Skip to Content
Find More Like This
Return to Search

Neural network based system for equipment surveillance

United States Patent

5,745,382
April 28, 1998
View the Complete Patent at the US Patent & Trademark Office
Argonne National Laboratory - Visit the Technology Development and Commercialization Website
A method and system for performing surveillance of transient signals of an industrial device to ascertain the operating state. The method and system involves the steps of reading into a memory training data, determining neural network weighting values until achieving target outputs close to the neural network output. If the target outputs are inadequate, wavelet parameters are determined to yield neural network outputs close to the desired set of target outputs and then providing signals characteristic of an industrial process and comparing the neural network output to the industrial process signals to evaluate the operating state of the industrial process.
Vilim; Richard B. (Aurora, IL), Gross; Kenneth C. (Bolingbrook, IL), Wegerich; Stephan W. (Glendale Hts., IL)
ARCH Development Corporation (Chicago, IL)
08/ 521,892
August 31, 1995
The invention was made with U.S. Government support under Contract No. W-31-109-ENG-38 awarded by the Department of Energy, and the U.S. Government has certain rights in this invention.