Error detection/correction and fault detection/recovery – Data processing system error or fault handling – Reliability and availability
Reexamination Certificate
2000-05-26
2003-08-19
Iqbal, Nadeem (Department: 2184)
Error detection/correction and fault detection/recovery
Data processing system error or fault handling
Reliability and availability
Reexamination Certificate
active
06609217
ABSTRACT:
BACKGROUND OF THE INVENTION
The present invention relates generally to fault diagnosis and more particularly to using waveform data generated from a machine to provide diagnostics.
In either an industrial or commercial setting, a malfunctioning machine such as an imaging machine can impair a business severely. Thus, it is essential that a malfunctioning imaging machine be repaired quickly and accurately. Usually, during a malfunction of an imaging machine such as a computed tomography (CT) or a magnetic resonance imaging (MRI) machine, a field engineer is called in to diagnose and repair the machine. Typically, the field engineer will run a system performance test to analyze the image quality or the state of the imaging machine. The system performance test generates waveform data which provides a “signature” of the operation of the imaging machine. The waveform data comprises data sets of various readouts and slice combinations. After the system performance test has been run, the field engineer sends the data sets to a service engineer at a remote location for help in diagnosing the malfunction. The service engineer analyzes the data sets and uses their accumulated experience at solving imaging machine malfunctions to find any symptoms that may point to the fault. The field engineer then tries to correct the problem that may be causing the machine malfunction based on the diagnosis provided by the service engineer. If the data sets contain only a small amount of information, then this process will work fairly well. However, if the data sets contains a large amount of imprecise information, as is usually the case for large complex devices, then it is very difficult for the field engineer and the service engineer to quickly diagnose a fault. Therefore, there is a need for a system and method that can quickly diagnose a malfunctioning imaging machine from waveform data sets containing large amount of imprecise information.
SUMMARY OF THE INVENTION
One embodiment of the invention relates to a system and a method for diagnosing a machine from a remote facility over a network. In this embodiment, a diagnostic knowledge base contains a plurality of rules for diagnosing faults in a machine and a plurality of corrective actions for repairing the faults. A diagnostic fault detector categorizes the waveform data generated from the machine as normal and faulty data, wherein the machine is connected to the remote facility over the network. A diagnostic feature extractor extracts a plurality of features from the waveform data categorized as faulty data. A diagnostic fault isolator, coupled to the diagnostic feature extractor and the diagnostic knowledge base, isolates a candidate set of faults for the extracted features and identifies root causes most likely responsible for the candidate set of faults.
Another embodiment of the invention relates to a system and method for performing a validation of waveform data generated from a machine, from a remote facility over a network. The waveform data generated from the machine may be either run-time data or stand-by operation data. In this embodiment, a diagnostic knowledge base contains a plurality of rules for diagnosing faults in the machine. A diagnostic fault detector categorizes the waveform data as normal and faulty data. A diagnostic feature extractor extracts a plurality of features from the waveform data categorized as normal data.
REFERENCES:
patent: 4853946 (1989-08-01), Elliott et al.
patent: 5077768 (1991-12-01), Shigyo et al.
patent: 5331550 (1994-07-01), Stafford et al.
patent: 5463768 (1995-10-01), Cuddihy et al.
patent: 5805160 (1998-09-01), Yoshida et al.
patent: 6025717 (2000-02-01), Hertz et al.
patent: 6473659 (2002-10-01), Shah et al.
patent: 198 29 640 (1999-03-01), None
Bonissone Piero Patrone
Chen Yu-To
Johnson John Andrew
Ramani Vipin Kewal
Ramchandran Ramesh
Bonura Timothy M.
General Electric Company
Goldman David C.
Iqbal Nadeem
Johnson Noreen C.
LandOfFree
System and method for diagnosing and validating a machine... 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 diagnosing and validating a machine..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for diagnosing and validating a machine... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3076489