Neural network based system for equipment surveillance
Patent
·
OSTI ID:871513
- Aurora, IL
- Bolingbrook, IL
- Glendale Hts., IL
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.
- Research Organization:
- Argonne National Laboratory (ANL), Argonne, IL
- DOE Contract Number:
- W-31109-ENG-38
- Assignee:
- ARCH Development Corporation (Chicago, IL)
- Patent Number(s):
- US 5745382
- OSTI ID:
- 871513
- Country of Publication:
- United States
- Language:
- English
Review of Neural Networks for Speech Recognition
|
journal | March 1989 |
Modular Construction of Time-Delay Neural Networks for Speech Recognition
|
journal | March 1989 |
Similar Records
Neural network based system for equipment surveillance
Neural Network Based System for Equipment Startup Surveillance
Opening up the black box of artificial neural networks
Patent
·
Tue Apr 28 00:00:00 EDT 1998
·
OSTI ID:644423
Neural Network Based System for Equipment Startup Surveillance
Software
·
Wed Dec 18 00:00:00 EST 1996
·
OSTI ID:1230377
Opening up the black box of artificial neural networks
Journal Article
·
Sun May 01 00:00:00 EDT 1994
· Journal of Chemical Education
·
OSTI ID:131612
Related Subjects
/706/702/
achieving
ascertain
based
characteristic
close
comparing
data
desired
desired set
determined
determining
device
equipment
evaluate
inadequate
industrial
industrial process
involves
memory
method
network
network based
neural
neural net
neural network
operating
output
outputs
parameters
performing
performing surveillance
process
process signals
providing
reading
set
signals
steps
surveillance
target
training
training data
transient
transient signal
values
wavelet
weighting
yield
achieving
ascertain
based
characteristic
close
comparing
data
desired
desired set
determined
determining
device
equipment
evaluate
inadequate
industrial
industrial process
involves
memory
method
network
network based
neural
neural net
neural network
operating
output
outputs
parameters
performing
performing surveillance
process
process signals
providing
reading
set
signals
steps
surveillance
target
training
training data
transient
transient signal
values
wavelet
weighting
yield