Error detection/correction and fault detection/recovery – Data processing system error or fault handling – Reliability and availability
Reexamination Certificate
2000-01-26
2003-11-04
Beausoliel, Robert (Department: 2184)
Error detection/correction and fault detection/recovery
Data processing system error or fault handling
Reliability and availability
C701S029000, C701S030000, C701S035000
Reexamination Certificate
active
06643801
ABSTRACT:
BACKGROUND OF THE INVENTION.
The present invention relates generally to machine diagnostics, and more specifically, to a system and method for estimating time-to-road failure using fault pattern recognition and time-line analysis.
A machine, such as a locomotive or other complex systems used in industrial processes, medical imaging, telecommunications, aerospace applications, power generation, etc., includes elaborate controls and sensors that generate faults when anomalous operating conditions of the machine are encountered. Typically, a field engineer will look at a fault log and determine whether a repair is necessary.
Approaches like neural networks, decision trees, etc., have been employed to learn over input data to provide prediction, classification, and function approximation capabilities in the context of diagnostics. Often, such approaches have required structured and relatively static and complete input data sets for learning, and have produced models that resist real-world interpretation.
Another approach, Case Based Reasoning (CBR), is based on the observation that experiential knowledge (memory of past experiences—or cases) is applicable to problem solving as learning rules or behaviors. CBR relies on relatively little pre-processing of raw knowledge, focusing instead on indexing, retrieval, reuse, and archival of cases. In the diagnostic context, a case refers to a problem/solution description pair that represents a diagnosis of a problem and an appropriate repair.
CBR assumes cases described by a fixed, known number of descriptive attributes. Conventional CBR systems assume a corpus of fully valid or “gold standard” cases that new incoming cases can be matched against.
U.S. Pat. No. 5,463,768 discloses an approach which uses error log data and assumes predefined cases with each case associating an input error log to a verified, unique diagnosis of a problem. In particular, a plurality of historical error logs are grouped into case sets of common malfunctions. From the group of case sets, common patterns, i.e., consecutive rows or strings of data, are labeled as a block. Blocks are used to characterize fault contribution for new error logs that are received in a diagnostic unit. Unfortunately, for a continuous fault code stream where any or all possible fault codes may occur from zero to any finite number of times and where the fault codes may occur in any order, predefining the structure of a case is nearly impossible.
U.S. patent application Ser. No. 09/285,611, (Attorney Docket No. RD-26,576), assigned to the same assignee of the present invention and herein incorporated by reference, discloses a system and method for processing historical repair data and fault log data, which is not restricted to sequential occurrences of fault log entries and which provides weighted repair and distinct fault cluster combinations to facilitate analysis of new fault log data from a malfunctioning machine. Further, U.S. patent application Ser. No. 09/285,612, (Attorney Docket No. 20-LC-1927), assigned to the same assignee of the present invention and herein incorporated by reference, discloses a system and method for analyzing new fault log data from a malfunctioning machine wherein the system and method are not restricted to sequential occurrences of fault log entries, and further wherein the system and method predict one or more repair actions using predetermined weighted repair and distinct fault cluster combinations.
It is believed that the inventions disclosed in the foregoing patent applications provide substantial advantages and advancements in the art of diagnostics. It would be desirable, however, to be able to provide accurate and reliable estimates of the time it takes for a road failure to actually occur from the time predetermined faults or fault patterns begin to occur in the locomotive. The foregoing ability would be particularly useful to determine not only whether an impending road failure is developing but would enable to quantify when that road failure is likely to occur. Road failures in locomotives and other machines give rise to costly inefficiencies since, in the case of a locomotive, they stop the locomotive from transporting freight and passengers and contribute to lost revenue, productivity and good will. Having the ability to reliably and accurately predict the cause and the timing of any road failure is desirable since it would enable to schedule corrective action at the most appropriate time. For example, instead of rushing the locomotive to the nearest service center, depending on the length of the predicted time before the road failure, the locomotive could still be operated for a certain period of time thereby preventing loss of revenue and productivity. Conversely, if the predicted time before the road failure is relatively short, then the locomotive repair may be prioritized over other locomotives that are not facing an imminent road failure.
BRIEF SUMMARY OF THE INVENTION
Generally speaking, the present invention fulfills the foregoing needs by providing a method for analyzing fault log data and repair data to estimate time before a machine-disabling failure occurs. The method allows for searching in a database of historical fault log data from a plurality of machines for the occurrence of respective fault patterns indicative of incipient failures of a respective machine subsystem. The method further allows for searching in a database of historical repair data for respective repairs executed on the respective machine subsystem. The method also allows for computing elapsed time between respective occurrences of the fault patterns and the executed repairs.
The present invention further fulfills the foregoing needs by providing a system for analyzing fault log data and repair data to estimate time before a machine-disabling failure occurs. The system includes a database of historical fault log data from a plurality of machines and a first search module configured to search in the database of historical fault log data for the occurrence of respective fault patterns indicative of incipient failures of a respective machine subsystem. The system further includes a database of historical repair data and a search module configured to search in the database of historical repair data for respective repairs executed on the respective machine subsystem. A computer module is configured to compute elapsed time between respective occurrences of the fault patterns and the executed repair.
REFERENCES:
patent: 4041470 (1977-08-01), Slane et al.
patent: 4270174 (1981-05-01), Karlin et al.
patent: 4463418 (1984-07-01), O'Quin, II et al.
patent: 4517468 (1985-05-01), Kemper et al.
patent: 4695946 (1987-09-01), Andreasen et al.
patent: 4823914 (1989-04-01), McKinney et al.
patent: 4970725 (1990-11-01), McEnroe et al.
patent: 4977390 (1990-12-01), Saylor et al.
patent: 5113489 (1992-05-01), Cihiwsky et al.
patent: 5123017 (1992-06-01), Simpkins et al.
patent: 5210704 (1993-05-01), Husseiny
patent: 5253184 (1993-10-01), Kleinschnitz
patent: 5274572 (1993-12-01), O'Neill et al.
patent: 5282127 (1994-01-01), Mii
patent: 5321837 (1994-06-01), Daniel et al.
patent: 5329465 (1994-07-01), Arcella et al.
patent: 5400018 (1995-03-01), Scholl et al.
patent: 5406502 (1995-04-01), Haramaty et al.
patent: 5445347 (1995-08-01), Ng
patent: 5463768 (1995-10-01), Cuddihy et al.
patent: 5508941 (1996-04-01), Leplingard et al.
patent: 5528516 (1996-06-01), Yemini et al.
patent: 5594663 (1997-01-01), Messaros et al.
patent: 5596712 (1997-01-01), Tsuyama et al.
patent: 5633628 (1997-05-01), Denny et al.
patent: 5638296 (1997-06-01), Johnson et al.
patent: 5661668 (1997-08-01), Yemini et al.
patent: 5666534 (1997-09-01), Gilbert et al.
patent: 5678002 (1997-10-01), Fawcett et al.
patent: 5742915 (1998-04-01), Stafford
patent: 5933821 (1999-08-01), Matsumoto et al.
patent: 5950147 (1999-09-01), Sarangapani et al.
patent: 6247145 (2001-06-01), Witteried
patent: 6418361 (2002-07-01), Sinex
Butler, K. L.; “An Expert System Based Framework For An Incipient Failure Detection and P
Bliley Richard Gerald
Jammu Vinay Bhaskar
Schneider William Roy
Agosti Ann M.
Beausoliel Robert
Beusse Brownlee Bowdoin & Wolter PA
Duncan Marc M
General Electric Company
LandOfFree
Method and system for estimating time of occurrence of... 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 system for estimating time of occurrence of..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and system for estimating time of occurrence of... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3158864