Image formation system, image formation apparatus, method, and program

Abstract

To improve prediction accuracy of a service life of an intermediate transfer belt.MEANS FOR SOLVING THE PROBLEM: An image formation system includes: an image formation apparatus which has an image carrier, image formation means which forms a toner image on a surface of the image carrier, and an intermediate transfer body which rotates while being in contact with the image carrier; and an information processing apparatus which can communicate with the image formation apparatus. The image formation apparatus has: an apparatus state acquisition unit which acquires state information indicating a state of the image formation apparatus; a prediction processing unit which predicts a service life of the intermediate transfer body by using a learned model obtained through machine learning with the state information as learning data; and a machine control unit which calculates the number of remaining usable days of the intermediate transfer body according to a prediction result by the prediction processing unit. The information processing apparatus has a machine learning unit which generates the learned model by machine-learning the learning data generated from the state information. The state information includes a primary transfer bias supplied when transferring a toner image from the image carrier to the intermediate transfer body.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present invention relates to an image forming system, an image forming apparatus, a method, and a program.

Background Art

[0002] Conventionally, there has been known a technique of using a state estimation model with the state quantity of an image forming apparatus as learning data and estimating the state of a photoreceptor drum based on the latest state quantity acquired from the image forming apparatus.

Summary of the Invention

Problems to be Solved by the Invention

[0003] In the above-described conventional technique, estimating the state of the intermediate transfer belt is not considered. Further, in the above-described conventional technique, the total running distance, the exposure amount, the printing density, and the number of printed sheets are used as the state quantities of the image forming apparatus. Therefore, when the above-described conventional technique is applied to estimating the state of the intermediate transfer belt, if any of these quantities exceeds a certain number, the intermediate transfer belt may be determined to have reached the end of its life and replaced even though it can still be used.

[0004] The disclosed technique has been made in view of the above circumstances, and an object thereof is to improve the prediction accuracy of the life of the intermediate transfer belt.

Means for Solving the Problems

[0005] The disclosed technology is an image forming system including an image forming apparatus having an image carrier, an image forming means for forming a toner image on the surface of the image carrier, and an intermediate transfer member that rotates while contacting the image carrier, and an information processing apparatus capable of communicating with the image forming apparatus. The image forming apparatus includes a device state acquisition unit that acquires state information indicating the state of the image forming apparatus, a prediction processing unit that predicts the life of the intermediate transfer member using a learned model obtained by machine learning the state information as learning data, and a machine control unit that calculates the remaining available days of the intermediate transfer member according to the prediction result by the prediction processing unit. The information processing apparatus includes a machine learning unit that generates the learned model by machine learning the learning data generated from the state information. The state information includes a primary transfer bias supplied when transferring the toner image from the image carrier to the intermediate transfer member.

Advantages of the Invention

[0006] The prediction accuracy of the life of the intermediate transfer belt can be improved.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3A

Figure 3B

Figure 4

Figure 5A

Figure 5B

Figure 6

Figure 7

Figure 8

[0008] Hereinafter, with reference to the drawings, this embodiment will be described. FIG. 1 is a diagram for explaining the outline of the structure of the image forming apparatus. FIG. 1(A) shows the configuration of the secondary transfer roller, and FIG. 1(B) shows the configuration of the secondary transfer belt.

[0009] The image forming apparatus 100 of this embodiment includes a photosensitive drum 1, a charger 2, an exposure means 3, a developing means 4, primary transfer rollers 5-1 to 5-4, a photosensitive cleaning unit 7, and a process unit 10. Further, the image forming apparatus 100 includes a transfer belt 15, a cleaning opposing roller 16, a tension roller 20, a transfer driving roller 21, a transfer material cassette 22, a paper feed conveying roller 23, a resist roller pair 24, a secondary transfer roller 25, a cleaning blade 26, a secondary transfer roller cleaning unit 27, a secondary transfer belt 28, and a tension roller 29.

[0010] Furthermore, the image forming apparatus 100 has a cleaning blade 31, a transfer belt cleaning unit 32, a waste toner storage section 33, a fixing means 40, a discharge port 41, and a manual insertion port 42.

[0011] The photosensitive drum 1 is cylindrical and rotates in the direction of the arrow shown in FIG. 1. The charger 2 is roller-shaped and is pressed against the photosensitive drum 1 to charge the surface of the photosensitive drum 1. Further, the charger 2 rotates in a driven manner by the rotation of the photosensitive drum 1, and uniformly charges the surface of the photosensitive drum 1 by applying a DC voltage or a bias voltage in which an AC voltage is superimposed on the DC voltage by a high-voltage power source (not shown). Note that although the charging method is roller-shaped, it may be a wire discharge type.

[0012] The exposure means 3 is a latent image forming means. The photoreceptor drum 1 is exposed to image information by the exposure means 3, and an electrostatic latent image is formed. The exposure by this exposure means 3 is performed by a laser beam scanner using a laser diode, an LED (light-emitting diode), or the like.

[0013] The developing means 4 is a developing device, and visualizes the electrostatic latent image on the photoreceptor drum 1 as a toner image by a predetermined developing bias supplied from a high-voltage power source (not shown). Toner is stored in the developing means 4.

[0014] The photoreceptor cleaning unit 7 has a photoreceptor cleaning blade 6 inside and cleans the photoreceptor drum 1.

[0015] The process unit 10 is a process unit in which the photoreceptor drum 1, the charger 2, the exposure means 3, the developing means 4, and the photoreceptor cleaning unit 7 are integrated.

[0016] Four process units 10 are arranged in parallel, and when forming a full-color image, toner images of each color (black, cyan, magenta, yellow) are sequentially superimposed and transferred onto the transfer belt 15 that is abutted, thereby forming a full-color image.

[0017] The transfer belt 15 is stretched by the transfer drive roller 21, the cleaning opposing roller 16, the primary transfer roller 5, and the tension roller 20, and is rotationally driven via the transfer drive roller 21 by a drive motor (not shown). Note that the transfer drive roller 21 also serves as a secondary transfer opposing roller.

[0018] The transfer belt 15 of the present embodiment is an example of an intermediate transfer body that rotates while contacting the photoreceptor drum 1 which is an image carrier.

[0019] Note that the drive sources of the process unit 10 and the transfer drive roller 21 can be either independent or common. However, it is common to turn on / off at the same time at least for the process unit for black and the transfer drive, and it is desirable to make them common for downsizing and cost reduction of the main body. Also, as a transfer belt tensioning mechanism, the tension roller 20 is pressed by springs on both sides of the roller.

[0020] The transfer belt cleaning unit 32 performs cleaning by scraping off the residual transfer toner on the transfer belt 15 with a cleaning blade 31 that is counter-abutted against the transfer belt 15. Note that the cleaning method by the transfer belt cleaning unit 32 is not a blade cleaning method, and an electrostatic brush method, an electrostatic roller method, etc. can also be installed. However, from the viewpoints of downsizing and cost reduction of the main body and cleanability, the blade cleaning method is more preferable. The reason is that in the case of the electrostatic method, a cleaning brush / roller to which a bias is applied is arranged instead of the cleaning blade 31, and preliminary charging of the residual transfer toner may be required depending on the usage situation of the image forming apparatus 100, resulting in drawbacks such as the cleaning unit itself becoming larger, one or two additional high-voltage power supplies, and the need for extra operations for bias screening.

[0021] The residual transfer toner scraped off by the cleaning blade 31 is stored in the waste toner storage unit 33 through a toner conveyance path (not shown).

[0022] The primary transfer rollers 5-1 to 5-4 are metal rollers or conductive sponge rollers, and are arranged opposite to the photosensitive drum 1 via the transfer belt 15. By applying a predetermined primary transfer bias with a single high-voltage power supply (not shown), the toner image on the photosensitive drum 1 is transferred to the transfer belt 15. For the primary transfer roller 5-1, metal rollers (aluminum, SUS), ion conductive rollers (urethane + carbon dispersion, NBR, hydrin rubber), electron conductive type rollers (EPDM), etc. are used.

[0023] As the material used for the transfer belt 15, an endless belt in the form of a resin film is used, which is obtained by dispersing a conductive material such as carbon black in PVDF (polyvinylidene fluoride), ETFE (ethylene-tetrafluoroethylene copolymer), PI (polyimide), PC (polycarbonate), TPE (thermoplastic elastomer), etc.

[0024] The secondary transfer unit consists of a roller configuration or a belt configuration. In the case of the roller configuration, the secondary transfer roller 25 is a sponge roller, and an ion conductive roller (urethane + carbon dispersion, NBR, hydrin), an electron conductive type roller (EPDM), etc. are used.

[0025] The secondary transfer roller cleaning unit 27 performs cleaning by scraping off the remaining toner on the secondary transfer roller 25 with a cleaning blade 26 that counter-contacts the secondary transfer roller 25.

[0026] In the case of the belt configuration, the secondary transfer belt 28 is stretched by a secondary transfer roller 25 to which a driving bias is applied and a tension roller 29, and is rotationally driven via the secondary transfer roller 25 by a driving motor (not shown).

[0027] The transfer material (recording medium) is set in the transfer material cassette 22 or the manual insertion slot 42, and is fed in accordance with the timing when the leading end of the toner image on the surface of the transfer belt 15 reaches the secondary transfer position by the paper feed conveyance roller 23, the registration roller pair 24, etc. A predetermined secondary transfer bias is applied by a high voltage power supply (not shown), and the toner image on the transfer belt 15 is transferred to the transfer material. In this configuration, the paper feed takes a vertical path. The transfer material is separated from the transfer belt 15 by the curvature of the transfer drive roller 21, and the toner image transferred to the transfer material is fixed by the fixing means 40 and then discharged from the discharge port 41.

[0028] As the secondary transfer bias, there are two methods: an attractive transfer method that forms a secondary transfer electric field by applying a positive bias to the secondary transfer roller 25 and grounding the transfer driving roller 21, and a repulsive transfer method that forms a secondary transfer electric field by applying a negative bias to the transfer driving roller 21 and grounding the secondary transfer roller 25.

[0029] Next, an image forming system including the image forming apparatus 100 shown in FIG. 1 will be described. FIG. 2 is a diagram showing an example of the system configuration of the image forming system.

[0030] The image forming system 1000 of the present embodiment includes an image forming apparatus 100, a machine learning server 102, a general-purpose computer 103, and a data server 105. In the image forming apparatus 100, each device is connected by a network such as a LAN. Note that the network connecting each device may be wired or wireless, and the machine learning server 102 and the data server 105 may be connected to the image forming apparatus 100 so as to be communicable via the Internet or the like.

[0031] The image forming apparatus 100 includes a printer, a multifunction device, a FAX, and the like. The image forming apparatus 100 is equipped with an AI (Artificial Intelligence) function, and uses this AI function to estimate the life of the transfer belt 15.

[0032] The machine learning server 102 generates a learned model for realizing the AI function mounted on the image forming apparatus 100.

[0033] The general-purpose computer 103 transmits print data to the image forming apparatus 100 and the like. The data server 105 collects learning data used for performing machine learning in the machine learning server 102 from external devices such as the image forming apparatus 100 and provides it to the machine learning server 102. The learning data includes various types of information indicating the state of the image forming apparatus 100. Details of the learning data will be described later.

[0034] In the image forming system 1000, the image forming apparatus 100 may receive a learned model generated by the machine learning server 102 from the machine learning server 102 and implement a specific AI function using the learned model. Also, in the image forming system 1000, the machine learning server 102 receives learning data necessary for learning a learned model for implementing a specific AI function from external devices such as the data server 105, the image forming apparatus 100, and the general-purpose computer 103. Then, the machine learning server 102 generates a learned model by performing learning processing using some or all of them.

[0035] In this embodiment, in this way, the estimation accuracy of the life of the transfer belt 15 can be improved by using a learned model generated using learning data including information indicating the state of the image forming apparatus 100.

[0036] Note that the machine learning server 102 and the data server 105 of this embodiment may be realized on the same computer. Also, the image forming apparatus 100 may be provided with functions similar to those of the machine learning server 102 and the data server 105. Furthermore, the machine learning server 102 and the data server 105 may be realized by one computer or may be realized by a plurality of computers. For example, the machine learning server 102 and the data server 105 may be realized by cloud computing technology.

[0037] Next, the hardware configurations of the image forming apparatus 100 and the machine learning server 102 will be described. FIG. 3A is a diagram showing an example of the hardware configuration of the image forming apparatus.

[0038] As shown in FIG. 3A, the image forming apparatus 100 includes a controller 910, a short-range communication circuit 920, an engine control unit 930, an operation panel 940, a network I / F 950, and a sensor group 960.

[0039] Among these, the controller 910 includes a CPU (Central Processing Unit) 901 which is the main part of the computer, a system memory (MEM-P) 902, a north bridge (NB) 903, a south bridge (SB) 904, an ASIC (Application Specific Integrated Circuit) 906, a local memory (MEM-C) 907 which is a storage unit, an HDD (Hard Disk Drive) controller 908, and an HD (Hard Disk) 909 which is a storage unit. It is configured such that the NB 903 and the ASIC 906 are connected by an AGP (Accelerated Graphics Port) bus 921.

[0040] Among these, the CPU 901 is a control unit that performs overall control of the image forming apparatus 100. The NB 903 is a bridge for connecting the CPU 901, the MEM-P 902, the SB 904, and the AGP bus 921, and has a memory controller that controls reading and writing to the MEM-P 902, a PCI (Peripheral Component Interconnect) master, and an AGP target.

[0041] The MEM-P 902 consists of a ROM (Read-Only Memory) 902a which is a memory for storing programs and data for realizing each function of the controller 910, and a RAM (Random Access Memory) 902b which is used as a memory for developing programs and data and for drawing during memory printing. Note that the programs stored in the RAM 902b may be provided in an installable or executable format and recorded on a computer-readable recording medium such as a CD-ROM, CD-R, or DVD.

[0042] SB904 is a bridge for connecting NB903 with a PCI device and peripheral devices. ASIC906 is an IC (Integrated Circuit) for image processing applications having hardware elements for image processing, and serves as a bridge for connecting an AGP bus 921, a PCI bus 922, an HDD controller 908, and a MEM-C907 respectively. This ASIC906 consists of a PCI target and an AGP master, an arbiter (ARB) forming the core of the ASIC906, a memory controller for controlling MEM-C907, a plurality of DMACs (Direct Memory Access Controllers) for performing operations such as rotation of image data by means of hardware logic, etc., and a PCI unit for performing data transfer via the PCI bus 922 between a scanner unit 931 and a printer unit 932. Note that an interface for USB (Universal Serial Bus) or an interface for IEEE1394 (Institute of Electrical and Electronics Engineers 1394) may be connected to the ASIC906.

[0043] MEM-C907 is a local memory used as a print image buffer and a code buffer. HD909 is a storage for accumulating image data, accumulating font data used at the time of printing, and accumulating forms. HD909 controls reading or writing of data to / from HD909 in accordance with the control of the CPU901. The AGP bus 921 is a bus interface for a graphics accelerator card proposed for speeding up graphic processing, and can speed up the graphics accelerator card by directly accessing the MEM-P902 with high throughput.

[0044] Also, the short-range communication circuit 920 is provided with an antenna 920a. The short-range communication circuit 920 is a communication circuit such as NFC or Bluetooth.

[0045] Furthermore, the engine control unit 930 is constituted by the printer unit 932 and may have a scanner unit 931. Also, the operation panel 940 includes a panel display unit 940a such as a touch panel for displaying current setting values, selection screens, etc. and receiving inputs from the operator, and an operation panel 940b composed of a numeric keypad for receiving setting values of conditions related to image formation such as density setting conditions and a start key for receiving a copy start instruction. The controller 910 controls the entire image forming apparatus 100, for example, controls drawing, communication, inputs from the operation panel 940, etc. The printer unit 932 or the scanner unit 931 includes an image processing part such as error diffusion and gamma conversion. The operation panel 940 is an example of a display device included in the image forming apparatus 100.

[0046] Note that the image forming apparatus 100 may switch various functions such as settings, color adjustment, print and maintenance schedule management, etc. in addition to the printer function by the application switching key of the operation panel 940. Note that the document box function, copy function, facsimile function, etc. may be sequentially switched and selected. Also, the network I / F 950 is an interface for performing data communication using a communication network. The short-range communication circuit 920 and the network I / F 950 are electrically connected to the ASIC 906 via the PCI bus 922.

[0047] The sensor group 960 includes various sensors for detecting the state of the image forming apparatus 100. Specifically, the sensor group 960 may include a sensor for detecting the primary transfer bias voltage, a sensor for detecting the toner density of the density adjustment pattern formed on the transfer belt 15, and a sensor for detecting the interval of the density adjustment pattern. Also, the sensor group 960 may include a sensor for detecting the torque of the transfer drive roller 21 that rotationally drives the transfer belt 15 (the drive current of the motor that rotates the transfer drive roller 21). Also, the sensor group 960 may include a sensor for detecting the temperature and humidity of the space where the image forming apparatus 100 is installed and a sensor for detecting the temperature and humidity inside the image forming apparatus 100.

[0048] FIG. 3B is a diagram showing an example of the hardware configuration of the machine learning server. The machine learning server 102 of the present embodiment is constructed by a computer and includes a CPU 501, a ROM 502, a RAM 503, an HD 504, an HDD (Hard Disk Drive) controller 505, a display 506, an external device connection I / F (Interface) 508, a network I / F 509, a data bus 510, a keyboard 511, a pointing device 512, a DVD-RW (Digital Versatile Disk Rewritable) drive 514, and a media I / F 516.

[0049] Among these, the CPU 501 controls the operation of the entire machine learning server 102. The ROM 502 stores programs used for driving the CPU 501 such as the IPL. The RAM 503 is used as a work area for the CPU 501. The HD 504 stores various data such as programs. The HDD controller 505 controls the reading or writing of various data to and from the HD 504 according to the control of the CPU 501. The display 506 displays various information such as a cursor, a menu, a window, characters, or images. The external device connection I / F 508 is an interface for connecting various external devices. The external devices in this case are, for example, a USB (Universal Serial Bus) memory, a printer, and the like. The network I / F 509 is an interface for performing data communication using a communication network. The data bus 510 is an address bus, a data bus, etc. for electrically connecting the components such as the CPU 501 shown in FIG. 3B.

[0050] Also, the keyboard 511 is a type of input means having a plurality of keys for inputting characters, numerical values, various instructions, etc. The pointing device 512 is a type of input means for selecting and executing various instructions, selecting a processing target, moving a cursor, etc. The DVD-RW drive 514 controls reading or writing of various data to / from the DVD-RW 513 as an example of a removable recording medium. Note that it may be not only a DVD-RW but also a DVD-R or the like. The media I / F 516 controls reading or writing (storage) of data to / from the recording medium 515 such as a flash memory.

[0051] Note that since the hardware configurations of the general-purpose computer 103 and the data server 105 in this embodiment may be the same as that of the machine learning server 102, the description thereof is omitted.

[0052] Next, with reference to FIG. 4, the functional configurations of the respective devices included in the image forming system 1000 will be described. FIG. 4 is a diagram for explaining the functional configurations of the respective devices included in the image forming system.

[0053] Each functional unit shown in FIG. 4 is realized by using hardware resources and programs as shown in FIGS. 3A and 3B, for example. Note that the programs for realizing each functional unit shown in FIG. 4 are stored in the storage for each of its components, read into the RAM, and executed by the CPU.

[0054] Specifically, in the image forming apparatus 100, the program as described above is stored in the HD909, read into the RAM902b, and executed by the CPU901. In the machine learning server 102, the program as described above is stored in the HD504, read into the RAM503, and executed by the CPU501. Similarly, in the data server 105, the program as described above is stored in the HD, read into the RAM, and executed by the CPU.

[0055] Each functional unit shown in FIG. 4 learns information for predicting the remaining life of the transfer belt 15 of the image forming apparatus 100 in the image forming system 1000 of the present embodiment, performs an estimation process of the remaining life, and realizes a function of performing highly accurate remaining life prediction.

[0056] First, the functions of the image forming apparatus 100 will be described. The image forming apparatus 100 of the present embodiment includes a data storage unit 401, a JOB control unit 403, a machine control unit 411, a pattern reading unit 404, a prediction processing unit 405, a counter unit 406, and a device state acquisition unit 407.

[0057] The data storage unit 401 records image data, learning data described later, learned models, and other data that the image forming apparatus 100 inputs and outputs with respect to the RAM 902b and the HD 909 in the hardware configuration shown in FIG. 3A.

[0058] Further, the data storage unit 401 may store state information and history information described later. Furthermore, information indicating the usage environment of the user of the image forming apparatus 100 and information indicating the replacement history of the parts of the image forming apparatus 100 may be stored in the data storage unit 401.

[0059] The information indicating the usage environment of the user may be, for example, information for specifying a busy period or a slack period. The information indicating the replacement history of the parts may be, for example, information indicating the presence or absence of the transfer belt 15 and the replacement time of the transfer belt 15 in the past.

[0060] When a job based on a user's instruction is input, the JOB control unit 403 executes the basic functions of the image forming apparatus 100 such as copy, fax, and print according to the job. Further, the JOB control unit 403 issues instructions to other functional units and performs transmission and reception of data in accordance with the execution of the basic functions.

[0061] In addition, the JOB control unit 403 of the present embodiment may store history information indicating the execution history of jobs in the data storage unit 401. The history information may include the size of the paper used when a job was executed in the past, the image area ratio when a job was executed in the past, the image pattern formed on the recording medium by the execution of the job, the date and time when the job was executed, and the like.

[0062] Note that the image area ratio indicates the ratio occupied by the image portion (the portion where the toner image is formed) per unit area on the recording medium.

[0063] The machine control unit 411 performs control according to the life prediction result of the transfer belt 15. The control by the machine control unit 411 includes control for displaying an instruction to replace the transfer belt 15 on the operation panel 940. In addition, the machine control unit 411 includes control for placing an order for replacement parts and the like.

[0064] Based on an instruction from the JOB control unit 403, the pattern reading unit 404 optically reads the pattern on the transfer belt 15 by the in-line sensor in the apparatus using the recording paper.

[0065] The prediction processing unit 405 predicts the life of the transfer belt 15 using the learned model learned by the machine learning server 102. The prediction processing by the prediction processing unit 405 is performed based on an instruction from the JOB control unit 403. The result of the prediction processing by the prediction processing unit 405 is transmitted to the JOB control unit 403 and sent from the JOB control unit 403 to the machine control unit 411. The machine control unit 411 may display the prediction result on the operation panel 940. Specifically, the machine control unit 411 may display information including the replacement timing of the transfer belt 15 and the like on the operation panel 940.

[0066] The counter unit 406 records and manages various counter values (for example, the total number of printed sheets) in the image forming apparatus 100.

[0067] The apparatus state acquisition unit 407 acquires state information indicating the state of the image forming apparatus 100 at the time of receiving a print job or the like and transmits it to the data server 105.

[0068] Specifically, the device state acquisition unit 407 acquires, as state information, information detected by the sensor group 960, a count value managed by the counter unit 406, history information indicating the execution history of jobs, and the like. Note that the device state acquisition unit 407 may store the state information in the data storage unit 401. The state information stored in the data storage unit 401 may be periodically transmitted to the data server 105.

[0069] The state information of the present embodiment will be described below.

[0070] The state information of the present embodiment includes, for example, the primary transfer bias, the density adjustment pattern, the interval between density adjustment patterns, the torque of the transfer driving roller 21, the temperature and humidity outside the housing of the image forming apparatus 100, the temperature and humidity inside the housing of the image forming apparatus 100, and the like. These pieces of information are the information detected by the sensor group 960.

[0071] Note that the density adjustment pattern is a pattern image for adjusting the density of the image formed on the surface of the transfer belt 15, and the interval between density adjustment patterns is the interval between the pattern images formed on the surface of the transfer belt 15.

[0072] Further, the state information of the present embodiment includes the running distance of the transfer belt 15 and the number of printed sheets. The running distance of the transfer belt 15 and the total number of printed sheets so far may be information acquired by the counter unit 406.

[0073] Further, the state information of the present embodiment includes information indicating the size of the recording medium used so far, the image pattern formed by the execution of the job, and the image area ratio. These pieces of information may be included in the history information indicating the execution history of the job.

[0074] Further, the state information of the present embodiment may include information indicating the usage environment of the user of the image forming apparatus 100 and information indicating the replacement history of the transfer belt 15.

[0075] Next, the functions of the data server 105 will be described. The software of the data server 105 includes a data collection and provision unit 410 and a data storage unit 412.

[0076] The data collection and provision unit 410 collects and provides learning data for learning in the machine learning server 102. Specifically, the data collection and provision unit 410 collects the status information acquired by the device status acquisition unit 407 from the image forming apparatus 100 and stores it in the data storage unit 412. Further, the data collection and provision unit 410 transmits the status information stored in the data storage unit 412 to the machine learning server 102.

[0077] Next, the functions of the machine learning server 102 will be described. The machine learning server 102 includes a learning data generation unit 413, a machine learning unit 414, and a data storage unit 415.

[0078] The learning data generation unit 413 generates learning data from the status information received from the data server 105. Specifically, the learning data generation unit 413 removes unnecessary data that becomes noise in order to obtain the desired learning effect from the status information. Further, the learning data generation unit 413 optimizes the learning data by adjusting the data format for inputting the status information into the learned model generated by the machine learning unit 414.

[0079] The machine learning unit 414 uses the learning data generated by the learning data generation unit 413 as input and performs machine learning by utilizing the learning method using the learning model described later.

[0080] The data storage unit 415 temporarily stores the status information received from the data server 105, the learning data generated by the learning data generation unit 413, and the learned model generated by the machine learning unit 414.

[0081] Hereinafter, with reference to FIGS. 5A and 5B, the machine learning unit 414 of the present embodiment will be described. FIG. 5A is a first conceptual diagram showing an example of an input / output structure using a learning model in the machine learning unit, and FIG. 5B is a second conceptual diagram showing an example of an input / output structure using a learning model in the machine learning unit. Here, a learning model using a neural network is exemplified.

[0082] As an example for explaining the features of the image forming system 1000 of the present embodiment, the elements of the learning data related to the generation of a learning model for predicting (outputting) the life of the transfer belt 15 with the state information as an input by this neural network are shown as X1 to X10.

[0083] Note that, as an example of the factors related to the life of the transfer belt 15 in FIG. 5A, the elements of the learning data are shown, but the present invention is not limited thereto.

[0084] In the present embodiment, each piece of information included in the state information acquired from the image forming apparatus 100 is used as an element of the learning data. Details of the elements of the learning data of the present embodiment will be described later.

[0085] Note that the elements of the learning data are not limited to the information included in the state information, and other information may be included.

[0086] Specific algorithms for machine learning include, in addition to neural networks, the k-nearest neighbor method, the naive Bayes method, decision trees, support vector machines, and the like. Also, deep learning (deep learning) that uses a neural network to generate its own feature amounts and combined weight coefficients for learning is also included. Appropriately, those of the above algorithms that can be used can be applied to the present embodiment.

[0087] Also, the learning model may include an error detection unit and an update unit. Hereinafter, the learning model will be described with reference to FIG. 5B.

[0088] The error detection unit of the learning model obtains the error between the output data Y calculated by the neural network according to the input data X input to the input layer and output from the output layer, and the teacher data T, and calculates the loss L representing the error using the loss function.

[0089] The update unit updates the connection weight coefficients between the nodes of the neural network so that the loss becomes small (so that the loss L approaches 0) based on the loss L obtained by the above-described error detection unit. For example, this update unit uses the error backpropagation method to update the connection weight coefficients between the nodes of the neural network. The error backpropagation method is a method of adjusting the connection weight coefficients between the nodes of each neural network so that the above error becomes small.

[0090] Hereinafter, the learning process will be described with reference to FIG. 5B. In the machine learning server 102 of the present embodiment, the learning data generation unit 413 first prepares a large number of learning data 50 in which "input data (X) with known correct values (teacher data)" and "teacher data (T)" are set (step S1).

[0091] Next, the machine learning unit 414 inputs the input data X corresponding to the teacher data T to the learning model W (step S2), and obtains the output data Y by the calculation of the learning model W (step S3) (step S4). Next, the machine learning unit 414 obtains the error between the output data Y and the teacher data T, and calculates the loss L representing the error using the loss function (step S5). Next, the machine learning unit 414 updates the connection weight coefficients between the nodes of the neural network so that the loss becomes small based on the loss L (step S6).

[0092] In the present embodiment, by adjusting the connection weight coefficients between the nodes of the neural network in this way, a highly accurate learning model W is obtained. In the following embodiments, this process is called the learning process, and the learning model adjusted through this learning process is called the "trained model".

[0093] Further, the learning data 50 in the present embodiment may be data in which the state information of the image forming apparatus 100 when the transfer belt 15 is replaced and determined to have reached the end of its life is used as the input data X, and the teacher data T "no remaining life of the transfer belt 15" is set.

[0094] In the present embodiment, by using such learning data, the learning model W can be machine-learned about the relationship between the state of the image forming apparatus 100 indicated by the state information and the remaining life of the transfer belt 15. In other words, in the present embodiment, a learned model can be generated that takes the state information of the image forming apparatus 100 as input and outputs the remaining life of the transfer belt 15.

[0095] Note that the remaining life in the present embodiment indicates the number of sheets that can be printed until the transfer belt 15 in use reaches a predetermined limit state from the current time.

[0096] Hereinafter, the elements of the learning data of the present embodiment will be described. In the present embodiment, the items included in the state information acquired by the image forming apparatus 100 may be the elements of the learning data.

[0097] Specifically, for example, in the present embodiment, the primary transfer bias and the density adjustment pattern may be the elements of the learning data. In the present embodiment, thereby, the remaining life of the transfer belt 15 taking into account the degree of contamination on the surface of the transfer belt 15 can be obtained.

[0098] Also, in the present embodiment, the interval of the density adjustment pattern may be the element of the learning data. Since the transfer belt 15 is indirectly driven by the transfer drive roller 21, when the back surface of the transfer belt 15 gets dirty, the contact portion with the transfer drive roller 21 slips and the conveyance speed of the transfer belt 15 changes, and the interval of the density adjustment pattern becomes narrower.

[0099] In the present embodiment, paying attention to this point, by using the interval of the density adjustment pattern as an element of the learning data, the remaining life of the transfer belt 15 taking into account the degree of contamination on the back surface of the transfer belt 15 can be obtained.

[0100] Further, in the present embodiment, the temperature and humidity outside the image forming apparatus 100, the temperature and humidity inside the image forming apparatus 100, the difference between the outside temperature and the inside temperature, and the difference between the outside humidity and the inside humidity may be elements of the learning data. Thereby, it is possible to obtain the remaining life of the transfer belt 15 in consideration of the deterioration state of the transfer belt 15 due to the environment and the possibility of image abnormalities occurring.

[0101] Also, in the present embodiment, the running distance and the number of printed sheets of the transfer belt 15 may be elements of the learning data. In the present embodiment, thereby, it is possible to obtain the remaining life of the transfer belt 15 in consideration of the wear state of the transfer belt 15.

[0102] Further, in the present embodiment, the image area ratio may be an element of the learning data. In the present embodiment, thereby, it is possible to obtain the remaining life of the transfer belt 15 in consideration of the deterioration state of the transfer belt 15 due to the environment and the possibility of image abnormalities occurring.

[0103] Also, in the present embodiment, the paper size as the recording medium on which the image is formed may be an element of the learning data. The transfer belt 15 is damaged at the edge of the paper. For this reason, for example, in the paper passed through the image forming apparatus 100, when there are many papers of a specific size, the portion of the transfer belt 15 that contacts the edge of the specific paper deteriorates faster than other portions.

[0104] In the present embodiment, paying attention to this point, by making the paper size an element of the learning data, it is possible to obtain the remaining life of the transfer belt 15 in consideration of the deterioration of the transfer belt 15 caused by the paper size.

[0105] Also, in the present embodiment, the image pattern formed by the image forming apparatus 100 may be an element of the learning data. For example, the same image pattern may be formed at a specific location on the transfer belt 15, such as a ruled line in a standard format. In such a case, a specific location on the transfer belt 15 deteriorates faster than other locations.

[0106] In this embodiment, paying attention to this point, by using an image pattern as an element of learning data, it is possible to obtain the remaining life of the transfer belt 15, taking into account the deterioration of the transfer belt 15 caused by the formation of many specific image patterns.

[0107] Also, in this embodiment, the torque of the transfer driving roller 21 may be used as an element of the learning data. The torque of the transfer driving roller 21 decreases when the back surface of the transfer belt 15 gets dirty, and increases when the back surface of the transfer belt 15 wears.

[0108] In this embodiment, paying attention to this point, by using the torque of the transfer driving roller 21 as an element of the learning data, it is possible to obtain the remaining life of the transfer belt 15, taking into account the state of the back surface of the transfer belt 15.

[0109] Also, in this embodiment, the usage environment of the user of the image forming apparatus 100 may be used as an element of the learning data. In this embodiment, thereby, it is possible to obtain the remaining life of the transfer belt 15, taking into account busy periods, slack periods, etc.

[0110] Also, in this embodiment, the history of the replacement of the past transfer belt 15 may be used as an element of the learning data. In this embodiment, thereby, it is possible to obtain the remaining life of the transfer belt 15, taking into account the usage method of the image forming apparatus 100 by the user.

[0111] Next, with reference to FIG. 6, the operation of the image forming system 1000 of this embodiment will be described. FIG. 6 is a sequence diagram for explaining the operation of the image forming system.

[0112] The processes from step S601 to step S607 in FIG. 6 show the process of generating a learned model. Also, the processes from step S608 to step S613 in FIG. 6 show the process of predicting the life of the transfer belt 15 for the image forming apparatus 100. The process of generating a learned model and the process of predicting the life of the transfer belt 15 may be executed at different timings as independent processes.

[0113] First, a process of generating a learned model will be described.

[0114] The image forming apparatus 100 according to the present embodiment acquires the state information of the image forming apparatus 100 by the apparatus state acquisition unit 407 (step S601), and transmits it to the data server 105 (step S602). Note that the image forming apparatus 100 may acquire the state information by the apparatus state acquisition unit 407 and transmit it to the data server 105 every time, for example, a job is executed. Further, the image forming apparatus 100 stores the state information acquired by the apparatus state acquisition unit 407 every time a job is executed in the data storage unit 401, and periodically or at an arbitrary timing, transmits the state information stored in the data storage unit 401 to the data server 105.

[0115] The data server 105 acquires the state information by the data collection / providing unit 410 (step S603), and stores it in the data storage unit 412 (step S604).

[0116] Further, the data server 105 transmits the state information acquired from the image forming apparatus 100 to the machine learning server 102 by the data collection / providing unit 410 (step S605). Note that the data server 105 may transmit the state information to the machine learning server 102 when the amount of the state information stored in the data storage unit 412 becomes a certain amount or more.

[0117] When the machine learning server 102 acquires the state information, the learning data generation unit 413 generates learning data (step S605). The learning data generation unit 413 according to the present embodiment may use, for example, the state information when the transfer belt 15 is replaced or the state information when the transfer belt 15 is maintained as learning data.

[0118] Subsequently, the machine learning server 102 performs machine learning using the learning data generated by the learning data generation unit 413 to generate a learned model (step S606), and transmits the generated learned model to the image forming apparatus 100 (step S607).

[0119] The above is the process of generating a learned model. Note that the learned model transmitted to the image forming apparatus 100 may be held by the prediction processing unit 405.

[0120] Next, a process of predicting the remaining life of the transfer belt 15 will be described.

[0121] The image forming apparatus 100 acquires state information of the image forming apparatus 100 by the apparatus state acquisition unit 407 (step S608).

[0122] Subsequently, the image forming apparatus 100 predicts the remaining life of the transfer belt 15 by the prediction processing unit 405 (step S609). Specifically, the prediction processing unit 405 inputs the acquired state information into the learned model held by the prediction processing unit 405, and obtains the remaining life of the transfer belt 15 as the output of the learned model.

[0123] In this embodiment, the remaining life of the transfer belt 15 may be obtained for each paper width, for example. Specifically, for example, for a paper width such that the short side of the A4 size is perpendicular to the paper feed direction, the remaining number of printable copies, and for a paper width such that the long side of the A4 size is perpendicular to the paper feed direction. The remaining life of the transfer belt 15 may be obtained as the remaining number of printable copies.

[0124] Subsequently, the image forming apparatus 100 performs control according to the prediction result by the machine control unit 411 (step S610). Details of the control in step S610 will be described later.

[0125] As described above, in this embodiment, since the remaining life of the transfer belt 15 is predicted from the state information of the image forming apparatus 100, the accuracy of the prediction can be improved.

[0126] Note that in the example of FIG. 6 described above, the learned model generated by the machine learning server 102 is transmitted to the image forming apparatus 100, and the image forming apparatus 100 holds the learned model, but the present invention is not limited to this.

[0127] The learned model may remain held in the machine learning server 102 and may not be transmitted to the image forming apparatus 100. In that case, the prediction processing unit 405 of the image forming apparatus 100 transmits the state information to the machine learning server 102. When receiving the state information, the machine learning server 102 inputs the received state information into the learned model, obtains the remaining life of the transfer belt 15, and may notify the image forming apparatus 100 of the remaining life of the transfer belt 15 as a prediction result.

[0128] Next, control according to the prediction result by the machine control unit 411 of the present embodiment will be described.

[0129] The machine control unit 411 of the present embodiment may, for example, display the remaining life of the transfer belt 15 on the operation panel 940. The machine control unit 411 may display the remaining life of the transfer belt 15 as the remaining number of printable sheets, or may display it as the remaining number of available days.

[0130] The remaining number of available days is obtained by dividing the remaining number of printable sheets, which is obtained as the remaining life of the transfer belt 15, by the number of printed sheets per day.

[0131] Specifically, for example, when the remaining number of printable sheets indicated by the remaining life is 1000 sheets and the number of printed sheets per day is 10 sheets, the remaining number of days is 100 days. Note that the number of printed sheets per day may be calculated from the history information stored in the data storage unit 401 or the like.

[0132] Further, the machine control unit 411 of the present embodiment may, for example, place an order for a new transfer belt 15 when the remaining number of available days of the transfer belt 15 becomes equal to or less than a predetermined number of days, or when the remaining number of printable sheets becomes equal to or less than a predetermined number of sheets.

[0133] Specifically, the machine control unit 411 pre-holds a threshold value for determining whether to order the transfer belt 15 with respect to the remaining available days or the remaining number of printable sheets of the transfer belt 15, and may place an order according to the determination result. When placing an order, the machine control unit 411 may transmit, for example, the part number etc. that identifies the transfer belt 15 mounted on the image forming apparatus 100 to an information processing apparatus etc. managed by the provider of the transfer belt 15 via an Internet line or the like. Further, the machine control unit 411 may display a message instructing the order of the transfer belt 15 on the operation panel 940 of the image forming apparatus 100.

[0134] Furthermore, for example, when the remaining number of printable sheets for a certain paper width becomes equal to or less than a predetermined number, or when the life has been reached (the remaining number of printable sheets is 0), the machine control unit 411 of the present embodiment performs alternative printing using paper with a width different from this paper width.

[0135] Hereinafter, with reference to FIG. 7, the alternative printing by the machine control unit 411 will be described. FIG. 7 is a diagram for explaining the alternative printing by the machine control unit.

[0136] In the example of FIG. 7, a case is shown where the remaining number of printable sheets for the paper width overlapping the area 15a has reached the end of life due to deterioration of the area 15a on the surface of the transfer belt 15.

[0137] In this case, for example, when printing is instructed for the paper 71 whose paper width overlaps the area 15a, the machine control unit 411 may change the paper 71 to the paper 72 and perform printing. The paper 72 is a paper with a paper width that does not overlap the area 15a and whose remaining number of printable sheets has not reached the end of life. Note that the paper 71 and the paper 72 may be the same A4 size paper.

[0138] In the present embodiment, by performing alternative printing in this way, the period until the transfer belt 15 is replaced can be extended.

[0139] Note that in the above-described embodiment, the generation of the learned model is performed by the machine learning server 102, but it is not limited to this.

[0140] The functions of the machine learning server 102 and the data server 105 may be provided in the image forming apparatus 100.

[0141] Next, with reference to FIG. 8, another example of the image forming apparatus 100 will be described. FIG. 8 is a diagram showing another example of the functional configuration of the image forming apparatus.

[0142] The image forming apparatus 100A shown in FIG. 8 includes, in addition to the functions of the image forming apparatus 100 shown in FIG. 4, a learning data generation unit 413 and a machine learning unit 414 included in the machine learning server 102, and a data collection / providing unit 410 including the data server 105.

[0143] Thus, by providing the learning data generation unit 413 and the machine learning unit 414 in the image forming apparatus 100A, the image forming apparatus 100A can generate a learned model by itself.

[0144] Further, when the image forming apparatus included in the image forming system 1000 has a data collection / providing unit 410, a learning data generation unit 413, and a machine learning unit 414 like the image forming apparatus 100A, the image forming system 1000 may not include the machine learning server 102 and the general-purpose computer 103.

[0145] Also, in the present embodiment, a learned model is generated using state information indicating the state of the image forming apparatus 100 as learning data, and the life of the transfer belt 15 is predicted using the learned model. However, the member of the apparatus whose life is the target is not limited to this.

[0146] The machine learning server 102 of the present embodiment may, for example, acquire state information of a specific apparatus other than the image forming apparatus, and generate a learned model for predicting the life of a member included in the specific apparatus. Thus, the present embodiment can be applied to an apparatus capable of acquiring state information indicating the state of an apparatus and a member included in the apparatus.

[0147] Note that each function of the embodiments described above can be realized by one or more processing circuits. Here, the "processing circuit" in this specification refers to a processor programmed to execute each function by software, such as a processor implemented by an electronic circuit, an ASIC (Application Specific Integrated Circuit) designed to execute each function described above, a DSP (digital signal processor), an FPGA (field programmable gate array), and devices such as conventional circuit modules.

[0148] Also, the device groups described in each embodiment merely represent one of a plurality of computing environments for executing the embodiments disclosed in this specification.

[0149] In one embodiment, the machine learning server 102 and the image forming apparatus 100 include a plurality of computing devices such as a server cluster. The plurality of computing devices are configured to communicate with each other via an arbitrary type of communication link including a network and a shared memory, and execute the processes disclosed in this specification. Similarly, the machine learning server 102 and the image forming apparatus 100 can include a plurality of computing devices configured to communicate with each other.

[0150] Furthermore, the machine learning server 102 and the image forming apparatus 100 can be configured to share the disclosed processing steps in various combinations. For example, a process executed by a predetermined unit can be executed by the machine learning server 102 and the image forming apparatus 100. Similarly, the functions of a predetermined unit can be executed by each of the machine learning server 102 and the image forming apparatus 100. Also, in each of the machine learning server 102 and the image forming apparatus 100, each element they have may be grouped into one server device or divided into a plurality of devices.

[0151] Note that the image forming apparatus 100 may be any apparatus having a communication function. The image forming apparatus 100 may be, for example, an output device such as a PJ (Projector), a digital signage, a HUD (Head Up Display) device, an industrial machine, an imaging device, a sound collecting device, a medical device, a network home appliance, an automobile (Connected Car), a notebook PC (Personal Computer), a mobile phone, a smartphone, a tablet terminal, a game machine, a PDA (Personal Digital Assistant), a digital camera, a wearable PC, or a desktop PC.

[0152] Aspects of the present invention are as follows, for example. <1> An image forming system including an image forming apparatus having an image carrier, an image forming unit that forms a toner image on the surface of the image carrier, and an intermediate transfer member that rotates while contacting the image carrier, and an information processing apparatus capable of communicating with the image forming apparatus, wherein the image forming apparatus has a device state acquisition unit that acquires state information indicating the state of the image forming apparatus, a prediction processing unit that predicts the life of the intermediate transfer member using a learned model obtained by machine learning the state information as learning data, and a machine control unit that calculates the remaining available days of the intermediate transfer member according to the prediction result by the prediction processing unit, wherein the information processing apparatus has a machine learning unit that generates the learned model by machine learning the learning data generated from the state information, wherein the state information includes a primary transfer bias supplied when transferring the toner image from the image carrier to the intermediate transfer member, and an image forming system. <2> An image forming system including an image forming apparatus having an image carrier, an image forming unit that forms a toner image on the surface of the image carrier, and an intermediate transfer member that rotates while contacting the image carrier, and an information processing apparatus capable of communicating with the image forming apparatus, wherein the image forming apparatus An apparatus state acquisition unit that acquires state information indicating the state of the image forming apparatus; A prediction processing unit that predicts the remaining life of the intermediate transfer body using a learned model obtained by machine learning with the state information as learning data; A machine control unit that calculates the remaining available days of the intermediate transfer body according to the prediction result by the prediction processing unit, and has: The information processing apparatus A machine learning unit that generates the learned model by machine learning of the learning data generated from the state information; The state information An image forming system including a density adjustment pattern for adjusting the density of an image formed on the surface of the intermediate transfer body. <3> An image forming system including an image forming apparatus having an image carrier, an image forming means for forming a toner image on the surface of the image carrier, and an intermediate transfer body that rotates while contacting the image carrier, and an information processing apparatus capable of communicating with the image forming apparatus, The image forming apparatus An apparatus state acquisition unit that acquires state information indicating the state of the image forming apparatus; A prediction processing unit that predicts the remaining life of the intermediate transfer body using a learned model obtained by machine learning with the state information as learning data; A machine control unit that calculates the remaining available days of the intermediate transfer body according to the prediction result by the prediction processing unit, and has: The information processing apparatus A machine learning unit that generates the learned model by machine learning of the learning data generated from the state information; The state information An image forming system including an interval of a density adjustment pattern for adjusting the density of an image formed on the surface of the intermediate transfer body. <4> An image forming system including an image forming apparatus having an image carrier, an image forming means for forming a toner image on the surface of the image carrier, and an intermediate transfer body that rotates while contacting the image carrier, and an information processing apparatus capable of communicating with the image forming apparatus, The image forming apparatus includes an apparatus state acquisition unit that acquires state information indicating the state of the image forming apparatus, a prediction processing unit that predicts the remaining life of the intermediate transfer body using a learned model obtained by machine learning the state information as learning data, and a machine control unit that calculates the remaining available days of the intermediate transfer body according to the prediction result by the prediction processing unit. The information processing apparatus includes a machine learning unit that generates the learned model by machine learning the learning data generated from the state information. The state information includes the temperature and humidity outside the housing of the image forming apparatus, the temperature and humidity inside the housing of the image forming apparatus, the difference between the temperature outside the housing and the temperature inside the housing, and the difference between the humidity outside the housing and the humidity inside the housing, in an image forming system. <5> The state information includes the running distance of the intermediate transfer body and the number of printed sheets by the image forming apparatus, in the image forming system according to any one of <1> to <4>. <6> The state information includes an image area ratio indicating the ratio of the portion where the toner image is formed to the unit area of the recording medium, in the image forming system according to any one of <1> to <5>. <7> The state information includes information indicating the size of the recording medium, the pattern of the image formed on the recording medium, and the torque of the transfer driving roller that rotationally drives the intermediate transfer body, in the image forming system according to any one of <1> to <6>. <8> The state information includes information indicating the usage environment of the user of the image forming apparatus, and the information indicating the usage environment of the user includes information indicating a busy period and a slack period, in the image forming system according to any one of <1> to <7>. <9> The state information An image forming system according to any one of <1> to <8>, including information indicating the replacement history of the intermediate transfer body. <10> The image forming apparatus has a display device, The machine control unit, An image forming system according to any one of <1> to <9>, wherein when the remaining available days of the intermediate transfer body become equal to or less than a predetermined number of days, a notification instructing replacement of the intermediate transfer body is displayed on the display device. <11> The machine control unit, An image forming system according to any one of <1> to <10>, wherein when the remaining available days of the intermediate transfer body become equal to or less than a predetermined number of days, an order for the intermediate transfer body is placed. <12> The prediction processing unit, Predicts the life of the intermediate transfer body for each paper width of the recording medium, The machine control unit, When a print instruction for a recording medium of a certain paper width is received, if the intermediate transfer body reaches the life for the recording medium of the certain paper width, the print instruction is executed using a recording medium of a paper width different from the certain paper width. An image forming system according to any one of <1> to <11>. <13> An image forming apparatus having an image carrier, an image forming means for forming a toner image on the surface of the image carrier, and an intermediate transfer body that rotates while being in contact with the image carrier. An apparatus state acquisition unit that acquires state information including a primary transfer bias supplied when transferring the toner image from the image carrier to the intermediate transfer body, A prediction processing unit that predicts the life of the intermediate transfer body using a learned model that has been machine-learned with the state information as learning data, A machine control unit that calculates the remaining available days of the intermediate transfer body according to the prediction result by the prediction processing unit. <14> An image forming system including an image forming apparatus having an image carrier, an image forming means for forming a toner image on the surface of the image carrier, and an intermediate transfer member that rotates while contacting the image carrier, and an information processing apparatus capable of communicating with the image forming apparatus, the method comprising: the image forming apparatus acquires state information indicating the state of the image forming apparatus, predicts the life of the intermediate transfer member using a learned model obtained by machine learning the state information as learning data, calculates the remaining available days of the intermediate transfer member according to the prediction result, the information processing apparatus generates the learned model by machine learning the learning data generated from the state information, the state information includes a primary transfer bias supplied when transferring the toner image from the image carrier to the intermediate transfer member, the method. <15> In an image forming apparatus having an image carrier, an image forming means for forming a toner image on the surface of the image carrier, and an intermediate transfer member that rotates while contacting the image carrier, acquires state information including a primary transfer bias supplied when transferring the toner image from the image carrier to the intermediate transfer member, predicts the life of the intermediate transfer member using a learned model obtained by machine learning the state information as learning data, A program for causing execution of a process of calculating the remaining available days of the intermediate transfer member according to the prediction result.

[0153] Although the present invention has been described based on each embodiment above, the present invention is not limited to the requirements shown in the above embodiments. In these respects, it can be changed without departing from the gist of the present invention, and can be appropriately determined according to the application form.

Explanation of Reference Numerals

[0154] 100, 100A Image forming apparatus 102 Machine learning server 103 General-purpose computer 105 Data server 401, 412, 415 Data storage unit 403 JOB control unit 404 Pattern reading unit 405 Prediction processing unit 406 Counter unit 407 Device state acquisition unit 410 Data collection and provision unit 411 Machine control unit 413 Learning data generation unit 414 Machine learning unit 1000 Image forming system

Prior art documents

Patent documents

[0155]

Patent Document 1

Claims

1. An image forming system including an image forming apparatus having an image carrier, an image forming means for forming a toner image on the surface of the image carrier, and an intermediate transfer member that rotates while contacting the image carrier, and an information processing apparatus capable of communicating with the image forming apparatus, wherein the image forming apparatus, has a device state acquisition unit that acquires state information indicating the state of the image forming apparatus, a prediction processing unit that predicts the life of the intermediate transfer member using a learned model that has been machine-learned with the state information as learning data, and a machine control unit that calculates the remaining available days of the intermediate transfer member according to the prediction result by the prediction processing unit, and the information processing apparatus, has a machine learning unit that machine-learns the learning data generated from the state information to generate the learned model, wherein the state information, includes a primary transfer bias supplied when transferring the toner image from the image carrier to the intermediate transfer member, an image forming system.

2. An image forming system including an image forming apparatus having an image carrier, an image forming means for forming a toner image on the surface of the image carrier, and an intermediate transfer member that rotates while contacting the image carrier, and an information processing apparatus capable of communicating with the image forming apparatus, wherein the image forming apparatus, has a device state acquisition unit that acquires state information indicating the state of the image forming apparatus, a prediction processing unit that predicts the life of the intermediate transfer member using a learned model that has been machine-learned with the state information as learning data, and a machine control unit that calculates the remaining available days of the intermediate transfer member according to the prediction result by the prediction processing unit, and the information processing apparatus, has a machine learning unit that machine-learns the learning data generated from the state information to generate the learned model, wherein the state information, includes a density adjustment pattern for adjusting the density of an image formed on the surface of the intermediate transfer member, an image forming system.

3. An image forming system including an image forming apparatus having an image carrier, an image forming means for forming a toner image on the surface of the image carrier, and an intermediate transfer member that rotates while contacting the image carrier, and an information processing apparatus capable of communicating with the image forming apparatus, wherein the image forming apparatus, has a device state acquisition unit that acquires state information indicating the state of the image forming apparatus, a prediction processing unit that predicts the life of the intermediate transfer member using a learned model that has been machine-learned with the state information as learning data, A machine control unit that calculates the remaining available days of the intermediate transfer body according to the prediction result by the prediction processing unit, The information processing apparatus, A machine learning unit that generates the learned model by performing machine learning on the learning data generated from the state information, The state information, An image forming system including an interval of a density adjustment pattern for adjusting the density of an image formed on the surface of the intermediate transfer body.

4. An image forming system including an image forming apparatus having an image carrier, an image forming means for forming a toner image on the surface of the image carrier, and an intermediate transfer body that rotates while contacting the image carrier, and an information processing apparatus capable of communicating with the image forming apparatus, The image forming apparatus, An apparatus state acquisition unit that acquires state information indicating the state of the image forming apparatus, A prediction processing unit that predicts the life of the intermediate transfer body using a learned model obtained by performing machine learning on the state information as learning data, A machine control unit that calculates the remaining available days of the intermediate transfer body according to the prediction result by the prediction processing unit, The information processing apparatus, A machine learning unit that generates the learned model by performing machine learning on the learning data generated from the state information, The state information, An image forming system including the temperature and humidity outside the housing of the image forming apparatus, the temperature and humidity inside the housing of the image forming apparatus, the difference between the temperature outside the housing and the temperature inside the housing, and the difference between the humidity outside the housing and the humidity inside the housing.

5. The state information, The image forming system according to any one of claims 1 to 4, including the running distance of the intermediate transfer body and the number of printed sheets by the image forming apparatus.

6. The state information, The image forming system according to any one of claims 1 to 4, including an image area ratio indicating a ratio occupied by a portion where the toner image is formed per unit area of the recording medium.

7. The state information, The image forming system according to any one of claims 1 to 4, including information indicating the size of the recording medium, the pattern of the image formed on the recording medium, and the torque of the transfer driving roller that rotationally drives the intermediate transfer body.

8. The state information, The image forming system according to any one of claims 1 to 4, including information indicating the usage environment of the user of the image forming apparatus, and the information indicating the usage environment of the user includes information indicating a busy period and a slack period.

9. The state information, The image forming system according to any one of claims 1 to 4, including information indicating the replacement history of the intermediate transfer body.

10. The image forming apparatus has a display device, The machine control unit, When the remaining available days of the intermediate transfer body become equal to or less than a predetermined number of days, a notification instructing replacement of the intermediate transfer body is displayed on the display device. The image forming system according to any one of claims 1 to 4.

11. The machine control unit, When the remaining available days of the intermediate transfer body become equal to or less than a predetermined number of days, an order for the intermediate transfer body is placed. The image forming system according to any one of claims 1 to 4.

12. The prediction processing unit, Predicts the life of the intermediate transfer body for each paper width of the recording medium, The machine control unit, When a print instruction for a recording medium of a certain paper width is received, if the intermediate transfer body reaches the life for the recording medium of the certain paper width, the print instruction is executed using a recording medium of a paper width different from the certain paper width. The image forming system according to any one of claims 1 to 4.

13. An image forming apparatus having an image carrier, an image forming means for forming a toner image on the surface of the image carrier, and an intermediate transfer body that rotates while contacting the image carrier, An apparatus state acquisition unit that acquires state information including a primary transfer bias supplied when transferring the toner image from the image carrier to the intermediate transfer body, A prediction processing unit that predicts the life of the intermediate transfer body using a learned model that has been machine-learned with the state information as learning data, A machine control unit that calculates the remaining available days of the intermediate transfer body according to the prediction result of the prediction processing unit.

14. A method by an image forming system including an image forming apparatus having an image carrier, an image forming means for forming a toner image on the surface of the image carrier, and an intermediate transfer body that rotates while contacting the image carrier, and an information processing apparatus capable of communicating with the image forming apparatus, The image forming apparatus, Acquires state information indicating the state of the image forming apparatus, Predicts the life of the intermediate transfer body using a learned model that has been machine-learned with the state information as learning data, Calculates the remaining available days of the intermediate transfer body according to the prediction result, The information processing apparatus, Machine-learns the learning data generated from the state information to generate the learned model, The state information is, A method including a primary transfer bias supplied when transferring the toner image from the image carrier to the intermediate transfer member.

15. In an image forming apparatus having an image carrier, an image forming means for forming a toner image on the surface of the image carrier, and an intermediate transfer member that rotates while contacting the image carrier, acquire state information including a primary transfer bias supplied when transferring the toner image from the image carrier to the intermediate transfer member, predict the life of the intermediate transfer member using a learned model that has been machine-learned with the state information as learning data, A program that causes execution of a process of calculating the remaining available days of the intermediate transfer member according to the prediction result.

Images