JP2008276522A - State detector, state detection method, state detection program and state detection system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a state detector, a state detection method, a state detection program and a state detection system, in which occurrence of a serious abnormality can be detected based on a detection value changed according to a change of a state. <P>SOLUTION: An occurrence rate per day for each error item is derived, and the resulting occurrence rate is stored as history in a database 34. Every time when the occurrence rate is derived, a threshold is derived based on the history of occurrence rate stored in the database 34, whether the state is normal or abnormal is determined by comparing the occurrence rate of the day with the derived threshold, and a display control circuit 30 is controlled to display and report the determination result on a display device. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to a state detection device, a state detection method, a state detection program, and a state detection system.

  Conventionally, when detecting the occurrence (failure) of an abnormal state in a production line, an apparatus, or the like, a value that changes when an abnormal state occurs is detected. Whether or not the detected value has changed due to an abnormality can be determined using, for example, a threshold value.

  For example, as in Patent Document 1, when performing measurement by sampling a product in a production process, trend management is performed in consideration of variations in quality characteristics, and prior measures are taken when an abnormal trend appears, resulting in less trouble. In order to enable production, it has been proposed to determine a workpiece to be extracted using production information and extraction conditions.

  Further, for example, in Patent Document 2, the additional certainty factor is determined from the relative change amount of the time series data, the latest certainty factor is obtained using the certainty factor coupling function, and the threshold value for the certainty factor is used to obtain the time series data. It has been proposed to detect the tendency of minute fluctuations.

  Further, in Patent Document 3, when the characteristic data exceeds the abnormal level, the least square approximation of the data is performed from the characteristic data and the past data, and when the circuit stop level line is exceeded by extrapolating the approximate line. It has been proposed to predict

In Patent Document 4, the current of the laser light source is detected, the detected current is compared with a preset reference current, and the laser light source is deteriorated when the detected current exceeds the reference current. It has been proposed to inform.
JP 2001-0667109 A JP-A-5-072005 JP-A-9-054613 JP 2000-280522 A

  An object of the present invention is to provide a state detection device, a state detection method, a state detection program, and a state detection system that can detect that a serious abnormality has occurred based on a detection value that changes in accordance with a change in state. It is.

  The invention of claim 1 is a detection means for detecting a value that changes in response to a change in state, a holding means for holding the detection value detected by the detection means as a history, and a detection value held by the holding means. On the basis of the history, the deriving means for deriving the threshold value and comparing the detected value detected by the detecting means with the threshold value derived by the deriving means determines whether the state is normal or abnormal A state detection apparatus comprising: a determination unit; and a notification unit that notifies a determination result by the determination unit.

  The invention according to claim 2 is the state detection apparatus according to claim 1, wherein the detection means detects the number of occurrences of defects.

  According to a third aspect of the present invention, in the state detection device according to the first aspect, the detecting means periodically detects a failure occurrence rate within a preset unit period.

  According to a fourth aspect of the present invention, the deriving unit derives a detection value of a predetermined rank from the higher or lower detection value as the threshold value based on the frequency distribution of the detection value detected by the detection unit. The state detection device according to any one of Items 1 to 3.

  According to a fifth aspect of the present invention, the deriving unit specifies a detection value having a predetermined rank from a higher or lower detection value based on a frequency distribution of the detection value detected by the detection unit, and the specified detection. The state detection device according to claim 1, wherein a value obtained by subtracting a statistic of the detection value from the value is derived as a threshold value.

  According to a sixth aspect of the present invention, the deriving means derives a detection value having a predetermined rank from the higher or lower detection value as the threshold based on a statistical distribution to which the same average as the average of the detection values is applied. The state detection apparatus in any one of Claims 1-3.

  In the invention of claim 7, the deriving means specifies and specifies detection values of a predetermined rank from the higher or lower detection value based on a statistical distribution to which the same average as the average of the detection values is applied. The state detection device according to claim 1, wherein a value obtained by subtracting a statistic of the detection value from the detection value is derived as a threshold value.

  The invention according to claim 8 is the state according to any one of claims 1 to 7, wherein the deriving means derives a threshold value based on detection values for a predetermined period until the most recently held as history in the holding means. Detection device.

  The invention according to claim 9 is the state detection device according to any one of claims 1 to 8, wherein the holding means holds detection values for a predetermined period until the latest as a history.

  The invention according to claim 10 is the state detection device according to any one of claims 1 to 9, wherein the notification means notifies the determination result when the determination result is abnormal.

  The invention of claim 11 further comprises a communication means capable of exchanging information by communication with an external device, and the notification means transmits the determination result to the external device by the communication means as the notification. The state detection device according to any one of 10.

  The invention of claim 12 further comprises display means for displaying characters and images, and the notification means displays the determination result on the display means as the notification. The state detection device described.

  According to the invention of claim 13, a detection value obtained by detecting a value that changes in accordance with a change in the state is stored as a history in the storage means, and a value that changes in accordance with the change in the state is detected. Each time, a threshold value is derived based on a history of detected values stored in the storage means, and the detected value is compared with the derived threshold value to determine whether the state is normal or abnormal, and a determination result is obtained. State detection method to notify.

  According to a fourteenth aspect of the present invention, there is provided a detection unit that detects a value that changes in response to a change in state, a holding unit that holds the detection value detected by the detection unit as a history, and the holding unit. Whether the state is normal or abnormal by comparing the detected value detected by the detecting means with the deriving means for deriving the threshold based on the history of detected values A state detection program for functioning as a determination unit for determining the determination result and a notification unit for notifying the determination result by the determination unit.

  The invention of claim 15 includes a plurality of detection means for detecting the occurrence rate of defects at each manufacturing stage in the manufacturing process, and a holding means for holding the occurrence rate of each defect detected by each detection means as a history, respectively. Derivation means for deriving a threshold value based on the history of each defect held in the holding means, and comparing the detection value detected by each detection means with the corresponding threshold value derived by the derivation means, respectively. A state detection system comprising: determination means for determining whether the factory state is normal or abnormal; and notification means for notifying the determination result when the determination means determines that there is an abnormality.

  According to the present invention, it is possible to detect that a serious abnormality has occurred based on a detection value that changes in accordance with a change in state.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

  FIG. 1 schematically shows the configuration of the state detection system 11 according to the present embodiment. In the present embodiment, as an example, a mode in which state detection is performed in an electronic device production factory will be described.

  As shown in the figure, the state detection system 11 includes a management apparatus 10 and a plurality (three in the example shown in the figure) of abnormality detection apparatuses 12A, 12B, and 12C. 14 and the like, and are configured to be capable of data communication with each other via a factory LAN 14.

  FIG. 2 shows an electrical configuration of the management apparatus 10. As shown in the figure, the management device 10 includes a central processing unit (CPU) 22, a read only memory (ROM) 24, a random access memory (RAM) 26, a communication interface (I / I). F) 28 is included. These CPU 22, ROM 24, RAM 26, and communication I / F 28 are each connected to the bus 20.

  The ROM 24 stores in advance various programs including various control programs that mainly control the entire apparatus executed by the CPU 22, various data, and the like. The RAM 26 temporarily stores various data associated with the processing of the CPU 22.

  In addition, the communication I / F 28 performs communication with the in-factory LAN 14 and external devices by wire or wireless via a network or communication line (not shown).

  The management device 10 includes a display control circuit 30, a display device 32, and a database 34. The display control circuit 30 and the database 34 are connected to the bus 20, respectively.

  The CPU 22 controls display on the display device 32 via the display control circuit 30 and inputs / outputs various information to / from the database 34.

  On the other hand, in each abnormality detection apparatus 12A, 12B, 12C, the presence or absence of abnormality in each process of production is detected. In the present embodiment, the number of abnormality detection devices 12 is assumed to be 3 in order to avoid complicated explanations, but the number is not particularly limited.

  In addition, each of the abnormality detection devices 12A, 12B, and 12C outputs an abnormality detection signal indicating an abnormality detection state to the management device 10 via the factory LAN 14. In addition, each abnormality detection apparatus 12 is good also as a structure which detects the abnormality regarding one operation | movement or a site | part, and is good also as a structure which detects a some abnormality. In the present embodiment, a description will be given of a configuration in which abnormalities in a plurality of operations and parts are detected and a plurality of abnormality detection signals are output.

  FIG. 3 shows a functional block diagram related to a state detection process executed mainly by the CPU 22 of the management apparatus 10. As shown in the figure, in the management device 10, based on each abnormality detection signal input from the abnormality detection device 12, data indicating an abnormality occurrence state for the error item corresponding to each abnormality detection signal is stored in the database 34 as needed. Accumulate.

  The state detection processing unit 40 performs state detection for each abnormality detection signal based on data stored in the database to determine whether or not a serious abnormality has occurred.

  The state detection processing unit 40 includes an occurrence rate deriving unit 42, a threshold deriving unit 44, and a state detecting unit 46.

  The occurrence rate deriving unit 42 derives the occurrence rate of today's abnormality from the total number of times of detection of today and the number of times of detection of abnormality. The derived abnormality occurrence rate is stored in a database.

  In addition, the threshold deriving unit 44 derives a threshold based on the distribution state of the incidence in a predetermined period until the previous day, and outputs the threshold to the state detecting unit 46.

  The state detection unit 46 compares the threshold value input from the threshold value derivation unit 44 with the today's abnormality occurrence rate derived by the incidence rate deriving unit 42 for the error item corresponding to each abnormality detection signal, and generates an abnormality. Detect state. Specifically, in the state detection unit 46, for an error item whose today's abnormality occurrence rate exceeds the threshold value, there is a high possibility that some abnormality has occurred, and for the error item whose today's abnormality occurrence rate does not exceed the threshold value. Detects that there is no high probability that an abnormality has occurred. In addition, the result of the state detection by the state detection unit 46 is also stored in the database.

  When the state detection by the state detection unit 46 is completed, the detection result is displayed on the display device 32 via the display control circuit 30.

  Here, in the present embodiment, as an example, a state inspection process when a multifunction machine is produced in a factory will be described.

  FIG. 4 shows an electrical configuration of the multi-function device 50. As shown in the figure, the multi-function device 50 includes a CPU 62, a ROM 64, a RAM 66, and a communication I / F 68 that control the operation of the entire apparatus. These CPU 62, ROM 64, RAM 66, and communication I / F 68 are each connected to the bus 60.

  The ROM 64 stores in advance various programs including various control programs that mainly control the entire apparatus executed by the CPU 62, various data, and the like. The RAM 66 temporarily stores various data associated with the processing of the CPU 62.

  The communication I / F 68 performs communication with an external device by wire or wireless via a network or communication line (not shown).

  The multi-function device 50 includes a display control circuit 70 and a display device 72. The display device 72 is connected to the display control circuit 70, and the display control circuit 70 is connected to the bus 20. The CPU 62 controls display on the display device 72 via the display control circuit 70.

  The multi-function device 50 further includes an image processing circuit 74, a motor control circuit 76, and a scanner 78. The image processing circuit 74, the motor control circuit 76, and the scanner 78 are incorporated in the image reading unit and mounted on the multi-function device 50.

  The image processing circuit 74 and the motor control circuit 76 are connected to the bus 60, driven by the CPU 62, and connected to the scanner 78, respectively.

  The scanner 78 includes an imaging device such as a glass plate (so-called platen glass) on which a reading document is set, a light source, and a CCD (Charge Coupled Device) image sensor. In a state where the original image is set to face the platen glass, the original image is read by irradiating the light from the light source through the platen glass and capturing the reflected light with the CCD image sensor. When the CCD image sensor is a line sensor or an area sensor having a size smaller than the document image size, the entire document image can be read by scanning and moving the light source and the CCD.

  The motor control circuit 76 drives various motors for moving the light source, the CCD image sensor, and the like when the original is read by the scanner 78. The image processing circuit 74 acquires digital image data based on an output signal from the CCD image sensor.

  The multi-function device 50 is configured to further include an image processing circuit 84, a motor control circuit 86, and an image forming apparatus 88. The image processing circuit 84, the motor control circuit 86, and the image forming apparatus 88 are incorporated in the image forming unit and mounted on the multi-function device 50.

  The image processing circuit 84 and the motor control circuit 86 are connected to the bus 60, driven by the CPU 62, and connected to the image forming apparatus 88.

  The image forming unit 88 includes, for example, a transport mechanism that transports a recording medium and an image forming unit that forms an image on the transported recording medium. The image forming unit forms an image by ejecting ink droplets directly onto the transported recording medium, or forms a latent image by scanning a light beam on the photoreceptor, and develops it with toner and transfers it to the recording medium. Thus, various configurations such as a configuration for forming an image can be employed.

  The motor control circuit 86 drives various motors for operating the transport mechanism and other parts when the image forming unit 88 forms an image. The image processing circuit 84 converts the digital image data input via the scanner 78 or the digital image data input from an external device via the communication I / F 68 into data in a form corresponding to the image forming apparatus 88. To do.

  The production process of the multi-function device 50 includes, for example, a machine control unit that controls the entire image forming apparatus, an image reading unit that includes a scanner 78, and an image forming apparatus 88 with the CPU 62 at the center. Image forming units are produced respectively. At this point, each unit is inspected to detect whether it operates normally or an abnormality occurs.

  Thereafter, the image forming unit is set on the machine control unit and assembled, and the machine control unit and the image forming unit are electrically connected. Even at this time, whether the connection state is normal or abnormal is detected, and an image is actually formed by the image forming unit, the density control state, the degree of image formation position deviation, and the occurrence of dots and streaks on the image. Whether each state is normal or abnormal is detected.

  Further, the image reading unit is set and assembled in the housing, and the image reading unit and the machine control unit are electrically connected. Even at this time, whether the connection state and the reading control state are normal or abnormal is detected.

  These detections are executed by the abnormality detection device 12, and the detection result is input to the management device 10 as an abnormality detection signal.

  In addition, as an error item input as an abnormality detection signal to the management device 10, in addition to an error item related to management such as the number of production per day, an error item related to assembly trouble such as contact failure or component non-mounting, density failure, Error items related to image quality problems such as dots, streaks, misalignment, and skew, error items related to paper conveyance problems such as jam, skew, and size detection function, systems such as control system errors and communication system errors, fan failure, electrical systems, and machines There are error items related to system problems.

  FIG. 5 shows, as an example, derived based on an abnormality detection signal corresponding to an error item in the density state, which is input to the management device 10 from the abnormality detection device 12 that detects an abnormality in image quality due to the produced image forming unit. The transition of the error occurrence rate per day is shown as a solid line graph. In the figure, the horizontal axis represents the day, the vertical axis represents the incidence, and one scale on the horizontal axis corresponds to 7 days.

  As shown in the figure, the error occurrence rate has increased since the date indicated by S, and it can be determined that some problem has occurred at this time. The detection of the occurrence of any problem based on such an error rate can be performed based on whether or not the error rate has exceeded a predetermined threshold.

  Here, for example, when the threshold value is fixed, the error rate is different for each error item. Therefore, a different threshold value must be set for each error item in consideration of the tendency of the error rate. In addition, the threshold may need to be reset according to a change in the error rate, a change in the inspection condition, or the like, and the process for managing the threshold becomes complicated.

  Therefore, in the present embodiment, as described above, the threshold deriving unit 46 derives the threshold based on the distribution of error occurrence rates in the predetermined period T up to the previous day, and uses the derived threshold to detect the state. 46 detects whether any problem has occurred.

  In the threshold value derivation by the threshold value derivation unit 46, the upper K% occurrence rate of the error occurrence rate is set in the predetermined period T until the previous day.

  Specifically, in the present embodiment, the threshold value deriving unit 46 presets a set value K for threshold value derivation, derives the rank corresponding to the upper K%, and uses the error occurrence rate of that rank as the threshold value. Derived. That is, the rank corresponding to the upper K% can be derived by multiplying the predetermined period T by K / 100. When the predetermined period T is 30 days and K is 10%, the error occurrence rate of the upper third is Derived as a threshold. If the rank derived based on the values of the predetermined periods T and K is not an integer rank, the rounded rank is derived.

  The threshold value thus derived changes as shown by a dotted line in the figure.

  FIG. 6 shows the distribution of the occurrence rate during a predetermined period T (30 days) until the next day of the day indicated by S in FIG. The error rate shown in the figure is 0 if the error rate x is 0 ≦ x <0.5, 0.5 if 0.5 ≦ x <1, 1 if 0.5 ≦ x <1.5,・ Approximate values.

  As shown in the figure, it can be seen that in the past 30 days, 90% has an occurrence rate of less than 4.5% and an error occurrence rate rarely exceeds 4.5%.

  In the present embodiment, the factory holiday data is not used, and the total frequency (number of days) is 27 days as shown in FIG. For this reason, the rank corresponding to the top 10% is 2.7, but if it is not an integer as described above, it is rounded to the third place.

  Thus, the error occurrence rate exceeding 4.5% means that the error occurs only occasionally, and it may be determined that some problem has occurred. It should be noted that the degree of occurrence (occurrence rate at which it is determined that some problem has occurred) can be adjusted as appropriate by changing the set value K.

  The operation of the present embodiment will be described below.

  In the management apparatus 10, after the operation of the production line of the factory is stopped, a state detection process is executed based on an operation input to the management apparatus 10 by the administrator.

  FIG. 7 is a flowchart showing a processing flow of a state detection processing program mainly executed by the CPU 22. Hereinafter, the state detection process according to the present embodiment will be described with reference to FIG. The state detection processing program is stored in advance in a predetermined area of the ROM 24.

  First, in step 100, 1 is set to the variable N, and in the next step 102, the error occurrence rate of the error item N today is derived. In addition, today's error occurrence rate can be obtained by dividing the number of error occurrences by, for example, the number of productions or the number of inspections.

  In the next step 104, the derived error rate of today is stored in the database 34, and then the process proceeds to step 106.

  In step 106, the error occurrence rate of the predetermined period T up to the previous day is read from the database 34, and then the process proceeds to step 108, and the rank according to the set value K is derived using the set value K and the predetermined period T. . Thereafter, the process proceeds to step 110 where the error rate of the derived rank is set as a threshold value. In the next step 112, today's error rate is compared with the threshold value, and today's error rate is smaller than the threshold value. It is determined whether or not. If the determination is negative, the error occurrence rate exceeds the threshold value, and it is determined that some problem that occurs only occasionally occurs based on past circumstances, and the process proceeds to step 114.

  In step 114, the display control circuit 30 is controlled to display on the display device 32 that some kind of problem has occurred, and then the process proceeds to step 116 to indicate that the threshold for error item N has been exceeded. And then move to step 118.

  On the other hand, if the determination in step 112 is affirmative, the process proceeds to step 118 without executing the processes in steps 114 and 116 for the error item N.

  In step 118, it is determined whether or not the value of N is equal to or greater than the number of error items (abnormality detection signals) input to the management apparatus 10. If the determination is negative, the process proceeds to step 120. In step 120, N is incremented (1 is added to N), and then the process returns to step 102 again.

  On the other hand, if the determination in step 118 is affirmative, the present state detection processing program is terminated.

  As described above, according to the present embodiment, the daily occurrence rate for each error item is derived, and the obtained occurrence rate is stored as a history in the database 34 to derive the occurrence rate. Each time, a threshold value is derived based on the history of the occurrence rate stored in the database 34, and the occurrence rate of today is compared with the derived threshold value to determine whether the state is normal or abnormal, and the determination result is obtained. Since the display control circuit 30 is controlled so as to be displayed and notified on the display device, it can be detected that a serious abnormality has occurred based on a detection value that changes in accordance with a change in state.

  In the present embodiment, the form in which the starting date of the predetermined period T is the day before the execution date of the state detection process has been described. However, the present invention is not limited to this, and the starting date is the status of the production process. And can be set as appropriate according to the execution timing of the state detection process.

  For example, the threshold value may be derived based on the distribution of error occurrence rates for a predetermined period T including the current day, or may be derived based on the distribution of error occurrence rates for a predetermined period from the day before the previous day, such as 5 days ago. May be.

  In the embodiment, the predetermined period T is 30 days, but the period can be set as appropriate, such as 15 days or 45 days. In addition, it is better to omit data such as factory closed days during the predetermined period T.

  Here, FIG. 8 shows the threshold value (dashed line) derived as the predetermined period T = 30 and the threshold value (dashed line) derived as the predetermined period T = 60 for all the periods shown in FIG. . As shown in the figure, when the error occurrence rate (solid line) temporarily increases, the threshold value increases (overshoot) after being dragged by the temporarily increased error occurrence rate.

  Further, as shown in the figure, when the predetermined period is set long, the overshoot tends to be prolonged.

  For example, FIG. 9 shows error occurrence rates for error items different from the error items shown in FIGS. 5 and 8 (solid line). Also in the figure, one scale on the horizontal axis corresponds to 7 days. As shown in the figure, the overshoot is smaller as the change amount of the error occurrence rate is smaller, and the overshoot is eliminated in a shorter period as the number of days with the higher error occurrence rate is smaller.

  Therefore, when setting the period, it is preferable to set in consideration of the tendency of the error rate and the overshoot.

  Furthermore, the overshoot can be reduced by executing the derivation of the threshold value using the statistical amount (sum, average, standard deviation, median, etc.) of the error occurrence rate during the predetermined period T.

  In FIG. 10, for all periods shown in FIG. 5, the predetermined period T = 30 days is derived using the threshold derived by the derivation method of the above embodiment and the error occurrence rate statistic in order to reduce overshoot. Thresholds are shown. In the figure, the graph indicated by the alternate long and short dash line indicates the threshold value using the derivation method of the above embodiment, and the graph of the countermeasure A (thick chain line) indicates the threshold value derived in the same manner as in the above embodiment, for a predetermined period T. Shows the value divided by the average value of the error rate at.

  Further, the graph of the measure B (chain line) shows a value obtained by dividing the threshold derived in the same manner as in the above embodiment by the standard deviation of the error occurrence rate in the predetermined period T.

  As shown in the figure, the overshoot is reduced in the threshold value derived by performing the countermeasure A and the countermeasure B.

  In addition, although illustration is abbreviate | omitted, it replaces with an average or a standard deviation, and even if it uses a median, the effect that an overshoot can be reduced is acquired.

  As a simpler example, substantially the same effect can be obtained by subtracting the sum (or a value proportional to the sum) of the error occurrence rates for the predetermined period T from the threshold value.

Moreover, although the said embodiment demonstrated the form which derives | requires a threshold value based on the incidence rate, you may derive | lead-out a threshold value based on the number of occurrences. In this case as well, the threshold value can be derived using the frequency distribution of the number of occurrences as in the case of deriving the threshold value based on the occurrence rate.

  In the above embodiment, the threshold value is derived using the frequency distribution of the occurrence rate and the number of occurrences, but instead of these frequency distributions, the same average value as the average value of the occurrence rate or the number of occurrences is used. Statistical distribution can be used.

  For example, FIG. 11 shows the frequency of the error occurrence rate for a predetermined period T normalized so that the frequency sum is 1 and the Poisson distribution having the same average for the error items different from FIG. ing. As shown in the figure, the error rate of 10% from the top of the distribution is almost 2% in both cases, and it is shown that the result is almost the same regardless of which distribution is used to derive the threshold value. Yes. Note that the distribution of error rates shown in the figure is an example.

  The database 34 only needs to store a history of at least the predetermined period T.

  The configuration of the state detection system 11 according to the above embodiment is an example, and can be appropriately changed without departing from the gist of the present invention.

  As shown in FIG. 12, a configuration may be adopted in which management devices 10 of a plurality of factories are connected by an in-house network 16 constituted by an intranet or the like, and are collectively managed by a management center server 18 similarly connected to the in-house network 16. . In this case, the state detected by each management apparatus 10 is transmitted to the management center server 18 via the in-house network 16, and the state of each factory is grasped by the management center server 18 to cope with troubles in each factory. The production number may be adjusted.

  Further, the management apparatus 10 only derives the daily error rate for each error item, and transmits the error rate for each derived error item to the management center server 18 via the in-house network 16 for management. In the center server 18, threshold value derivation and state detection may be executed, and the detection result may be transmitted to each management apparatus 10.

  Further, as shown in FIG. 13, even after the image forming apparatus 50 produced in each factory is on the market, for example, the image forming apparatus 50 in the market is connected to the Internet 19 and used. It is also possible to adopt a configuration in which the error occurrence status is transmitted to the management center server 18 via the network. In this case, it is possible to grasp which part of the image forming apparatus 50 produced in which factory at which time is abnormal, so if there is a cause in the production process, factory, parts, etc., the cause Effective for early identification and early countermeasures.

  Further, the flow of processing according to the above embodiment is an example, and it is needless to say that the flow can be appropriately changed without departing from the gist of the present invention.

  FIG. 14 is an explanatory diagram of an example of a computer program, a storage medium storing the computer program, and a computer when the state detection processing function of the state detection system 11 of the present invention is realized by a computer program. In the figure, 550 is a program, 552 is a computer, 554 is a magneto-optical disk, 556 is an optical disk, 558 is a magnetic disk, 560 is a memory, 562 is an internal memory, 566 is a reading unit, 570 is a hard disk, 568 and 574 are interfaces, Reference numeral 572 denotes a communication unit.

  Part or all of the functions of the respective units of the state detection system 11 of the present invention described in the above embodiment can be realized by a program 550 that can be executed by a computer. In that case, the program 550, data used by the program, and the like can be stored in a computer-readable storage medium. As a storage medium, the reading unit 566 provided in the hardware resource of the computer causes a change state of energy such as magnetism, light, electricity, etc. according to the description content of the program, and a signal corresponding to the change state is generated. In this format, the description content of the program can be transmitted to the reading unit 566. For example, a magneto-optical disk 554, an optical disk 556 (including a CD and a DVD), a magnetic disk 558, a memory 560 (including an IC card and a memory card), and the like. Of course, these storage media are not limited to portable types.

  The program 550 is stored in these storage media, and the program 550 is read from the computer by, for example, mounting these storage media on the reading unit 566 or the interface 574 of the computer 552, and stored in the internal memory 562 or the hard disk 570. By executing the program 550 by the CPU 564, the function of the state detection process of the present invention can be realized. Alternatively, the program 550 is transferred to the computer 552 via a network or the like, and the computer 552 receives the program 550 by the communication unit 572, stores the program 550 in the internal memory 562 or the hard disk 570, and executes the program 550 by the CPU 564. You may implement | achieve the function of the state detection process of invention. In addition, the computer 552 can be connected to various devices via an interface 568. For example, a display device for displaying information and an input device for inputting information by a user are also connected.

  Of course, some functions may be configured by hardware, or all may be configured by hardware. Alternatively, it can be configured as a program including the present invention together with other configurations.

It is the schematic which shows the structure of the state detection system which concerns on embodiment. It is a block diagram which shows the structure of the control system of a management apparatus. It is a functional block diagram regarding the state detection process which concerns on embodiment. It is a block diagram which shows an example of a structure of the control system of the image recording process produced in the factory which concerns on embodiment. As an example, it is a graph showing a transition of an error occurrence rate for an error item related to the density of an image formed by an image forming unit produced in a factory. It is a graph which shows the distribution state of the error occurrence rate within a predetermined period. It is a flowchart which shows the flow of a state detection process. It is a graph which shows transition of an error incidence rate, and transition of two kinds of thresholds from which a predetermined period differs, respectively. It is a graph which shows transition of the error incidence rate about another error item, and transition of a threshold. It is a graph which shows transition of an error occurrence rate, and transition of a threshold value each derived by three kinds of methods. It is a graph which shows the distribution of the normalized error incidence, and the Poisson distribution which has the same average as the said distribution. It is a block diagram of another state detection system. It is a block diagram of another state detection system. It is explanatory drawing of an example of a computer program in the case of implement | achieving the function of a state detection process with a computer program, the storage medium which stored the computer program, and a computer.

Explanation of symbols

10 Management Device 11 Status Detection System 12 Abnormality Detection Device 14 Factory LAN
16 Internal network 18 Management center server 19 Internet 22 CPU
24 ROM
26 RAM
50 Image forming apparatus

Claims (15)

Detecting means for detecting a value that changes in response to a change in state;
Holding means for holding the detection value detected by the detection means as a history;
Derivation means for deriving a threshold based on a history of detection values held in the holding means;
Discrimination means for discriminating whether the state is normal or abnormal by comparing the detection value detected by the detection means with the threshold value derived by the derivation means;
An informing means for informing a discrimination result by the discriminating means;
A state detection device.   The state detection apparatus according to claim 1, wherein the detection unit detects the number of occurrences of a defect.   The state detection device according to claim 1, wherein the detection unit periodically detects a failure occurrence rate within a preset unit period.   The derivation means derives a detection value of a predetermined rank from the higher or lower detection value as the threshold based on the frequency distribution of the detection values detected by the detection means. The state detection device according to item 1.   The deriving unit specifies a detection value of a predetermined rank from the higher or lower detection value based on the frequency distribution of the detection value detected by the detection unit, and detects the statistical value of the detection value from the specified detection value. The state detection device according to claim 1, wherein a value obtained by subtracting the amount is derived as a threshold value.   The derivation means derives a detection value having a predetermined rank from the higher or lower detection value as the threshold based on a statistical distribution to which the same average as the average of the detection values is applied. The state detection device according to claim 1.   The derivation means specifies a detection value of a predetermined rank from a higher or lower detection value based on a statistical distribution to which the same average as the average of the detection values is applied, and from the specified detection value, The state detection device according to claim 1, wherein a value obtained by subtracting the statistic is derived as a threshold value.   The state detection device according to any one of claims 1 to 7, wherein the deriving unit derives a threshold value based on detection values for a predetermined period until the latest stored in the holding unit as a history.   The state detection device according to any one of claims 1 to 8, wherein the holding unit holds detection values for a predetermined period up to the latest as a history.   The state detection device according to claim 1, wherein the notification unit notifies the determination result when the determination result is abnormal. It further comprises a communication means that can exchange information by communication with an external device,
The state detection device according to claim 1, wherein the notification unit transmits the determination result to an external device through the communication unit as the notification. It further comprises display means for displaying characters and images,
The state detection device according to claim 1, wherein the notification unit displays the determination result on the display unit as the notification. The detection value obtained by detecting the value that changes according to the change in the state is stored as a history in the storage means,
Each time a value that changes according to the change in the state is detected, a threshold value is derived based on a history of detection values stored in the storage means,
A state detection method in which a detected value is compared with a derived threshold value to determine whether the state is normal or abnormal and to notify the determination result. Computer
Detecting means for detecting a value that changes in response to a change in state;
Holding means for holding the detection value detected by the detection means as a history;
Derivation means for deriving a threshold based on a history of detection values held in the holding means;
Discrimination means for discriminating whether the state is normal or abnormal by comparing the detection value detected by the detection means with the threshold value derived by the derivation means;
An informing means for informing a discrimination result by the discriminating means;
Status detection program to function as A plurality of detection means for detecting the occurrence rate of defects at each manufacturing stage in the manufacturing process;
Holding means for holding each defect occurrence rate detected by each detecting means as a history;
Derivation means for deriving a threshold based on the history of each defect held in the holding means;
Discriminating means for discriminating whether the state of the factory is normal or abnormal by comparing the detected value detected by each detecting means with the corresponding threshold value derived by the deriving means, respectively;
An informing means for informing a determination result when the determining means determines that there is an abnormality;
A state detection system.

Images