Method and procedure for neural control of dynamic processes

• US 5,175,678 A
• Filed: 08/15/1990
• Issued: 12/29/1992
• Est. Priority Date: 08/15/1990
• Status: Expired due to Fees

• Current Assignee: Elsag International NV
• Original Assignee: Elsag International NV
• Inventors: Keyes, Marion A. IV, Kaya, Azmi, Frerichs, Donald K.
• Primary Examiner(s): Smith, Jerry
• Assistant Examiner(s): GORDON, PAUL P
• Application Number:
  US07/567,873
• Time in Patent Office: 867 Days
• Field of Search: 364/148, 364/164, 364/165, 395/21
• US Class Current: 700/47
• CPC Class Codes: G05B 13/027 using neural networks only
• CPC Class Codes: Y10S 706/906 Process plant

Abstract

A neural network control based on a general multi-variable nonlinear dynamic model incorporating time delays is disclosed. The inverse dynamics of the process being controlled is learned represented by a multi-layer neural network which is used as a feedforward control to achieve a specified closed loop response under varying conditions. The weights between the layers in the neural network are adjusted during the learning process. The learning process is based on minimizing the combined error between the desired process value and the actual process output and the error between the desired process value and the inverse process neural network output.

Claims

1. A system for controlling a dynamic process to produce a desired process value comprising means for producing an inverse dynamics of the process being controlled, means responsive to said inverse dynamics producing means, said responsive means modifying the desired process value to produce a signal causing an output of the process to approach the desired process value, first means for determining an error between the desired process value and the output of the process, said inverse dynamic producing means being responsive to the error produced by said first error determining means, and second means for determining the error between the desired process value and the output of said inverse process dynamics producing means, said inverse dynamic producing means being responsive to the error produced by said second error producing means.