US5265192A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method for the automated editing of seismic traces using an adaptive network
Assignee: Atlantic Richfield Co
•
Filing: 1990-09-20
•
Granted: 1993-11-23
•
Expires: 2010-09-20
Abstract
Abstract An adaptive, or neural, network and a method of operating the same is disclosed which is particularly adapted for performing seismic trace editing for seismic shot records. The adaptive network is first trained according to the generalized delta rule. The disclosed training method includes backpropagation is performed according to the worst case error trace, including adjustment of the learning and momentum factors to increase as the worst case error decreases. Slow convergence regions are detected, and methods applied to escape such regions including restoration of previously trimmed dormant links, renormalization of the weighting factor values, and the addition of new network layers with links between nodes that skip the hidden layer. After the training of the network, data corresponding to a Discrete Fast Fourier Transform of each trace, and to certain other attributes of the trace and adjacent traces thereto, are presented to the network. The network classifies the trace as good or noisy according to the inputs thereto, and to the weighting factors therewithin, such classification useful for ignoring noisy traces in subsequent data analysis. The analysis may be repeated for all of the traces in the shot record, and in multiple shot records.
Inventors
- 👤 Michael D. McCormack
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-25 22:14
CPC Classifications
G; G01; G01V; G01V1/00; G01V1/28; G01V1/36; G01V1/364; G01V2210/00; G01V2210/30; G01V2210/32
Claims Analysis
Total Claims: 22
Claim 1
Independent Claim
119 words
A method for operating a computer as an adaptive network to classify each of a plurality of seismic traces as useful or noisy, according to noise amplitude of in each trace, each of said traces corresponding to seismic vibrations detected responsive to a seismic source input signal, comprising: retrieving stored data representative of a first of said plurality of traces; generating a frequency domain amplitude spectrum for said first trace from said retrieved data; presenting data from said frequency domain amplitude spectrum to input nodes of said adaptive network, said adaptive network indicating, responsive to said frequency domain amplitude spectrum data, a classification of said first trace as useful or noisy; and storing the result of said presenting step.
Claim 2
Independent Claim
119 words
A method for operating a computer as an adaptive network to classify each of a plurality of seismic traces as useful or noisy, according to noise amplitude of in each trace, each of said traces corresponding to seismic vibrations detected responsive to a seismic source input signal, comprising: retrieving stored data representative of a first of said plurality of traces; generating a frequency domain amplitude spectrum for said first trace from said retrieved data; presenting data from said frequency domain amplitude spectrum to input nodes of said adaptive network, said adaptive network indicating, responsive to said frequency domain amplitude spectrum data, a classification of said first trace as useful or noisy; and storing the result of said presenting step.
Claim 3
Dependent Claim
37 words
A method of claim 1, further comprising: generating a plurality of attributes for said first trace from said retrieved stored data; and wherein said presenting step also presents said attributes to input nodes of said adaptive network.
Claim 4
Dependent Claim
42 words
The method of claim 2, wherein said retrieved stored data corresponds to time domain amplitudes of said seismic vibrations; and wherein said generating step comprises: performing a Fast Fourier Transform on said time domain amplitudes to generate said frequency domain amplitude spectrum.
Claim 5
Dependent Claim
71 words
The method of claim 3, wherein said generating step further comprises: normalizing the amplitudes of said frequency domain amplitude spectrum to within a predetermined range, said frequency domain amplitude spectrum comprising amplitude values at sample frequencies; and assigning a digital value to each sample frequency corresponding to the amplitude value of the sample frequency; and wherein said presenting step presents said digital value to said input nodes of the adaptive network.
Claim 6
Dependent Claim
13 words
The method of claim 2, wherein said attributes correspond to said first trace.
Claim 7
Dependent Claim
18 words
The method of claim 2, wherein said retrieving and generating steps are for a plurality of said traces.
Claim 8
Dependent Claim
31 words
The method of claim 6, wherein a first of said attributes corresponds to said first trace, and a second of said attributes corresponds to said first trace and a second trace.
Claim 9
Dependent Claim
42 words
The method of claim 1, wherein said retrieved stored data corresponds to time domain amplitudes of said seismic vibrations; and wherein said generating step comprises: performing a Fast Fourier Transform on said time domain amplitudes to generate said frequency domain amplitude spectrum.
Claim 10
Dependent Claim
71 words
The method of claim 8, wherein said generating step further comprises: normalizing the amplitudes of said frequency domain amplitude spectrum to within a predetermined range, said frequency domain amplitude spectrum comprising amplitude values at sample frequencies; and assigning a digital value to each sample frequency corresponding to the amplitude value of the sample frequency; and wherein said presenting step presents said digital value to said input nodes of the adaptive network.
Claim 11
Dependent Claim
19 words
The method of claim 1, further comprising: setting weighting factors in said adaptive network according to a backpropagation method.
Claim 12
Dependent Claim
152 words
The method of claim 10, wherein said setting step comprises: displaying a sample shot record; identifying a useful sample trace and a noisy sample trace; generating a frequency domain amplitude spectrum for each of said useful and noisy sample traces; presenting data from said frequency domain amplitude spectrum for each of said useful and noisy sample traces to input nodes of said adaptive network, said adaptive network indicating, responsive to said frequency domain amplitude spectrum data and to said weighting factors, values at its output corresponding to classification of each of said useful and noisy sample traces as useful or not useful; comparing the output of said adaptive network for each of said sample traces with a desired output for each of said useful and noisy sample traces; and adjusting the weighting factors of said adaptive network according to a generalized delta rule and responsive to the result of said comparing step.
Claim 13
Independent Claim
163 words
A method of operating an adaptive network in a computing apparatus, said apparatus including stored data representative of a seismic shot record including a plurality of traces, said stored data corresponding to time domain data for each of said traces, comprising: retrieving a portion of said stored data corresponding to a plurality of traces; generating a frequency domain amplitude spectrum for a first trace from said retrieved data; calculating a first attribute value for said first trace from said retrieved data; applying data from said frequency domain amplitude spectrum and said first attribute value to a computer program having the form of an adaptive network, said adaptive network generating outputs for indicating whether the trace associated with the data presented to its inputs is useful or is noisy, said indication based upon the setting of adaptive network weighting factors according to the generalized delta rule from sample useful and noisy traces; and storing the outputs of said adaptive network for said first trace.
Claim 14
Independent Claim
163 words
A method of operating an adaptive network in a computing apparatus, said apparatus including stored data representative of a seismic shot record including a plurality of traces, said stored data corresponding to time domain data for each of said traces, comprising: retrieving a portion of said stored data corresponding to a plurality of traces; generating a frequency domain amplitude spectrum for a first trace from said retrieved data; calculating a first attribute value for said first trace from said retrieved data; applying data from said frequency domain amplitude spectrum and said first attribute value to a computer program having the form of an adaptive network, said adaptive network generating outputs for indicating whether the trace associated with the data presented to its inputs is useful or is noisy, said indication based upon the setting of adaptive network weighting factors according to the generalized delta rule from sample useful and noisy traces; and storing the outputs of said adaptive network for said first trace.
Claim 15
Dependent Claim
62 words
The method of claim 12, wherein said retrieving step retrieves stored data for a plurality of traces; further comprising: calculating a second attribute for said first trace, said second attribute corresponding to an attribute of said first trace relative to a second trace; and wherein said applying step also applies data corresponding to said second attribute to inputs of said adaptive network.
Claim 16
Dependent Claim
24 words
The method of claim 12, wherein said frequency domain amplitude spectrum comprises a set of discrete amplitude values, each associated with a sample frequency.
Claim 17
Dependent Claim
44 words
The method of claim 12, further comprising: assigning a digital value to each of said sample frequencies in said frequency domain amplitude spectrum, said digital values for said set of discrete amplitude values corresponding to a graphical representation of said frequency domain amplitude spectrum.
Claim 18
Dependent Claim
24 words
The method of claim 15, wherein said applying step applies each bit of said digital values to an input node of said adaptive network.
Claim 19
Dependent Claim
21 words
The method of claim 12, wherein said calculating step comprises calculating a decay rate for said trace as said first attribute.
Claim 20
Dependent Claim
22 words
The method of claim 12, wherein said calculating step comprises calculating said first attribute based on a peak amplitude of said trace.
Claim 21
Dependent Claim
19 words
The method of claim 12, wherein said calculating step comprises calculating a maximum cross-correlation value as said first attribute.
Claim 22
Dependent Claim
19 words
The method of claim 12, wherein said calculating step comprises calculating an average frequency value as said first attribute.
References Cited (Backward Citations)
US5150323A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1996-11-22 | 1997-05-24 | 1997-11-23 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2000-11-22 | 2001-05-24 | 2001-11-23 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2004-11-22 | 2005-05-24 | 2005-11-23 | $7700.00 | Window Closed / Lapsed |