Data processing: measuring – calibrating – or testing – Measurement system in a specific environment – Earth science
Reexamination Certificate
1999-05-28
2001-06-12
Patidar, Jay (Department: 2862)
Data processing: measuring, calibrating, or testing
Measurement system in a specific environment
Earth science
C702S017000
Reexamination Certificate
active
06246962
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Technical Field
The present invention relates to an improved method and apparatus for filtering noise to detect downhole events. More specifically, the invention utilizes a neural-network based filtering system to detect faint signals from within a noisy environment such as an oil well.
2. Description of the Related Art
It is important to know if a perforation gun has detonated completely, partially, or not at all. However, this can be difficult to know with absolute certainty when the gun has been lowered several thousand feet into an oil well. The fluid in the well can dampen the vibration from the detonation. The sound from the detonation can be detected and amplified. However. the amplified signal can still be undecipherable because it is intermixed with the random and periodic noises produced around the well. Noise sources can include engines and pumps, the sound of fluid passing through pipes, and the impact of metal tools on pipes. A need exists for an improved method of filtering the noise from the signal so that the undetonated or partially detonated gun is safely handled.
In addition to perforation guns, it is also desirable to monitor many downhole events, such as the actuation of a device, the latching of two interconnecting devices, or the breaking of shear pins. In each case, a distinctive sound or signal will be produced. But, detecting this signal will be hampered by the inherent noise of the environment. And while the examples given so far involve detection of the signal at the surface of a downhole event, the need may be reversed so that an intelligent downhole device can adequately detect a signal initiated at the surface.
A need exists for an improved method of filtering the noise from the desired signal. Such a method should include an adaptive method of correcting the error from earlier filtering efforts, in essence tuning itself to the needs of the particular well and surface environments.
SUMMARY
The present invention relates to a method of applying adaptive filtering methods for the purpose of improving the detection of event signals in in an oil well environment. Event signals can include, but not be limited to, sound, vibrations, electromagnetic energy, and pressure fluctuations. The use of adaptive filtering allows the user to both amplify desirable signals and remove unwanted contaminating signals, which tend to “mask” the desirable signals. The method can be implemented in an apparatus that uses real-time adaptive neural network filtering to enhance the detection of an event signal such as a subsurface explosive detonation in an oil well.
Adaptive neural networks can be used to effectively enhance signal detection in the inherently noisy environment of an oil well. The neural network can be either non-recurrent or recurrent in nature. The system is implemented with a computer that accepts input from at least one sensor mounted to the wellhead or near the wellhead. The detected contaminated signal is a combination of the event signal and the noise from the environment. The event signal can be, for example, the detonation of a perforation gun. The noise can be either random or periodic. The use of adaptive filtering allows the noise to be more precisely predicted and then subtracted from the contaminated signal to produce a cleaner representation of the event signal. Once the predicted noise is subtracted, the remaining representation of the event signal can be analyzed using voice or sound recognition to produce an output describing what event occurred.
REFERENCES:
patent: 5339036 (1994-08-01), Clark
patent: 5576703 (1996-11-01), MacLeod et al.
patent: 5694474 (1997-12-01), Ngo et al.
patent: 5941307 (1999-08-01), Tubel
Burleson John D.
Schultz Roger L.
Carstens David W.
Halliburton Energy Service,s Inc.
Herman Paul I.
Patidar Jay
Taylor Victor J.
LandOfFree
Method and apparatus for adaptively filtering noise to... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for adaptively filtering noise to..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for adaptively filtering noise to... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2462653