Data processing: database and file management or data structures – Database design – Data structure types
Reexamination Certificate
1999-10-08
2002-08-27
Alam, Hosain T. (Department: 2172)
Data processing: database and file management or data structures
Database design
Data structure types
C707S793000, C706S047000, C714S026000, C714S025000
Reexamination Certificate
active
06442542
ABSTRACT:
FIELD OF THE INVENTION
The present invention generally relates to diagnostic systems and, in particular, to a diagnostic system with learning capabilities.
BACKGROUND OF THE INVENTION
Hospitals and other medical facilities utilize a variety of imaging scanner equipment, including computed tomography (“CT”) scanners, magnetic resonance imaging (“MRI”) systems, and x-ray apparatus to produce images of internal parts of test subjects under examination. Over time, these medical imaging devices may develop a wide variety of mechanical or electrical problems. If such problems are not resolved promptly, malfunctioning imaging devices may exhibit image quality imperfections, resulting in possible misdiagnosis in addition to economic losses.
One way to diagnose and repair imaging equipment suspected of malfunction is to have a field engineer run a system performance test (“SPT”) to analyze the image quality or the state of the equipment. The SPT generates a number of data files which provide a “signature” of the operation of the; imaging equipment. The data files generated by the imaging equipment are analyzed by a knowledge facilitator (e.g., service engineer) who will try to identify faulty components or conditions associated therewith based on his/her accumulated experience with identifying malfunctions. Then, based on the diagnosis provided by the knowledge facilitator, the field engineer will try to correct the problem that may be causing the equipment malfunction.
One problem that occurs with the use of a knowledge facilitator to manually analyze data files is the difficulty associated with evaluating a large amount of imprecise information, as is usually the case for complex devices such as medical imaging equipment.
BRIEF SUMMARY OF THE INVENTION
Thus, there is a particular need for a system that is capable of diagnosing a machine by analyzing data generated thereby. In particular, there is a need for a diagnostic system capable of learning so that after each learning process the system's ability to identify the fault causing the machine malfunction may be enhanced. The learning process may occur in response to a misdiagnosis produced by the diagnostic system or in response to the system's inability to identify any fault. During the learning process, the trained data and rules used for diagnosing faults may be updated, based on fault type input by a knowledge facilitator, so as to more accurately identify a faulty component or condition during subsequent analysis.
The present invention is directed to a diagnostic system and corresponding method for identifying faults in a machine (e.g., CT scanner, MRI system, x-ray apparatus) by analyzing a data file generated thereby. The diagnostic system includes a trained database containing a plurality of trained data, each trained data associated with one of plurality of known fault types. Each trained data is represented by a trained set of feature values and corresponding weight values. Once a data file is generated by the machine (e.g., by performing a system performance test), a current set of feature values is extracted from the data file by performing various analyses (e.g., time domain analysis, frequency domain analysis, wavelet analysis). The current set of feature values extracted is analyzed by a fault detector which produces a candidate set of faults based on the trained set of feature values and corresponding weight values for each of the fault types. The candidate set of faults produced by the fault detector is presented to a user along with a recommended repair procedure. In cases where no fault is identified or a wrong fault is diagnosed, the user may interactively input a faulty condition associated with the machine being diagnosed (e.g., based on his/her experience). The diagnostic system further includes a learning subsystem which automatically updates the plurality of trained data based on the faulty condition input by the user.
REFERENCES:
patent: 5046034 (1991-09-01), Stark et al.
patent: 5214653 (1993-05-01), Elliott, Jr. et al.
patent: 5347595 (1994-09-01), Bokser
patent: 5351247 (1994-09-01), Dow et al.
patent: 5463768 (1995-10-01), Cuddihy et al.
patent: 5533093 (1996-07-01), Horton et al.
patent: 5566092 (1996-10-01), Wang et al.
patent: 5764509 (1998-06-01), Gross et al.
patent: 6105149 (2000-08-01), Bonissone et al.
patent: 6138109 (2000-10-01), Grichnik et al.
patent: 9829640 (1999-03-01), None
“Generic Software Tool to Improve Diagnostic Systems by Feedback of Field Experience Data,” Setaruddin et al., Proceedings of the 1990 IEEE conference on AUTOTESTCON, Sep. 17-21, 1990, pp. 485-490.*
“Wavelet Analysis for Diagnostic Problems,” Contu et al., Proceedings of the 1996 MELECON Conference, IEEE, vol. 3, May 13-16 1996, pp. 1571-1574.*
“Pattern-Based Fault Diagnosis Using Neural Networks,” Dietz et al., Proceedings of the First International Conference of Industrial & Engineering Applications of Artificial Intelligence & Expert System, 1988, ACM Press, pp. 13-23.
Bonissone Piero Patrone
Chen Yu-To
Johnson John Andrew
Ramachandran Ramesh
Ramani Vipin Kewal
Alam Hosain T.
Breedlove Jill M.
Goldman David C.
LandOfFree
Diagnostic system with learning capabilities does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Diagnostic system with learning capabilities, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Diagnostic system with learning capabilities will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2905943