US5654497A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Motor vehicle fuel analyzer
Assignee: Lockheed Martin Energy Systems Inc
•
Filing: 1996-06-03
•
Granted: 1997-08-05
•
Expires: 2016-06-03
Abstract
Abstract A gas detecting system for classifying the type of liquid fuel in a container or tank. The system includes a plurality of semiconductor gas sensors, each of which differs from the other in its response to various organic vapors. The system includes a means of processing the responses of the plurality of sensors such that the responses to any particular organic substance or mixture is sufficiently distinctive to constitute a recognizable "signature". The signature of known substances are collected and divided into two classes based on some other known characteristic of the substances. A pattern recognition system classifies the signature of an unknown substance with reference to the two user-defined classes, thereby classifying the unknown substance with regard to the characteristic of interest, such as its suitability for a particular use.
Inventors
- 👤 Barbara S. Hoffheins
- 👤 Robert J. Lauf
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-31 13:47
CPC Classifications
G; G01; G01N; G01N33/00; G01N33/26; G01N33/28; G01N33/2829
Claims Analysis
Total Claims: 31
Claim 1
Independent Claim
156 words
A system for classifying mixtures of hydrocarbon fuels according to octane or cetane number comprising: an array of gas sensors having different response characteristics to the vapors of different known and unknown fuels such that the set of responses for each of said fuels forms a distinctive signature pattern with respect to octane or cetane number of said fuels, said array comprising at least four sensors; a data acquisition system coupled to said sensor array for deriving said distinctive signature patterns of said known fuels, said data acquisition system comprising at least an analog-to-digital convertor; and a data analysis system comprising at least a neural network coupled to said data acquisition system for comparing the pattern of a sampled fuel mixture to the signature pattern of said known fuels whereby said sampled signature pattern of octane or cetane number is classified with respect to said known patterns of octane or cetane numbers by said neural network.
Claim 2
Independent Claim
156 words
A system for classifying mixtures of hydrocarbon fuels according to octane or cetane number comprising: an array of gas sensors having different response characteristics to the vapors of different known and unknown fuels such that the set of responses for each of said fuels forms a distinctive signature pattern with respect to octane or cetane number of said fuels, said array comprising at least four sensors; a data acquisition system coupled to said sensor array for deriving said distinctive signature patterns of said known fuels, said data acquisition system comprising at least an analog-to-digital convertor; and a data analysis system comprising at least a neural network coupled to said data acquisition system for comparing the pattern of a sampled fuel mixture to the signature pattern of said known fuels whereby said sampled signature pattern of octane or cetane number is classified with respect to said known patterns of octane or cetane numbers by said neural network.
Claim 3
Dependent Claim
51 words
The system of claim 1 wherein said data acquisition system and said data analysis system are incorporated in a digital computer, and wherein said analog-to-digital convertor is a multiple channel analog-to-digital circuit within said digital computer, said analog-to-digital circuit being connected to said gas sensors to receive said set of responses.
Claim 4
Dependent Claim
22 words
The system of claim 2 wherein said data acquisition system further includes a bit pattern conversion program running in said digital computer.
Claim 5
Dependent Claim
20 words
The system of claim 2 wherein said neural network is a software neural network program operating within said digital computer.
Claim 6
Dependent Claim
26 words
The system of claim 2 wherein said data acquisition system further includes a computer program controlling the acquisition of gas sensor data by said analog-to-digital convertor.
Claim 7
Dependent Claim
19 words
The system of claim 1 wherein at least one of said gas sensors is an independently heated gas sensor.
Claim 8
Dependent Claim
26 words
The system of claim 1, wherein the differences in said response characteristics of at least some of said gas sensors result from differences in their preparation.
Claim 9
Dependent Claim
27 words
The system of claim 1, wherein the differences in said response characteristics of at least some of said gas sensors result from differences in their operating temperature.
Claim 10
Dependent Claim
17 words
The system of claim 1, wherein at least one of said gas sensors is a semiconductor sensor.
Claim 11
Dependent Claim
18 words
The system of claim 1, wherein at least one of said gas sensors is a solid state sensor.
Claim 12
Dependent Claim
19 words
The system of claim 1, wherein at least one of said gas sensors is a homogeneous semiconductor gas sensor.
Claim 13
Dependent Claim
26 words
The system of claim 1, wherein the differences in said response characteristics of at least some of said gas sensors result from differences in their composition.
Claim 14
Dependent Claim
21 words
The system of claim 1, wherein said neural network is a software neural network program stored on a programmable memory chip.
Claim 15
Dependent Claim
22 words
The system of claim 1, wherein said data analysis system is an application-specific integrated circuit comprising at least a neural network processor.
Claim 16
Dependent Claim
17 words
The system of claim 1 wherein said array of gas sensors is fabricated onto a single substrate.
Claim 17
Dependent Claim
19 words
A system according to claim 1, wherein said array of gas sensors is fabricated into a single sensor head.
Claim 18
Dependent Claim
47 words
The system of claim 16 further including a plurality of said sensor heads, each in separate locations dispersed about an environment, and means responsive to signals derived from all of said sensors of said heads to determine the identities fuel mixtures present at each of said locations.
Claim 19
Dependent Claim
26 words
The system of claim 1 wherein said known fuel mixtures are taken from the group of liquid fuels comprising gasoline, diesel fuel, aviation fuel, and gasohol.
Claim 20
Dependent Claim
72 words
The system of claim 18 wherein said array of gas sensors additionally have different response characteristics to the vapors of different known and unknown fuels such that the set of responses for each of said fuels additionally forms a distinctive signature pattern with respect to oxygenate or deicer content and wherein said neural network can additionally classify said sampled signature pattern with respect to said know patterns of oxygenate or deicer content.
Claim 21
Dependent Claim
15 words
The system of claim 1 wherein said gas sensor array comprises metal oxide gas sensors.
Claim 22
Dependent Claim
25 words
The system of claim 1 wherein said data acquisition system further includes a bit pattern conversion means for converting said signature patterns into bit patterns.
Claim 23
Dependent Claim
13 words
The system of claim 1 wherein said neural network is a Hamming network.
Claim 24
Dependent Claim
13 words
The system of claim 1 wherein said neural network is a Boltzmann network.
Claim 25
Dependent Claim
30 words
The system of claim 1 wherein said array of gas sensors includes at least ten sensors and wherein at least one of said sensors is dissimilar from the other sensors.
Claim 26
Independent Claim
135 words
A method identifying mixtures of hydrocarbon fuels according to octane or cetane number comprising the steps of: selecting an array of gas sensors, each of said sensors having different response characteristics to the vapors of different known fuels such that the set of sensor responses to each of said known fuels forms a distinctive signature pattern with respect to the octane or cetane number of said fuels, said array of sensors comprising at least four sensors; deriving said signature patterns of said known fuels by analog-to-digital conversion means; and analyzing the signature pattern of a sampled fuels with respect to the signature patterns of said known fuels by neural network means whereby said sampled signature pattern of octane or cetane numbers is classified with respect to said known signature patterns of octane or cetane numbers.
Claim 27
Independent Claim
135 words
A method identifying mixtures of hydrocarbon fuels according to octane or cetane number comprising the steps of: selecting an array of gas sensors, each of said sensors having different response characteristics to the vapors of different known fuels such that the set of sensor responses to each of said known fuels forms a distinctive signature pattern with respect to the octane or cetane number of said fuels, said array of sensors comprising at least four sensors; deriving said signature patterns of said known fuels by analog-to-digital conversion means; and analyzing the signature pattern of a sampled fuels with respect to the signature patterns of said known fuels by neural network means whereby said sampled signature pattern of octane or cetane numbers is classified with respect to said known signature patterns of octane or cetane numbers.
Claim 28
Dependent Claim
21 words
The method of claim 25 including the further step of controlling said analog-to-digital conversion means by a data acquisition computer program.
Claim 29
Dependent Claim
21 words
The method of claim 25 wherein said neural network means is a software neural network program operating within a digital computer.
Claim 30
Dependent Claim
26 words
The method of claim 25 wherein said known fuel mixtures are taken from the group of liquid fuels comprising gasoline, diesel fuel, aviation fuel, and gasohol.
Claim 31
Dependent Claim
23 words
The method of claim 25 including the further step of converting said signature patterns to bit patterns by a bit pattern conversion means.
References Cited (Backward Citations)
US4457161A
Cited
US4638443A
Cited
US4542640A
Cited
US4670405A
Cited
US5106563A
Cited
US4631952A
Cited
US4907441A
Cited
US4818348A
Cited
US5209275A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2000-08-04 | 2001-02-03 | 2001-08-05 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2004-08-04 | 2005-02-03 | 2005-08-05 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2008-08-04 | 2009-02-03 | 2009-08-05 | $7700.00 | Window Closed / Lapsed |