JP2013033149A - Image quality abnormality predicting system and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technique to predict the occurrence of an image quality abnormality in an image formation device from a new standpoint.SOLUTION: A trouble sign determination data group generation part 34 measures a time taken for executing calibration and the amount of change in an adjustment parameter by the calibration for each of instances in which an image quality abnormality occurs after the calibration is executed, on the basis of maintenance information of a maintenance information storage part 32, machine information of a machine information storage part 33, and an image quality adjustment execution log. A measurement data group in which measured data is collected for each instance is stored in a trouble sign determination data group storage part 35 as a trouble sign determination data group. A trouble sign determination part 36 compares obtained measurement data on the latest calibration executed by an image formation device 10 which is an object for predicting the image quality abnormality with a trouble sign determination data group to determine whether or not the image quality abnormality may occur in the image formation device 10.

Description

  The present invention relates to an image quality abnormality prediction system and program.

  Image formation having an image forming function for forming and outputting an image of a document on a recording material such as paper, such as a printer (document printing apparatus), a copier (document copying apparatus), a facsimile apparatus (document transfer apparatus), etc. There is a device.

  In the image forming apparatus, in order to maintain the image quality of the image formed on the recording material in a normal state, a calibration process (image quality adjustment process called calibration or the like) for calibrating the parameter value for adjusting the image quality by feedback control or the like is performed. Executed. The calibration is executed intermittently (for example, once a day) in response to an instruction from the operator or when a predetermined timing arrives. Generally, the calibration is performed so that the calibration is performed in a time zone that does not affect the use of the image forming apparatus (for example, when it is not in operation such as midnight).

  As a method for predicting a defect such as an image quality abnormality in such an image forming apparatus, for example, the change tendency of various parameters for controlling the image forming process is monitored and compared with a threshold value, or a change point is extracted. For example, a method for predicting whether or not there is a tendency to deviate from the normal state.

Further, the following inventions have been proposed so far with regard to a technique for predicting a failure by monitoring the state of an apparatus.
For example, an invention has been proposed in which various parameter information when an output image is determined to be normal is accumulated as normal data to obtain a calculation parameter as a reference (see Patent Document 1).
For example, there has been proposed an invention that has a plurality of types of normal data groups with different combinations of data types and determines whether or not there is an abnormality corresponding to each data group (see Patent Document 2).

JP 2005-266380 A JP 2006-349809 A

  An object of the present invention is to propose a technique for predicting that an image quality abnormality will occur in an image forming apparatus from a new viewpoint.

  The present invention according to claim 1 relates to a plurality of cases where an image quality abnormality has occurred in the image forming apparatus after executing a calibration process for calibrating a parameter value for adjusting the image quality of an image formed on the recording material by the image forming apparatus. It is executed by a storage means for storing a measurement data group that collects measurement data of one or both of the time required for executing the calibration process and the amount of change in the parameter value due to the calibration process, and the image forming apparatus that is to predict the image quality abnormality. Output means for outputting a notification that an image quality abnormality has occurred in the target image forming apparatus when measurement data of the most recent calibration processing is included in a range characterizing the measurement data group stored in the storage means; And an image quality abnormality prediction system.

  According to a second aspect of the present invention, in the first aspect of the present invention, the storage unit includes a measurement data group when an image quality abnormality occurs after the calibration process and a measurement data group when no image quality abnormality occurs. In the image quality abnormality prediction system, a measurement data group is stored when an image quality abnormality occurs after the calibration process when the degree of deviation from the threshold value is equal to or greater than a threshold value.

  According to a third aspect of the present invention, in the present invention according to the first or second aspect, the storage means sets each measurement data in a measurement data group when an image quality abnormality occurs after the calibration process. An image quality abnormality prediction system characterized by storing a measurement data group obtained by extracting measurement data classified into a large side when classified according to size.

  According to a fourth aspect of the present invention, in the first aspect of the present invention according to the first or second aspect, the storage means does not occur after the calibration process from the measurement data group when the image quality abnormality occurs after the calibration process. An image quality abnormality prediction system is characterized by storing a measurement data group excluding measurement data that overlaps the measurement data group in the case of the measurement data.

  According to a fifth aspect of the present invention, there is provided a plurality of image quality abnormalities occurring in the image forming apparatus after executing calibration processing for calibrating parameter values for adjusting the image quality of an image formed on the recording material by the image forming apparatus. A storage function for storing a measurement data group that collects measurement data of one or both of the time required for execution of calibration processing and the amount of change in parameter value due to calibration processing, and an image forming apparatus for predicting image quality abnormality When the measurement data of the most recent calibration process executed in step 1 is included in the range characterizing the measurement data group stored by the storage function, a notification that an image quality abnormality has occurred in the target image forming apparatus is output. This is a program for realizing the output function.

  According to the first and fifth aspects of the present invention, from the viewpoint of one or both of the time required for executing the calibration process and the amount of change in the parameter value due to the calibration process, the latest calibration performed in the target image forming apparatus. It is possible to predict whether an image quality abnormality will occur after processing.

  According to the second aspect of the present invention, it is possible to effectively predict the occurrence of an image quality abnormality by using a measurement data group having a different tendency from the case where no image quality abnormality has occurred after the calibration process.

  According to the third and fourth aspects of the present invention, it is possible to effectively predict the occurrence of an image quality abnormality by using a measurement data group that more characteristically represents a tendency when no image quality abnormality has occurred after the calibration process. It can be carried out.

It is a figure which shows the structural example of the image quality abnormality prediction system which concerns on one Embodiment of this invention. It is a figure which illustrates the maintenance information accumulate | stored in a maintenance information storage part. It is a figure which illustrates the machine information accumulate | stored in a machine information storage part. It is a figure which shows the functional block of the trouble sign determination data group production | generation part of a 1st structural example, and a trouble sign determination part. It is a figure which illustrates the relationship between the data group at the time of trouble occurrence, and the data group at the time of normality. It is a figure which shows the example of the clustering by the clustering process part of a 1st structural example. It is a figure which illustrates the holding | maintenance data of the trouble symptom determination data group storage part of a 1st structural example. It is a figure which illustrates the processing flow by the trouble symptom determination data group production | generation part of a 1st structural example. It is a figure which illustrates the relationship between the distribution range of the data group at the time of trouble occurrence, and the distribution range of the data group at the time of normality. It is a figure which illustrates the processing flow by the trouble sign determination part of a 1st structural example. It is a figure which shows the functional block of the trouble sign determination data group production | generation part of a 2nd structural example, and a trouble sign determination part. It is a figure which shows the example of the normal time data group removal by the data group extraction part of a 2nd structural example. It is a figure which illustrates the holding data of the trouble symptom determination data group storage part of the 2nd example of composition. It is a figure which illustrates the processing flow by the trouble sign determination data group production | generation part of a 2nd structural example. It is a figure which illustrates the processing flow by the trouble sign determination part of a 2nd structural example. It is a figure which illustrates the hardware constitutions of a management apparatus.

An image quality abnormality prediction system according to an embodiment of the present invention will be described with reference to the drawings.
FIG. 1 illustrates the configuration of an image quality abnormality prediction system according to an embodiment of the present invention.
The image quality abnormality prediction system of this example includes an image forming apparatus 10 that forms and outputs an image on a recording material such as paper, and a maintenance information input terminal 20 that is used by an administrator or a maintenance person of the image forming apparatus 10. ,have. In the example of FIG. 1, two image forming apparatuses 10 and two maintenance information input terminals 20 are shown, but the number of these is arbitrary.

  Further, the image quality abnormality prediction system of this example is connected to each of the image forming apparatus 10 and the maintenance information input terminal 20 via a communication network so as to be able to communicate by wire or wirelessly, and image formation is performed using information collected from these. The management apparatus 30 that predicts the occurrence of an image quality abnormality in the apparatus 10 is provided. In the example of FIG. 1, the management device 30 is configured by a single device, but each functional unit 31 to 36 described later may be distributed to a plurality of devices.

  The image forming apparatus 10 is an apparatus having an image forming function for forming and outputting an image on a recording material such as paper. Examples of the image forming apparatus 10 include apparatuses such as a printer (document printing apparatus), a copier (document copying apparatus), and a facsimile apparatus (document transfer apparatus). Is also included.

The image forming apparatus 10 of this example has a parameter value for adjusting the image quality of an image formed on a recording material in addition to a function of executing various jobs (units of a certain processing work) accompanied by image formation such as printing and copying. It has a function of executing calibration (image quality adjustment) that is calibrated by feedback control or the like, and performs calibration in response to an instruction from the operator or when a predetermined timing arrives.
Also, according to the execution of calibration, an image quality adjustment execution log in which the execution result is recorded is generated. In the image quality adjustment execution log, in addition to the calibration execution result, the apparatus identification information of itself (the image forming apparatus 10), the calibration start date and time, and the end date and time are also recorded.
The image quality adjustment execution log generated by the image forming apparatus 10 is transmitted to the management apparatus 30 automatically in response to the generation or in response to a request from the management apparatus 30.

In addition, the image forming apparatus 10 of the present example has various monitoring parameters (including adjustment parameters by calibration) related to image forming processing, and each monitoring parameter is provided by a sensor provided in each unit related to image formation. Can be detected at any time.
In this example, in addition to detecting monitoring parameter values triggered by the execution of various jobs, monitoring parameter values (especially adjustment parameter values by calibration) are detected at the start and end of calibration. Then, machine information in which the detected value is recorded is generated. In the machine information, in addition to the detection values of the respective monitoring parameters, the device identification information of itself (image forming apparatus 10), the detection date and time indicating the date and time when the value detection is performed, and the like are also recorded.
The machine information generated by the image forming apparatus 10 is transmitted to the management apparatus 30 automatically in response to the generation or in response to a request from the management apparatus 30.

Next, the maintenance information input terminal 20 will be described.
The maintenance information input terminal 20 in this example inputs maintenance information related to the maintenance work from the maintenance staff who actually visited the place where the image forming apparatus 10 was installed and who performed the maintenance work or who received the report. Accept and transmit to the management device 30. In addition, the maintenance information input terminal 20 of the present example receives predictive information of troubles (failures) in the image forming apparatus 10 from the management apparatus 30 and displays the information on a display device provided in the maintenance information input terminal 20.
In this example, the maintenance information transmitted to the management apparatus 30 includes apparatus identification information for identifying the image forming apparatus 10 that is the object of the maintenance work, a maintenance date and time indicating the date and time when the maintenance work was performed, and removed by the maintenance work. The category indicating the classification of the trouble, the failure type indicating the specific type of the trouble, the treatment applied to the target image forming apparatus 10 and the like are recorded.

Next, the management device 30 will be described.
The management device 30 of this example is a device that predicts the occurrence of a trouble in the image forming apparatus 10, and includes a maintenance / machine information collection unit 31, a maintenance information storage unit 32, a machine information storage unit 33, and a trouble sign determination data group generation unit. 34, a trouble sign determination data group storage unit 35, and a trouble sign determination unit 36.

  The maintenance / monitoring information collection unit 31 collects (receives) maintenance information transmitted from the maintenance information input terminal 20 and stores (maintains) it in the maintenance information storage unit 32, and a machine transmitted from the image forming apparatus 10. Information and image quality adjustment execution logs are collected (received) and accumulated (stored) in the machine information accumulation unit 33.

FIG. 2 illustrates the maintenance information stored in the maintenance information storage unit 32.
According to FIG. 2, for example, the image forming apparatus 10 identified by “# 1001” belongs to the “image quality (density fluctuation)” category by the maintenance work performed on “2010/1/10 13:00”. The problem of “density unevenness” has been eliminated. For example, the maintenance of “2010/1/12 15:00” for the image forming apparatus 10 identified by “# 1002” It can be seen that the trouble of “no power on” belonging to the category has been eliminated.

FIG. 3 illustrates machine information stored in the machine information storage unit 33.
According to FIG. 3, for example, the monitoring parameter in the print job executed at “2010/1/1 10:00” for the image forming apparatus 10 identified by “# 1001” is the sheet passing time “ a ₁ second ”, the charging voltage is“ A ₁ V ”,... and is executed at“ 2010/1/3 15:00 ”for the image forming apparatus 10 identified by“ # 1002 ”, for example. It is understood that the monitoring parameters in the print job are “b ₁ second” for the paper passage time, “B ₁ V” for the charging voltage, and so on.

The trouble sign determination data group generation unit 34 predicts the occurrence of a trouble based on the maintenance information stored in the maintenance information storage unit 32, the machine information stored in the machine information storage unit 33, and the image quality adjustment execution log. A trouble sign determination data group serving as a reference is generated and stored (stored) in the trouble sign determination data group storage unit 35.
In the trouble sign determination data group generation unit 34 of this example, in particular, troubles (hereinafter simply referred to as image quality) belonging to the category of image quality abnormality (for example, the category of “image quality (density variation)” or “image quality (dirt)” in FIG. 2). Maintenance information for the error) and machine information at each of the calibration start and end times, and a plurality of image quality anomalies that occurred within a predetermined length of time after the calibration was executed. For each case, measure the amount of time required to execute the calibration (execution time) and the amount of change in the adjustment parameters (for example, charging voltage, development bias, laser light quantity, etc.) due to the calibration. A set of measurement data (collection of execution time and change amount) is used as a standard for predicting the occurrence of abnormal image quality. And stores the trouble sign determination data group storage unit 35 as a data group.

  The trouble sign determination unit 36 is a trouble sign determination unit in which measurement data obtained for the most recent calibration executed in the image forming apparatus 10 that is the target of predicting image quality abnormality is stored in the trouble sign determination data group storage unit 35. It is determined whether or not the data group is included in a range that characterizes the data group. When the data group is included in the range, predictive information that notifies that an image quality abnormality occurs is transmitted to the maintenance information input terminal 20, and the maintenance information input terminal 20 Display output by a display device provided in

Hereinafter, the operations of the trouble sign determination data group generation unit 34 and the trouble sign determination unit 36 will be described more specifically.
(First configuration example)
FIG. 4 shows functional blocks of the trouble sign determination data group generation unit 34 and the trouble sign determination unit 36 in the first configuration example.
First, the trouble sign determination data group generation unit 34 of the first configuration example will be described.
As shown in FIG. 4A, the trouble sign determination data group generation unit 34 of the first configuration example includes a trouble occurrence data acquisition unit 41, a trouble occurrence data group generation unit 42, a normal time data acquisition unit 43, and a normal operation. A time data group generation unit 44, a data group selection unit 45, and a clustering processing unit 46 are included.

The trouble occurrence data acquisition unit 41 traces the occurrence date and time for each case of image quality abnormality based on information such as the maintenance date, category, and defect type in the maintenance information stored in the maintenance information storage unit 32. Further, machine information and image quality adjustment execution log related to calibration executed within a predetermined length of time are acquired from the machine information storage unit 33. That is, with respect to a case where an image quality abnormality has occurred within the attention period after the execution of calibration, a calibration image quality adjustment execution log and machine information at each of the calibration start and end times are acquired.
In this example, the date and time of maintenance work (maintenance date and time) for image quality abnormality is treated as the image quality abnormality occurrence date and time, but there is another mechanism for specifying the image quality abnormality occurrence date and time. In such a case, the image quality abnormality occurrence date and time specified by the mechanism may be used for processing.

  The trouble occurrence data group generation unit 42 is based on the machine information and the image quality adjustment execution log for each case in which an image quality abnormality has occurred within the attention period after the execution of calibration, acquired by the trouble occurrence data acquisition unit 41. The calibration execution time and the amount of change of each adjustment parameter due to calibration are measured, and the trouble occurrence data group that collects measurement data (a set of execution time and change amount) for each case is measured for each adjustment parameter. To generate.

In this example, the calibration execution time is calculated (measured) from the relationship between the calibration start date and end date and time in the image quality adjustment execution log. Further, the amount of change in the adjustment parameter due to calibration is calculated (measured) for each adjustment parameter from the relationship between the detection value of each adjustment parameter at the start of calibration and the detection value of each adjustment parameter at the end of calibration. .
Here, the image forming apparatus 10 of this example has a plurality of types of calibration, and in each calibration, a plurality of adjustment parameters corresponding to the types are calibrated. For this reason, in this example, the calibration execution time for each measurement data is common for each type of calibration.

  The normal time data acquisition unit 43 selects a period of the same length as the period used in the trouble occurrence data acquisition unit 41 and in which no image quality abnormality has occurred, and relates to the calibration executed within that period. Machine information and an image quality adjustment execution log are acquired from the machine information storage unit 33. In other words, contrary to the trouble occurrence data acquisition unit 41, the calibration image quality adjustment execution log and the start and end of calibration for the case where the image quality abnormality did not occur within the attention period after the calibration was performed. Get machine information at each point in time.

The normal data group generation unit 44 is based on the machine information and the image quality adjustment execution log for each case in which no image quality abnormality has occurred within the attention period after execution of calibration, acquired by the normal data acquisition unit 43. Measure the calibration execution time and the amount of change of each adjustment parameter by calibration, and collect the normal data group that collects the measurement data (set of execution time and change amount) for each case for each adjustment parameter. Generate.
In this example, the calibration execution time is calculated (measured) and the adjustment parameter change amount is calculated (measured) by the same method as the trouble occurrence data group generation unit 42.

The data group selection unit 45 diverges between the trouble occurrence data group for each adjustment parameter generated by the trouble occurrence data group generation unit 42 and the normal time data group for each adjustment parameter generated by the normal time data acquisition unit 43. A distance representing the degree is calculated for each adjustment parameter, and a data group at the time of occurrence of the trouble of the adjustment parameter for which the distance is equal to or greater than a predetermined threshold is selected and given to the clustering processing unit 46.
In this example, the distance between these centroids is used as the distance representing the degree of divergence between the data group at the time of trouble occurrence and the data group at normal time.For example, the values obtained by other methods such as Mahalanobis distance are You may make it use as a deviation degree of a data group and a normal time data group.

The operation of the data group selection unit 45 will be conceptually described.
FIG. 5 illustrates the relationship between the trouble occurrence data group and the normal data group on a graph in which the horizontal axis represents calibration execution time (ΔT) and the vertical axis represents adjustment parameter change amount (Δx). It is. The distribution of measurement data belonging to the data group at the time of trouble occurrence is indicated by x, the distribution range (range characterizing the data group at the time of trouble occurrence) is surrounded by a solid line, and the measurement data belonging to the normal time data group is also shown. While the distribution is indicated by Δ, the distribution range (the range characterizing the normal data group) is surrounded by a dotted line.
FIG. 5A is an example in the case where the trouble occurrence data group is not extracted (when the distance is less than the threshold), and FIG. 5B is the case where the trouble occurrence data group is extracted (the distance is greater than or equal to the threshold). Example).
As described above, in the data group selection unit 45 of this example, a trouble occurs with respect to an adjustment parameter that is remarkably different from that in the case where the tendency of the measurement data at the time of the image quality abnormality is normal (the state in which the image quality abnormality and its sign do not occur). Extract time data group.

  The clustering processing unit 46 divides the adjustment parameter trouble data group given from the data group selection unit 45 into four quadrants ((calibration execution time, adjustment parameter variation)) = ( Small, small), (small, large), (large, small), (large, large)), and stored in the trouble sign determination data group storage unit 35 for each adjustment parameter as a trouble sign determination data group.

The operation of the clustering processing unit 46 will be conceptually described.
FIG. 6 shows an example of clustering by the clustering processing unit 46.
In the example of FIG. 6, the distribution range of measurement data belonging to the trouble occurrence data group is classified into four quadrants according to the magnitude of the calibration execution time and the amount of change in the adjustment parameter. The distribution range of the measurement data belonging to the large quadrant (upper right quadrant in the figure) is shown surrounded by a solid line.
As described above, in the data group selection unit 45 of this example, the trouble occurrence data group is classified into four quadrants from the viewpoint of the calibration execution time and the amount of change in the adjustment parameter, and the trouble sign determination data group accumulation unit 35. Remember me.

FIG. 7 illustrates data held in the trouble sign determination data group storage unit 35 of the first configuration example.
As described above, the trouble sign determination data group storage unit 35 of the first configuration example stores, for each adjustment parameter, measurement data (a set of execution time and change amount) belonging to the trouble sign determination data group corresponding to the adjustment parameter. Each of the quadrants is classified and stored from the viewpoint of the calibration execution time and the amount of change in the adjustment parameter.

Next, the trouble sign determination unit 36 of the first configuration example will be described.
As shown in FIG. 4B, the trouble sign determination unit 36 of the first configuration example includes a log / parameter data acquisition unit 51, a determination data calculation unit 52, a trouble sign determination data acquisition unit 53, and a clustering determination unit 54. Have

  The log / parameter data acquisition unit 51 is acquired from the image forming apparatus 10 that is the target of predicting the image quality abnormality and is stored in the machine information storage unit 33 within a period of a predetermined length retroactive to the current point. Machine information and image quality adjustment execution log related to the calibration executed in the first step are acquired. That is, for the calibration executed in the target image forming apparatus 10 within the latest attention period, the calibration image quality adjustment execution log and the machine information at each of the start and end of calibration are acquired.

The determination data calculation unit 52 is based on the machine information and the image quality adjustment execution log relating to the calibration executed by the target image forming apparatus 10 within the latest attention period, acquired by the log / parameter data acquisition unit 51. The calibration execution time and the amount of change in the detected value of each adjustment parameter due to calibration are measured, and determination data (a set of execution time and amount of change) is generated for each adjustment parameter.
In this example, the calibration execution time is calculated (measured) and the amount of change in the detected value of the adjustment parameter due to calibration is calculated (measured) by the same method as the trouble occurrence data group generation unit 42.

  The trouble sign determination data acquisition unit 53 uses the trouble sign determination data group (the trouble classified into the four quadrants) for the adjustment parameter (adjustment parameter for which the trouble sign determination data group is generated) used for the image quality abnormality sign determination. Occurrence data group) is acquired from the trouble sign determination data group storage unit 35.

In the clustering determination unit 54, determination data (a set of execution time and change amount) for each adjustment parameter generated by the determination data calculation unit 52 is acquired by the trouble sign determination data acquisition unit 53 for the adjustment parameter. Which of the four quadrants of the trouble sign determination data group is included (or closest) is determined.
In this example, the distance between the center of gravity of each quadrant and the determination data is calculated, and it is determined that the determination data is included in the quadrant with the shortest distance. When the calculated distance is equal to or greater than a predetermined threshold, it is determined that the calculated distance is not included in any quadrant (not included in the range characterizing the trouble sign determination data group).
As a result of the determination, if it is determined that the determination data is included in the (execution time, change) = (large, large) quadrant (upper right quadrant in FIG. 6), that is, it is determined that a data abnormality has occurred. In such a case, assuming that there is a sign that an image quality abnormality will occur in the target image forming apparatus 10, the sign information notifying that an image quality abnormality will occur is transmitted to the maintenance information input terminal 20.

The flow of processing by the trouble sign determination data group generation unit 34 and the trouble sign determination unit 36 in the first configuration example will be described.
FIG. 8 illustrates a processing flow by the trouble sign determination data group generation unit 34 of the first configuration example.
First, the trouble occurrence data acquisition unit 41 extracts a case of an image quality abnormality based on information such as the maintenance date / time, category, and defect type in the maintenance information stored in the maintenance information storage unit 32 (step S11). The machine information and the image quality adjustment execution log related to the calibration executed within a predetermined length of the period from the date and time of occurrence are acquired from the machine information storage unit 33 (step S12).
Further, the normal data acquisition unit 43 selects a period of the same length as that used by the trouble occurrence data acquisition unit 41 and in which no image quality abnormality has occurred, and the calibration performed within that period. Machine information and image quality adjustment execution log for the job are acquired from the machine information storage unit 33 (step S13).

Next, the trouble occurrence data group generation unit 42, based on the machine information and the image quality adjustment execution log acquired by the trouble occurrence data acquisition unit 41, the calibration execution time and the change of each adjustment parameter due to the calibration. Then, a trouble occurrence data group in which measurement data (a set of execution time and change amount) for each case is collected is generated for each adjustment parameter (step S15).
Similarly, based on the machine information and image quality adjustment execution log acquired by the normal time data acquisition unit 43, the normal time data group generation unit 44 determines the calibration execution time and the amount of change of each adjustment parameter due to the calibration. Are calculated for each adjustment parameter (step S15), and a normal data group in which measurement data (a set of execution time and change amount) for each case is collected is generated (step S15).

Then, set the initial value 1 to a variable i for identifying each adjustment parameter (step S16), and directed to the adjustment parameter x _i is identified by the variable i performs the following process.
The data group selection unit 45 diverges between the trouble occurrence data group for each adjustment parameter generated by the trouble occurrence data group generation unit 42 and the normal time data group for each adjustment parameter generated by the normal time data acquisition unit 43. A distance representing the degree is calculated (step S17), and it is determined whether or not the distance is equal to or greater than a predetermined threshold (step S18).
When the calculated distance is equal to or greater than the threshold, the clustering processing unit 46 classifies the data group at the time of trouble occurrence into four quadrants according to the amount of calibration execution time and the amount of change in the adjustment parameter, thereby determining a trouble sign As a data group, the trouble sign determination data group storage unit 35 stores the data (step S19). If the calculated distance is less than the threshold, step S19 is not performed.
Thereafter, the value of the variable i and the number n of adjustment parameter types are compared (step S20). If i ≦ n, 1 is added to the variable i (step S21), and the next adjustment parameter x _i is targeted. Steps S17 to S19 are repeated. On the other hand, if i> n, the process is terminated. That is, the above steps S17 to S19 are repeated for all the adjustment parameters x _i (1 ≦ i ≦ n).

As a result, an adjustment parameter in which the trouble occurrence data group and the normal data group are separated from each other by a certain amount is specified, and the trouble occurrence data group of the adjustment parameter indicates the amount of calibration execution time and the amount of change in the adjustment parameter. Are stored in the trouble sign determination data group storage unit 35 as a trouble sign determination data group.
For example, in the case where the distribution ranges of the trouble occurrence data group and the normal time data group of the adjustment parameters x _{1 to} x ₄ are illustrated in FIG. 9A, the distribution ranges are illustrated in FIG. 9B. In this manner, the trouble sign determination data group is set for the adjustment parameters x ₂ and x ₄ where the distance between the trouble occurrence data group and the normal data group is long. In FIG. 9, the distribution range of the trouble occurrence data group is indicated by a solid line, and the distribution range of the normal data group is indicated by a dotted line.

FIG. 10 illustrates a processing flow by the trouble sign determination unit 36 of the first configuration example.
First, the trouble sign determination data acquisition unit 53 acquires the trouble sign determination data group from the trouble sign determination data group storage unit 35 for the adjustment parameter used for the image quality abnormality sign determination (step S31).
In addition, the log / parameter data acquisition unit 51 has a predetermined length that is acquired from the image forming apparatus 10 that is the target of predicting the image quality abnormality and stored in the machine information storage unit 33 and is traced back to the current point. Machine information and image quality adjustment execution log related to calibration executed within the period are acquired (step S32), and the determination data calculation unit 52 acquires the machine information and image quality adjustment execution log acquired by the log / parameter data acquisition unit 51. Based on the above, the calibration execution time and the amount of change in the detected value of each adjustment parameter due to calibration are measured, and determination data (a set of execution time and change amount) is generated for each adjustment parameter ( Step S33).

Then, set the initial value 1 to a variable i for identifying each adjustment parameter (step S34), intended for adjustment parameter x _i is identified by the variable i performs the following process.
The clustering determination unit 54 determines the gravity center of each quadrant of the trouble sign determination data group acquired by the trouble sign determination data acquisition unit 53 and the determination data for each adjustment parameter generated by the determination data calculation unit 52 (execution) The distance from the set of time and change amount is calculated (step S35), and it is determined whether or not the distance from the quadrant of (execution time, change) = (large, large) is minimum (step S36).
Then, when the distance from the quadrant of (execution time, change) = (large, large) is not minimum, the value of the variable i is compared with the number m of adjustment parameter types used for predictive judgment of image quality abnormality (step) S37), if i ≦ m, and adds 1 to the variable i (step S38), directed to the next adjustment parameter _{x i} and repeats the above steps S35, S36. On the other hand, if i> m, the process ends. That is, the above steps S35 and S36 are repeated for all the adjustment parameters x _i (1 ≦ i ≦ m).
On the other hand, when the distance from the quadrant of (execution time, change) = (large, large) is minimum, it is assumed that there is a sign that an image quality abnormality will occur in the target image forming apparatus 10, and an image quality abnormality will occur. Is transmitted to the maintenance information input terminal 20 (step S39).

As described above, in this example, determination data (a set of execution time and change amount) obtained for the calibration executed in the target image forming apparatus 10 within the most recent attention period is the trouble sign determination data group. If the execution time and the amount of change are both included in the large quadrant when the calibration time is categorized by the magnitude of the calibration execution time and the amount of change in the adjustment parameter, it is determined that there is a sign that image quality abnormality will occur. The sign information notifying that fact is transmitted to the maintenance information input terminal 20.
It should be noted that when either the execution time or the amount of change is included in the large quadrant, it may be determined that there is a sign that an image quality abnormality will occur, and may be arbitrarily determined according to the operation mode of the image quality abnormality prediction system, etc. You only have to set it.

  Further, in this example, for each type of adjustment parameter, the type of image quality abnormality that is assumed to occur when a data abnormality occurs in the adjustment parameter (the type of image quality abnormality that occurred frequently in past cases) An associated correspondence table is provided, and the type of image quality abnormality having a sign of occurrence can be determined in light of the correspondence table. Note that the efficiency of the maintenance work may be improved by preparing a correspondence table that further associates information such as measures for resolving the image quality abnormality.

(Second configuration example)
FIG. 11 shows functional blocks of the trouble sign determination data group generation unit 34 and the trouble sign determination unit 36 in the second configuration example.
First, the trouble sign determination data group generation unit 34 of the second configuration example will be described.
As shown in FIG. 11A, the trouble sign determination data group generation unit 34 of the second configuration example includes a trouble occurrence data acquisition unit 61, a trouble occurrence data group generation unit 62, a normal data acquisition unit 63, and a normal operation. A time data group generation unit 64, a data group selection unit 65, and a data group extraction unit 66 are included. Since the functional units 61 to 65 have the same configuration and operation as the corresponding functional units 41 to 45 in the first configuration example, description thereof is omitted.

The data group extraction unit 66 obtains the measurement data that overlaps the normal data group for each adjustment parameter generated by the normal data acquisition unit 43 from the trouble occurrence data group of the adjustment parameters given from the data group selection unit 45. The trouble occurrence data group after the exclusion is stored as a trouble sign determination data group in the trouble sign determination data group storage unit 35 for each adjustment parameter.
Note that the data group extraction unit 66 of this example excludes measurement data belonging to a predetermined distance from the center of gravity of the normal data group.

FIG. 12 shows an example of normal data group removal by the data group extraction unit 66.
As described above, the data group extraction unit 66 of this example identifies a range that excludes a range that overlaps the distribution range of the normal data group from the distribution range of the trouble occurrence data group, and collects measurement data belonging to the range. The trouble sign determination data group accumulating unit 35 stores the collected data group as a trouble sign determination data group.

FIG. 13 illustrates data held in the trouble sign determination data group storage unit 35 of the second configuration example.
As described above, the trouble sign determination data group storage unit 35 of the second configuration example stores, for each adjustment parameter, measurement data (a set of execution time and change amount) belonging to the trouble sign determination data group corresponding to the adjustment parameter. keeping.

Next, the trouble sign determination unit 36 of the second configuration example will be described.
As shown in FIG. 11B, the trouble sign determination unit 36 of the second configuration example includes a log / parameter data acquisition unit 71, a determination data calculation unit 72, a trouble sign determination data acquisition unit 73, and a distance determination unit 74. Have Since the functional units 71 to 73 have the same configuration and operation as the corresponding functional units 51 to 53 in the first configuration example, the description thereof is omitted.

  The distance determination unit 74 is acquired by the trouble sign determination data acquisition unit 73 for each adjustment parameter generated by the determination data calculation unit 72 (a set of execution time and change amount) and the adjustment parameter. The distance to the trouble sign determination data group is calculated, and when the calculated distance is less than a predetermined threshold, it is determined that the determination data is included in the range characterizing the trouble sign determination data group, and the target image Assuming that there is a sign that an image quality abnormality will occur in the forming apparatus 10, sign information notifying that an image quality abnormality will occur is transmitted to the maintenance information input terminal 20.

The flow of processing by the trouble sign determination data group generation unit 34 and the trouble sign determination unit 36 in the second configuration example will be described.
FIG. 14 illustrates a processing flow by the trouble sign determination data group generation unit 34 of the second configuration example.
First, the trouble occurrence data acquisition unit 61 extracts an image quality abnormality case based on information such as the maintenance date / time, category, and defect type in the maintenance information stored in the maintenance information storage unit 32 (step S11). The machine information and the image quality adjustment execution log related to the calibration executed within a predetermined length of the period from the date and time of occurrence are acquired from the machine information storage unit 33 (step S12).
Further, the normal data acquisition unit 63 selects a period of the same length as the period used by the trouble occurrence data acquisition unit 61 and in which no image quality abnormality has occurred, and calibration executed within that period. Machine information and image quality adjustment execution log for the job are acquired from the machine information storage unit 33 (step S13).

Next, based on the machine information and image quality adjustment execution log acquired by the trouble occurrence data acquisition unit 61, the trouble occurrence data group generation unit 62 performs the calibration execution time and the change of each adjustment parameter due to the calibration. Then, a trouble occurrence data group in which measurement data (a set of execution time and change amount) for each case is collected is generated for each adjustment parameter (step S15).
Similarly, based on the machine information and image quality adjustment execution log acquired by the normal time data acquisition unit 63, the normal time data group generation unit 64 performs the calibration execution time and the amount of change of each adjustment parameter due to the calibration. Are calculated for each adjustment parameter (step S15), and a normal data group in which measurement data (a set of execution time and change amount) for each case is collected is generated (step S15).

Then, set the initial value 1 to a variable i for identifying each adjustment parameter (step S16), and directed to the adjustment parameter x _i is identified by the variable i performs the following process.
The data group selection unit 65 diverges between the trouble occurrence data group for each adjustment parameter generated by the trouble occurrence data group generation unit 62 and the normal time data group for each adjustment parameter generated by the normal time data acquisition unit 63. A distance representing the degree is calculated (step S17), and it is determined whether or not the distance is equal to or greater than a predetermined threshold (step S18).
When the calculated distance is equal to or larger than the threshold, the data group extraction unit 66 adjusts the adjustment parameter generated by the normal data acquisition unit 43 from the trouble occurrence data group of the adjustment parameter given from the data group selection unit 45. The measurement data overlapping with each normal data group is excluded, and the trouble occurrence data group after the exclusion is stored in the trouble sign determination data group storage unit 35 as a trouble sign determination data group (step S19 ′). If the calculated distance is less than the threshold, step S19 ′ is not performed.
Thereafter, the value of the variable i and the number n of adjustment parameter types are compared (step S20). If i ≦ n, 1 is added to the variable i (step S21), and the next adjustment parameter x _i is targeted. Steps S17 to S19 ′ are repeated. On the other hand, if i> n, the process is terminated. That is, the above steps S17 to S19 ′ are repeated for all the adjustment parameters x _i (1 ≦ i ≦ n).

  As a result, an adjustment parameter in which the trouble occurrence data group and the normal data group are separated to some extent is identified, and the measurement data overlapping the normal data group is excluded from the trouble occurrence data group of the adjustment parameter. The group is held in the trouble sign determination data group storage unit 35 as a trouble sign determination data group.

FIG. 15 illustrates a processing flow by the trouble sign determination unit 36 of the second configuration example.
First, the trouble sign determination data acquisition unit 73 acquires the trouble sign determination data group from the trouble sign determination data group storage unit 35 for the adjustment parameters used for the image quality abnormality sign determination (step S31).
In addition, the log / parameter data acquisition unit 71 has a predetermined length that is acquired from the image forming apparatus 10 that is the target of predicting the image quality abnormality and stored in the machine information storage unit 33 and is traced back to the starting point. Machine information and image quality adjustment execution log related to calibration executed within the period are acquired (step S32), and the determination data calculation unit 72 acquires the machine information and image quality adjustment execution log acquired by the log / parameter data acquisition unit 71. Based on the above, the calibration execution time and the amount of change in the detected value of each adjustment parameter due to calibration are measured, and determination data (a set of execution time and change amount) is generated for each adjustment parameter ( Step S33).

Then, set the initial value 1 to a variable i for identifying each adjustment parameter (step S34), intended for adjustment parameter x _i is identified by the variable i performs the following process.
The distance determination unit 74 includes the trouble sign determination data group acquired by the trouble sign determination data acquisition unit 73 and the determination data (execution time and change amount) for each adjustment parameter generated by the determination data calculation unit 72. A distance to the set) (step S35 '), and determines whether the calculated distance is less than a predetermined threshold (step S36'),
Then, when the calculated distance is not less than the threshold, the value of the variable i is compared with the number m of adjustment parameters used for predicting image quality abnormality (step S37). adding (step S38), the step S35 in the subject for the next adjustment parameter _{x i} ', S36' repeats. On the other hand, if i> m, the process ends. That is, the above steps S35 ′ and S36 ′ are repeated for all the adjustment parameters x _i (1 ≦ i ≦ m).
On the other hand, when the calculated distance is less than the threshold, it is assumed that there is a sign that an image quality abnormality will occur in the target image forming apparatus 10, and sign information that notifies that an image quality abnormality will occur is transmitted to the maintenance information input terminal 20. (Step S39).

  As described above, in this example, determination data (a set of execution time and change amount) obtained for the calibration executed in the target image forming apparatus 10 within the most recent attention period is the trouble sign determination data group. Is determined (when these distances are less than the threshold), it is determined that there is a sign that an image quality abnormality will occur, and the sign information notifying that is transmitted to the maintenance information input terminal 20. .

  Further, in this example, for each type of adjustment parameter, the type of image quality abnormality that is assumed to occur when a data abnormality occurs in the adjustment parameter (the type of image quality abnormality that occurred frequently in past cases) An associated correspondence table is provided, and the type of image quality abnormality having a sign of occurrence can be determined in light of the correspondence table. Note that the efficiency of the maintenance work may be improved by preparing a correspondence table that further associates information such as measures for resolving the image quality abnormality.

In the example described so far, the management apparatus 30 predicts the occurrence of an image quality abnormality for a plurality of image forming apparatuses 10. For example, the management apparatus 30 uses the created trouble sign determination data group for each image. The image forming apparatus 10 may be configured so that each image forming apparatus 10 predicts the occurrence of an image quality abnormality for itself based on the trouble sign determination data group received by the management apparatus 30.
In addition, the image forming apparatus 10 related to the generation of the trouble sign determination data group and the image forming apparatus 10 that is the target of image quality abnormality prediction may be the same apparatus or different apparatuses. That is, by creating a trouble sign determination data group based on past maintenance information, machine information, and the like in one or more image forming apparatuses 10 (which may include the image forming apparatus 10 that is the target of image quality abnormality prediction), Thereafter, the occurrence of an image quality abnormality can be predicted for the image forming apparatus 10 to be predicted for the image quality abnormality using the trouble sign determination data group.

FIG. 16 illustrates a hardware configuration of the management apparatus 30.
In this example, a main memory such as a CPU (Central Processing Unit) 81 that performs various arithmetic processing, a RAM (Random Access Memory) 82 that is a work area of the CPU 81, and a ROM (Read Only Memory) 83 that records basic control programs. Device, auxiliary storage device such as HDD (Hard Disk Drive) 84 for storing programs and various data according to an embodiment of the present invention, display device for displaying and outputting various information, and operations used for input operations by the operator Hardware resources such as an input / output I / F 85 that is an interface with an input device such as a button or a touch panel, and a communication I / F 86 that is an interface that performs wired or wireless communication with other devices are stored in the management device 30. The computer has.
Then, the program according to the embodiment of the present invention is read from the auxiliary storage device 84 and the like, loaded into the RAM 82, and executed by the CPU 81, thereby realizing the above-described functional units on the computer of the management device 30. Yes.

Note that the program according to the embodiment of the present invention is managed according to this example by, for example, a format read from an external storage medium such as a CD-ROM storing the program or a format received via a communication network. Set in the computer of the device 30.
Moreover, it is not restricted to the aspect which implement | achieves each function part by software configuration like this example, You may make it implement | achieve each function part with a dedicated hardware module.

10: Image forming apparatus, 20: Maintenance information input terminal, 30: Management apparatus,
31: Maintenance / machine information collection unit 32: Maintenance information storage unit 33: Machine information storage unit 34: Trouble sign determination data group generation unit 35: Trouble sign determination data group storage unit 36: Trouble sign determination unit 41 : Trouble occurrence data acquisition unit, 42: Trouble occurrence data group generation unit, 43: Normal data acquisition unit, 44: Normal data group generation unit, 45: Data group selection unit, 46 Clustering processing unit,
51: Log / parameter data acquisition unit 52: Determination data calculation unit 53: Trouble sign determination data acquisition unit 54: Clustering determination unit

Claims (5)

The time required for executing the calibration process for a plurality of cases in which image quality abnormality occurred in the image forming apparatus after executing the calibration process for calibrating the parameter value for adjusting the image quality of the image formed on the recording material by the image forming apparatus. Storage means for storing a group of measurement data obtained by collecting one or both measurement data of the amount of change in the parameter value due to the calibration process;
When the measurement data of the latest calibration process executed by the target image forming apparatus that predicts the image quality abnormality is included in a range that characterizes the measurement data group stored in the storage unit, the target image forming apparatus An output means for outputting a notification that an abnormality has occurred;
An image quality abnormality prediction system characterized by comprising: The storage means stores the image quality abnormality after the calibration process when the deviation between the measurement data group when the image quality abnormality occurs after the calibration process and the measurement data group when the image quality abnormality does not occur is equal to or greater than a threshold value. Memorize measurement data group when
The image quality abnormality prediction system according to claim 1. The storage means stores a measurement data group obtained by extracting the measurement data classified into the large side when the measurement data is classified according to the magnitude of the value among the measurement data groups when the image quality abnormality occurs after the calibration process. To
The image quality abnormality prediction system according to claim 1 or 2, characterized in that The storage means stores a measurement data group that excludes measurement data that overlaps with a measurement data group that does not occur after the calibration process, from a measurement data group when an image quality abnormality occurs after the calibration process,
The image quality abnormality prediction system according to claim 1 or 2, characterized in that On the computer,
The time required for executing the calibration process for a plurality of cases in which image quality abnormality occurred in the image forming apparatus after executing the calibration process for calibrating the parameter value for adjusting the image quality of the image formed on the recording material by the image forming apparatus. A storage function for storing a measurement data group in which measurement data of one or both of the amount of change in the parameter value due to the calibration process is collected;
When the measurement data of the latest calibration process executed by the target image forming apparatus that predicts the image quality abnormality is included in the range characterizing the measurement data group stored by the storage function, the target image forming apparatus An output function that outputs a notification that an abnormality has occurred;
Program to realize.

Images