Data processing: measuring – calibrating – or testing – Measurement system – Statistical measurement
Reexamination Certificate
1999-11-04
2003-09-23
Hoff, Marc S. (Department: 2857)
Data processing: measuring, calibrating, or testing
Measurement system
Statistical measurement
Reexamination Certificate
active
06625567
ABSTRACT:
TECHNICAL FIELD
The present invention relates to methods and systems for analyzing data relating to events occurring in industrial processes. More particularly, the present invention relates to automated methods and systems for analyzing time-tagged data associated with events occurring in industrial processes.
BACKGROUND ART
Time-tagged data may be used to record events that occur in industrial processes. For example, in paper or sheet article processing, such as mail processing, machines such as, for example, inserters, turnover sequencers, accumulators, folders, and collectors include optical sensors that monitor the flow of sheet articles through the machines. The sheet articles can also include individual or stacked, folded or unfolded sheet articles such as envelopes, envelope inserts and other suitable sheet articles.
Each sheet article processing machine can comprise a processor, a memory buffer, and a communications circuit, all of which can cooperate to produce time-tagged data for a machine. The optical sensors can be used to detect events, such as the presence of a sheet of paper. The processing circuit receives the data from each of the sensors and associates a time value with the output of each sensor. The processing circuit can also convert the output into a code or text string indicative of the event detected by each sensor. The combination of a time value and a code or text string indicative of an event that occurred in an industrial process is referred to herein as “time-tagged data”. The communication circuits of each of the machines transmit the time-tagged data to a central location for storage.
The central location can be a suitable computer that communicates with each of the machines, e.g., using a serial interface, to receive the time-tagged data from the machines. The time-tagged data can be stored as a log file in a bulk storage medium, such as a hard disk, at the central location. Each line of data in the log file is referred to as an entry. Each entry contains one unit of time-tagged data, i.e., one time tag and one event portion. The entries in the log file are analyzed manually by a technician or an engineer to identify problems associated with the industrial process.
One problem with this method of recording and analyzing data regarding an industrial process is that time-tagged data is difficult to interpret. For example, because time-tagged data is output from multiple sensors on multiple machines or multiple parts of the same machine, and because many events can occur simultaneously, no clear sequence of time-tagged data relating to a single event appears in the log file. Entries recorded by a single sensor can be interspersed with other entries in the log file. In addition, the text or codes associated with each event might not readily convey to the observer the nature of the event. As a result, skilled technicians or even engineers can be required to analyze the time-tagged data. Because of the complex nature of the time-tagged data, extra labor can be required even for skilled persons to interpret the time-tagged data.
The following lines of text are an example of time-tagged data recorded in a log file for a paper processing operation:
0000.013977 00.465718??.?????? BIN_MUX_IN CLR-board=0,port=06,pin=000
0000.014343 00.465718??.?????? BIN_MUX_IN CLR-board=0,port=06,pin=000
0000.027557 00.465718??.?????? BIN_MUX_IN SET-board=0,port=05,pin=000
0000.031738 00.465718??.?????? BIN-MUX_IN CLR-board=0,port=06,pin=000
0000.033447 00.465718??.?????? HTA Variable-WRITE: I#3219, val=65535/0xffff
0000.033569 00.465718??.?????? HTA Page Data-INSIDE: s#=16,p#=2,tg=73,ct=1
0000.033661 00.000091 00.000091 FED_EOS-HTA Page Data: 1ST_SUBSETFOLD_LIMIT
0000.061371 00.465718??.?????? BIN_MUX_IN SET-board=0,port=09,pin=000
0000.061798 00.465718??.?????? BIN_MUX_IN SET-board=0,port=09,pin=000
0000.062683 00.465718??.?????? HTA Variable-WRITE: I#2419, val=8/0×0008
In each log file entry, the numbers on the left side indicate the event occurrence time in milliseconds measured from a predetermined start time. The text on the right side of each entry indicates the type of event, the name of the sensor that detected the event, and variable values associated with the event. As can be seen from the data above, it can be difficult to determine a real-world event from the event portion of each entry. The difficulty is increased when an event of interest spans multiple separated time-tagged data entries.
In light of these difficulties, there exists a long-felt need for improved methods and systems for analyzing time-tagged data, identifying events in an industrial process based on the time-tagged data, and presenting the data in a format that is easily understood.
DISCLOSURE OF THE INVENTION
The present invention includes automated methods and systems for analyzing time-tagged data. The phrase “time-tagged data”, as used herein, refers to any data associated with an industrial process that has a time value or time-tag indicating when an event occurred and that has an event portion that indicates the nature of an event. The methods and systems according to the present invention analyze the time-tagged data by applying computer-implemented state machines to time-tagged data entries to produce data indicative of real-world events that occur in an industrial process. Statistical measures are computed for the data output from the state machines, and the statistical measures are compared to design limits. The statistical measures and the results of comparing the statistical measures to the design limits are presented to a user in a format that facilitates interpretation of the time-tagged data.
According to another aspect, the present invention includes methods and systems for analyzing non-time-tagged data associated with an industrial process and presenting output in a manner that facilitates understanding of the data.
Accordingly, it is an object of the present invention to provide novel automated methods and systems for analyzing time-tagged data.
It is another object of the invention to provide methods and systems for analyzing time-tagged data to produce output that facilitates interpretation of the time-tagged data.
It is another object of the invention to provide methods and systems for analyzing non-time-tagged data associated with an industrial process.
These objects and others are met in whole or in part by the present invention. Some of the objects of the invention having been stated hereinabove, other objects will become evident as the description proceeds, when taken in connection with the accompanying drawings, as best described hereinbelow.
REFERENCES:
patent: 4346446 (1982-08-01), Erbstein et al.
patent: 4718005 (1988-01-01), Feigenbaum et al.
patent: 5144566 (1992-09-01), Anderson et al.
patent: 5155693 (1992-10-01), Altmayer et al.
patent: 5355327 (1994-10-01), Stent et al.
patent: 5390107 (1995-02-01), Nelson et al.
patent: 5680329 (1997-10-01), Lloyd et al.
patent: 5749291 (1998-05-01), Nast et al.
patent: 5828882 (1998-10-01), Hinckley
patent: 5850388 (1998-12-01), Anderson et al.
patent: 5870696 (1999-02-01), Randolph
patent: 6038690 (2000-03-01), Jacobson et al.
patent: 6163761 (2000-12-01), Kent
patent: 6182084 (2001-01-01), Cockrell et al.
patent: 6199018 (2001-03-01), Quist et al.
patent: 6263290 (2001-07-01), Williams et al.
patent: 6282267 (2001-08-01), Nolting
patent: 6324665 (2001-11-01), Fay
patent: 6385301 (2002-05-01), Nolting et al
Bell & Howell Messaging Technologies Company
Hoff Marc S.
Kim Paul
LandOfFree
Automated methods and systems for analyzing data associated... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Automated methods and systems for analyzing data associated..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Automated methods and systems for analyzing data associated... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3014046