Fault occurrence prediction system, image forming system, fault occurrence prediction method, and image formation control method

Abstract

To provide an operational state prediction system, a defect occurrence prediction system, an image forming system, and an operational state prediction method that can obtain a result of prediction of an operational state so as to effectively deal with a defect according further to the state.SOLUTION: An operational state prediction system comprises: a state acquisition unit (P1) that acquires data related to operational states at respective timings of an operating device to be monitored in association with information on the timings; and a state prediction unit (P2) that predicts, for each of a plurality of periods different in length from the present time, a future operational state according to the operational states acquired by the state acquisition unit (P1).SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] This invention , non Condition prediction system, image forming system , a problem occurs Forecasting Methodology and image formation control method Regarding. [Background technology]

[0002] In an operating device that performs various operations, various malfunctions occur due to the accumulation of changes (mainly deterioration) over time that accompanies the operation. The occurrence of such malfunctions depends not only on the simple amount of operation or operation time, but also on the operating environment such as the surrounding temperature and humidity. Patent Document 1 discloses a technology for predicting the number of days until a malfunction occurs based on the current usage status in an image forming device, by training a machine learning model based on learning data that inputs the usage status during the period in which a symptom of a malfunction is observed, based on the date of the malfunction. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2015-174256 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, there are cases where it is inconvenient if a predicted malfunction does not occur as predicted. In response to this, it is possible to adjust the occurrence timing to some extent by changing the operating conditions. However, some operating conditions are difficult to change immediately, and even if they are changed, the magnitude of the impact on the malfunction occurrence timing and the immediate effect vary. Therefore, there is a problem that it is sometimes not possible to deal with the malfunction flexibly and effectively after it is predicted.

[0005] The object of the present invention is to obtain a prediction result of an operating situation that enables more effective countermeasures according to the situation. Not Condition prediction system, image forming system , a problem occurs Forecasting Methodology and image formation control method The purpose of this invention is to provide [Means for solving the problem]

[0006] In order to achieve the above object, the invention described in claim 1 comprises: a status acquisition unit that acquires data relating to an operational status of a monitoring target operating device at each timing in association with information on the timing; a situation prediction unit that predicts a future operation situation according to the operation situation acquired by the situation acquisition unit for each of a plurality of periods having different lengths from the present; a third storage unit configured to store a first correspondence relationship between the operating status and the occurrence of a predetermined malfunction in the operating device; a failure prediction unit that calculates a predetermined index related to the likelihood of occurrence of the failure based on the predicted operating condition and the first correspondence relationship; a fourth storage unit configured to store a second correspondence relationship between an operation setting of the operating device and a degree of contribution of the operation setting to the occurrence of the predetermined malfunction; A setting acquisition unit that acquires the operation setting; Equipped with 、 The failure prediction unit obtains the degree of contribution based on the acquired operation setting and the second correspondence relationship, and corrects the predetermined index based on the degree of contribution. The present invention is characterized by comprising A problem occurred It is a predictive system.

[0007] The invention described in claim 2 is the same as the invention described in claim 1. A problem occurred In the prediction system, The device is characterized by comprising a first storage unit that stores data relating to the acquired operating conditions.

[0008] The invention described in claim 3 is the same as the invention described in claim 1 or 2. A problem occurred In the prediction system, The operating conditions include an environmental condition of the operating device.

[0009] The invention according to claim 4 is a method for producing a composition according to any one of claims 1 to 3. A problem occurred In the prediction system, The situation prediction unit is a machine learning method that is trained using data related to the operation situation as training data. The present invention is characterized by having a model.

[0010] The invention described in claim 5 is the same as the invention described in claim 4. A problem occurred In the prediction system, a second storage unit configured to store the operation status predicted for each of the plurality of time periods by the status prediction unit; a comparison unit that compares the predicted operation status with an actual operation status at each predetermined timing within the plurality of periods related to the predicted operation status; an update unit that further learns and updates the machine learning model based on a comparison result by the comparison unit; The present invention is characterized by comprising:

[0011] The invention according to claim 6 can be applied to the invention according to claim 4 or 5. A problem occurred In the prediction system, The device is characterized in that it includes a generation unit that generates the machine learning model using data related to the operational status as training data.

[0012] The invention according to claim 7 further comprises the method according to any one of claims 1 to 6. A problem occurred In the prediction system, The predicted operating conditions include information related to the probability of occurrence of a predetermined operating condition.

[0015] Also, claims 8 The invention described is as follows: Any one of 1 to 7 In the defect occurrence prediction system described, The defect prediction unit is characterized in that it obtains the predetermined index for each of the different periods.

[0016] Also, claims 9 The invention described is Claim 1~8 13. An image forming system comprising the defect occurrence prediction system according to claim 12.

[0017] Also, claims 10 The invention described is as follows: 9 In the image forming system described above, A suppression operation unit that performs a predetermined operation to suppress the occurrence of a malfunction; A suppression control unit that controls the operation of the suppression operation unit; Equipped with The suppression control unit controls the operation of the suppression operation unit according to operation conditions corresponding to the predetermined indexes in the different periods. It is characterized by: The invention described in claim 11 is as follows: a status acquisition unit that acquires data relating to an operational status of a monitoring target operating device at each timing in association with information on the timing; a situation prediction unit that predicts a future operation situation according to the operation situation acquired by the situation acquisition unit for each of a plurality of periods having different lengths from the present; a third storage unit configured to store a first correspondence relationship between the operating status and the occurrence of a predetermined malfunction in the operating device; a failure prediction unit that calculates a predetermined index related to the likelihood of occurrence of the failure based on the predicted operating condition and the first correspondence relationship; A suppression operation unit that performs a predetermined operation to suppress the occurrence of a malfunction; A suppression control unit that controls the operation of the suppression operation unit; Equipped with The suppression control unit controls the operation of the suppression operation unit according to operation conditions corresponding to the predetermined indexes in the different periods. The image forming system is characterized in that:

[0018] Also, claims 12 The invention described is as follows: 10 or 11 In the image forming system described above, At least a part of the operational status is acquired based on job data related to an image formation command.

[0019] Also, claims 13 The invention described is A method for predicting a malfunction by a control unit of a malfunction prediction system, comprising: a status acquisition step of acquiring data relating to an operational status of the monitoring target operating device at each timing in association with information on the timing; a situation prediction step of predicting a future operation situation according to the operation situation acquired in the situation acquisition step, for each of a plurality of periods of different lengths from the present; storing a first correspondence relationship between the operating status and the occurrence of a predetermined malfunction in the operating device; a failure prediction step of calculating a predetermined index relating to the likelihood of occurrence of the failure based on the predicted operating condition and the first correspondence relationship; storing a second correspondence between an operation setting of the operating device and a degree of contribution of the operation setting to the occurrence of the predetermined malfunction; A setting acquisition step of acquiring the operation setting; Includes 、 In the defect prediction step, the degree of contribution is obtained based on the acquired operation setting and the second correspondence relationship, and the predetermined index is corrected based on the degree of contribution. child It is characterized by do. The invention described in claim 14 is as follows: An image formation control method by a control unit of an image forming system, comprising: a status acquisition step of acquiring data relating to an operational status of a monitoring target operating device at each timing in association with information on the timing; a situation prediction step of predicting a future operation situation according to the operation situation acquired in the situation acquisition step, for each of a plurality of periods of different lengths from the present; storing a first correspondence relationship between the operating status and the occurrence of a predetermined malfunction in the operating device; a failure prediction step of calculating a predetermined index relating to the likelihood of occurrence of the failure based on the predicted operating condition and the first correspondence relationship; a suppression operation step of performing a predetermined operation to suppress the occurrence of a defect; a suppression control step of controlling the operation in the suppression operation step; Including, In the suppression control step, the operation in the suppression operation step is controlled according to operation conditions corresponding to the predetermined indexes in the different multiple periods. It is characterized by: Effect of the Invention

[0020] According to the present invention, it is possible to obtain a prediction result of an operating situation that enables more effective measures according to the situation. [Brief description of the drawings]

[0021] [Figure 1] FIG. 2 is a block diagram showing a functional configuration of the image forming apparatus. [Diagram 2] 11 is a diagram illustrating a flow of an operation for predicting the occurrence of an abnormality in an image forming apparatus. [Diagram 3] 1 is a chart showing an example of operational parameter contribution data. [Figure 4] 13 is a flowchart showing a control procedure of a malfunction occurrence prediction process. [Diagram 5] 13 is a flowchart showing a control procedure for a prediction model update process. [Figure 6] 10 is a flowchart showing a control procedure of a short-term suppression control process related to the occurrence of a problem of toner spillage. [Figure 7] 10 is a flowchart showing a control procedure of a long-term suppression control process related to the occurrence of a problem of toner spillage. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0022] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing the functional configuration of an image forming system according to the present embodiment, that is, an image forming apparatus 1 including an operation status prediction system and a malfunction occurrence prediction system.

[0023] The image forming apparatus 1 includes a control unit 10, a memory unit 20 (first memory unit, second memory unit, third memory unit, fourth memory unit), a communication unit 30, an interface 40 (I / O), a forming operation unit 60 (operating device to be monitored), a measurement unit 70, etc. A display unit 51, an operation reception unit 52, etc. are connected to the interface 40.

[0024] The control unit 10 centrally controls the overall operation of the image forming apparatus 1. The control unit 10 includes a CPU 11 (Central Processing Unit), a RAM 12 (Random Access Memory), and the like.

[0025] The CPU 11 is a hardware processor that performs arithmetic processing related to various control operations. The RAM 12 provides a working memory space for the CPU 11 and stores temporary data and the like. The data stored in the RAM 12 includes job data including image data and operation setting data related to image formation commands. The RAM that stores the job data and its processing data may have a dedicated area set separately from other RAMs.

[0026] The storage unit 20 stores various programs and setting data. The storage unit has a non-volatile memory such as a flash memory and / or an HDD (Hard Disk Drive). A part of the storage unit 20 may be a volatile memory. The storage unit 20 stores usage data 21, environmental measurement data 22, prediction data 23, malfunction response data 24, operating parameter contribution data 25, programs 26, and the like.

[0027] The usage status data 21 includes data on the operating status of the forming operation unit 60 of the image forming apparatus 1 obtained based on the job data 121 acquired by the image forming apparatus 1, such as the image size, the type of medium on which the image is formed, the cumulative number of images formed, the distribution of the image forming range, the distribution of the toner concentration, and the distribution of the amount of operation per hour (such as the number of images formed). A plurality of unit times may be defined for the amount of operation per hour. For example, the unit time may include some or all of an hour, a day, each day of the week, a week, a month, etc.

[0028] The environmental measurement data 22 stores the internal and external environmental conditions of the image forming apparatus 1 measured by the measurement unit 70. The usage status data 21 and the environmental measurement data 22 configure data related to the operating status of this embodiment, and correspond to the storage contents of the first storage unit.

[0029] The predicted data 23 stores and holds predicted data of the usage status and environmental state predicted in advance as described later. Note that the usage status data 21, the environmental measurement data 22, and the predicted data 23 may be deleted as they become old and unnecessary, in which case the memory of the storage unit 20 is released and reused at appropriate intervals. The predicted data 23 corresponds to the stored contents of the second storage unit in this embodiment.

[0030] The failure response data 24 is quantitative data relating to a relationship determined in advance from past cases, experiments, etc. between the environment and a failure occurring in the image forming apparatus 1. The operation parameter contribution data 25 is data indicating the contribution of operation parameters to a failure occurring in the image forming apparatus 1 in advance from past cases, experiments, etc. The program 26 includes a prediction model 261. The failure response data 24, the operation parameter contribution data 25, and the program 26 will be described later.

[0031] The communication unit 30 controls data communication with external devices. The communication unit 30 has, for example, a network card and controls communication with external electronic devices connected via a LAN (Local Area Network), for example, a PC (Personal Computer) operating as a print server.

[0032] The interface 40 includes connection terminals and drivers for connection with peripheral devices. As described above, the display unit 51 and the operation reception unit 52 are connected to the interface 40.

[0033] The display unit 51 has, for example, a display screen, and displays various information, such as the status of the image formation situation and a menu related to settings accepted from the user, under the control of the control unit 10. The operation acceptance unit 52 has, for example, a touch panel located over the display screen, detects a touch operation from the outside, such as a user, and outputs it to the control unit 10 as an input signal. The display unit 51 has, for example, a liquid crystal display screen, but is not limited to this, and may have LED lamps (Light Emitting Diodes) of various colors, etc. Furthermore, the operation acceptance unit 52 may have a numeric keypad, a keyboard, a pointing device (such as a mouse), a push button switch, a rocker switch, etc. in addition to / instead of the touch panel.

[0034] The forming operation unit 60 performs an operation of supplying a specified medium and forming an image specified by the job data 121 on the surface of the medium. Here, the forming operation unit 60 performs an image forming operation by applying and fixing four color toners, cyan (C), magenta (M), yellow (Y), and black (K), to the medium by an electrophotographic method. The forming operation unit 60 includes a charging unit 61, an exposure unit 62, a developing unit 63, a fixing unit 64, a static electricity removing unit 65, a cleaning unit 66, a vibration unit 67, and the like.

[0035] The charging unit 61 charges the photoconductor drum. The exposure unit 62 irradiates the surface of the photoconductor drum with laser light to form a latent image according to the image data to be formed. The development unit 63 supplies toner mixed with a developer by a development roller (developing sleeve) to the surface of the photoconductor drum on which the latent image has been formed by the exposure unit 62, and causes the toner according to the latent image to adhere to the surface. The toner adhered to the photoconductor drum is transferred to a medium. The fixing unit 64 fixes the toner on the medium to form an image. The charge removing unit 65 removes the charge of the toner particles (including the developer) remaining on the photoconductor drum after transfer. The cleaning unit 66 removes the toner particles remaining on the photoconductor drum with a brush, blade, or the like, and applies a lubricant to the surface of the photoconductor drum after removal.

[0036] The vibration unit 67 generates vibrations in each component of the forming operation unit 60, particularly in the housing that houses the developing unit 63. The vibration unit 67 has, for example, a motor that rotates a weight or the like, and strikes the housing at each rotation period of the weight to generate vibrations in the housing. The operation of the vibration unit 67 causes the toner attached inside the housing to fall. The vibration intensity of the vibration unit 67 can be set to multiple stages within a range that does not adversely affect the image formation accuracy of the image forming device 1. In the initial state, the vibration intensity may be set to the lowest possible level. A suction port of a suction unit that sucks in the falling toner may be located inside the housing. In the image forming system of this embodiment, the vibration unit 67 is included in a suppression operation unit that suppresses the occurrence of at least a malfunction related to toner spillage.

[0037] The measuring unit 70 measures the environmental conditions inside and outside the image forming apparatus 1. Examples of the environmental conditions include temperature and humidity. The measurement data of the environmental conditions is sent to the control unit 10 at a predetermined cycle, for example, at one-minute cycles, and is stored in the environmental measurement data 22 of the storage unit 20. The environmental conditions may include not only individual values ​​of temperature and humidity, but also the amount and speed of change thereof. The humidity may be absolute humidity in addition to the commonly used relative humidity.

[0038] In addition, the image forming apparatus 1 (image forming system) may be provided with various post-processing devices that perform post-processing, such as cutting, on the medium on which the image is formed. Also, when operating as an image forming system, a monitoring device that comprehensively monitors the operating status of each unit may be provided separately.

[0039] Next, operational problems of the image forming apparatus 1 will be described. In the image forming apparatus 1, each part, consumables, fixed assembly parts, etc. deteriorate due to continuous long-term use of the forming operation unit 60 in particular. If such deterioration exceeds a reference level, the image quality of the formed image may be adversely affected, and defects (noise) such as stains, bleeding, blurring, and loss of the image may occur. The reference level at which such adverse effects on the image due to deterioration appear varies depending on the content of the image. For example, depending on the bias of each toner, the density and size of the formed image, and the change in density and image formation range between the previous image and the next image, defects may appear earlier than the average deterioration state, or conversely, the effects may be less noticeable. In addition, the influence of deterioration may be strengthened or weakened depending on the environmental state, that is, the change in the state of each part depending on the temperature and humidity, for example, the hardness of the blade of the cleaning unit 66 (for example, it is made of resin and its hardness changes depending on the temperature) and the change in the fixing temperature by the fixing unit 64.

[0040] In addition, the operation of the image forming apparatus 1 has several variable parameters. For example, the maximum image density Dmax and the like can be changed by adjusting the charge amount (Q / M) of the toner, the ratio of the rotation speed of the developing roller (developing sleeve) to the rotation speed of the photosensitive drum (developing θ), the toner concentration Tc, and the like. In addition, depending on the situation, the operation frequency of the vibration unit 67, the contact angle of the blade of the cleaning unit 66, the amount of lubricant applied, and the like can be changed. Although not particularly limited, here, the development θ can be set in two ways, large and small, and when the development θ is set to large, a flag indicating that (developing θ flag) is set, and when the development θ is set to small, the development θ flag is reset.

[0041] Therefore, whether or not an image defect (abnormality in the quality of the formed image) will occur is determined by a combination of cumulative usage conditions, as well as the most recent operation, the effects of environmental conditions, etc. (collectively referred to as the operating conditions), and the operating parameter settings, etc. To predict the occurrence of an image abnormality in advance, the future operating conditions are predicted, and then the effects of the current operating parameters are also taken into account.

[0042] In the image forming apparatus 1, a prediction model 261 is used to predict the operating status. The prediction model 261 is a model (machine learning model) that can mechanically learn based on prediction data related to past operating status and actual data (as teacher data). The algorithm of the prediction model 261 is not particularly limited, and an algorithm suitable for the output content may be used. For example, a machine learning model trained by deep learning using a neural network or the like may be used to learn and predict the usage status. Furthermore, an autoregressive integrated moving average (ARIMA) model or the like may be used to learn and predict the operating environment such as temperature and humidity. Furthermore, an autoregressive forgetting learning algorithm (SDAR) may be used to extract a change point related to the operating environment. With these, an output variable that is the same as the input variable of each period may be obtained as a predicted value, or time series data may be output. Alternatively, something like a distribution of the occurrence probability of each variable related to the operating status within a corresponding period may be output.

[0043] The operating conditions including the environmental conditions are previously associated with index values ​​(failure occurrence indexes; predetermined indexes relating to the likelihood of malfunctions occurring) indicating the likelihood of malfunctions (malfunctions) occurring by a correspondence table or conversion formula (first correspondence relationship) as malfunction response data 24. The combinations of operating condition elements associated with the multiple types of malfunctions (predetermined malfunctions) may differ. The malfunction response data 24 corresponds to the contents stored in the third storage unit of this embodiment.

[0044] Moreover, each of the operation parameters (operation settings) is associated with a score indicating its contribution to the occurrence of an abnormality based on the operation parameter contribution data 25, and furthermore, the sum of the scores related to each operation parameter is converted into the degree of contribution (contribution coefficient) to the malfunction occurrence index (these are collectively referred to as the second correspondence relationship). The final likelihood of malfunction occurrence is obtained by multiplying the obtained malfunction occurrence index by the contribution degree. The malfunction occurrence index may be a direct value such as the probability of an abnormality occurring, or may be a unique index value. The operation parameter contribution data 25 corresponds to the contents stored in the fourth embodiment of this embodiment.

[0045] FIG. 2 is a diagram for explaining the flow of an operation for predicting the occurrence of an abnormality in the image forming apparatus 1. In FIG. First, job data and measurement data are acquired as input data, and usage status data is acquired from the job data (P1). For cumulative data (such as the cumulative number of images formed), history data may be acquired directly from the image forming apparatus 1, or the control unit 10 may store the count. The job data may also include a cancellation log for when an image forming operation is stopped midway. The operating status (usage status and measurement data) is input to a prediction model 261, and a future operating status prediction is output from the prediction model 261 (P2).

[0046] Here, the prediction model 261 outputs operation status predictions for two different types of time periods, long and short. Short-term prediction predicts the usage status and operation environment for a period of several hours to one day from the time point when the data is input. Long-term prediction predicts the usage status and operation environment for two days to one month from the time point when the data is input.

[0047] A malfunction occurrence index is calculated (P3) based on the malfunction response data 24 from each prediction data of the usage status and the operating environment. This malfunction occurrence index is also calculated separately for the short-term prediction and the long-term prediction.

[0048] On the other hand, the predicted data of the usage status and the operating environment are stored and are read and compared when the usage status and the operating environment for the target period of the prediction are acquired and measured (P4). The comparison results are fed back to each parameter of the machine learning model (P5).

[0049] In addition, the current operational parameters related to the image forming operation are acquired and converted into scores related to the contribution to the occurrence of the defect using the operational parameter contribution data 25 (P6). The scores are added up, and the sum is further converted into a contribution coefficient (P7).

[0050] The long and short defect occurrence indexes are multiplied by the contribution coefficients to calculate the corrected defect occurrence index (P8).

[0051] 3 is a chart showing an example of the operation parameter contribution data 25. Here, the score settings of the operation parameters related to the occurrence of toner spillage, which is one of the causes of medium staining, and the relationship between the sum of the scores (total score) and the contribution coefficient are shown. The toner spillage here refers to the overall state in which toner unintentionally adheres to the medium, and may include, for example, in addition to the case where toner spills directly onto the medium from the developing unit 63, it may also include the case where toner particles scattered during development or cleaning adhere to various parts and indirectly stain the medium.

[0052] As shown in FIG. 3(a), the toner spillage is determined as an operating parameter related to the developer life, i.e., the number of images formed since the current developer was first used, the toner charge amount (Q / M), and the number of output sheets after the most recent vibration by the vibration unit 67.

[0053] The developer is mixed with the toner to give the toner an appropriate charge and voltage. The developer adheres to the developing roller, carries the toner, and then transfers the toner to the photoconductor drum according to the exposure state of the photoconductor drum surface. The developer deteriorates after long-term use, making it difficult to properly carry the toner to the photoconductor drum surface. Here, for example, if the developer life is less than 500kp (500,000 sheets), the score is "0." If the developer life is between 500kp and 1500kp (hereinafter, "~" indicates a number equal to or greater than the preceding number and less than the succeeding number), the score is "3." If the developer life is 1500kp or more, the score is "6."

[0054] Similarly, if the charge amount is 50 μC / g or more, the score is "0". If the charge amount is 35 to 50 μC / g, the score is "7". If the charge amount is less than 35 μC / g, the score is "15". Furthermore, if the number of output sheets after the most recent vibration by the vibration unit 67 is less than 500, the score is "0". If the number of output sheets is 500 to 2000, the score is "5". If the number of output sheets is 2000 or more, the score is "10".

[0055] Here, the scores are divided into three stages, but are not limited to this. Also, the scores may be determined continuously by a formula without being determined in stages. The three scores are different from each other, that is, the score of an operational parameter that has a relatively large effect on toner spillage may be higher than the scores of other operational parameters.

[0056] Once the three scores are obtained according to these three operating parameters, the three scores are added together to obtain a total score. As shown in Figure 3(b), the total score is divided into four levels, and a contribution coefficient is determined according to the corresponding total score. This contribution coefficient is multiplied by the separately obtained defect occurrence index to calculate the corrected defect occurrence index.

[0057] Here, when the total score is less than 10, the contribution coefficient is 0.8, i.e., smaller than 1.0, so it can be seen that the operating parameters are generally on the side that suppresses the occurrence of malfunctions. On the other hand, when the total score is 17 or more, the contribution coefficient is greater than 1.0, so it can be seen that the operating parameters are generally on the side that promotes the occurrence of malfunctions.

[0058] FIG. 4 is a flowchart showing a control procedure by the control unit 10 of the malfunction occurrence prediction process executed by the image forming apparatus 1. This malfunction occurrence prediction process includes the operating status prediction method (malfunction occurrence prediction method) of this embodiment, and is initiated, although not limited to, when the image forming apparatus 1 starts operating or during operation, periodically at intervals of approximately the short-term prediction period of the usage status and operating environment to approximately half this period, or based on user input operations, etc.

[0059] The control unit 10 (CPU 11) acquires job data within an appropriate period and measured operating environment data (step S101). The control unit 10 acquires the usage status based on the job data (step S102). The appropriate period for acquiring the usage status from the job data is set to the most recent predetermined time, but in the case of starting the image forming device 1, it may be set to a predetermined time period from the timing when the power supply to the image forming device 1 was most recently cut off. As described above, the usage status may be, for example, the average number of images formed (print volume, A4 size conversion, etc.). Examples of the usage status include the number of images formed per job, the average density of each color toner applied in each area, the size of margins and gaps (coverage), and the rate of change thereof. As described above, the average may be calculated for each job and for multiple unit times, and multiple average target periods may be set within the above-mentioned predetermined time. In addition, the usage status may include the type of media (size, paper type, basis weight, etc.), and further, if the image forming apparatus 1 has a post-processing device or a separate monitoring device, the usage status may also include the status related to the use of the post-processing device or monitoring device.

[0060] The operating environment data may include, for example, the temperature and humidity within the housing of the image forming apparatus 1 during the above-mentioned predetermined period, and the external temperature and humidity at a predetermined position outside the image forming apparatus 1. Each acquired data is associated with timing information. The processes of steps S101 and S102 (corresponding to P1 in FIG. 2) constitute the status acquisition unit and status acquisition step of this embodiment. As a result, data related to the operating status at each timing is obtained and input to the prediction model 261.

[0061] The control unit 10 stores the obtained usage status data in the storage unit 20 as usage status data 21. The control unit 10 stores the obtained operating environment data in the storage unit 20 as environment measurement data 22 (step S103).

[0062] The control unit 10 inputs the obtained operation status data into the prediction model 261 (step S104). The control unit 10 acquires each of the predicted values ​​of future operation status output from the prediction model 261 (step S105). The predicted values ​​acquired at this time are of two types (multiple periods of different lengths), short-term and long-term, as described above. The processing of steps S104 and S105 (corresponding to P2 in FIG. 2) constitute the status prediction unit and status prediction step of this embodiment.

[0063] The control unit 10 associates each of the acquired prediction results with date and time information of the prediction period and stores them in the storage unit 20 as prediction data 23 (step S106). The control unit 10 calculates, based on the failure response data 24, an index relating to the likelihood of a failure occurring (probability of occurrence) according to the acquired prediction of the usage status and the prediction of the operating environment as a failure occurrence index for each long and short period (for a plurality of different periods) (step S107; failure prediction unit; corresponding to P3 in FIG. 2).

[0064] The control unit 10 acquires the current operation parameters (step S108; setting acquisition unit). The control unit 10 acquires scores corresponding to each operation parameter based on the operation parameter contribution data 25, and adds them up. The control unit 10 converts the total score value into a contribution coefficient by referring to the operation parameter contribution data 25 (step S109; corresponding to P6 and P7 in FIG. 2). The control unit 10 corrects the malfunction occurrence index by multiplying the contribution coefficient by the malfunction occurrence index (step S110; corresponding to P8 in FIG. 2). The processing of steps S109 and S110 may also be included in the configuration of the malfunction prediction unit of this embodiment. Then, the control unit 10 ends the malfunction occurrence prediction processing.

[0065] 5 is a flowchart showing a control procedure of the prediction model update process by the control unit 10. The execution frequency of this prediction model update process may be equal to or less than the execution frequency of the above-mentioned malfunction occurrence prediction process, and the execution timings may be different from each other. For example, the prediction model update process may be executed after the image formation operation of the day is completed and before the power supply is cut off.

[0066] When the prediction model update process is started, the control unit 10 (CPU) acquires actual values ​​of the usage status and the operating environment stored in the storage unit 20 from the usage status data 21 and the environmental measurement data 22 (step S201). The control unit 10 acquires predicted values ​​of the stored usage status and the operating environment from the prediction data 23 (step S202). The control unit 10 selects, from among the predicted values, periods corresponding to the acquisition timing of the actual values ​​(step S203).

[0067] The control unit 10 compares the actual value (actual operating condition) with the associated predicted value (predicted operating condition) (step S204; comparison unit, corresponding to P4 in FIG. 2). The control unit 10 obtains the degree of deviation (degree of agreement) as a comparison result. The degree of deviation may not be determined uniformly, but may be considered to reduce the influence of a specific change (in the case of irregularity) and / or emphasize (in the case of actual discontinuous change). The control unit 10 feeds back (learns) each parameter of the prediction model 261 according to the obtained degree of deviation, and updates the prediction model 261 (step S205; update unit, corresponding to P5 in FIG. 2, also corresponding to the generation unit). Then, the control unit 10 ends the prediction model update process.

[0068] The prediction model update process may be performed not only during update but also during initial learning, i.e., when generating a prediction model. In this case, input data (teacher data) must be prepared in advance for the initial learning. Also, if there are changes in the operating environment due to seasonal fluctuations, learning may take a year using only the measurement data of the device itself. Therefore, for example, effective initial learning may be possible by storing general common data in advance or making it available via a network.

[0069] As described above, when information on the likelihood of a malfunction occurring is obtained, the user responds according to the information. For example, in addition to arranging for replacement parts or substitutes and adjusting schedules related to image forming operations (in the short term, adjusting the order of jobs, and in the long term, planning downtime for maintenance, etc.), the image forming apparatus 1 may also adjust its operation under operating conditions according to the malfunction occurrence index so as to obtain a grace period before an actual malfunction occurs. In this case, there are adjustments that, although temporary, avoid an immediate malfunction, and adjustments that postpone the occurrence of a malfunction in the long term. The former adjustments are made according to the short-term malfunction occurrence index, and the latter adjustments are made according to the long-term malfunction occurrence index.

[0070] 6 is a flowchart showing a control procedure of the short-term suppression control process executed by the control unit 10 in response to a short-term prediction result regarding the occurrence of a toner spill defect. This short-term suppression control process may be executed following the acquisition of the result of the defect occurrence prediction process.

[0071] When the short-term suppression control process is started, the control unit 10 (CPU 11) determines whether the obtained defect occurrence index is 100 or more (step S301). If it is determined that the defect occurrence index is 100 or more ("YES" in step S301), the control unit (CPU 11) sets the vibration unit 67 to perform a vibration operation (step S302). Since the vibration operation is not performed during an image formation operation, it is performed immediately when no image is being formed, and during an image formation operation, it is performed after the current image formation operation is completed.

[0072] The control unit 10 sets the toner refresh operation (step S303). The refresh operation is performed to prevent deterioration of the toner supplied from a supply unit such as a toner cartridge and held in the developing unit 63 if the toner is held for a long period of time without being used. Therefore, a discharge latent image that is not used in actual image formation is formed on the photosensitive drum, and the toner is discharged by developing the discharge latent image, thereby accelerating the replacement of the toner. The discharged toner is removed by the cleaning unit 66 without being transferred to a medium or the like. Then, the control unit 10 ends the short-term suppression control process.

[0073] If it is determined in the determination process of step S301 that the defect occurrence index is not 100 or more (is less than 100) ("NO" in step S301), the control unit 10 determines whether the defect occurrence index is 80 or more (step S304). If it is determined that the defect occurrence index is 80 or more ("YES" in step S304), the process of the control unit 10 proceeds to step S303.

[0074] If it is determined that the defect occurrence index is not 80 or more (is less than 80) ("NO" in step S304), the control unit 10 determines whether the defect occurrence index is 50 or more (step S305). If it is determined that the defect occurrence index is 50 or more ("YES" in step S305), the control unit 10 determines whether the development θ flag is set, that is, whether the development θ is set high (step S306). If it is determined that the development θ flag is set ("YES" in step S306), the control unit 10 lowers the development θ. Also, the control unit 10 adjusts the maximum image density Dmax accordingly (step S307). The control unit 10 resets the development θ flag (step S308). Then, the control unit 10 ends the short-term suppression control process.

[0075] If it is determined that the development θ flag is not set ("NO" in step S306), the control unit 10 ends the short-term suppression control process.

[0076] If it is determined in the determination process of step S305 that the defect occurrence index is not 50 or more ("NO" in step S305), the control unit 10 determines whether the development θ flag is in a reset state (step S309). If it is determined that the development θ flag is in a reset state ("YES" in step S309), the control unit 10 increases the development θ. Also, the control unit 10 adjusts the maximum image density Dmax accordingly (step S310). The control unit 10 sets the development θ flag (step S311). Then, the control unit 10 ends the short-term suppression control process. If it is determined that the development θ flag is not in a reset state (is set) ("NO" in step S309), the control unit 10 ends the short-term suppression control process.

[0077] In this way, when the defect occurrence index is high, factors that currently lead to toner spills are quickly reduced by immediately executing a vibration operation, a toner refresh operation, etc. Also, when the defect occurrence index has risen to a medium level, the development θ is lowered to reduce toner scattering and reduce the trigger factors for toner spills.

[0078] 7 is a flowchart showing a control procedure of the long-term suppression control process executed by the control unit 10 in response to a long-term prediction result regarding the occurrence of a toner spill defect. This long-term suppression control process may be executed following the short-term suppression control process when the result of the defect occurrence prediction process is acquired.

[0079] When the long-term suppression control process is started, the control unit 10 (CPU 11) determines whether the malfunction occurrence index is 50 or more (step S401). If it is determined that the malfunction occurrence index is 50 or more ("YES" in step S401), the control unit 10 determines whether the vibration intensity of the vibration unit 67 is set to the upper limit value (step S402). If it is determined that it is not the upper limit value ("NO" in step S402), the control unit 10 sets the vibration intensity to be one step stronger (increased) (step S403).

[0080] The control unit 10 determines whether the target value of the toner concentration Tc is the lower limit value (step S404). If it is determined that the target value of the toner concentration Tc is not the lower limit value ("NO" in step S404), the control unit 10 sets the target value of the toner concentration Tc to be lowered by one step (step S405). The target value of the toner concentration Tc is lowered by increasing the charge amount. Then, the control unit 10 ends the long-term suppression control process.

[0081] If it is determined in the determination process of step S404 that the target value of toner concentration Tc is already the lower limit value ("YES" in step S404), control unit 10 determines whether the vibration intensity is the upper limit value or whether the defect occurrence index is 50 or more (step S431). If it is determined that either is the case ("YES" in step S431), control unit 10 ends the long-term suppression control process. If it is determined that neither is the case ("NO" in step S431), control unit 10 sets the vibration intensity by vibration unit 67 to be increased by one step (step S432). Then, control unit 10 ends the long-term suppression control process.

[0082] If it is determined in the determination process of step S402 that the vibration intensity is the upper limit value ("YES" in step S402), the control unit 10 determines whether the target value of the toner concentration Tc is the lower limit value (step S411). If it is determined that the target value of the toner concentration Tc is not the lower limit value ("NO" in step S411), the process of the control unit 10 proceeds to step S405.

[0083] When it is determined that the target value of the toner concentration Tc is the lower limit ("YES" in step S411), the control unit 10 determines whether the developer life is 1500 kp or more (step S412). When it is determined that the developer life is 1500 kp or more ("YES" in step S412), the control unit 10 performs a notification operation to prompt the user to replace the developer. The notification operation may be performed, for example, by displaying a character indicating that, an identification number or a figure of a warning on the display unit 51. Also, an LED lamp or the like may light up or flash in a color indicating a warning. Upon seeing this warning, the user (administrator) may check the inventory and / or arrange for a replacement developer, or may request a maintenance company, a service center, or the like to take action. Then, the control unit 10 ends the long-term suppression control process. When it is determined that the developer life is not 1500 kp or more (is less than 1500 kp) ("NO" in step S412), the control unit 10 ends the long-term suppression control process.

[0084] When it is determined in the determination process of step S401 that the malfunction occurrence index is not 50 or more (is less than 50) ("NO" in step S401), the control unit 10 sets the vibration intensity by the vibration unit 67 to be reduced by one stage (step S421). Note that, if the vibration intensity is already at the minimum stage, it may be maintained at the minimum stage.

[0085] The control unit 10 determines whether the defect occurrence index is equal to or greater than 30 (step S422). If it is determined that the defect occurrence index is equal to or greater than 30 ("YES" in step S422), the process of the control unit 10 proceeds to step S404.

[0086] If it is determined that the defect occurrence index is not 30 or more (is less than 30) ("YES" in step S422), the control unit 10 sets the target value of the toner concentration Tc to be increased by one step (step S423). If the target value of the toner concentration Tc is already the maximum value, the control unit 10 may maintain the target value of the toner concentration Tc as it is. Then, the control unit 10 ends the long-term suppression control process.

[0087] Since the long-term inhibition control process is not an immediate process, measures are set at a lower stage than the short-term inhibition control process, such as when the malfunction occurrence index is 30 or more. On the other hand, the short-term inhibition control process is a process that keeps the system in a state where malfunctions are less likely to occur for a short period of time when the possibility of malfunctions increasing, so measures are set when the malfunction occurrence index is 50 or more, and especially 80 or more. In this way, by calculating two types of malfunction occurrence index, long and short, it is possible to take appropriate measures depending on the urgency of the malfunction occurrence.

[0088] In addition to the above, operational parameters that affect toner spillage include, for example, the fogging margin (the difference between the bias voltage of the photosensitive drum and the developing voltage. The ease with which toner adheres to the photosensitive drum changes depending on the magnitude of this difference, so it also affects the amount of toner consumed). By changing the settings so that images are formed by consuming more toner not only in the refresh operation in the above short-term suppression control process but also in the image forming operation, it is possible to reduce the amount of deteriorated toner remaining in the developing unit 63. The above-mentioned short-term suppression control process and the above-mentioned suppression control process both constitute the operation of the suppression control unit of this embodiment.

[0089] Although toner spillage has been described above as an example of a defect, other defects may also be suppressed based on predictions and prediction results according to the corresponding usage conditions and operating parameters. For example, when predicting and suppressing image smearing, it is expected that the possibility of occurrence will increase in the short term due to an increase in absolute humidity or a paper type with a lot of paper dust. In addition, since a shortage of lubricant or the amount of ozone generated may have an effect, the magnitude of the discharge voltage, the period of use of the lubricant application mechanism, the contact angle of the brush that applies the lubricant, etc. may be used as operating parameters in calculating the contribution coefficient.

[0090] In addition, in a prediction limited to a defective removal of toner particles by the cleaning unit 66, the temperature inside the housing of the forming operation unit 60, which affects the degree of hardening of the cleaning blade member, and the coverage (partial coverage) related to the amount of toner particles removed, can be the corresponding input data. In addition, the period of use of the lubricant application mechanism related to the shortage of lubricant and the contact angle of the application brush may also be used as operation parameters in calculating the contribution coefficient.

[0091] As described above, the image forming apparatus 1 having the operation status detection system of this embodiment includes the control unit 10. The control unit 10, as a status acquisition unit, acquires data relating to the operation status at each timing of the image forming apparatus 1 to be monitored (particularly the forming operation unit 60 in this case) in association with timing information, and as a status prediction unit, predicts the future operation status according to the acquired operation status for each of a plurality of periods of different lengths from the present. In this way, the operating conditions are predicted for a number of different time periods, so that short-term measures and long-term preparations and measures can be used appropriately according to the contents of the multiple predictions. Therefore, the results of the prediction of the operating conditions make it possible to take more effective measures according to the situation.

[0092] The image forming apparatus 1 also includes a storage unit 20, which serves as a first storage unit and stores acquired data relating to operating conditions as usage condition data 21 and environmental measurement data 22. By storing and holding data in this manner, it is possible to easily input time-series data and select necessary data.

[0093] The operating conditions also include the environmental conditions of the image forming apparatus 1. Since the operation is also affected by the temperature and humidity of each part, by including these in the operating conditions to be predicted, future operation can be predicted more reliably.

[0094] Furthermore, the control unit 10 has, as a situation prediction unit, a prediction model 261 which is a machine learning model trained using data related to the operating situation as teacher data. By performing operation prediction using the prediction model 261 obtained from actual data, it is possible to flexibly and appropriately improve prediction accuracy according to the operating environment and usage characteristics of each image forming apparatus 1.

[0095] Moreover, the storage unit 20, as a second storage unit, stores the operation status predicted for each of the multiple time periods by the control unit 10, as a status prediction unit, in prediction data 23. The control unit 10, as a comparison unit, compares the predicted operation status with the actual operation status at a predetermined timing within each of the multiple time periods related to the predicted operation status, and as an update unit, further learns and updates the prediction model 261 based on the comparison result. In this way, by comparing its own prediction results with the corresponding actual operating conditions and feeding them back to the prediction model 261, it is possible to flexibly respond to changes in the usage conditions of the image forming apparatus 1 and output appropriate prediction results.

[0096] Furthermore, the control unit 10, as a generating unit, generates a prediction model 261 using data related to the operating status as teacher data. By making it possible to generate the prediction model 261 by itself in this manner, it is possible to predict the operating status by using an appropriate prediction model 261 according to the usage characteristics and operating environment characteristics of each image forming apparatus 1.

[0097] In addition, the predicted operating conditions include information on the probability of occurrence of a given operating condition. By expressing the operating conditions as a probability distribution rather than simply as a representative predicted value, it becomes possible to take more flexible measures that take into account the range of predictions.

[0098] In addition, the image forming apparatus 1 having the defect occurrence prediction system of this embodiment is equipped with each of the above-mentioned components, and the memory unit 20, as a third memory unit, stores a first correspondence relationship between the operating status and the occurrence of a specified defect in the image forming apparatus 1 in defect response data 24, and the control unit 10, as a defect prediction unit, is equipped with a defect prediction unit that calculates a specified index related to the possibility of a defect occurrence based on the predicted operating status and the first correspondence relationship. In this way, the occurrence of a malfunction is further predicted based on the obtained prediction results of the operating conditions, so it is possible to obtain more accurate information such as whether the situation is such that a malfunction is likely to occur soon depending on the usage conditions and changes in the environment such as that day and that time, and to what extent the device can still be used.

[0099] Moreover, the storage unit 20, as a fourth storage unit, stores a second correspondence relationship (contribution coefficient) between the operation parameters of the image forming apparatus 1 and the degree of contribution of the operation parameters to the occurrence of a predetermined defect in the operation parameter contribution data 25. The control unit 10, as a setting acquisition unit, acquires the operation parameters, and as a defect prediction unit, acquires a contribution coefficient based on the acquired operation parameters and the second correspondence relationship, and corrects the defect occurrence index by the contribution coefficient. In this way, by using the operation parameters as an auxiliary to estimate the degree of defect occurrence, it is possible to further improve the prediction accuracy. Furthermore, since these operation parameters are instantaneous values ​​rather than cumulative values, they are separated from the prediction model 261 and evaluated as an auxiliary contribution to the defect occurrence index, so that the prediction model 261 is not made more complicated than necessary.

[0100] Furthermore, the control unit 10, as a failure prediction unit, obtains a failure occurrence index for each of a plurality of different time periods. By performing failure prediction for a plurality of time periods in accordance with the prediction of the operating conditions for a plurality of time periods, it is possible to flexibly respond according to the situation, such as whether it is enough to endure for a short period until maintenance becomes possible while looking at future schedules, or whether it is necessary to operate the equipment as it is for a certain period of time while adjusting operating parameters, etc., in advance to prevent failures from occurring.

[0101] The image forming apparatus 1 of the present embodiment is also provided with the above-mentioned malfunction prediction system. This makes it possible to obtain predictions of malfunctions, such as abnormalities in image quality during image formation operations, for both long and short periods. Particularly in business applications, it may be problematic if abnormalities occur in image quality, and it may be difficult to immediately stop use and perform maintenance. Therefore, predictions of such malfunctions allow for more flexible and appropriate handling according to schedules, etc.

[0102] The image forming apparatus 1 also includes a suppression operation unit, such as a vibration unit 67, that performs a predetermined operation to suppress the occurrence of a defect, and the control unit 10, as a suppression control unit, controls the operation of the suppression operation unit. As a suppression control unit, the control unit 10 controls the operation of the suppression operation unit according to operation conditions corresponding to the defect occurrence indexes in different periods. The suppression operation unit here is not limited to a dedicated configuration for suppressing the occurrence of a defect, but includes all units that can change the normal operation settings to a state in which the defect is easily suppressed. In other words, the image forming apparatus 1 can change the operation parameters, etc., to enable reasonable operation based on long-term and short-term predictions of the occurrence of defects.

[0103] At least a part of the operating status is acquired based on job data related to an image formation command. By directly using job data including the operating settings and image data related to the image to be formed, a prediction model 261 that appropriately grasps the characteristics and time-series changes of the usage status can be obtained, and this prediction model 261 makes it possible to predict the future usage status.

[0104] The operating status prediction method of the present embodiment includes a status acquisition step of acquiring data related to the operating status at each timing of the operating device to be monitored in association with information on the timing, and a status prediction step of predicting future operating statuses for each of a plurality of periods of different lengths from the present according to the operating status acquired in the status acquisition step. By predicting the operating status for such a plurality of periods, it becomes possible to flexibly take short-term and long-term countermeasures, and it becomes possible to efficiently set the timing and time of maintenance, and to easily avoid maintenance at undesirable times.

[0105] The present invention is not limited to the above-described embodiment, but may be modified in various ways. For example, in the above embodiment, two types of defect occurrence indexes, short-term and long-term, are output, but three or more types, for example, a mid-term prediction or a prediction longer than the above-mentioned long-term (2 days to 1 month) may be performed. Also, the indices output for the short term and the long term do not have to be the same.

[0106] Furthermore, the malfunction occurrence index may be displayed on the display unit 51 or the like. In this case, the extent to which the malfunction occurrence index has decreased due to the setting change by the short-term suppression control processing / long-term suppression control processing may also be displayed.

[0107] In the above embodiment, the machine learning model using a neural network and the ARIMA model are described as examples of prediction models, but the present invention is not limited to these. For example, algorithms such as perceptron and logistic regression may be used, and various other time series models may be used. The "teacher data" in learning these models broadly refers to correct answer data in general.

[0108] In addition, the machine learning model does not need to be generated within the image forming apparatus 1, and may be generated by an external computer. In addition, the learning process for updating may also be performed externally, and only the updated parameters may be acquired by the image forming apparatus 1 thereafter.

[0109] Furthermore, the prediction operation itself does not have to be performed within the image forming apparatus 1, and some or all of the measurement results of the measuring unit 70 do not have to be acquired and / or stored by the image forming apparatus 1. Using the results measured by an external measuring device, prediction-related processing may be performed by an external computer or the like.

[0110] In the above embodiment, the occurrence of a problem in image quality in the image forming apparatus 1 is predicted, but it may be possible to predict other problems in addition to image quality. Predictions may also be made regarding the operating conditions of operating devices other than the image forming apparatus 1 (particularly, devices that physically operate something), and in this case, predictions may be made regarding the occurrence of various types of problems according to the predicted operating conditions and operating devices.

[0111] In addition, the prediction of the operating status does not necessarily have to be used to predict the occurrence of a malfunction, but may be used, for example, to control the operation of an air conditioning system in a room in which the operating device is located, or to adjust the work schedule of a user of the operating device.

[0112] In addition, the machine learning model does not necessarily have to be updated periodically. Since learning including irregular data or abnormal data may actually reduce prediction accuracy, the machine learning model may be updated only when learning data is generated by a separate analysis process.

[0113] In the above embodiment, the operating parameters are used to calculate the contribution to the malfunction occurrence index calculated separately, but the operating parameters may also be used directly to calculate the malfunction occurrence index. The index indicating the likelihood of malfunction does not have to be a numerical value such as an index. Even if it is a numerical value, it does not have to be obtained by calculation, and may be obtained, for example, from a table shown in a matrix. In addition, the specific configurations, contents and procedures of the processing operations, etc. shown in the above embodiments can be modified as appropriate without departing from the spirit of the present invention. The scope of the present invention includes the scope of the invention described in the claims and its equivalents. [Explanation of symbols]

[0114] 1. Image forming device 10 Control section 11 CPU 12 RAM 121 Job Data 20 Memory section 21 Usage Data 22 Environmental measurement data 23 Prediction Data 24. Defect response data 25 Operating Parameter Contribution Data 26 Programs 261 Predictive Models 30 Communications Department 40 Interfaces 51 Display section 52 Operation reception section 60 Forming operation section 61 Charging section 62 Exposure section 63 Development Section 64 Fixing section 65 Static electricity removal section 66 Cleaning Department 67 Vibration section 70 Measurement section

Claims

1. a status acquisition unit that acquires data relating to an operational status of a monitoring target operating device at each timing in association with information on the timing; a situation prediction unit that predicts a future operation situation according to the operation situation acquired by the situation acquisition unit for each of a plurality of periods having different lengths from the present; a third storage unit configured to store a first correspondence relationship between the operating status and the occurrence of a predetermined malfunction in the operating device; a failure prediction unit that calculates a predetermined index relating to the likelihood of occurrence of the failure based on the predicted operating condition and the first correspondence relationship; a fourth storage unit configured to store a second correspondence relationship between an operation setting of the operating device and a degree of contribution of the operation setting to the occurrence of the predetermined malfunction; A setting acquisition unit that acquires the operation setting; Equipped with The failure prediction unit obtains the degree of contribution based on the acquired operation setting and the second correspondence relationship, and corrects the predetermined index based on the degree of contribution. A defect occurrence prediction system.

2. 2. The malfunction occurrence prediction system according to claim 1, further comprising a first storage unit that stores the acquired data relating to the operating condition.

3. 3. The malfunction occurrence prediction system according to claim 1, wherein the operating conditions include an environmental condition of the operating device.

4. The malfunction occurrence prediction system according to any one of claims 1 to 3, characterized in that the situation prediction unit has a machine learning model trained using data related to the operating situation as teacher data.

5. a second storage unit configured to store the operation status predicted for each of the plurality of time periods by the status prediction unit; a comparison unit that compares the predicted operation status with an actual operation status at each predetermined timing within the plurality of periods related to the predicted operation status; an update unit that further learns and updates the machine learning model based on a comparison result by the comparison unit; 5. The defect occurrence prediction system according to claim 4, further comprising:

6. The malfunction occurrence prediction system according to claim 4 or 5, further comprising a generation unit that generates the machine learning model using data related to the operational status as training data.

7. 7. The malfunction occurrence prediction system according to claim 1, wherein the predicted operating condition includes information related to the occurrence probability of a predetermined operating condition.

8. 8. The system for predicting malfunction occurrence according to claim 1, wherein the malfunction prediction unit calculates the predetermined index for each of the different periods.

9. 9. An image forming system comprising the defect occurrence prediction system according to claim 1.

10. A suppression operation unit that performs a predetermined operation to suppress the occurrence of a malfunction; A suppression control unit that controls the operation of the suppression operation unit; Equipped with The suppression control unit controls the operation of the suppression operation unit according to operation conditions corresponding to the predetermined indexes in the different periods.

10. The image forming system according to claim 9.

11. A status acquisition unit that acquires data relating to an operating status at each timing of an operating device to be monitored in association with information on the timing; a situation prediction unit that predicts a future operation situation according to the operation situation acquired by the situation acquisition unit for each of a plurality of periods having different lengths from the present; a third storage unit configured to store a first correspondence relationship between the operating status and the occurrence of a predetermined malfunction in the operating device; a failure prediction unit that calculates a predetermined index relating to the likelihood of occurrence of the failure based on the predicted operating condition and the first correspondence relationship; A suppression operation unit that performs a predetermined operation to suppress the occurrence of a malfunction; A suppression control unit that controls the operation of the suppression operation unit; Equipped with The suppression control unit controls the operation of the suppression operation unit according to operation conditions corresponding to the predetermined indexes in the different periods.

1. An image forming system comprising:

12. 12. The image forming system according to claim 10, wherein at least a part of the operation status is acquired based on job data related to an image forming command.

13. A method for predicting the occurrence of a malfunction by a control unit of a malfunction prediction system, comprising: a status acquisition step of acquiring data relating to an operational status of the monitoring target operating device at each timing in association with information on the timing; a situation prediction step of predicting a future operation situation according to the operation situation acquired in the situation acquisition step, for each of a plurality of periods of different lengths from the present; storing a first correspondence between the operating status and the occurrence of a predetermined malfunction in the operating device; a failure prediction step of calculating a predetermined index relating to the likelihood of occurrence of the failure based on the predicted operating condition and the first correspondence relationship; storing a second correspondence between an operation setting of the operating device and a degree of contribution of the operation setting to the occurrence of the predetermined malfunction; A setting acquisition step of acquiring the operation setting; Including, In the defect prediction step, the degree of contribution is obtained based on the acquired operation setting and the second correspondence relationship, and the predetermined index is corrected based on the degree of contribution. A defect occurrence prediction method comprising:

14. A method for controlling image formation by a control unit of an image forming system, comprising: a status acquisition step of acquiring data relating to an operational status of a monitoring target operating device at each timing in association with information on the timing; a situation prediction step of predicting a future operation situation according to the operation situation acquired in the situation acquisition step, for each of a plurality of periods of different lengths from the present; storing a first correspondence between the operating status and the occurrence of a predetermined malfunction in the operating device; a failure prediction step of calculating a predetermined index relating to the likelihood of occurrence of the failure based on the predicted operating condition and the first correspondence relationship; a suppression operation step of performing a predetermined operation to suppress the occurrence of a defect; a suppression control step of controlling the operation in the suppression operation step; Including, In the suppression control step, the operation in the suppression operation step is controlled according to operation conditions corresponding to the predetermined indexes in the different multiple periods.

23. An image formation control method comprising:

Images