System and method for predicting parameter of hydrocarbon...

Data processing: artificial intelligence – Neural network – Learning task

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C324S303000

Reexamination Certificate

active

06477516

ABSTRACT:

BACKGROUND OF THE INVENTION
The invention relates to a system and method for predicting parameters of a hydrocarbon using spectroscopy and neural networks.
In the oil industry, it is frequently desirable or necessary to accurately determine crude, feed and product quality parameters in order to comply with customer specifications without quality give away. These determinations are also very useful for advanced process control. There are in existence technologies, like Near Infrared and UV-Visible spectroscopy, that can handle measurements in some of the feedstocks and products processed in the industry. However, these techniques lack the capability of analyzing heavy crude oils and heavy products, due to the fact that they are optical spectroscopies. A way to overcome this situation is by means of Nuclear Magnetic Resonance (NMR) Spectroscopy, which has the capability to detect signals from the entire range of hydrocarbons mentioned above, including the heavy hydrocarbon products.
Some examples of useful heavy products having properties that must be known or measured are heavy distillation cuts, such as vacuum gasoil, vacuum residua, asphalts, pitches and the like. Asphalts are classified, based on rheological properties that have a temperature dependency, according to the Strategic Highway Research Program (SHRP) parameters which frequently must be determined by performing conventional, time consuming laboratory analysis including aging, further processing and the like. For alternative analytical methods, only one publication (Michon, L.; Hanquet, B.; Diawara, B.; Martin, D.; Planche, J-P. Asphalt Study by Neuronal networks. Correlation between Chemical and Rheological Properties. Energy & Fuel, 11, 1188-93, 1997) has been found which attempts to correlate bitumen rheological properties and average molecular parameters using
13
C NMR and neural networks. The quality of the results of Michon et al. does not comply with the precision and low cost needed for a viable commercial application.
Asphalts are typically a blend of various different hydrocarbon ingredients and actual samples of different blends must conventionally be prepared in order for their properties or parameters to be measured. Clearly, the need remains for a faster yet reliable method for determining such parameters.
Further hydrocarbon products include heavy petroleum products such as pitch, vacuum residua and vacuum gasoil, all of which have properties which must be known in order to determine the potential commercial value of these products. However, determining parameters of these products is subject to the same delays and complications in connection with laboratory analysis as with the asphalt scenario outlined above.
It is therefore the primary object of the present invention to provide a system and method for predicting a parameter of a hydrocarbon.
It is a further object of the present invention to provide a system and method which provide a prediction in a relatively short time period, without sacrificing accuracy.
It is still another object of the present invention to provide a system and method which can be used to predict parameters of various blends of hydrocarbons without requiring preparation of samples of each blend.
It is another object of the present invention to provide a system and method that can be used to predict parameters of a wide range of types of hydrocarbons including heavy hydrocarbons and other hydrocarbons as well.
It is still another object of the present invention to provide a system and method which can be used to predict stability and compatibility parameters of various crude, crude blends, hydrocarbons products and hydrocarbon product blends.
Other objects and advantages of the present invention will appear hereinbelow.
SUMMARY OF THE INVENTION
In accordance with the present invention, the foregoing objects and advantages have been readily attained.
According to one embodiment of the invention, a method is provided for predicting parameters of hydrocarbons, which method comprises the steps of generating an NMR spectrum of a sample of a hydrocarbon; determining at least one average molecular parameter from said spectrum so as to provide at least one spectrum extracted quantity, and applying said at least one spectrum extracted quantity to a trained neural network trained to correlate spectrum extracted quantities with hydrocarbon parameters so as to predict said desired parameter from said spectrum extracted quantity.
According to an another embodiment of the invention, a a method is provided for predicting parameters of hydrocarbons, which method comprises the steps of generating an NMR spectrum of a sample of a hydrocarbon having different hydrogen or carbon types; dividing said NMR spectrum into regions corresponding to said different hydrogen or carbon types; selecting at least one of said regions based upon a desired parameter to be predicted; quantifying a signal intensity of said at least one region, so as to provide at least one spectrum extracted quantity; and applying said at least one spectrum extracted quantity to a trained neural network trained to correlate spectrum extracted quantities with hydrocarbon parameters so as to predict said desired parameter from said spectrum extracted quantity.
In further accordance with the invention, a system has been provided for predicting parameters of hydrocarbons, which system comprises means for generating an NMR spectrum from a hydrocarbon sample; a processor member communicated with said means for generating and adapted to provide at least one spectrum extracted quantity; and a trained neural network communicated with said processor member so as to receive said at least one spectrum extracted quantity, said trained neural network being programmed to correlate spectrum extracted quantities with hydrocarbon parameters so as to predict said desired parameter from said spectrum extracted quantity.


REFERENCES:
patent: 5218529 (1993-06-01), Meyer et al.
patent: 5302897 (1994-04-01), Tache et al.
patent: 5319308 (1994-06-01), Dechene et al.
patent: 5519319 (1996-05-01), Smith et al.
patent: 5530350 (1996-06-01), Dechene et al.
patent: 5625750 (1997-04-01), Puskorius et al.
patent: 5650722 (1997-07-01), Smith et al.
patent: 5675253 (1997-10-01), Smith et al.
patent: 5871805 (1999-02-01), Lemeison
patent: 6060293 (2000-05-01), Bohr et al.
patent: 6255819 (2001-07-01), Day et al.
patent: 6272479 (2001-08-01), Furry et al.
patent: 6295504 (2001-09-01), Ye et al.
patent: 6337568 (2002-01-01), Tutunji et al.
patent: 6341629 (2002-01-01), Clark et al.
patent: WO9202886 (1992-02-01), None
patent: WO 92/02886 (1992-02-01), None
Average molecular weight of oil fractions by nuclear magnetic resonance, Viadimir Leon; Fuel 1987, vol. 66 Oct.*
Estimation of average structural parameters of bitumens by 13c nuclear resonance spectroscopy, Laurent Michon; Didier Martin; Jean-Pascal Planche and Bernard Hanquet; Feul (1997) vol. 76, No. 1.*
Average Molecular Weight of Oil Fractions by Nuclear Magnetic Resonance, by Leon, Fuel, 1987, vol. 66, pp. 1445-1446.
Estimation of Average Structural Parameters of Bitumens 13C Nuclear Magnetic Resonance Spectroscopy, by Michon et al., Fuel, vol. 76, No. 1, pp. 9-15, 1997.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

System and method for predicting parameter of hydrocarbon... 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 predicting parameter of hydrocarbon..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for predicting parameter of hydrocarbon... will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-2930551

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.