Data processing: artificial intelligence – Neural network – Learning task
Reexamination Certificate
2000-07-15
2003-10-21
Patel, Ramesh (Department: 2121)
Data processing: artificial intelligence
Neural network
Learning task
C706S021000, C706S046000
Reexamination Certificate
active
06636842
ABSTRACT:
BACKGROUND OF THE INVENTION
The invention relates to a system and method for controlling industrial processes and, more particularly, to a system and method for controlling, monitoring and optimizing processes by processing, transforming and interpreting the process variables.
Industrial processes such as processes within the oil and gas industry are typified by a large number of variables, many of which cannot readily be calculated or predicted using conventional mathematical relationships. A growing volume of available information for such processes has combined with growing complexity of business technology and a greater need for industrial security so as to safeguard personnel, installations and the environment, such that monitoring of multi-variable processes such as those within the oil and gas industry has become a highly complex task.
It is clear that the need exists for a system and method whereby the vast amount of information available regarding various industrial processes, which information contains potentially large numbers of different variables, can be accurately and effectively monitored so as to allow control and/or optimization of a single process or subprocess within the processes being monitored, on an as needed basis. It is therefore the primary object of the present invention to provide a system and method which transforms the multi-variable environment of such processes so as to allow focused attention by an operator on a particular process undergoing unexpected behavior.
It is a further object of the present invention to provide a system and method which allows for local and global optimization of process performance.
It is a still further object of the present invention to provide a system and method which allow for early detection of and reaction to abnormal process situations.
Other objects and advantages of the present invention will appear herein below.
SUMMARY OF THE INVENTION
In accordance with the invention, the foregoing objects and advantages have been readily attained.
In accordance with the invention, a method is provided for monitoring an industrial process, comprising the steps of: providing a knowledge base comprising a two-dimensional representation of operational conditions for said process; obtaining process real time data from said industrial process for a plurality of process variables; selecting relevant features from said real time data; obtaining an operational condition classification from said relevant features; transforming said operational condition classification into a two-dimensional point; and displaying said point on said knowledge base.
In further accordance with the present invention, a system is provided for monitoring an industrial process having at least two process variables, which system comprises a sensor member for obtaining real time data for said process variables; a processor unit for receiving said real time data, extracting relevant features from said real time data, obtaining an operational condition classification from said relevant features, and generating a two-dimensional point corresponding to said operational condition classification; and a knowledge-base having a two-dimensional representation of process operational conditions and being associated with said processor unit to display said point on said representation.
REFERENCES:
patent: 4228509 (1980-10-01), Kennedy
patent: 4358822 (1982-11-01), Sanchez
patent: 5023912 (1991-06-01), Segawa
patent: 5339257 (1994-08-01), Layden et al.
patent: 5373486 (1994-12-01), Dowla et al.
patent: 5949678 (1999-09-01), Wold et al.
patent: 6286363 (2001-09-01), Discenzo
patent: 6295510 (2001-09-01), Discenzo
patent: 0 952 501 (1999-10-01), None
An article entitled, “Kohonen and Counterpropagation Artificial Neural Networks, In Analytical Chemistry,” By Zupan et al., published by Chemometrics and Intelligent Laboratory Systems, vol. 38, Feb. 27, 1997, pp. 1-23.
Aponte Hugo E.
Fernandes Jose
Suarez Alexis A
Vazquez Manuel
Zambrano Alexander
Bachman & LaPointe P.C.
Hirl Joseph P.
Intevep S.A.
Patel Ramesh
LandOfFree
System and method for controlling an industrial process... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for controlling an industrial process..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for controlling an industrial process... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3137275