transfer function embedded with knowledge of the physical system for converting the at least one output into an intermediate output, and a plurality of output nodes each receiving at least one intermediate outputs from the plurality of intermediate nodes and comprising a transfer function for outputting the average measurement of a component when the transfer function evaluates to a value greater than zero wherein the PBNN is trained with a predetermined data set.

Claims

1. A physics based neural network (PBNN) for validating data in a physical system comprising:

a plurality of input nodes each receiving at least one input comprising an average measurement of a component and a standard deviation measurement of a component of said physical system and comprising a transfer function for converting said at least one input into an output;

a plurality of intermediate nodes each receiving at least one output from at least one of said plurality of input nodes and comprising a transfer function embedded with knowledge of said physical system for converting said at least one output into an intermediate output; and

a plurality of output nodes each receiving at least one intermediate output from said plurality of intermediate nodes and comprising a transfer function for outputting said average measurement of a component when said transfer function evaluates to a value greater than zero;

wherein said PBNN is trained with a predetermined data set.

2. The PBNN of claim 1 wherein said plurality of average measurements and said plurality of standard deviation measurements are computed by a PBNN.

3. The PBNN of claim 1 additionally comprising a rule based output combined with said outputted average measurement of said component.