JP2010101948A - Failure prediction device and image forming apparatus - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To avoid the generation of misinformation caused by the fact that maintenance operation is performed for an object to be inspected, in such a configuration that the failures of the object to be inspected are predicted on the basis of the result of determining whether or not peculiar motion is taken with respect to the past behavior, on useful prediction information. <P>SOLUTION: In a failure prediction device 120 determining whether or not the failures occur soon on the process unit of a color image forming apparatus being the object to be inspected, on the basis of the useful prediction information such as a P-value, a Q-value and an R-value obtained on the process unit, when maintenance information obtained on the process unit shows the execution of the maintenance operation, it is determined that the failures have not occurred yet, regardless of the behavior of the useful prediction information on the process unit, for a fixed period after th maintenance operation. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a failure prediction apparatus that determines whether or not a failure will occur soon based on a result of determining whether or not predictive useful information useful for failure prediction has a specific movement with respect to past behavior. It is about. The present invention also relates to an image forming apparatus such as a copying machine, a facsimile machine, or a printer equipped with such a failure prediction apparatus.

  Conventionally, in various machines and devices on the market, when a failure occurs, depending on the content of the failure, it may be disabled for a considerable period of time until the completion of repair, which may inconvenience the user. . For this reason, it is desired to predict the occurrence of a failure in advance and deal with it before the occurrence.

  As a failure prediction apparatus that predicts the occurrence of a failure in advance, a device described in Patent Document 1 is known. This failure prediction apparatus monitors, for each job, the paper preparation time required from the start of a paper preparation operation to the completion of paper preparation executed at the start of a print job for a copying machine to be examined. An indication that a paper feeder of a copier will cause a failure is that paper preparation time becomes longer. Accordingly, the variance of the paper preparation time is calculated from the past going back a predetermined period to the present, and an error is warned to the user when the calculation result exceeds a predetermined limit value. Accordingly, it is possible to notify the user in advance that a failure is about to occur in the paper feeding device.

Japanese Patent Publication No. 3-68385

  However, in this failure prediction device, when a user or service person voluntarily performs maintenance work on the paper feeding device regardless of the error warning described above, the failure of the paper feeding device immediately follows. There was a risk of mispredicting. Specifically, in a copying machine, the rate of increase in paper preparation time increases rapidly immediately before a paper feeder failure occurs, so the dispersion of paper preparation time from the past to the present exceeds the limit value. . Thereby, it is possible to predict in advance the occurrence of a failure of the sheet feeding device. However, the paper preparation time of the paper feeder starts to be extended little by little from a point in time that is considerably earlier than the failure occurrence timing. When users or service personnel voluntarily perform maintenance work on the paper feeder, the paper preparation time will be suddenly restored to the normal value from the value that has been gradually extended until then. Increases temporarily. Due to this increase, if the variance exceeds the limit value, the arrival of a fault is predicted incorrectly.

  So far, the problems that occur in the configuration that performs failure prediction based on the dispersion of paper preparation time as predictive useful information have been described, but not limited to this configuration, if the following configuration is adopted, the same Problems occur. That is, the prediction useful information useful for failure prediction such as the paper preparation time is configured to perform failure prediction based on the result of determining whether or not the behavior is unique with respect to the past behavior.

  The present invention has been made in view of the above background, and an object thereof is to provide the following failure prediction apparatus and image forming apparatus. That is, in the configuration that predicts failure of the test object based on the result of determining whether or not the prediction useful information has a specific movement with respect to the past behavior, maintenance work is performed on the test object. A failure prediction device or the like that can avoid the occurrence of false alarms due to failure.

In order to achieve the above object, the invention according to claim 1 is acquired by predictive useful information acquisition means for acquiring predictive useful information useful for failure prediction from a subject to be examined at a predetermined cycle, and the predicted useful information acquisition means. Whether or not the predicted useful information has a specific movement with respect to the past behavior is determined, and based on the determination result, a failure will occur soon or not yet In the failure prediction apparatus comprising: a determination unit that determines whether the failure is occurring; and a notification unit that notifies the fact that the determination unit determines that a failure will occur soon. Maintenance information acquisition means for acquiring maintenance information as to whether or not maintenance work has been performed is provided, and maintenance information indicating that maintenance work has been performed is received by the maintenance information acquisition means. If it is, the subsequent period of time, regardless of the behavior of the prediction useful information, to perform a determination that still fault does not occur, is characterized in that constitute the determining means.
According to a second aspect of the present invention, in the failure prediction apparatus of the first aspect, the predictive useful information acquisition unit is configured to acquire a plurality of types of predictive useful information at the predetermined period. Based on the result of applying individual weighting to each judgment result, it is judged whether or not there is a specific movement with respect to past behavior for each type of predictive useful information. The determination means is configured to determine whether or not a failure has occurred or whether a failure has not occurred yet.
According to a third aspect of the present invention, in the failure prediction apparatus according to the first or second aspect, the predicted useful information is acquired so that the predicted useful information is acquired from each of a plurality of parts or internal devices constituting the test object. Each of the plurality of parts or internal devices is configured to determine whether a failure will soon occur or whether a failure has not occurred yet, based on the unique predictive useful information and the maintenance information. The determination means is configured to perform the processing to be performed individually, and the notification means is configured to individually notify information indicating that a failure will occur soon for each of the plurality of parts or the internal device. It is characterized by this.
According to a fourth aspect of the present invention, in the failure prediction apparatus according to the third aspect, the predicted useful information is affected by maintenance work for other parts or internal devices among the plurality of components or internal devices. For things, in addition to the maintenance information about itself, based on the maintenance information about the other parts or internal devices, whether a failure will occur soon or whether a failure has not occurred yet The determination means is configured to determine whether or not there is a feature.
According to a fifth aspect of the present invention, in the failure prediction apparatus according to any one of the first to fourth aspects, the past useful information is grasped based on a predetermined number of past acquisition results for the predicted useful information, and maintenance is performed. When the maintenance information indicating that the work has been performed is acquired, the determination is performed so that the process until the predicted useful information is acquired for the predetermined number of times is performed as the fixed period. It is characterized by comprising means.
According to a sixth aspect of the present invention, in the failure prediction apparatus according to any one of the first to fifth aspects, the image forming apparatus is a test object.
According to a seventh aspect of the present invention, in the failure prediction apparatus according to the sixth aspect, the predicted useful information is such that a period every time a predetermined number of image forming operations are performed by the image forming apparatus is used as the predetermined period. The acquisition means is configured.
The invention according to claim 8 provides the failure prediction apparatus according to claim 6 or 7 which is an object to be examined in an image forming apparatus provided with an image forming means for forming an image on a recording medium based on image information. It is characterized by this.

  In these inventions, when maintenance work is performed on the test object, the test object is not related to the predicted useful information until the behavior of the predicted useful information after the maintenance work is newly grasped. Since it is determined that a failure has not yet occurred, it is possible to avoid the occurrence of a false alarm resulting from the maintenance work being performed.

Hereinafter, as an image forming apparatus to which the present invention is applied, an embodiment of a color image forming apparatus that forms an image by an electrophotographic method will be described.
FIG. 1 is a schematic configuration diagram illustrating a color image forming apparatus 1 according to the embodiment. FIG. 2 is a block diagram illustrating a connection state between the control unit 100 mounted on the color image forming apparatus 1 and the surrounding electrical devices.

  In FIG. 1, the color image forming apparatus 1 includes a paper feeding unit 10, a transfer unit 20 having an intermediate transfer belt 21, and yellow (Y), magenta (M), cyan (colored) disposed along the intermediate transfer belt 21. The image forming units 30Y, 30M, 30C, and 30Bk, which are toner image forming units for the respective colors C) and black (Bk), are provided in a main body housing (not shown). Further, an adhesion amount detection unit 50 for detecting the toner adhesion amount of the toner image on the intermediate transfer belt 21 is provided. In addition to these, a control unit 100 for controlling each device of the color image forming apparatus 1 is provided.

  The image forming unit 30 for each color will be described. Here, the Bk color image forming unit 30Bk will be described, but the Y, M, and C image forming units 30Y to 30C have the same configuration. In the image forming unit 30Bk, a charging unit 32Bk, an exposure unit 33Bk, a developing unit 34Bk, a primary transfer unit 35Bk, a cleaning unit 36Bk, and the like are disposed around the photoreceptor 31Bk.

  At the time of image formation, when a normal operation signal is instructed by the controller 110 of the color image forming apparatus, the photoreceptor 31Bk is rotationally driven by a drive motor (not shown) under the control of the control unit 100. Further, as shown in FIG. 2, the CPU of the control unit 100 sequentially outputs a bias means for each image forming process including a driving means such as a photoconductor motor and a charging bias sequentially. The color image signal from the external device is subjected to image processing such as color conversion processing by the image signal generation circuit 101 of the control unit 100, and a Bk color image signal is output to the exposure unit 33Bk. The exposure unit 33Bk converts the Bk image signal into an optical signal by the exposure drive circuit 102 of the control unit 100, and scans and exposes the photoconductor 31Bk while the exposure laser diode blinks based on the optical signal. Thus, an electrostatic latent image is formed.

  The electrostatic latent image on the photoreceptor 31Bk is developed by the developing unit 34Bk to become a Bk toner image, and the Bk toner image on the photoreceptor 31Bk is transferred onto the intermediate transfer belt 21 by the transfer unit 35Bk. The photoreceptor 31Bk is prepared for the next image formation by cleaning the residual toner by the cleaning unit 36Bk after transferring the toner image and removing the charge by the charge removing lamp 38Bk.

  Similarly, the image forming units 30Y, 30M, and 30C include a charging unit, a developing unit, a cleaning unit, a charge removal lamp, and the like around the photoreceptors 31Y, 31M, and 31C. Then, Y, M, and C toner images are formed on the photoreceptors 31Y, 31M, and 31C, and these images are primarily transferred while being superimposed on the intermediate transfer belt 21.

  A transfer unit 20 serving as a transfer unit is disposed below the image forming unit for each color. The transfer unit 20 includes an endless intermediate transfer belt 21, driven rollers 22, 23, a driving roller 24, and the like. An intermediate transfer belt 21, which is an image carrier that carries a plurality of color toner images, is stretched around a drive roller 24, driven rollers 22, 23, and the like. The intermediate transfer belt 21 is made of a material having extremely high smoothness in order to avoid toner sticking. For example, a belt material having a glossy surface such as PVDF (polyvinylidene fluoride) or polyimide can be suitably used. The intermediate transfer belt 21 is rotationally driven counterclockwise in FIG. 1 by the drive roller 24 being rotationally driven by a drive mechanism such as a motor (not shown) under the control of the control unit 100 shown in FIG. The Y, M, C, and Bk toner images formed on the photoconductors 31Y, 31M, 31C, and 31BB for each color are primarily transferred onto the intermediate transfer belt 21 in a primary transfer nip for each color. As a result, a four-color superimposed toner image (hereinafter referred to as a four-color toner image) is formed on the intermediate transfer belt 21.

  A secondary transfer bias roller 61 is in contact with the driving roller 24 around the intermediate transfer belt 21 from the belt front surface side, thereby forming a secondary transfer nip 6. As shown in FIG. 2, a secondary transfer bias is applied to the secondary transfer bias roller 61 by a bias power supply circuit 104 under the control of the control unit 100. Thereby, a secondary transfer electric field is formed between the secondary transfer bias roller 61 and the grounded secondary transfer nip back roller 24. The four-color toner image formed on the intermediate transfer belt 21 enters the secondary transfer nip as the belt moves endlessly.

  The paper supply unit 10 separates the recording paper (transfer paper) 12 in the paper supply cassette 11 one by one by, for example, a paper supply roller 11a and a separation member 11b (not shown) and sends them to a pair of registration rollers (not shown). The registration roller pair adjusts the timing of the recording paper 12 sent from the paper feed cassette 11 and sends the recording paper 12 toward the secondary transfer nip 6 at a predetermined timing. At the secondary transfer nip 6, the four-color toner image on the intermediate transfer belt 21 is collectively transferred onto the recording paper 12 by the action of the secondary transfer electric field and nip pressure, and combined with the white color of the recording paper 12, Become.

  The recording paper 12 on which the full color image is formed in this way is conveyed to the fixing unit 40. The fixing unit 40 heats and presses the recording paper 12 on which the full-color image is formed by the fixing roller 41 and the pressure roller 42 to fix the toner of each color on the recording paper 12, and the discharge roller pair (not shown) discharges the toner. Eject onto the paper tray.

  In the image forming unit 30 including the photosensitive member 31, the charging unit 32, the exposure unit 33, the developing unit 34, the primary transfer unit 35, and the cleaning unit 36, the exposure unit 33 and the primary transfer among these units. The part excluding the part 35 is configured as a process unit. In this process unit, the photosensitive member 31, the charging unit 32, the developing unit 34, and the cleaning unit 36 are held by a common holding unit, and these are integrally attached to and detached from the image forming apparatus main body as one unit. Is.

  The adhesion amount detection unit 50 is disposed downstream of the black (Bk) image forming unit 30Bk in the movement direction of the intermediate transfer belt 21, and as shown in FIG. A pair of optical sensors 51 and 52 as optical detection means are provided. As shown in FIGS. 4 and 5, the optical sensors 51 and 52 are respectively a light emitting element 151 made of a light emitting diode, a first light receiving element 152 that receives diffusely reflected light, and a second light receiving element that receives regular reflected light. 153. The first light receiving element 152 and the second light receiving element 153 use Si phototransistors, PDs (photodiodes), or the like. Each element 151, 152, 153 is mounted on the printed circuit board 150. In addition, a condensing lens 154 is disposed on the exit optical path, and the exit light from the light emitting element 151 is refracted by the condensing lens 154 and condensed on the irradiation target on the surface of the intermediate transfer belt 21 as an image carrier. Is done. Also, condensing lenses 155 and 156 are arranged on the incident optical path. The light receiving elements 152 and 153 receive the light collected by the condensing lenses 155 and 156 from the reflected light reflected from the toner that is the irradiation object on the intermediate transfer belt 12. The printed circuit board 150 is connected to the control unit 100. A voltage adjusted by the light amount adjustment circuit 105 of the control unit 100 shown in FIG. 2 is applied to the light emitting element 151. In addition, the control unit 100 converts the output signals from the first and second light receiving elements 152 and 153 into digital signals by the AD converter 106.

  As the optical sensors 51 and 52, those capable of detecting near infrared light and / or infrared light are used. Near-infrared light and / or infrared light are not affected by the colorant of the toner if the toner adhesion amount of the toner image is the same, and the output values of the light receiving elements show substantially the same value. Specifically, an optical element that emits light having a peak emission wavelength of about 840 [nm] is used, and a light receiving element having a peak spectral sensitivity of about 840 [nm] is used. Further, for example, the light emitting element may be a light emitting element that emits light from visible light to infrared light, and the light receiving element may be a light receiving element that receives near infrared light or infrared light. The light receiving element may be a light receiving element that receives light in a region from visible light to infrared light, and the light emitting element may be a light emitting element that emits near infrared light or infrared light. Even if the optical sensor has such a configuration, it can be an optical sensor that detects near-infrared light or infrared light. Note that when low-cost carbon black is used as the colorant for the black toner, carbon exhibits strong light absorption even in the infrared region, and as shown in FIG. 6, the amount of adhesion is detected compared to Y, M, and C colors. Sensitivity is lowered.

  In the color image forming apparatus according to the present embodiment, a process adjustment operation for adjusting a developing bias, a charging bias, an exposure amount, etc. in order to optimize the image density of each color when the power is turned on or every time a predetermined number of prints are performed. Has been done. In the electrophotographic system, there is a weak point that the image density fluctuates due to deterioration with time and environmental fluctuations. Therefore, the process adjustment operation is executed to control the image density to be stable.

  The control flow of this process adjustment operation is shown in FIG. A process adjustment operation signal is instructed to the controller 100 by the controller 110 when the power is turned on or before and after printing a predetermined number of sheets, and the process adjustment operation starts (see FIG. 2).

  When the process adjustment operation is started, the control unit 100 sets the image signal generation circuit 101 to the image pear state (S201). Next, as shown in FIG. 4, the CPU of the control unit 100 irradiates the intermediate transfer belt 21 with light and receives the specularly reflected light with the second light receiving element 153. Then, the light intensity adjustment circuit 105 adjusts the light emission intensity R of the light emitting element 151 of the optical sensors 51 and 52 so that the output (light reception signal) of the second light receiving element 153 becomes a predetermined value (S202 to S204). ). As shown in FIG. 8, the output value of the second light receiving element 153 varies due to individual differences in light emission efficiency of the light emitting element 151, temperature variation, and variation with time. Therefore, the toner image density can be accurately measured by adjusting the emission intensity R of the light emitting element 151 so that the output value of the second light receiving element 153 becomes the target output value. That is, S202 to S204 correspond to the calibration operation of the optical sensors 51 and 52 for accurately measuring the adhesion amount of the toner image by the optical sensors 51 and 52.

  When the calibration operation of the optical sensors 51 and 52 is completed, a pattern image 60 as shown in FIG. 9 is automatically formed on the intermediate transfer belt 21 at a position facing the optical sensors 51 and 52 (S205). The pattern image 60 is composed of about five patch images 60S having different density levels, and includes a Bk pattern image 60Bk, an M pattern image 60M, a C pattern image 60C (not shown), and a Y pattern image. 60Y (not shown) is sequentially formed on the intermediate transfer belt 12. The patch image 60S is formed by changing the exposure conditions. At this time, the charging and developing bias conditions are executed with predetermined specific values. The pattern image on the intermediate transfer belt is optically measured by the optical sensors 51 and 52 as shown in FIG. 5 (S206).

  Next, the five light reception signals of the first light receiving element 152 that receives the irregularly reflected light obtained by detecting each patch image 60S of each color pattern image are used as the amount of adhesion and the light receiving element as shown in FIG. Is converted into a toner adhesion amount (image density) using an adhesion amount calculation algorithm constructed based on the relationship with the output value. Thereby, the toner adhesion amount of each patch image 60S is detected. In this embodiment, since an optical sensor using near infrared and / or infrared light is used, there is no difference in the output value of the first light receiving element 152 depending on the color. There is no need to provide a common adhesion amount calculation algorithm. When carbon black is used as the black colorant, as shown in FIG. 6, the output values of the light receiving elements with respect to the adhesion amount are different between Y, M, C, and Bk. Two adhesion amount calculation algorithms for M and C and for Bk are used.

  When the toner adhesion amount of each patch image 60S is detected for each color, the relationship between the toner adhesion amount (per unit area) of each patch image and each development potential when each patch image is created is as shown in FIG. Then, a linearly approximated development potential-toner adhesion amount straight line is obtained for each color. The inclination γ and the intercept x0 are calculated for each color from the development potential-toner adhesion amount straight line (S207). By obtaining the slope γ and intercept x0 of each color in this way, the slope γ and intercept x0 of the straight line are deviated from the target characteristics (dotted line in the figure) due to the concentration variation factors (deterioration with time / environmental variation) described above. Can be detected. An exposure light amount correction parameter P for correcting the deviation of the inclination γ is determined from the inclination γ. Further, a development bias correction parameter Q is determined from the intercept x0 in order to correct a deviation of the development potential (intercept X0) at which development is started (S208).

  By multiplying the exposure light amount correction parameter P by the exposure signal, the inclination γ is mainly corrected, and by multiplying the development bias by the correction parameter Q, the intercept x0 is mainly corrected, thereby stabilizing the target image density. Can be obtained. In the above description, the exposure light amount and the development bias are corrected. However, other process control values that contribute to the image density such as a charging potential and a transfer current may be corrected.

  The cleaning units 36Y, 36M, 36C, 36Bk for cleaning the surface of the photoconductor in the image forming units 30Y, 30M, 30C, and 30Bk of the respective colors are not transferred to the intermediate transfer belt 21 as follows, , C and Bk, the transfer residual toner remaining on the surface is scraped off. That is, the transfer residual toner is scraped off from the surface by bringing a blade member such as a urethane rubber blade into contact with the photoreceptors 31Y, 31M, 31C, and 31Bk. In such a blade cleaning system, a part of the transfer residual toner goes under the blade member and passes through the cleaning portions 36Y, 36M, 36C, and Bk. For example, in the case of the image forming unit 30Bk for Bk, as shown in FIG. 11, the untransferred toner that has passed through the cleaning unit 36Bk sequentially passes through the charging unit 32Bk and the exposure unit 33Bk and is collected by the developing unit 34Bk. The ratio is high. However, a part of the transfer residual toner that has passed passes through the blade member BL and is collected by the developing unit 34Bk because it loses its charging characteristics or changes its shape due to frictional charging with the blade member BL. Disappear. Such transfer residual toner moves to the primary transfer portion and adheres to the intermediate transfer belt 21. Under normal conditions, a very small amount of transfer residual toner moves to the primary transfer portion for this reason. Accordingly, as shown in FIG. 12, the transfer residual toner that has passed on the intermediate transfer belt is only attached to the whole in a very small amount, and the image quality is not significantly impaired.

  On the other hand, if the blade member BL is worn out due to long-term use, the scraping force of the blade member BL is reduced. As a result, as shown in FIG. 13, the toner passing through the blade member BL tends to increase at an accelerated rate. Then, a large amount of toner passes in a streak shape from the worn part of the blade member BL. A large amount of untransferred toner that has passed through the blade member BL adheres to the charging portion 32Bk, contaminates the charging portion 32Bk, and lowers the charging ability. In addition, due to the large amount of untransferred toner on the photoconductor 31Bk, the surface of the photoconductor cannot be attenuated to a predetermined potential by the exposure unit 33Bk. As a result, an abnormal image is generated. Further, the developing unit 34Bk cannot collect such a large amount of transfer residual toner, and the transfer residual toner extending in a stripe shape is transferred to the intermediate transfer belt 21, and the vertical stripe-like abnormal image is formed on the intermediate transfer belt 21. Will occur. The image forming unit 30Bk in which a normal image cannot be obtained in this way needs to be repaired immediately.

  Slightly before the image forming unit 30Bk reaches such a state of repair, the amount of transfer residual toner that uniformly adheres to the entire surface of the intermediate transfer belt 21 increases as shown in FIG. This state is referred to as “slight scumming”, but it does not cause image degradation that is of concern to the user, and is very rarely noticed. When the process adjustment operation is performed in a state where there is “light soiling” which is a sign of failure of the cleaning unit 36Bk and the developing unit 34Bk due to blade wear, the amount of toner attached to the above-described patch image is the amount of toner attached to the low density portion Slightly higher than the target characteristics. As a result, a straight line indicating the relationship between the development potential and the toner adhesion amount causes a slight decrease in the slope γ and a slight decrease in the intercept X0 as shown in FIG. However, this is not much different from the change in the slope γ and the intercept X0 due to the environmental aging variation range (the dotted line range in the figure) of the toner and the photoconductor.

  Next, experiments conducted by the present inventors will be described.

  The inventors prepared a printer testing machine having the same configuration as that of the color image forming apparatus 1 shown in FIG. Using this printer tester, continuous printing was performed to continuously output test images. During the continuous printing, every time 100 sheets are output, the print job is temporarily stopped and the process adjustment operation described above is performed. Then, the above-described exposure light amount correction parameter P (hereinafter referred to as P value), development bias correction parameter Q (hereinafter referred to as Q value) and light emission intensity R (hereinafter referred to as R value) obtained by the process adjustment operation are stored as data. It was memorized sequentially in the means.

  FIG. 16 is a graph showing a change with time of the Q value in each color process unit. As shown in the figure, in the Bk process unit, the Q value fluctuation amount is temporarily increased in the other three Y, M, and C process units shortly before an abnormal image due to blade cleaning failure occurs. It can be seen that it has increased. That is, there is a sign that the variation amount of the Q value of the process unit of another color temporarily increases shortly before the process unit of a certain color fails. However, in the same figure, among the enormous amount of data obtained by repeated continuous print tests, the data in which the above-mentioned signs are noticeable is shown, but the fluctuation amount does not increase to the extent that it can be said to be a sign. There was also.

  Although Q value was demonstrated, it turned out that the same sign is seen also about P value. It has also been found that the amount of change in the R value of a certain color may temporarily increase before an abnormal image occurs in a certain color. Therefore, the present inventors considered that a failure is predicted by combining the P value, the Q value, and the R value. Therefore, first, a temporal feature amount indicating whether or not the P value, the Q value, and the R value are moving peculiar to the past behavior was calculated. An example of such a temporal feature amount is a standard deviation of sampling data for a predetermined number of times in the past. Moreover, the moving average value of the sampling data for the past predetermined number of times, the slope of the regression line of the sampling data for the past predetermined number of times, or the like may be used. Many methods for calculating temporal feature amounts have been proposed, such as the ARIMA model, and an appropriate method may be selected. In the experiment, the standard deviation of the past 10 sampling data was calculated as a temporal feature amount.

Next, with respect to the temporal feature quantities of the P value, the Q value, and the M value, weight values for contributing to failure prediction were calculated by a supervised learning algorithm called a boosting method. For the boosting method, see Mathematical Sciences. 489, MARCH, 2004 “Statistical Pattern Identification Information Geometry” provides a detailed explanation. In summary, first, a history from a normal state to a failure sign state is prepared for a data set composed of a plurality of types of data. For each history of various data, the predictive failure period is visually estimated from the shape of the time-varying graph, and data corresponding to the predictive failure period is labeled with a negative polarity, while other data ( A positive polarity label is attached to the data within the normal period. By repeating this operation 100 times, threshold values b _{1 to} b ₁₀₀ , discrimination polarities sgn _{1 to} sgn ₁₀₀ , and weight values α _{1 to} α ₁₀₀ are determined for various data. Next, it is determined whether each data is normal or abnormal based on temporal feature amounts of various data. Since this determination is not a decisive factor for failure prediction, the determination at this time is called weak determination processing. The weak discrimination process is performed as follows. Incidentally, C _i represents a time periodic feature amount.

When the weak discrimination processing is completed, an F value used for failure prediction determination is calculated based on the following equation.

  The above-described threshold value, discrimination polarity, and weighting value are determined so that the labeled supervised data is appropriately learned and only the data corresponding to the failure symptom period has a negative polarity F value. Therefore, when the F value obtained by the mathematical formula 3 is negative, it can be estimated that the failure sign period has been entered.

  Based on the time-series data of P value, Q value, and R value obtained by the continuous print test, the threshold value, the discrimination polarity, and the weighting value were determined by the boosting method, and the change with time of the F value was examined. The result is shown in FIG. As shown in the figure, at a point just before the occurrence of the abnormal image, that is, a point just before the failure of the process unit, the F value has changed from positive to negative, and the sign of failure can be accurately captured. Recognize.

  In order to check whether the threshold value determined by the boosting method, the discrimination polarity, and the weighting value are applicable to other individual machines, it is a test machine having the same specifications as the previous printer test machine. Units 3, 5 were prepared. Then, the F-time change with the same threshold value, discrimination polarity and weighting value was examined. The time-dependent change of the F value in Units 1, 2, 3, 4, and 5 is shown in FIGS. 18, 19, 20, 21, and 22. In any of the test machines, the F value has changed from positive to negative just before the failure of the process unit, and it can be seen that a sign of failure is accurately captured.

  From the above experiment, in the color image forming apparatus, the process unit for each color as an internal apparatus is performed by performing the following processing for each of a plurality of types of predictive useful information such as P value, Q value, and R value. It was found that the failure prediction can be accurately performed. In other words, it is determined whether or not there is a peculiar movement with respect to the past behavior, and whether or not a failure will soon occur based on the result of performing each weighting process on each determination result. This is a process for making a determination.

  However, it has been found through experiments that the following may occur. That is, when the user or service person voluntarily performs the process unit maintenance work regardless of the failure prediction result, immediately after that, the failure of the process unit may be erroneously predicted.

  FIG. 23 is a graph showing the change with time of the Q value in the Y process unit in a normal state. FIG. 24 is a graph showing the change over time of the standard deviation (temporal feature amount) for the past 10 times of the Q value (Y color) in the Y process unit in a normal state. In the process unit in the normal state, as shown in FIG. 23, the Q value varies with time, but the variation range is not so large. For this reason, as shown in FIG. 24, the standard deviation (hereinafter referred to as “10-point standard deviation”) of the past 10 Q values does not vary so much.

  FIG. 25 is a graph showing the change with time of the Q value in the process unit for Y when transitioning from the normal state to the failure state. FIG. 26 is a graph showing the change over time of the 10-point standard deviation of the Q value in the process unit for Y when transitioning from the normal state to the failure state. As shown in the figure, when the process unit enters the failure sign period, the 10-point standard deviation of the Q value increases rapidly. By capturing this variation, it is possible to detect that a failure sign period has been entered.

  However, even if the failure sign period is not entered, as shown in FIGS. 27 and 28, when the process unit is replaced, the 10-point standard deviation of the Q value increases rapidly immediately after that. As a result, it may be erroneously detected that the failure prediction period has been entered, and a false alarm may be generated.

Next, a characteristic configuration of the color image forming apparatus according to the embodiment will be described.
FIG. 29 is a block diagram illustrating an electric circuit of the failure prediction apparatus 120 mounted on the color image forming apparatus according to the embodiment. The failure prediction device 120 includes a data acquisition unit 120a that acquires prediction useful information such as a P value, a Q value, and an R value sent from the control unit 100 (see FIG. 2) of the color image forming apparatus 1, and a prediction usefulness. And a determination unit 120b as determination means for determining whether or not a failure is likely to occur based on the information. The determination unit 120b includes a temporal feature amount calculation unit 120c, a weighting processing unit 120e, a determination unit 120f, and the like.

  FIG. 30 is a flowchart showing a processing flow executed by the failure prediction apparatus 120. The data acquisition unit 120a of the failure prediction device 120 includes a data storage circuit (not shown) as a data set of a set of a plurality of types of predictive useful information sent from the control unit 100 for an internal device (for example, a process unit) to be tested. Memorize in time series. The temporal feature amount calculation unit 120c receives a predetermined number of past data from the data acquisition unit 120a for each of various types of useful prediction information stored in the data acquisition unit 120a, and calculates the temporal feature amount (S1). ~ S3). The weighting processing unit 120e assigns temporal feature amounts to the mathematical formulas shown in Equations 1 and 2 for various types of predictive useful information, and determines whether or not it is abnormal (S4). The F value is obtained while weighting the determination result by the mathematical formula shown in Equation 3 (S5). If the F value is positive polarity or zero (Y in S6), it is determined that no failure has occurred yet because the internal device to be tested has not yet entered the failure sign period. The process ends. On the other hand, when the F value has a negative polarity (N in S6), there is a possibility that the internal device to be examined has entered the failure sign period. However, since it is not in the failure sign period but immediately after the replacement, the F value may have changed to a negative polarity. Therefore, when the F value has a negative polarity, the determiner 120f reads the M value, which is maintenance information, from the data acquisition unit 120a (S7).

  Prior to this reading, the data acquisition unit 120a performs the following processing. That is, a user or service person who has performed maintenance work on the internal device inputs information to that effect to the operation panel 111 (see FIG. 2) of the color image forming apparatus. This information is sent to the data acquisition unit 120a of the failure prediction apparatus 120 via the controller 110 and the control unit 100. Then, when receiving the information, the data acquisition unit 120a changes the M value from “0” to “1” until the predicted useful information is received a predetermined number of times thereafter. That is, when the maintenance work of the internal device is performed, the M value is changed from “0” to “1” until the predicted useful information is acquired a predetermined number of times.

  When the M value read from the data acquisition unit 120a is “1”, that is, within a certain period after the maintenance work is performed (Y in S8), the determiner 120f enters the failure sign period. Since it does not enter, the process is terminated as it is. On the other hand, when the M value read from the data acquisition unit 120a is “0”, that is, when it is not within a certain period after the maintenance work is performed (N in S8), the failure sign period is entered. Therefore, the maintenance request is displayed on the display unit 112 including a display to notify the user that the internal device will soon break down. In such a configuration, when maintenance work is performed on the internal device to be examined, the behavior of predicted useful information after the maintenance work is re-established regardless of the F value. Therefore, since it is determined that a failure has not yet occurred, it is possible to avoid the occurrence of a false alarm resulting from the maintenance work being performed.

  As information for obtaining the M value, the cumulative number of operations of the internal device to be tested is grasped based on the counter information, and the maintenance work is grasped when the counter information is reset to zero. You may do it.

Note that the calculation of the F value and the calculation of the M value are performed individually for each of the four process units to be tested, as shown in Table 1 below. For example, in the case of a Y process unit, an F value specific to the Y process unit is obtained based on the P value, Q value, R value, etc., and the result and the M value for the Y process unit are obtained. Based on the above, it is determined whether or not to issue a warning that a failure will occur soon for the Y process unit.

  In the embodiment, the following period is adopted as a certain period after the maintenance work is performed. In other words, the color image forming apparatus includes a counter that counts up the count value every time one printing operation is performed. The failure prediction apparatus acquires the P value, the Q value, and the R value, which are useful prediction information, every time a predetermined number of printing operations are performed. Further, as described above, the temporal feature quantities (10-point standard deviation) of the P value, the Q value, and the R value are calculated based on the acquisition results for the past 10 times. In such a configuration, even if maintenance work is performed on the process unit, after the data for 10 times each of the P value, Q value, and R value is acquired, the maintenance work affects the F value. No effect. Therefore, when maintenance work is performed, a period until data of P value, Q value, and R value for 10 times is acquired is set as the above-described fixed period. When data of P value, Q value, and R value is acquired every 100 sheets printed, the predetermined period is 100 × 10 = 1,000 sheets.

Next, modifications of the color image forming apparatus according to the embodiment will be described. Unless otherwise specified, the configuration of the color image forming apparatus according to each modification is the same as that of the embodiment.
[First Modification]
FIG. 31 is a flowchart illustrating a processing flow executed by the failure prediction apparatus of the color image forming apparatus according to the first modification. The failure prediction device of the color image forming apparatus according to the embodiment calculates a F value based on the P value, the Q value, and the R value regardless of the contents of the M value, and then issues a warning that a failure will occur soon. Whether or not to do so was determined based on the M value. On the other hand, the failure prediction apparatus for the color image forming apparatus according to the first modification confirms the contents of the M value prior to the calculation of the F value, as shown (S4). When the content of the M value indicates that it is within a certain period after the maintenance work is performed (Y in S5), weak discrimination processing for the P value, the Q value, and the R value, A series of processing flow is ended without calculating the F value based on them. Thereby, when it is within a certain period after the maintenance work is performed, it is possible to omit the weak discrimination processing and the calculation of the F value, and to reduce the calculation addition.

[Second Modification]
The failure determination device of the color image forming apparatus according to the second modification uses its own useful prediction information by performing maintenance work on other components or units among a plurality of units (for example, process units) as an internal device to be tested. (For example, P values, Q values, R values) are affected by M values for other parts or units in addition to M values as maintenance information for the units themselves. It is determined whether a failure will occur soon or whether a failure has not occurred yet. Among the following units A to D, the unit C and the unit D are this type of unit.

  In Table 2, for unit C, whether the failure will occur soon or not yet based on the M value of unit D in addition to the M value of unit C itself. Judgment is made if there is. Even if the F value indicates an abnormality, if either unit C or unit D is within a certain period after maintenance work, the failure has not yet occurred regardless of the behavior of the predicted useful information. Make a decision. For this reason, as shown in Table 2, even if the F value indicates an abnormality, if either unit C or unit D is within a certain period after maintenance work, a warning that a failure will occur soon is not given. . For unit D, whether the failure will occur soon or not yet based on the M value of unit B as well as the M value of unit D itself. It comes to judge. Even if the F value indicates an abnormality, if either unit D or unit B is within a certain period after maintenance work, no failure has occurred yet, regardless of the behavior of the predicted useful information. Make a decision. For this reason, as shown in Table 2, even if the F value indicates an abnormality, if either unit D or unit B is within a certain period after maintenance work, a warning that a failure will occur soon is not given. .

  As described above, in the color image forming apparatus according to the embodiment, prediction is performed so that a plurality of types of useful information such as P value, Q value, and R value are acquired at a predetermined cycle (every 100 prints). The data acquisition part 120a as a useful information acquisition means is comprised. In addition, for each of these predictive useful information, it is determined by weak determination processing whether or not there is a specific movement with respect to the past behavior indicated by the 10-point standard deviation, and each determination result is individually weighted. Based on the result of the processing, the determination unit 120b as a determination unit is configured to determine whether a failure will occur soon or whether a failure has not occurred yet. In such a configuration, the result of the weak decision on multiple types of predictive useful information is weighted according to the degree of contribution to the failure prediction, respectively, and finally it is determined whether or not a failure will occur soon. Thus, the determination accuracy can be improved.

  Further, in the color image forming apparatus according to the embodiment, the data acquisition unit 120a is configured to acquire predictive useful information from a plurality of process units as a plurality of internal devices constituting the test target. In addition, for each of the plurality of process units, whether a failure will soon occur or whether a failure has not yet occurred based on unique predictive useful information (P value, etc.) and maintenance information (M value). The determination unit 120b is configured to individually perform the process of determining whether or not. Further, the display unit 112 as a notification unit is configured to individually notify information indicating that a failure will occur soon for each of the plurality of process units. With such a configuration, it is possible to notify a user or the like whether a failure will occur soon for each of the plurality of process units or whether a failure has not yet occurred.

  Further, in the color image forming apparatus according to the second modification, among the plurality of units as the plurality of internal devices, those that are influenced by the predicted useful information by the maintenance work for other units are themselves Whether the failure will occur soon or not yet based on the maintenance information (M value) for the other unit in addition to the maintenance information (M value) for itself. The determination unit 120b is configured so as to determine the above. In such a configuration, for units that are affected by their own useful useful information due to maintenance work on other units, in addition to the occurrence of false alarms due to the maintenance work being performed on themselves, Thus, it is possible to avoid the occurrence of false alarms due to maintenance work.

  Further, in the color image forming apparatus according to the embodiment, the P value, the Q value, and the R value as the useful prediction information are past behaviors based on the acquisition results of the past 10 times (predetermined times). When the point standard deviation is grasped and the maintenance information indicating that the maintenance work has been performed is acquired (when the M value is 1), until the predicted useful information is acquired only 10 times thereafter. The determination unit 120b is configured to perform a process in which the period is set to a fixed period in which it is determined that a failure has not yet occurred regardless of the useful prediction information. In such a configuration, normal failure prediction can be resumed immediately after the acquisition timing for 10 times does not affect the determination of failure prediction due to the execution of maintenance work.

  In the color image forming apparatus according to the embodiment, the data acquisition unit 120a is configured to use a cycle every time a predetermined number of image forming operations are performed as a predetermined sampling cycle. In such a configuration, an existing print number counter can be used as a means for grasping the sampling period.

1 is a schematic configuration diagram illustrating a color image forming apparatus according to an embodiment. FIG. 3 is a block diagram illustrating a connection state between a control unit mounted on the color image forming apparatus and electric devices around the control unit. FIG. 3 is a perspective view showing four photoconductors and a transfer unit of the color image forming apparatus. The schematic diagram which shows the adhesion amount detection part which makes the test object the solid surface of an intermediate transfer belt. FIG. 3 is a schematic diagram illustrating an adhesion amount detection unit that uses a toner image on an intermediate transfer belt as a test target. The graph which shows the relationship between the output from the light receiving element which receives irregularly reflected light, and a toner adhesion amount. 6 is a flowchart showing a control flow of a process adjustment operation in the image forming apparatus. The graph which shows the relationship between the output from the light receiving element which receives regular reflection light, and LED electric current (light emission amount). FIG. 3 is a schematic diagram showing a pattern image formed on the surface of an intermediate transfer belt. 6 is a graph showing the relationship between the toner adhesion amount and the development potential for a pattern image. FIG. 5 is a schematic diagram for explaining initial symptoms of transfer residual toner blade slipping in the Y image forming unit. The enlarged schematic diagram which shows the belt surface of the state which has caused very slight ground dirt by the blade slipping of the initial symptom. FIG. 5 is a schematic diagram for explaining initial symptoms of transfer residual toner blade slipping in the Y image forming unit. The enlarged schematic diagram which shows the belt surface of the state which has caused the severe ground dirt by the blade slipping of the terminal symptom. The graph explaining the fall phenomenon of inclination (gamma) and intercept X0 by mild ground dirt. The graph which shows the time-dependent change of Q value in the process unit of each color. The graph which shows the time-dependent change of F value in Unit 0. The graph which shows the time-dependent change of F value in the 1st machine. The graph which shows the time-dependent change of F value in No. 2. The graph which shows the time-dependent change of F value in No. 3. The graph which shows the time-dependent change of F value in No. 4. The graph which shows the time-dependent change of F value in No.5 machine. The graph which shows the time-dependent change of Q value in the process unit for Y of a normal state. The graph which shows the time-dependent change of 10-point standard deviation of Q value (Y color) in the process unit. The graph which shows the time-dependent change of Q value in the process unit at the time of changing from a normal state to a failure state. The graph which shows the time-dependent change of 10-point standard deviation of Q value in the same process unit at the time of changing from a normal state to a failure state. The graph which shows the time-dependent change of Q value in the process unit before and after the maintenance operation | work with respect to a unit is performed. The graph which shows the time-dependent change of 10 point standard deviation of Q value in the same process unit before and after the maintenance operation | work with respect to a unit is performed. FIG. 3 is a block diagram showing an electric circuit of a failure prediction apparatus mounted on the color image forming apparatus. The flowchart which shows the processing flow implemented by the failure prediction apparatus. 9 is a flowchart showing a processing flow executed by a failure prediction device for a color image forming apparatus according to a first modification.

Explanation of symbols

1: Color image forming device (subject to be examined)
20: Transfer unit (part of image forming means)
30Y, M, C, Bk: Image forming unit (internal device, part of image forming means)
100: Control unit (predictive useful information acquisition means, determination means)
111: Operation panel (maintenance information acquisition means)
112: Display unit (notification means)
120: Failure prediction device 120a: Data acquisition unit (predictive useful information acquisition means)

120b: determination unit (determination means)

Claims (8)

Predictive useful information acquisition means for acquiring useful predictive information useful for failure prediction from a subject to be examined at a predetermined cycle, and predictive useful information acquired by the predictive useful information acquisition means with respect to past behavior Determination means for determining whether or not a failure will occur soon for the subject to be examined or whether a failure has not yet occurred based on the determination result; In a failure prediction device comprising notification means for notifying that when a determination is made that a failure will occur soon by the determination means,
Provided with maintenance information acquisition means for acquiring maintenance information as to whether maintenance work has been performed on the subject to be examined;
When maintenance information indicating that maintenance work has been performed is acquired by the maintenance information acquisition means, it is determined that a failure has not occurred yet, regardless of the behavior of the predicted useful information, for a certain period thereafter. As described above, a failure prediction apparatus comprising the determination means. The failure prediction apparatus according to claim 1,
As the predictive useful information, the predictive useful information acquisition unit is configured to acquire a plurality of types of information at the predetermined cycle,
Based on the results of applying individual weighting to each judgment result, it is judged whether or not there is a specific movement with respect to past behavior for each of multiple types of useful prediction information. A failure prediction apparatus comprising the determination means configured to determine whether a failure has occurred or whether a failure has not occurred yet. The failure prediction apparatus according to claim 1 or 2,
The predicted useful information acquisition means is configured to acquire the predicted useful information from each of a plurality of components or internal devices constituting the test object,
For each of these parts or internal devices, a process for individually determining whether a failure will occur soon or whether a failure has not yet occurred based on the unique predictive useful information and the maintenance information described above. Configure the determination means to do so,
In addition, the failure prediction device is characterized in that the notification means is configured to individually notify information indicating that a failure will occur soon for the plurality of components or internal devices. The failure prediction apparatus according to claim 3,
Among the plurality of parts or internal devices, those that are affected by the predicted useful information of themselves due to maintenance work on other parts or internal devices, in addition to the maintenance information about itself, The determination means is configured to determine whether a failure is about to occur or whether a failure has not occurred yet, based on the maintenance information about the component or the internal device. Failure prediction device. The failure prediction apparatus according to any one of claims 1 to 4,
For the predicted useful information, when the past behavior is grasped based on the past predetermined number of acquisition results and maintenance information indicating that the maintenance work has been performed is acquired, the predicted useful information is thereafter A failure prediction apparatus, characterized in that the determination means is configured to perform a process of setting the period until the predetermined number of times is acquired as the predetermined period. The failure prediction apparatus according to any one of claims 1 to 5,
A failure prediction apparatus, characterized in that an image forming apparatus is a test target. The failure prediction apparatus according to claim 6,
The failure prediction apparatus according to claim 1, wherein the predictive useful information acquisition unit is configured to use a period for each predetermined number of image forming operations performed by the image forming apparatus as the predetermined period. In an image forming apparatus including an image forming unit that forms an image on a recording body based on image information,
8. An image forming apparatus comprising the failure prediction apparatus according to claim 6 or 7 which makes itself a test object.

Images