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

Abstract

To improve the accuracy of estimating residual toner levels. [Solution] The image forming apparatus is an image forming apparatus for forming a toner image on a sheet, comprising: an image carrier that carries the toner image; a cleaning member that collects residual toner that remains on the image carrier without being transferred; an image reading unit that reads the toner image formed on the sheet; and a control unit that controls the operation of the image forming apparatus, wherein the control unit includes a first estimation unit that identifies the type of abnormal image based on the difference between the formed image data of the toner image formed on the sheet and the read image data of the toner image formed on the sheet and read by the image reading unit, and estimates the amount of residual toner caused by the identified abnormal image.

Description

Technical Field

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

Background Art

[0002] An image forming apparatus that forms a toner image on a sheet is known.

[0003] For example, Patent Document 1 discloses a technique in which the toner amount of a chart formed on a sheet is detected by a toner adhesion amount detection device, and the residual toner amount is calculated by estimating the toner transfer rate from the detected toner amount of the chart.

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the technique of Patent Document 1, in the toner image formed on the sheet, the remaining amount of residual toner due to an abnormal image generated by a scratch or the like on the image carrier cannot be estimated. As a result, the estimation accuracy of the residual toner amount may be low.

[0005] An object of the present disclosure is to improve the estimation accuracy of the residual toner amount.

Means for Solving the Problems

[0006] An image forming apparatus according to an aspect of the present disclosure is an image forming apparatus that forms a toner image on a sheet, including an image carrier that carries the toner image, a cleaning member that collects residual toner remaining on the image carrier without being transferred, an image reading unit that reads the toner image formed on the sheet, and a control unit that controls the operation of the image forming apparatus. The control unit includes a first estimation unit that identifies the type of an abnormal image based on the difference between the formation image data of the toner image to be formed on the sheet and the read image data of the toner image formed on the sheet and read by the image reading unit, and estimates the residual toner amount of the residual toner caused by the identified abnormal image. [Effects of the Invention]

[0007] According to this disclosure, the accuracy of estimating the amount of residual toner can be improved. [Brief explanation of the drawing]

[0008] [Figure 1] This is a schematic cross-sectional view showing the overall configuration of the image forming apparatus according to the first embodiment. [Figure 2] This is a block diagram showing the hardware configuration of an image forming apparatus according to the first embodiment. [Figure 3] This is a block diagram showing the functional configuration of the controller in the image forming apparatus according to the first embodiment. [Figure 4] This figure shows an example of formed image data in the image forming apparatus according to the first embodiment. [Figure 5] This figure shows a first example of read image data including an abnormal image in an image forming apparatus according to the first embodiment. [Figure 6] This figure shows a second example of read image data including an abnormal image in the image forming apparatus according to the first embodiment. [Figure 7] This is a flowchart showing the estimation operation of the residual toner amount in the image forming apparatus according to the first embodiment. [Figure 8] This is a block diagram showing the functional configuration of the controller in the image forming apparatus according to the second embodiment. [Figure 9] This is a schematic diagram of the neuron learning model in the image forming apparatus according to the second embodiment. [Figure 10] This is a schematic diagram of the neural network learning model in the image forming apparatus according to the second embodiment. [Figure 11] This is a flowchart showing the operation of generating a learning model by an image forming apparatus according to the second embodiment. [Figure 12] This figure shows an example of a training dataset used in generating a learning model for an image forming apparatus according to the second embodiment. [Figure 13]This flowchart shows the operation of creating abnormal image management information by the image forming apparatus according to the second embodiment. [Figure 14] This figure shows an example of abnormal image management information in an image forming apparatus according to the second embodiment. [Figure 15] This is a flowchart showing the estimation operation of the residual toner amount by the image forming apparatus according to the second embodiment. [Figure 16] This is a block diagram showing the functional configuration of the controller in the image forming apparatus according to the third embodiment. [Figure 17] This is a flowchart showing the additional learning operation by the image forming apparatus according to the third embodiment. [Figure 18] This is a block diagram showing the functional configuration of the controller in the image forming apparatus according to the fourth embodiment. [Figure 19] This is a schematic diagram showing the overall configuration of the image forming system according to the fifth embodiment. [Figure 20] This is a block diagram showing the hardware configuration of a server in the image forming system according to the fifth embodiment. [Figure 21] This is a block diagram showing the functional configuration of the controller of the image forming apparatus in the image forming system according to the fifth embodiment. [Figure 22] This is a block diagram showing the functional configuration of the server in the image forming system according to the fifth embodiment. [Modes for carrying out the invention]

[0009] The image forming apparatus, image forming method, and program according to the embodiments of this disclosure will be described in detail with reference to the drawings. However, the embodiments shown below are illustrative and not limited to those described below. Note that the size, positional relationships, etc., of the components shown in each drawing may be exaggerated for clarity of explanation.

[0010] In the following description, terms indicating a specific direction or position (for example, "up", "down", and other terms including these terms) may be used. However, these terms are merely used for ease of understanding of the relative direction or position in the referenced drawings. As long as the relative direction or position relationship based on terms such as "up" and "down" in the referenced drawings is the same, in drawings other than the present disclosure, actual products, etc., they do not have to be arranged in the same manner as the referenced drawings. In the following description, the same names and reference numerals indicate the same or similar members, and detailed descriptions will be omitted as appropriate. Also, "arrange" is not limited to the case of direct contact, but also includes the case of arranging indirectly, for example, through other members.

[0011] [First Embodiment] <Configuration of the Image Forming Apparatus According to the First Embodiment> (Overall Configuration) FIG. 1 is a schematic cross-sectional view showing the overall configuration of an image forming apparatus 1 according to the first embodiment.

[0012] The image forming apparatus 1 shown in FIG. 1 is a printer that forms a toner image on a sheet P. The sheet P is, for example, paper. A toner image refers to an image formed using toner. However, the image forming apparatus according to the embodiments of the present disclosure is not limited to a printer, and may be an MFP (Multifunction Peripheral), a copying machine, a facsimile apparatus, etc., as long as it is an apparatus capable of forming a toner image on the sheet P. Also, the sheet P is not limited to paper, and may be a sheet or film etc. configured to contain resin etc. Toner images include color toner images using yellow toner, magenta toner, cyan toner, black toner, etc., or monochrome toner images using only any one of yellow toner, magenta toner, cyan toner, or black toner. Note that hereinafter, for simplicity of explanation, yellow may be represented as Y, cyan as C, magenta as M, and black as K.

[0013] As shown in Figure 1, the image forming apparatus 1 has photoreceptor drums (231Y, 231C, 231M, 231K) and an intermediate transfer belt 243, each carrying a toner image. The image forming apparatus 1 also has cleaning members (236Y, 236C, 236M, 236K) for collecting residual toner that remains on at least one of the photoreceptor drums (231Y, 231C, 231M, 231K) and the intermediate transfer belt 243 without being transferred. Furthermore, the image forming apparatus 1 has an image reading unit 270 for reading the toner image formed on the sheet P. Each of the photoreceptor drums (231Y, 231C, 231M, 231K) and the intermediate transfer belt 243 corresponds to an example of an image carrier that carries a toner image.

[0014] The photoconductor drum 231Y is a photoconductor drum used in image formation using Y toner. The photoconductor drum 231C is a photoconductor drum used in image formation using C toner. The photoconductor drum 231M is a photoconductor drum used in image formation using M toner. The photoconductor drum 231K is a photoconductor drum used in image formation using K toner. In the following description, when referring to any of the photoconductor drums (231Y, 231C, 231M, 231K), it may be referred to as photoconductor drum 231. Also, when referring to any of the cleaning members (236Y, 236C, 236M, 236K), it may be referred to as cleaning member 236.

[0015] In the example shown in Figure 1, the image forming apparatus 1 includes a paper feeding unit 210 that supplies a sheet P to the image forming apparatus 1, a transport unit 220 that transports the sheet P supplied by the paper feeding unit 210, and an imaging unit 230 that forms a toner image on a photoreceptor drum 231. The image forming apparatus 1 also includes a transfer unit 240 that transfers the toner image formed on the photoreceptor drum 231 by the imaging unit 230 to the sheet P transported by the transport unit 220. Furthermore, the image forming apparatus 1 includes a fuser 250 that fixes the toner image transferred to the sheet P by the transfer unit 240 to the sheet P. In addition, the image forming apparatus 1 includes a storage member 260 that stores residual toner collected by a cleaning member 236, and a temperature and humidity detection unit 255 that detects the location where the image forming apparatus 1 is installed.

[0016] Image forming apparatus 1 is a tandem type image forming apparatus having a photoreceptor drum 231 and an intermediate transfer belt 243 as image carriers. However, the image forming apparatus according to the embodiment of this disclosure is not limited to a tandem type, and may be a type that directly transfers the toner image formed on the photoreceptor drum to a sheet P, etc.

[0017] The paper feeding unit 210 includes a paper feed cassette 211 on which the sheets P to be fed are stacked, and a paper feed roller 212 that feeds the sheets P stacked in the paper feed cassette 211 one by one.

[0018] The transport unit 220 has a roller 221 that transports the sheet P fed by the paper feed roller 212 toward the transfer unit 240. The transport unit 220 also has a pair of timing rollers 222 that hold the leading edge of the sheet P transported by the roller 221 and wait, then send the sheet P toward the transfer unit 240 at a predetermined timing. Furthermore, the transport unit 220 has a paper discharge roller 223 that discharges the sheet P on which the color toner image has been fixed toward the paper discharge tray 224.

[0019] The image-forming unit 230 includes an image-forming unit Y that forms an image using a developer containing Y toner, an image-forming unit C that uses a developer containing C toner, an image-forming unit M that uses a developer containing M toner, an image-forming unit K that uses a developer containing K toner, and an exposure unit 233.

[0020] The image forming units Y, C, M, and K are arranged in a cross section including the photoreceptor drum 231, with predetermined intervals between them, in a direction that intersects the vertical direction.

[0021] The exposure unit 233 is located below the image forming units Y, C, M, and K. The developer contains toner and a carrier. The four image forming units (Y, C, M, K) are substantially identical in their mechanical configuration, differing only in the developer they use.

[0022] The image forming unit (Y, C, M, K) is rotatable clockwise and has a photoreceptor drum 231 on which an electrostatic latent image and a toner image are formed. The image forming unit (Y, M, C, K) also has chargers (232Y, 232C, 232M, 232K) that uniformly charge the surface of the photoreceptor drum 231. Furthermore, the image forming unit (Y, M, C, K) has a developer (180Y, 180C, 180M, 180K) that develops the electrostatic latent image formed on the surface of the photoreceptor drum 231 by the exposure unit 233 into a toner image using toner of each color. In addition, the image forming unit (Y, M, C, K) has a cleaning member 236 that removes toner remaining on the surface of the photoreceptor drum 231.

[0023] Furthermore, the image forming unit (Y, C, M, K) has toner cartridges (234Y, 234C, 234M, 234K) that contain toner for each color, and sub-hoppers (160Y, 160C, 160M, 160K) for replenishing the toner supplied from the toner cartridges (234Y, 234C, 234M, 234K).

[0024] The toner of each color contained in the toner cartridges (234Y, 234C, 234M, 234K) is discharged by a transport screw and supplied to the sub-hopper 160 via a supply pipe. The sub-hopper 160 transports the toner of each color supplied from the toner cartridges (234Y, 234C, 234M, 234K) and supplies it to the developer 180. The developer 180 uses the toner supplied by the sub-hopper 160 to develop the electrostatic latent image formed on the photoreceptor drum 231.

[0025] Hereafter, when referring to any image forming unit (Y, C, M, K), it may be simply referred to as "image forming unit." When referring to any charger (232Y, 232C, 232M, 232K), it may be simply referred to as "charger 232." When referring to any toner cartridge (234Y, 234C, 234M, 234K), it may be simply referred to as "toner cartridge 234." When referring to any sub-hopper (160Y, 160C, 160M, 160K), it may be simply referred to as "sub-hopper 160." When referring to any developer (180Y, 180C, 180M, 180K), it may be simply referred to as "developer 180."

[0026] The photoreceptor drum 231 is not particularly limited, but examples include inorganic photoreceptor drums such as amorphous silicon photoreceptor drums and selenium photoreceptor drums, and organic photoreceptor drums such as polysilane photoreceptor drums and phthalopolymethine photoreceptor drums. Among these, amorphous silicon photoreceptor drums are preferred in terms of long lifespan.

[0027] The charger 232 is not particularly limited, but examples include known contact chargers equipped with conductive or semiconductive rolls, brushes, films, rubber blades, etc., and non-contact chargers utilizing corona discharge such as Corotron and Scorotron. The charger 232 is preferably positioned in contact with or without contact with the photoreceptor drum 231, and the outer surface of the photoreceptor drum 231 is charged by superimposing DC and AC voltages. Alternatively, the charger 232 is a charging roller positioned in close proximity to the photoreceptor drum 231 via a gap tape and without contact. The charger 232 preferably charges the surface of the photoreceptor drum 231 by superimposing DC and AC voltages onto the charging roller.

[0028] The exposure unit 233 reflects laser light L emitted from the light source 233a based on image information using polygon mirrors 233b (233bY, 233bC, 233bM, 233bK) that are rotated by a motor, and irradiates the photoreceptor drum 231 with the resulting light. The exposure unit 233 can be any type of exposure unit, such as a copying optical system, a rod lens array system, a laser optical system, or a liquid crystal shutter optical system. However, the exposure unit 233 is not particularly limited as long as it is capable of exposing the surface of the photoreceptor drum 231, which has been charged by the charger 232, in the manner of the image to be formed. In addition, a back-facing method may be employed in which the photoreceptor drum 231 is exposed in the manner of the image from the inner side.

[0029] The developer 180 is preferably a developer that contains a developer and applies the developer to the electrostatic latent image by contact or non-contact, and more preferably a developer equipped with a container for the developer. However, the developer 180 is not particularly limited as long as it is capable of developing using a developer. The developer 180 may be a single-color developer or a multi-color developer.

[0030] The cleaning member 236 is preferably equipped with a magnetic brush cleaner, electrostatic brush cleaner, magnetic roller cleaner, blade cleaner, brush cleaner, web cleaner, etc. However, the cleaning member 236 is not particularly limited as long as it is capable of recovering residual toner that remains on the photoreceptor drum 231 and the intermediate transfer belt 243 without being transferred. In the example shown in Figure 1, the cleaning member 236 is positioned to recover residual toner from the photoreceptor drum 231. However, the cleaning member 236 may also be positioned to recover residual toner from the intermediate transfer belt 243. The photoreceptor drum 231 or the intermediate transfer belt 243 from which the toner has been removed by the cleaning member 236 is electrostatically discharged, and the residual potential is removed, thereby completing the series of imaging processes performed on the photoreceptor drum 231. The residual toner recovered by the cleaning member 236 is stored in the storage member 260.

[0031] The transfer unit 240 includes a drive roller 241 and a driven roller 242, and an intermediate transfer belt 243 that can rotate counterclockwise in conjunction with the drive roller 241. The transfer unit 240 also has primary transfer rollers (244Y, 244C, 244M, 244K) positioned opposite the photoreceptor drum 231, with the intermediate transfer belt 243 in between. Furthermore, the transfer unit 240 has secondary opposing rollers 245 and secondary transfer rollers 246 positioned opposite the intermediate transfer belt 243 at the transfer position of the toner image to the sheet P.

[0032] When referring to any of the primary transfer rollers (244Y, 244C, 244M, 244K), it is sometimes simply referred to as primary transfer roller 244. A primary transfer bias with the opposite polarity to the toner polarity is applied to primary transfer roller 244. Meanwhile, the intermediate transfer belt 243 is sandwiched between primary transfer roller 244 and photoreceptor drum 231 to form a primary transfer nip. As a result, the toner images of each color formed on the surface of photoreceptor drum 231 are transferred (primary transfer) onto the intermediate transfer belt 243. As the intermediate transfer belt 243 rotates in the direction of the arrow 243a, the toner images of each color formed on the photoreceptor drum 231 are sequentially transferred onto the intermediate transfer belt 243 to form a color toner image.

[0033] A secondary transfer bias is applied to the secondary transfer roller 246 of the transfer section 240. As a result, the color toner image formed on the intermediate transfer belt 243 is transferred (secondary transfer) to the sheet P sandwiched between the secondary transfer roller 246 and the secondary opposing roller 245 at the secondary transfer nip.

[0034] The fuser unit 250 has a heater inside and includes a fuser belt 251 that heats the sheet P, and a pressure roller 252 that forms a nip by rotatably applying pressure to the fuser belt 251. The fuser unit 250 fixes the color toner image on the sheet P by applying heat and pressure to the color toner image on the sheet P using the fuser belt 251 and the pressure roller 252. The sheet P with the fixed color toner image is discharged into the paper output tray 224 by the paper output roller 223. The image formation process is completed when the sheet P with the fixed color toner image is discharged into the paper output tray 224.

[0035] The temperature and humidity detection unit 255 detects the temperature and humidity inside or outside the image forming apparatus 1 at the location where the image forming apparatus 1 is installed. The temperature and humidity detection unit 255 includes temperature and humidity sensor elements, a processing circuit for processing the detection results from the sensor elements, etc. Various detection methods such as capacitive type or electrical resistance type can be used for the temperature and humidity detection unit 255. Furthermore, if the fuser 250 has a temperature and humidity detection unit used in the fixing operation, that temperature and humidity detection unit may also be used as the temperature and humidity detection unit 255.

[0036] The image reading unit 270 can be positioned at any location between the secondary transfer roller 246 and the paper discharge roller 223. In the example shown in Figure 1, the image reading unit 270 is positioned downstream of the fuser 250 in the conveying direction Pa of the sheet P. The image reading unit 270 reads the toner image fixed to the sheet P and obtains read image data. In the example shown in Figure 1, the image reading unit 270 reads the toner image formed on one side of the conveyed sheet P. However, the image forming apparatus 1 may have a plurality of image reading units 270 arranged to read both sides of the sheet P, and may read the toner images formed on both sides of the conveyed sheet P in parallel.

[0037] The image reading unit 270 is, for example, a CCD (Charge Coupled Device) line sensor in which multiple pixels that output electrical signals corresponding to the received light intensity are arranged in a one-dimensional array. The multiple pixels in the image reading unit 270 are arranged so as to be able to read the entire width of the sheet P in a direction perpendicular to the transport direction Pa of the sheet P. The direction of the pixel arrangement is in a direction that intersects the transport direction Pa of the sheet P.

[0038] The image reading unit 270 includes a pixel array that receives red light (R), a pixel array that receives green light (G), and a pixel array that receives blue light (B). The image reading unit 270 outputs an electrical signal corresponding to the light intensity of the reflected light from the toner image formed on the sheet P, using each colored pixel array. The image reading unit 270 may also be equipped with a light source that illuminates the sheet P. Illuminating the sheet P with light from the light source ensures sufficient brightness when the image reading unit 270 reads the sheet. In addition, the image reading unit 270 may include CMOS (Complementary metal-oxide-semiconductor) or PD (Photodiode) arrays, etc., as pixels instead of a CCD.

[0039] (Hardware configuration) Figure 2 is a block diagram showing the hardware configuration of the image forming apparatus 1. The image forming apparatus 1 includes a controller 910, a short-range communication circuit 920, an engine control unit 930, an operation panel 940, and a network interface 950.

[0040] Controller 910 is an example of a control unit that controls the operation of the image forming apparatus 1. Controller 910 includes the main components of a computer: CPU 901, system memory (MEM-P) 902, northbridge (NB) 903, and southbridge (SB) 904. Controller 910 also includes an ASIC (Application Specific Integrated Circuit) 906, a storage unit called local memory (MEM-C) 907, an HDD (Hard Disk Drive) controller 908, and a storage unit called HD 909. NB 903 and ASIC 906 are connected by an AGP (Accelerated Graphics Port) bus 921.

[0041] The CPU 901 is a processor that realizes each function of the image forming apparatus 1 by reading programs or data stored in ROM 902a or the like onto RAM 902b and executing processing. However, the processor is not limited to the CPU 901, and may be a GPU (Graphics Processing Unit), ASIC, FPGA (Field Programmable Gate Array), etc. The NB 903 is a bridge for connecting the CPU 901 with MEM-P902, SB904, and AGP bus 921, and has a memory controller that controls reading and writing to MEM-P902, as well as a PCI (Peripheral Component Interconnect) master and an AGP target.

[0042] MEM-P902 consists of ROM902a, which is a memory for storing programs and data that realize the various functions of the controller 910, and RAM902b, which is used for program and data deployment and drawing during memory printing. The programs stored in RAM902b may be configured to be provided as installable or executable files recorded on a computer-readable recording medium such as a CD-ROM, CD-R, or DVD.

[0043] SB904 is a bridge for connecting NB903 to PCI devices and peripheral devices. ASIC906 is an integrated circuit (IC) for image processing applications that has hardware elements for image processing and acts as a bridge connecting the AGP bus 921, PCI bus 922, HDD908, and MEM-C907, respectively. This ASIC906 consists of a PCI target and AGP master, an arbiter (ARB) that forms the core of the ASIC906, a memory controller that controls the MEM-C907, multiple DMACs (Direct Memory Access Controllers) that perform image data rotation etc. using hardware logic, and a PCI unit that performs data transfer via PCI bus 922 between the scanner unit 931 and the printer unit 932. Note that the ASIC906 may also be connected to a USB (Universal Serial Bus) interface or an IEEE1394 (Institute of Electrical and Electronics Engineers 1394) interface.

[0044] MEM-C907 is local memory used as a copy image buffer and code buffer. HD909 is storage for storing image data, font data used during printing, and forms. HD909 controls data reading or writing to it according to the control of CPU901. AGP bus 921 is a bus interface for graphics accelerator cards proposed to speed up graphics processing. By allowing AGP bus 921 to directly access MEM-P902 with high throughput, graphics accelerator cards can be made faster.

[0045] The near-field communication circuit 920 has an antenna 920a. The near-field communication circuit 920 is a communication circuit such as NFC (Near Field Communication) or Bluetooth.

[0046] The engine control unit 930 is composed of a scanner unit 931 and a printer unit 932. The operation panel 940 has a panel display unit 940a, such as a touch panel, that displays the current settings or selection screen and accepts input from the operator, and an operation panel 940b consisting of a numeric keypad that accepts setting values ​​for image formation conditions such as density settings and a start key that accepts a copy start instruction. The controller 910 controls the entire image forming apparatus 1, for example, controlling drawing, communication, and input from the operation panel 940. The scanner unit 931 or the printer unit 932 includes an image processing section that performs error diffusion and gamma conversion.

[0047] Furthermore, the image forming apparatus 1 allows the user to sequentially switch between document box function, copy function, printer function, and facsimile function using the application switching key on the operation panel 940. When the document box function is selected, the system switches to document box mode; when the copy function is selected, it switches to copy mode; when the printer function is selected, it switches to printer mode; and when the facsimile mode is selected, it switches to facsimile mode.

[0048] Furthermore, the network interface 950 is an interface for data communication using the communication network 100. The short-range communication circuit 920 and the network interface 950 are electrically connected to the ASIC 906 via the PCI bus 922.

[0049] (Functional Configuration) Figure 3 is a block diagram showing the functional configuration of the controller 910. The controller 910 includes an input unit 10, a storage unit 11, a first estimation unit 12, and an output unit 13.

[0050] The functions of the input unit 10 and output unit 13 are realized by the network I / F 950, engine control unit 930, etc. Alternatively, the functions of the input unit 10 and output unit 13 may be realized by an electronic circuit such as the CPU 901 executing instruction codes stored in a memory such as the ROM 902a, or by an electronic circuit designed for a special purpose performing various processes. The functions of the storage unit 11 are realized by the HD 909, etc. The functions of the first estimation unit 12 are realized by an electronic circuit such as the CPU 901 executing instruction codes stored in a memory such as the ROM 902a, or by an electronic circuit designed for a special purpose performing various processes. However, some of the functions of the first estimation unit 12 may be realized by one or more devices or equipment other than the controller 910. Furthermore, some of the functions of the first estimation unit 12 may be realized by distributed processing between the controller 910 and one or more devices or equipment other than the controller 910.

[0051] The input unit 10 receives information or data from devices or equipment other than the controller 910 by controlling communication with those devices or equipment. The input unit 10 may control communication with devices or equipment other than the controller 910 via a network such as the Internet or a LAN (Local Area Network).

[0052] The storage unit 11 receives and stores the toner image data 111 transmitted by the user of the image forming apparatus 1 via the input unit 10. The storage unit 11 also receives and stores the read image data 112 of the toner image formed on the sheet P and read by the image reading unit 270 via the input unit 10.

[0053] The first estimation unit 12 obtains the formed image data 111 and the read image data 112 by referring to the storage unit 11. The first estimation unit 12 identifies the type of abnormal image based on the difference between the formed image data 111 and the read image data 112, and estimates the amount of residual toner caused by the identified abnormal image. For example, the first estimation unit 12 estimates the amount of residual toner caused by the identified abnormal image using a calculation method corresponding to the type of abnormal image identified. The first estimation unit 12 also calculates the amount of toner A calculated from the formed image data 111, which will be described later, and the amount of toner B calculated from the difference between the amount of toner in the formed image data 111 and the amount of toner in the read image data 112.

[0054] The first estimation unit 12 will now be explained in more detail. The first estimation unit 12 first calculates the standard amount of toner remaining on the photoconductor drum 231 and the intermediate transfer belt 243, respectively, based on the formed image data 111, information regarding the transfer rate from the photoconductor drum 231 to the intermediate transfer belt 243, and information regarding the transfer rate from the photoconductor drum 231 to the sheet P. Specifically, the amount of toner A is calculated by multiplying the amount of toner used for image formation in the formed image data 111 by "1 - transfer rate". If the formed image data 111 is represented in YMCK and the read image data 112 is represented in RGB, either the formed image data 111 or the read image data 112 is converted to match the other so that image difference calculation can be performed.

[0055] The first estimation unit 12 calculates the toner amount B by subtracting the toner amount in the read image data 112 from the toner amount used in the formed image data 111. The first estimation unit 12 also compares the formed image data 111 and the read image data 112. If there is an image in the formed image data 111 that is not in the read image data 112, the first estimation unit 12 adds the toner amount used for that image to the residual toner amount as a transfer defect. However, if there is an image in the read image data 112 that is not in the formed image data 111, and there is no regularity in the transport direction Pa of the sheet P, the first estimation unit 12 does not add the toner amount used for that image to the residual toner amount.

[0056] On the other hand, if a vertical streak image extending in the transport direction Pa of the sheet P is not present in the formed image data 111 but is present in the read image data 112, the first estimation unit 12 determines that the vertical streak image is an abnormal image. The first estimation unit 12 then adds the amount of toner D, obtained by multiplying the travel distance of the photoreceptor drum 231 by the width of the vertical streak image, to the amount of residual toner. The travel distance of the photoreceptor drum 231 is obtained by multiplying the circumference of the photoreceptor drum 231 by the number of rotations of the photoreceptor drum 231.

[0057] Furthermore, in the image forming apparatus 1, deterioration of the photoreceptor drum 231 may cause so-called background staining, where toner adheres to areas on the outer surface of the photoreceptor drum 231 where there is no image data. The first estimation unit 12 can estimate the amount of toner C corresponding to such background staining.

[0058] The first estimation unit 12 can estimate the amount of residual toner mainly by performing the above addition operations. The first estimation unit 12 can output the estimated amount of residual toner to a device or apparatus other than the controller 910 via the output unit 13.

[0059] The output unit 13 outputs information or data from devices or equipment other than the controller 910 by controlling communication with those devices or equipment. The output unit 13 may also control communication with devices or equipment other than the controller 910 via a network such as the Internet or a LAN (Local Area Network).

[0060] <Example of read image data containing abnormal images> (Example 1) Referring to Figures 4 and 5, a first example of read image data 112 including an abnormal image will be described. Figure 4 is a diagram showing an example of formed image data 111 in the image forming apparatus 1. Figure 5 is a diagram showing a first example of read image data 112 including an abnormal image in the image forming apparatus 1. Figure 6 is a diagram showing a second example of read image data 112 including an abnormal image in the image forming apparatus 1.

[0061] Comparing the formed image data 111 shown in Figure 4 with the read image data 112 shown in Figure 5, the vertical streak image E extending in the transport direction Pa of the sheet P is included only in the read image data 112. The vertical streak image E is an example of an abnormal image. The first estimation unit 12 determines that the vertical streak image E is an abnormal image and adds the amount of toner obtained by multiplying the travel distance of the photoreceptor drum 231 by the width of the vertical streak image E to the amount of residual toner, as a method for calculating the amount of residual toner corresponding to the vertical streak image E. In this case, the residual toner on the photoreceptor drum 231 is transferred to the sheet P. Also, residual toner remains even in the parts of the photoreceptor drum 231 where there is no sheet P. Because residual toner remains in the parts of the photoreceptor drum 231 where there is no sheet P, the cleaning member 236 always collects the residual toner while the photoreceptor drum 231 is rotating. The first estimation unit 12 adds the amount of toner obtained by multiplying the travel distance of the photoreceptor drum 231 by the width of the vertical streak image E to the amount of residual toner. This makes it possible to accurately estimate the amount of residual toner caused by the vertical streak image E.

[0062] (Example 2) Figure 6 shows a second example of read image data 112 containing an abnormal image in the image forming apparatus 1. The read image data 112 shown in Figure 6 is generally grayer than the formed image data 111 shown in Figure 4. In the formed image data 111 shown in Figure 4, the overall grayness is an example of an abnormal image. The reason for the overall grayness is background contamination due to deterioration of the photoreceptor drum 231. The first estimation unit 12 calculates the amount of toner C corresponding to such an abnormal image (background contamination) by multiplying the difference in image data between the formed image data 111 and the read image data 112 by (1 - transfer rate) and adds the amount of toner obtained by this multiplication to the residual toner amount. The amount of toner obtained by multiplying the difference in image data between the formed image data 111 and the read image data 112 by (1 - transfer rate) is added to the residual toner amount.

[0063] <Operation of the image forming apparatus according to the first embodiment> Referring to Figure 7, the operation of the image forming apparatus 1 according to the first embodiment will be described. Figure 7 is a flowchart showing the operation of the image forming apparatus 1 in estimating the amount of residual toner. For example, the image forming apparatus 1 starts the operation shown in Figure 7 when it receives formed image data 111 transmitted by the user of the image forming apparatus 1.

[0064] First, in step S11, the image forming apparatus 1 forms a toner image on the sheet P based on the received formed image data 111.

[0065] Next, in step S12, the image forming apparatus 1 reads the toner image formed on the sheet P using the image reading unit 270. As a result, the image forming apparatus 1 obtains toner image data 112. At this time, the image forming apparatus 1 determines the position of the formed image data 111 by setting the intersection of the downstream end of the sheet P in the transport direction Pa and the straight line connecting the downstream end and upstream end of the sheet P in the transport direction Pa as the origin.

[0066] Next, in step S13, the image forming apparatus 1 uses the first estimation unit 12 to calculate the toner amount A, which is a standard amount of residual toner, based on the formed image data 111. The toner amount A is calculated by multiplying the amount of toner used for image formation in the formed image data 111 by "1 - transfer rate".

[0067] Next, in step S14, the image forming apparatus 1 uses the first estimation unit 12 to determine whether the brightness value of the formed image data 111 is greater than the brightness value of the read image data. For example, the first estimation unit 12 compares the brightness value of the image formed area in the formed image data 111 with the brightness value of the corresponding area in the read image data 112. If the brightness value of the read image data 112 is lower as a result of the comparison, the first estimation unit 12 determines that the difference in brightness values ​​has been recovered as residual toner, and sets the amount of toner corresponding to this difference in brightness values ​​as the toner amount B. The image forming apparatus 1 has the brightness values ​​of both the read image data 112 and the formed image data 111 in advance, and can determine the amount of toner attached to the sheet P from the read image data 112.

[0068] In step S14, if it is determined that the brightness value of the formed image data 111 is greater than the brightness value of the read image data (step S14, YES), the image forming apparatus 1 executes step S15. In step S15, the image forming apparatus 1 uses the first estimation unit 12 to calculate the toner amount B from the difference image between the read image data 112 and the formed image data 111. On the other hand, in step S14, if it is determined that the brightness value of the formed image data 111 is not greater than the brightness value of the read image data (step S14, NO), the image forming apparatus 1 proceeds to step S16.

[0069] Next, in step S16, the image forming apparatus 1 determines whether or not there are images in the read image data 112 that are not present in the formed image data 111. If, in step S16, it is determined that there are no images in the read image data 112 that are not present in the formed image data 111 (step S16, NO), the image forming apparatus 1 executes step S17. In step S17, the image forming apparatus 1 uses the first estimation unit 12 to calculate the amount of residual toner from the sum of toner amount A and toner amount B, and uses this as the estimated result of the residual toner amount. After that, the image forming apparatus 1 terminates its operation.

[0070] On the other hand, if in step S16 it is determined that there is an image in the read image data 112 that is not in the formed image data 111 (step S16, YES), the image forming apparatus 1 executes step S18. In step S18, the image forming apparatus 1 determines whether the image that is only in the read image data 112 is a vertical streak image E extending in the transport direction Pa.

[0071] In step S18, if it is determined that the image present only in the read image data 112 is a vertical streak image E (step S18, YES), the image forming apparatus 1 executes step S19. The type of abnormal image is identified based on the presence or absence of the vertical streak image in step S18. In step S19, the image forming apparatus 1 calculates the toner amount D by multiplying the travel distance of the photoreceptor drum 231 by the width of the vertical streak image E using the first estimation unit 12.

[0072] Next, in step S20, the image forming apparatus 1 uses the first estimation unit 12 to calculate the amount of residual toner from the sum of toner amount A, toner amount B, and toner amount D, and uses this as the estimated result of the residual toner amount. After that, the image forming apparatus 1 terminates its operation.

[0073] On the other hand, if in step S18 it is determined that the image present only in the read image data 112 is not the vertical streak image E (step S18, NO), the image forming apparatus 1 executes step S21. In step S21, the image forming apparatus 1 calculates the toner amount C by subtracting the toner amount of the image present only in the read image data from the toner amount / transfer rate of the image present only in the read image data using the first estimation unit 12. In other words, if step S18 is NO, the image present in the read image data 112 but not in the formed image data 111 may be a so-called background stain image, where toner has adhered to an area on the outer surface of the photoreceptor drum 231 where there is no image data, due to the deterioration of the photoreceptor drum 231 as described above. Therefore, the amount of toner C remaining in the photoreceptor drum 231 due to such an abnormal image is calculated.

[0074] Next, in step S22, the image forming apparatus 1 uses the first estimation unit 12 to calculate the amount of residual toner from the sum of toner amount A, toner amount B, and toner amount C, and uses this as the estimated result of the residual toner amount. After that, the image forming apparatus 1 terminates its operation.

[0075] As described above, the image forming apparatus 1 can estimate the amount of residual toner.

[0076] <Effects of the Image Forming Apparatus 1 According to the First Embodiment> In this embodiment, the image forming apparatus 1 uses a first estimation unit 12 to identify the type of abnormal image based on the difference between the formed image data 111 and the read image data 112, and estimates the amount of residual toner caused by the identified abnormal image using a calculation method corresponding to the identified type of abnormal image. As a result, the image forming apparatus 1 can calculate the amount of residual toner caused by the type of abnormal image according to the type of abnormal image, and can estimate the amount of residual toner in more detail. In this embodiment, the estimation accuracy of the amount of residual toner contained in the storage member 260 can be increased.

[0077] The image forming apparatus 1 can appropriately manage the replacement timing of the storage member 260 due to its high accuracy in estimating the amount of residual toner stored in the storage member 260. For example, the image forming apparatus 1 can prompt a service technician or manager to replace the storage member 260 at the appropriate time. Furthermore, the image forming apparatus 1 can reduce waste caused by replacing the storage member 260 before it is full of collected residual toner. In addition, the image forming apparatus 1 can reduce contamination of the image forming apparatus 1 caused by leakage of collected residual toner from a full storage member 260.

[0078] [Second Embodiment] Next, an image forming apparatus according to the second embodiment will be described. Note that names and reference numerals identical to those used in the previously described embodiments indicate the same or identical components or configurations, and detailed explanations will be omitted as appropriate. This also applies to the embodiments described later.

[0079] Figure 8 is a block diagram showing the functional configuration of the controller 910a in the image forming apparatus 1 according to this embodiment.

[0080] Controller 910a has an information acquisition unit 14 that acquires environmental information 113 within the image forming apparatus 1 and information 114 regarding the type of sheet P on which the toner image is formed. Controller 910a also has an inference unit 15 that uses a learning model LM, which takes the environmental information 113 and the information 114 regarding the type of sheet P acquired by the information acquisition unit 14 as input and outputs correction parameters that correct the estimated amount of residual toner estimated from the formed image data 111, to infer correction parameters from the environmental information 113 and the information 114 regarding the type of sheet P acquired by the information acquisition unit 14. The first estimation unit 12 corrects the amount of residual toner estimated from the formed image data 111 using the correction parameters inferred by the inference unit 15. Controller 910a differs from controller 910 in these respects from controller 910 in the image forming apparatus 1 according to the first embodiment. In other words, controller 910a differs from controller 910 in that it estimates the amount of residual toner using AI (Artificial Intelligence) technology.

[0081] The functions of the information acquisition unit 14 are realized by the HDD controller 908, etc. The functions of the inference unit 15 are realized by electronic circuits such as the CPU 901 executing instruction codes stored in memory such as the ROM 902a, or by electronic circuits designed for special purposes performing various processes. However, some of the functions of the inference unit 15 may be realized by devices or equipment other than the controller 910, or by distributed processing between the controller 910 and one or more devices or equipment other than the controller 910.

[0082] In the example shown in Figure 8, the storage unit 11 receives information regarding temperature and humidity detected by the temperature and humidity detection unit 255 via the input unit 10 and stores it as environmental information 113. The storage unit 11 also receives and stores information regarding the type of sheet P 114 via the input unit 10. The information acquisition unit 14 can acquire the environmental information 113 and the information regarding the type of sheet P 114 by referring to the storage unit 11. However, the information acquisition unit 14 may also acquire the environmental information 113 and the information regarding sheet P 114 directly from the input unit 10 without going through the storage unit 11.

[0083] The inference unit 15 includes a machine learning unit 151 that takes environmental information 113 and information 114 regarding the type of sheet P as inputs and outputs correction parameters that correct the estimated amount of residual toner estimated from the formed image data 111. The machine learning unit 151 also includes a storage unit that stores the generated machine learning model LM.

[0084] The inference unit 15 infers correction parameters using a pre-trained learning model or while performing machine learning. Here, machine learning refers to a technique for enabling computers to acquire human-like learning abilities, in which a computer autonomously generates algorithms necessary for judgments such as data identification from pre-introduced training data, and applies these algorithms to new data to make predictions. The learning method for machine learning may be supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, or deep learning, or a combination of these learning methods; the learning method for machine learning is not limited.

[0085] Preferably, the machine learning unit 151 takes environmental information 113 and information 114 regarding the type of sheet P as inputs and generates a neural network learning model LM by machine learning, with correction parameters as output. Figure 9 is a schematic diagram showing a neuron learning model LM. Figure 10 is a schematic diagram showing a three-layer neural network learning model LM constructed by combining the neurons shown in Figure 9. The neural network is composed of a computing unit and memory, etc., that mimic a neuron (simple perceptron) model, for example, as shown in Figure 9.

[0086] As shown in Figure 9, a neuron outputs an output (result) y for multiple inputs x. In the example shown in Figure 9, inputs x1 to x3 correspond to multiple inputs x. Each input x(x1, x2, x3) is multiplied by a weight w(w1, w2, w3) corresponding to that input x. As a result, the neuron outputs an output y expressed by the following equation 1. Note that the inputs x, output y, and weights w are all vectors. Also, in equation 1 below, θ is the bias and fk is the activation function.

[0087]

number

[0088] Figure 10 shows a three-layer neural network constructed by combining the neurons shown in Figure 9. As shown in Figure 10, multiple inputs x are input from the left side of the neural network, and outputs y are output from the right side. In the example shown in Figure 10, inputs x1 to x3 correspond to multiple inputs x. Also, outputs y1 to y3 correspond to outputs y. Specifically, inputs x1, x2, and x3 are input to three neurons N11 to N13, each multiplied by the corresponding weight. These weights multiplied by the inputs are collectively denoted as W1.

[0089] Neurons N11 to N13 output z11 to z13, respectively. In Figure 10, these z11 to z13 are collectively denoted as the feature vector Z1, and can be considered as a vector from which the features of the input vector have been extracted. This feature vector Z1 is the feature vector between weights W1 and W2. For each of the two neurons N21 and N22, z11 to z13 are input multiplied by their corresponding weights. The weights multiplied by these feature vectors are collectively denoted as W2.

[0090] Neurons N21 and N22 output z21 and z22, respectively. In Figure 10, these z21 and z22 are collectively represented as the feature vector Z2. This feature vector Z2 is the feature vector between weights W2 and W3. z21 and z22 are input to each of the three neurons N31 through N33, multiplied by their corresponding weights. These weights multiplied by these feature vectors are collectively represented as W3.

[0091] Finally, neurons N31 to N33 output outputs y1 to y3, respectively. A neural network operates in two modes: a learning mode where it learns weights W1 to W3, and an estimation mode where it estimates outputs y1 to y3 from inputs x1 to x3. For example, in learning mode, weights W1 to W3 are learned using a training dataset, and these parameters are used to infer correction parameters α in estimation mode. Although we've used the term "estimation" for convenience, neural networks are capable of a variety of tasks, including detection and classification.

[0092] Furthermore, weights W1 to W3 can be learned using backpropagation. Error information enters from the right side of the neural network and flows to the left side. Backpropagation is a method that adjusts (learns) each weight for each neuron to minimize the difference (i.e., error) between the output y when input x is input and the true output y (i.e., label data).

[0093] Such neural networks can be made to have three or more layers, and even more layers can be added to perform deep learning. Furthermore, it is possible to automatically acquire a computing unit that has a convolutional neural network (CNN) that extracts input features stepwise, and a neural network that classifies or regresses the output, using only training data.

[0094] <Operation of the image forming apparatus according to the second embodiment> (The process of generating the learning model LM) The operation of generating the learning model LM by the image forming apparatus 1 according to the second embodiment will be described with reference to Figures 11 and 12. Figure 11 is a flowchart showing the operation of generating the learning model LM by the image forming apparatus 1. Figure 12 is a diagram showing an example of a training dataset used in the generation of the learning model LM by the image forming apparatus 1.

[0095] The image forming apparatus 1 starts the operation shown in Figure 1, for example, when it receives an operation input from the operator of the image forming apparatus 1 via the operation panel 940 to start the generation of the learning model LM.

[0096] First, in step S31, the image forming apparatus 1 receives the formed image data 111 transmitted by the operator of the image forming apparatus 1.

[0097] Next, in step S32, the image forming apparatus 1 forms a toner image on the sheet P based on the received formed image data 111.

[0098] Next, in step S33, the image forming apparatus 1 acquires environmental information 113 and information 114 regarding the type of sheet P input from the temperature and humidity detection unit 255 using the information acquisition unit 14.

[0099] In step S34, the image forming apparatus 1 reads the toner image formed on the sheet P using the image reading unit 270. As a result, the image forming apparatus 1 obtains toner image data 112.

[0100] Next, in step S35, the image forming apparatus 1 calculates the toner amount A based on the formed image data 111. The toner amount A is obtained by multiplying the amount of toner used in the image of the formed image data 111 by "1 - transfer rate".

[0101] Next, in step S36, the image forming apparatus 1 determines whether the brightness value of the formed image data 111 is greater than the brightness value of the read image data.

[0102] In step S36, if it is determined that the brightness value of the formed image data 111 is not greater than the brightness value of the read image data (step S36, NO), the image forming apparatus 1 proceeds to step S40. On the other hand, in step S36, if it is determined that the brightness value of the formed image data 111 is greater than the brightness value of the read image data (step S36, YES), the image forming apparatus 1 executes step S37. In step S37, the image forming apparatus 1 calculates the toner amount B from the difference image between the read image data 112 and the formed image data 111.

[0103] Next, in step S38, the image forming apparatus 1 calculates a correction parameter α by dividing the toner amount B by the toner amount A. Here, the correction parameter α is the value obtained by dividing the toner amount B calculated in step S36 by the toner amount A calculated in step S35 (α = B / A), and is a coefficient for calculating the excess or deficiency of residual toner resulting from the formed image data 111.

[0104] Next, in step S39, the image forming apparatus 1 stores a learning dataset, which includes information 114 about the sheet P, temperature and humidity information in the environmental information 113, and correction parameter α, in the storage unit 11 or the like. As shown in Figure 12, the learning dataset, which includes information 114 about the sheet P, temperature and humidity information in the environmental information 113, and correction parameter α, is stored cumulatively in association with each other. In the example shown in Figure 12, the learning dataset also includes date information for when the toner image was formed on the sheet in step S32.

[0105] Next, in step S40, the image forming apparatus 1 determines whether or not to terminate the acquisition of training datasets. For example, the image forming apparatus 1 may terminate when it has acquired a predetermined number of training datasets. Alternatively, the image forming apparatus 1 may terminate when the learning model has achieved a predetermined target indicator, or when the acquired datasets have a predetermined data distribution (i.e., the data is unbiased).

[0106] If it is determined in step S40 that the process will not terminate (step S40, NO), the image forming apparatus 1 repeats the operations from step S31 onwards until it is determined in step S40 that the process will terminate. On the other hand, if it is determined in step S40 that the process will terminate (step S40, YES), the image forming apparatus 1 executes step S41. In step S41, the image forming apparatus 1 uses the machine learning unit 151 to perform machine learning using the training dataset stored in the storage unit 11, etc., and generates a training model LM. The training model LM in Figure 11 takes environmental information 113 and information 114 about the type of sheet P as inputs and outputs a correction parameter α that corrects the estimated amount of residual toner estimated from the formed image data 111. After generating the training model LM, the image forming apparatus 1 terminates its operation.

[0107] As described above, the image forming apparatus 1 can generate a learning model LM. The image forming apparatus 1 can also acquire a learning dataset containing environmental information 113, information on the type of sheet P 114, and toner amounts A and B corresponding to this information, while performing the residual toner amount estimation process shown in Figure 7. Furthermore, the image forming apparatus 1 can generate and update the learning model LM using the learning dataset acquired while performing the residual toner amount estimation process. Additionally, the image forming apparatus 1 can acquire a learning dataset while performing the residual toner amount estimation process shown in Figure 15 (described later), and update the learning model LM using the acquired learning dataset.

[0108] (Creation of abnormal image management information) Referring to Figures 13 and 14, the operation of creating abnormal image management information by the image forming apparatus 1 according to the second embodiment will be described. Figure 13 is a flowchart showing the operation of creating abnormal image management information by the image forming apparatus 1. Figure 14 is a diagram showing an example of abnormal image management information in the image forming apparatus 1.

[0109] Abnormal image management information refers to information that shows the correspondence between abnormal images and the amount of residual toner. Here, when the image forming apparatus 1 infers the correction parameter α using the inference unit 15, it does not read the image formed on the sheet P, and therefore cannot calculate the toner amount C and toner amount D based on the read image data 112. In this case, the image forming apparatus 1 obtains the toner amount C and toner amount D by referring to the abnormal image management information according to the type of abnormal image identified. Note that the abnormal image management information is managed separately from the learning model LM. In addition to the correspondence between abnormal images and the amount of residual toner, the abnormal image management information also includes an abnormal image flag that is turned on when an abnormal image occurs.

[0110] For example, the image forming apparatus 1 starts the operation shown in Figure 13 when it receives an operation input from the operator of the image forming apparatus 1 via the control panel 940 to start the creation of abnormal image management information.

[0111] First, in step S51, the image forming apparatus 1 receives the formed image data 111 transmitted by the operator of the image forming apparatus 1.

[0112] Next, in step S52, the image forming apparatus 1 forms a toner image on the sheet P based on the received formed image data 111.

[0113] In step S53, the image forming apparatus 1 reads the toner image formed on the sheet P using the image reading unit 270. As a result, the image forming apparatus 1 obtains toner image data 112.

[0114] Next, in step S54, the image forming apparatus 1 determines whether or not there are images in the read image data 112 that are not present in the formed image data 111. If it is determined in step S54 that there are no images in the read image data 112 that are not present in the formed image data 111 (step S54, NO), the image forming apparatus 1 proceeds to step S61.

[0115] On the other hand, if in step S54 it is determined that there is an image in the read image data 112 that is not in the formed image data 111 (step S54, YES), the image forming apparatus 1 executes step S55. In step S55, the image forming apparatus 1 determines whether the image that is only in the read image data 112 is a vertical streak image E extending in the transport direction Pa.

[0116] In step S55, if it is determined that the image present only in the read image data 112 is a vertical streak image E (step S55, YES), the image forming apparatus 1 executes step S56. In step S56, the image forming apparatus 1 calculates the toner amount D by multiplying the travel distance of the photoreceptor drum 231 by the width of the vertical streak image E.

[0117] Next, in step S57, the image forming apparatus 1 turns on the abnormal image flag Df.

[0118] On the other hand, if in step S55 it is determined that the image present only in the read image data 112 is not the vertical streak image E (step S55, NO), the image forming apparatus 1 executes step S58. In step S58, the image forming apparatus 1 calculates the toner amount C by subtracting the toner amount of the image present only in the read image data from the toner amount / transfer rate of the image present only in the read image data.

[0119] Next, in step S59, the image forming apparatus 1 turns on the abnormal image flag Cf. The abnormal image in step S59 is a so-called background stain abnormal image, as explained in the second example of the read image data 112 above, where toner adheres to an area on the outer surface of the photoreceptor drum 231 where there is no image data due to deterioration of the photoreceptor drum 231.

[0120] Next, in step S60, the image forming apparatus 1 records the abnormal image flag Cf, abnormal image flag Df, toner amount C, and toner amount D in the abnormal image management information. As shown in Figure 14, the information for abnormal image flag Cf and toner amount C are associated, and the information for abnormal image flag Df and toner amount D are associated and recorded in the abnormal image management information. If the latest abnormal image flag is ON, the toner amount calculated when the abnormal image flag was turned ON is recorded. If the abnormal image flag is OFF, there is no toner amount information, so it becomes NULL.

[0121] Next, in step S61, the image forming apparatus 1 determines whether or not to terminate the creation of abnormal image management information. For example, the image forming apparatus 1 determines to terminate the creation of abnormal image management information when it receives an operation input from the operator of the image forming apparatus 1 via the operation panel 940 to terminate the creation of abnormal image management information.

[0122] If it is determined in step S61 that the process will not terminate (step S61, NO), the image forming apparatus 1 repeats the operations from step S51 onward until it is determined in step S61 that the process will terminate. On the other hand, if it is determined in step S61 that the process will terminate (step S61, YES), the image forming apparatus 1 terminates its operation.

[0123] As described above, the image forming apparatus 1 can create abnormal image management information. The abnormal image management information is stored, for example, in the storage unit 11. The image forming apparatus 1 can also create abnormal image management information by recording the calculated toner amount C and toner amount D while performing the residual toner amount estimation process shown in Figure 7.

[0124] (Estimation of residual toner amount) Referring to Figure 15, the residual toner estimation operation by the image forming apparatus 1 according to the second embodiment will be described. Figure 15 is a flowchart showing the residual toner amount estimation operation by the image forming apparatus 1. For example, the image forming apparatus 1 starts the operation shown in Figure 15 when it receives formed image data 111 transmitted by the user of the image forming apparatus 1.

[0125] First, in step S71, the image forming apparatus 1 acquires environmental information 113 and information 114 regarding the type of sheet P input from the temperature and humidity detection unit 255.

[0126] Next, in step S72, the image forming apparatus 1 calculates the toner amount A based on the formed image data 111 using the first estimation unit 12. The toner amount A is obtained by multiplying the amount of toner used in the image of the formed image data 111 by "1 - transfer rate".

[0127] Next, in step S73, the image forming apparatus 1 uses the inference unit 15 to infer the correction parameter α using the learning model LM based on the environmental information 113 and the information 114 related to sheet P.

[0128] Next, in step S74, the image forming apparatus 1 calculates the toner amount B using the correction parameter α with the first estimation unit 12. Specifically, the first estimation unit 12 calculates the toner amount B by multiplying the toner amount A obtained in step S72 by the correction parameter α. This makes it possible to calculate the toner amount B based on the difference between the toner amount of the image formed on the sheet and the toner amount required for the formed image data 111, without having to read the image formed on the sheet P.

[0129] Next, in step S75, the image forming apparatus 1 refers to the abnormal image management information and determines whether or not the abnormal image flag Cf is on. If it is determined in step S75 that the abnormal image flag Cf is on (step S75, YES), the image forming apparatus 1, in step S76, uses the first estimation unit 12 to obtain the toner amount C by referring to the abnormal image management information. On the other hand, if it is determined in step S75 that the abnormal image flag Cf is not on (step S75, NO), the image forming apparatus 1, in step S77, uses the first estimation unit 12 to set the toner amount C to 0.

[0130] Next, in step S78, the image forming apparatus 1 refers to the abnormal image management information and determines whether the abnormal image flag Df is on or off. If it is determined in step S78 that the abnormal image flag Df is on (step S78, YES), the image forming apparatus 1, in step S79, uses the first estimation unit 12 to obtain the toner amount D by referring to the abnormal image management information. On the other hand, if it is determined in step S78 that the abnormal image flag Df is not on (step S78, NO), the image forming apparatus 1, in step S80, uses the first estimation unit 12 to set the toner amount D to 0.

[0131] Next, in step S81, the image forming apparatus 1 uses the first estimation unit 12 to calculate the amount of residual toner from the sum of toner amount A, toner amount B, toner amount C, and toner amount D, and uses this as the estimated result of the residual toner amount. After that, the image forming apparatus 1 terminates its operation.

[0132] As described above, the image forming apparatus 1 can estimate the amount of residual toner.

[0133] <Effects of the Image Forming Apparatus 1 According to the Second Embodiment> In this embodiment, the inference unit 15 uses the learning model LM to infer a correction parameter α from the environmental information 113 and the sheet P type information 114 acquired by the information acquisition unit 14, and the first estimation unit 12 corrects the residual toner amount using the correction parameter α. As a result, in this embodiment, the estimation error of the residual toner amount according to the environmental information 113 and the sheet P type information 114 can be reduced, and the estimation accuracy of the residual toner amount can be improved. Furthermore, in this embodiment, by using the learning model LM, it is not necessary to read the sheet P each time the residual toner amount is estimated, so the residual toner amount can be easily estimated.

[0134] The inference unit 15 includes a machine learning unit 151 that generates a learning model LM. This allows the image forming apparatus 1 to generate the learning model LM using the machine learning unit 151 and estimate the amount of residual toner using the generated learning model LM. Furthermore, the machine learning unit 151 can update the learning model LM according to the installation location or usage conditions of the image forming apparatus 1, thereby optimizing the learning model LM and further improving the accuracy of residual toner estimation.

[0135] [Third Embodiment] Next, an image forming apparatus according to the third embodiment will be described.

[0136] <Configuration of the image forming apparatus according to the third embodiment> Figure 16 is a block diagram showing the functional configuration of the controller 910b of the image forming apparatus 1 according to this embodiment.

[0137] As shown in Figure 16, in this embodiment, the inference unit 15 has a result acquisition unit 152 that acquires correct / incorrect information regarding whether the correction of the residual toner amount is correct or not. The machine learning unit 151 updates the learning model LM based on the correct / incorrect information acquired by the result acquisition unit 152. In other words, in this embodiment, the inference unit 15 can update the learning model LM by additional learning based on the correct / incorrect information. Furthermore, the machine learning unit 151 learns information 115 regarding the deterioration of the image carrier as further input. These points differ from the image forming apparatus according to the second embodiment.

[0138] The correct / incorrect information is input to the controller 910b via the operation panel 940 by a service technician or user of the image forming apparatus 1 when the storage member 260 that holds the collected residual toner becomes full and is replaced. Specifically, the service technician or user measures the weight of the residual toner stored in the storage member 260 and inputs this weight information as correct / incorrect information to the controller 910b using the operation panel 940. The result acquisition unit 152 can acquire the correct / incorrect information from the service technician or user via the operation panel 940.

[0139] The information 115 regarding the deterioration of the image carrier, which is input to the machine learning unit 151, includes information such as the elapsed time since the start of use of the image carrier, the distance traveled by the image carrier, and the number of sheets P for which images were formed by the image forming apparatus. In the example shown in Figure 16, the image carrier corresponds to the photoreceptor drum 231 and the intermediate transfer belt 243.

[0140] <Operation of the image forming apparatus according to the third embodiment> Figure 17 is a flowchart showing the additional learning operation by the image forming apparatus 1 according to the third embodiment. For example, the image forming apparatus 1 starts the operation shown in Figure 17 when it displays a message prompting the replacement of the housing member 260 on the operation panel 940, or when it sends the message via email or the like.

[0141] First, in step S91, the image forming apparatus 1 acquires correctness information regarding whether the correction of the residual toner amount is correct or not using the result acquisition unit 152. For example, the result acquisition unit 152 acquires as correctness information the weight information of the residual toner measured by a service technician or user of the image forming apparatus 1 who has recognized a message prompting the replacement of the storage member 260.

[0142] Next, in step S92, the image forming apparatus 1 determines whether the residual toner amount is correct or not based on the correct / incorrect information acquired by the result acquisition unit 152. If it is determined to be correct in step S92 (step S92, YES), the image forming apparatus 1 determines that no further learning is necessary and terminates its operation.

[0143] On the other hand, if it is determined to be incorrect in step S92 (step S92, NO), in step S93, the image forming apparatus 1 performs additional learning based on the correct / incorrect information and information on the deterioration of the image carrier using the machine learning unit 151. For additional learning, the weight fixed method, weight constraint method, weight expansion method, etc., can be used. However, from the viewpoint of extending the weights of the existing learning model LM by imposing constraints on the weights of the existing model and adding parts that correspond to new data and tasks, the application of the weight expansion method is preferable. The machine learning unit 151 updates the learning model LM by performing additional learning based on the correct / incorrect information obtained by the result acquisition unit 152.

[0144] As described above, the image forming apparatus 1 can perform additional learning and appropriately update the learning model LM to match the operating environment of the image forming apparatus 1. In this embodiment, even if the learning model LM becomes unsuitable due to factors such as the operating environment of the image forming apparatus 1, the learning model LM can be updated to match the operating environment through additional learning, and the inferred correction parameter α can be optimized. For example, if the learning model LM becomes unsuitable due to the addition of a new type of sheet P, the correction parameter α can be suitably optimized. By optimizing the correction parameter α, the accuracy of estimating the residual toner amount is improved.

[0145] <Effects of learning using information 115 regarding the deterioration of the image carrier as further input> Even if the type of sheet P, temperature, and humidity are almost the same, the amount of residual toner may change due to the deterioration of the image carrier, such as the photoreceptor drum 231. In this embodiment, a learning model LM is used that takes environmental information 113 and information on the type of sheet P 114 as inputs, as well as information on the deterioration of the image carrier 115, and outputs a correction parameter α. The inference unit 15 uses the learning model LM to infer the correction parameter α from the environmental information 113, information on the type of sheet P 114, and information on the deterioration of the image carrier 115 acquired by the information acquisition unit 14. The information on the deterioration of the image carrier 115 is, for example, information that can estimate the aging deterioration of the image carrier (photoreceptor drum 231, intermediate transfer belt 243), such as the cumulative mileage and cumulative operating time of the image carrier. The first estimation unit 12 corrects the amount of residual toner using the correction parameter α inferred by the inference unit 15. As a result, in this embodiment, the effect of the deterioration of the image carrier can be reduced and the estimation accuracy of the amount of residual toner can be further improved.

[0146] [Fourth Embodiment] Next, an image forming apparatus according to the fourth embodiment will be described.

[0147] <Configuration of the image forming apparatus according to the fourth embodiment> Figure 18 is a block diagram showing the functional configuration of the controller 910c in the image forming apparatus 1 according to this embodiment.

[0148] As shown in Figure 18, the image forming apparatus 1 according to this embodiment differs from the image forming apparatus 1 according to the first embodiment in that the controller 910c further includes a second estimation unit 16. The second estimation unit 16 estimates the toner consumption based on the remaining toner amount estimated by the first estimation unit 12 and the read image data 112 of the toner image formed on the sheet P and read by the image reading unit 270.

[0149] The functions of the second estimation unit 16 are realized by electronic circuits such as the CPU 901 executing instruction codes stored in memory such as the ROM 902a, or by electronic circuits designed for special purposes performing various processes. However, some of the functions of the second estimation unit 16 may be realized by one or more devices or equipment other than the controller 910, or by distributed processing between the controller 910 and one or more devices or equipment other than the controller 910.

[0150] The toner consumption in an image forming apparatus includes not only the amount of toner used to form an image on the sheet P, but also the amount of toner recovered as residual toner. In this embodiment, the second estimation unit 16 estimates the amount of toner used to form an image on the sheet P based on the read image data 112. The second estimation unit 16 also receives information regarding the remaining toner amount estimated by the first estimation unit 12. The second estimation unit 16 estimates the toner consumption by adding the amount of toner used to form an image on the sheet P and the amount of residual toner.

[0151] The first estimation unit 12 can estimate the remaining toner amount with high accuracy. Therefore, the second estimation unit 16 can estimate the toner consumption with high accuracy by using the remaining toner amount estimated by the first estimation unit 12. The second estimation unit 16 can output the estimated toner consumption result via the output unit 13.

[0152] By accurately estimating toner consumption, the replacement timing of toner cartridges (234Y, 234C, 234M, 234K) can be appropriately managed. For example, service personnel or administrators of the image forming apparatus 1 can be prompted to replace toner cartridges (234Y, 234C, 234M, 234K) at the appropriate time. Furthermore, waste caused by replacing toner cartridges (234Y, 234C, 234M, 234K) while toner is still present can be reduced. In addition, downtime of the image forming apparatus 1 due to the toner running out in the toner cartridges (234Y, 234C, 234M, 234K) can be reduced.

[0153] Furthermore, the controller 910c according to this embodiment has an inference unit 15, and the inference unit 15 can also infer the amount of residual toner. The first estimation unit 12 can also estimate the amount of residual toner using the correction parameter α inferred by the inference unit 15.

[0154] [Fifth Embodiment] Next, the image forming system according to the fifth embodiment will be described.

[0155] <Configuration of the image forming system according to the fifth embodiment> (Overall structure) Figure 19 is a schematic diagram showing the overall configuration of the image forming system 2 according to the fifth embodiment. As shown in Figure 19, the image forming system 2 includes an image forming apparatus 1 and a server 3 that is connected to the image forming apparatus 1 via a communication network 100 such as the Internet or LAN.

[0156] (Hardware configuration of Server 3) Figure 20 is a block diagram showing the hardware configuration of Server 3.

[0157] Server 3 is built by a computer. Server 3 has a CPU 501, ROM 502, RAM 503, HD 504, HDD controller 505, display 506, external device connection I / F 508, network I / F 509, data bus 510, and keyboard 511. Server 3 also has a pointing device 512, a DVD-RW (Digital Versatile Disk Rewritable) drive 514, and media I / F 516.

[0158] The CPU 501 controls the overall operation of the server 3. The ROM 502 stores programs used to drive the CPU 501, such as the IPL. The RAM 503 is used as the 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 the HD 504 according to the control of the CPU 501.

[0159] The display 506 displays various information such as cursors, menus, windows, characters, or images. The external device connection interface 508 is an interface for connecting various external devices. In this case, external devices include, for example, USB (Universal Serial Bus) memory and printers. The network interface 509 is an interface for data communication using the communication network 100. The data bus 510 is an address bus and data bus for electrically connecting various components such as the CPU 501.

[0160] The keyboard 511 is a type of input means equipped with multiple keys for inputting characters, numbers, and various instructions. The pointing device 512 is a type of input means for selecting and executing various instructions, selecting processing targets, moving the cursor, etc. The DVD-RW drive 514 controls the reading or writing of various data to the DVD-RW 513, which is an example of a removable recording medium. Note that it is not limited to DVD-RW, but may also be DVD-R, etc. The media I / F 516 controls the reading or writing (storage) of data to the recording medium 515, such as flash memory.

[0161] (Functional configuration of controller 910d) Figure 21 is a block diagram showing the functional configuration of the controller 910d of the image forming apparatus 1, which is part of the image forming system 2.

[0162] The information acquisition unit 14 acquires environmental information 113 and information regarding the type of sheet P 114 from the storage unit 11 and transmits them to the server 3 via the output unit 13. The server 3 infers a correction parameter α based on the transmitted environmental information 113 and information regarding the type of sheet P 114, and transmits the inferred correction parameter α to the controller 910d.

[0163] The first estimation unit 12 receives a correction parameter α from the server 3 via the input unit 10. The first estimation unit 12 calculates the toner amount B using the correction parameter α. The first estimation unit 12 also calculates the toner amount A from the formed image data 111. Furthermore, the first estimation unit 12 obtains the toner amounts C and D by referring to the abnormal image management information, or sets the toner amounts C and D to 0 according to the abnormal image flag. The first estimation unit 12 calculates the residual toner amount by summing toner amounts A, B, C, and D. The first estimation unit 12 can output the estimated residual toner amount result via the output unit 13.

[0164] (Server 3 Functional Configuration) Figure 22 is a block diagram showing the functional configuration of the server 3 in the image forming system 2.

[0165] Server 3 comprises a receiving unit 31, an inference unit 15, and a transmitting unit 32. The inference unit 15 of Server 3 receives environmental information 113 and information 114 regarding the type of sheet P transmitted from the controller 910d via the receiving unit 31. The inference unit 15 infers correction parameters α using the learning model LM and transmits the inferred correction parameters α to the controller 910d via the transmitting unit 32.

[0166] <Effects of the Image Forming System 2 According to the Fifth Embodiment> In this embodiment, the correction parameter α is inferred by the inference unit 15 of the server 3, thereby reducing the computational load on the controller 910d of the image forming apparatus 1 and enabling the acquisition of the correction parameter α. In this embodiment, the amount of residual toner can be estimated with high accuracy by using the correction parameter α. Other effects are the same as those of the image forming apparatus 1 according to the second embodiment.

[0167] The controller 910d may have a second estimation unit 16. The second estimation unit 16 may estimate the toner consumption of the image forming apparatus 1 using information on the amount of residual toner estimated by the first estimation unit 12.

[0168] Although preferred embodiments have been described in detail above, the embodiments of this disclosure are not limited to those described above, and various modifications and substitutions can be made to the embodiments of this disclosure without departing from the scope of the claims.

[0169] The ordinal numbers, quantities, and other figures used in the description of the embodiments of this disclosure are all illustrative to specifically illustrate the technology of this disclosure, and this disclosure is not limited to the illustrative figures. Furthermore, the connection relationships between the components are illustrative to specifically illustrate the technology of this disclosure, and are not limited to the connection relationships that realize the functions of this disclosure.

[0170] Each function of the embodiments described herein can be implemented by one or more processing circuits. Hereinafter, "processing circuit" as used herein includes processors programmed to execute each function by software, such as processors implemented by electronic circuits, as well as devices such as ASICs (Application Specific Integrated Circuits), DSPs (Digital Signal Processors), FPGAs (Field Programmable Gate Arrays), and conventional circuit modules designed to execute the functions described above.

[0171] The aspects of this disclosure are, for example, as follows: <1> An image forming apparatus for forming a toner image on a sheet, comprising: an image carrier for carrying the toner image; a cleaning member for collecting residual toner remaining on the image carrier that has not been transferred; an image reading unit for reading the toner image formed on the sheet; and a control unit for controlling the operation of the image forming apparatus, wherein the control unit includes a first estimation unit that identifies the type of abnormal image based on the difference between the formed image data of the toner image formed on the sheet and the read image data of the toner image formed on the sheet and read by the image reading unit, and estimates the amount of residual toner caused by the identified abnormal image. <2> The first estimation unit includes an information acquisition unit that acquires environmental information within the image forming apparatus and information regarding the type of sheet on which the toner image is formed, and an inference unit that uses a learning model that takes the environmental information and the information regarding the type of sheet acquired by the information acquisition unit as input and outputs correction parameters that correct the estimated amount of residual toner estimated from the formed image data, and uses the environmental information and the information regarding the type of sheet acquired by the information acquisition unit to infer the correction parameters from the environmental information and the information regarding the type of sheet acquired by the information acquisition unit, wherein the first estimation unit corrects the amount of residual toner estimated from the formed image data using the correction parameters inferred by the inference unit. <1> This is the image forming apparatus described in [reference]. <3> The inference unit includes a machine learning unit that takes the environmental information and the information regarding the type of sheet as input and generates a learning model that outputs the correction parameters, <2> This is the image forming apparatus described in [reference]. <4> The inference unit has a result acquisition unit that acquires correctness information regarding whether the correction of the residual toner amount is correct or not, and the machine learning unit updates the learning model based on the correctness information acquired by the result acquisition unit. <3> This is the image forming apparatus described in [reference]. <5> The machine learning unit further learns information regarding the deterioration of the image carrier as input. <3> This is the image forming apparatus described in [reference]. <6> The device further includes a second estimation unit that estimates toner consumption based on the amount of residual toner estimated by the first estimation unit and the read image data of the toner image formed on the sheet and read by the image reading unit. <1> from the above <5> The image forming apparatus is one of the images described in any one of the following. <7> The first estimation unit estimates the amount of residual toner caused by the identified abnormal image using a calculation method corresponding to the type of abnormal image identified. <1> from the above <6> The image forming apparatus is one of the images described in any one of the following. <8> The first estimation unit estimates the amount of residual toner caused by the vertical streak image by multiplying the travel distance of the image carrier by the width of the vertical streak image, if the identified abnormal image is a vertical streak image extending in the transport direction of the sheet. <1> from the above <7> The image forming apparatus is one of the images described in any one of the following. <9> The first estimation unit, if the identified abnormal image is not a vertical streak image extending in the sheet transport direction, estimates the amount of residual toner caused by the abnormal image by subtracting the amount of toner in the image present only in the read image data from the value obtained by dividing the amount of toner in the image present only in the read image data by the transfer rate. <1> from the above <8> The image forming apparatus is one of the images described in any one of the following. <10> The control unit records abnormal image management information for each type of abnormal image, which associates the presence or absence of the abnormal image with the amount of residual toner caused by the abnormal image estimated by the first estimation unit. <1> from the above <9> The image forming apparatus is one of the images described in any one of the following. <11> An image forming method using an image forming apparatus that forms a toner image on a sheet, wherein the image forming apparatus carries the toner image on an image carrier, a cleaning member collects residual toner remaining on the image carrier that has not been transferred, an image reading unit reads the toner image formed on the sheet, a control unit controls the operation of the image forming apparatus, and the control unit, using a first estimation unit, identifies the type of abnormal image based on the difference between the formed image data of the toner image to be formed on the sheet and the read image data of the toner image formed on the sheet and read by the image reading unit, and estimates the amount of residual toner caused by the identified abnormal image. <12> A program that operates in an image forming apparatus for forming a toner image on a sheet, wherein the program causes the image forming apparatus to perform the following processes: the image carrier carries the toner image; the cleaning member collects the residual toner that remains on the image carrier without being transferred; the image reading unit reads the toner image formed on the sheet; the control unit controls the operation of the image forming apparatus; the control unit, using a first estimation unit, identifies the type of abnormal image based on the difference between the formed image data of the toner image to be formed on the sheet and the read image data of the toner image formed on the sheet and read by the image reading unit; and estimates the amount of residual toner caused by the identified abnormal image. <13> An image forming system comprising an image forming apparatus for forming a toner image on a sheet, and an information processing apparatus communicated with the image forming apparatus, wherein the image forming apparatus includes an image carrier for carrying the toner image, a cleaning member for collecting residual toner remaining on the image carrier that has not been transferred, and an image reading unit for reading the toner image formed on the sheet, The information processing device comprises a control unit that controls the operation of the image forming apparatus, and an information acquisition unit that acquires environmental information within the image forming apparatus and information about the type of sheet on which the toner image is formed based on the formation image data of the toner image formed on the sheet. The information processing device has an inference unit that takes the environmental information and the information about the type of sheet acquired by the information acquisition unit as input and uses a learning model that outputs a correction parameter for correcting the estimated amount of residual toner estimated from the formation image data of the toner image formed on the sheet to infer the correction parameter from the environmental information and the information about the type of sheet acquired by the information acquisition unit. The control unit includes a first estimation unit that identifies the type of abnormal image based on the difference between the formation image data of the toner image formed on the sheet and the read image data of the toner image formed on the sheet and read by the image reading unit, and estimates the amount of residual toner caused by the identified abnormal image. The first estimation unit corrects the amount of residual toner estimated from the formation image data using the correction parameter inferred by the inference unit. [Explanation of Symbols]

[0172] 1. Image forming apparatus 2. Image Forming System 3 servers 10 Input section 11 Preservation Department 12 1st estimation part 13 Output section 14 Information acquisition department 15 Reasoning part 16 Second estimation part 31 Receiver 32 Transmitter 100 Communication Networks 111 Formed image data 112 Read image data 113 Environmental information 114 Information on sheet types 115 Information regarding deterioration 151 Machine Learning Department 152 Result acquisition part 160Y, 160M, 160C, 160K Sub-hopper 210 Paper feed section 211 Paper feed cassette 212 Paper feed roller 220 Conveying section 221 Laura 222 Timing Roller 223 Paper output roller 224 Paper Output Tray 230 Image creation section 231, 231Y, 231M, 231C, 231K Photoconductor Drum 232, 232Y, 232M, 232C, 232K chargers 233 Exposure Unit 234, 234Y, 234C, 234M, 234K Toner Cartridges 236, 236Y, 236M, 236C, 236K Cleaning parts 240 Transfer section 241 Drive roller 242 Driven roller 243 Intermediate transfer belt 243a Arrow direction 244, 244Y, 244M, 244C, 244K Primary Transfer Rollers 245 Secondary opposing roller 246 Secondary Transfer Roller 250 Fuser 251 Fixing belt 252 Pressure roller 255 Temperature and Humidity Detection Unit 260 housing member 270 Image reading unit 501 CPU 502 ROM 503 RAM 504 HD 505 HDD Controller 506 displays 508 External device connection interface 509 Network Interface 510 Data Bus 511 keyboard 512 Pointing devices 513 DVD-RW 514 DVD-RW drive 515 Recording media 516 Media I / F 910, 910a, 910b, 910c, 910d controllers 901 CPU 902 System Memory (MEM-P) 902a ROM 902b RAM 903 Northbridge (NB) 904 Southbridge (SB) It is connected via port 921. 906 ASIC 907 Local Memory (MEM-C) 908 HDD Controller 909 HD 920 Near field communication circuit 920a antenna 921 AGP bus 922 PCI bus 930 Engine Control Unit 931 Scanner Unit 932 Printer Section 940 Control Panel 940a Panel display unit 940b Control Panel 950 Network Interface E Vertical stripe image P Sheet Pa Conveying Direction [Prior art documents] [Patent Documents]

[0173] [Patent Document 1] Japanese Patent Publication No. 2021-196523

Claims

1. An image forming apparatus for forming a toner image on a sheet, An image carrier that carries the aforementioned toner image, A cleaning member for collecting residual toner that remains on the image carrier without being transferred, An image reading unit that reads the toner image formed on the sheet, The system comprises a control unit for controlling the operation of the image forming apparatus, The control unit, An image forming apparatus including a first estimation unit that identifies the type of abnormal image based on the difference between the formed image data of the toner image formed on the sheet and the read image data of the toner image formed on the sheet and read by the image reading unit, and estimates the amount of residual toner caused by the identified abnormal image.

2. An information acquisition unit that acquires environmental information within the image forming apparatus and information regarding the type of sheet on which the toner image is formed, The system includes an inference unit that uses a learning model that takes the environmental information and the sheet type information acquired by the information acquisition unit as input and outputs correction parameters that correct the estimated amount of residual toner estimated from the formed image data, and infers the correction parameters from the environmental information and the sheet type information acquired by the information acquisition unit, The image forming apparatus according to claim 1, wherein the first estimation unit corrects the amount of residual toner estimated from the formed image data using the correction parameters inferred by the inference unit.

3. The image forming apparatus according to claim 2, wherein the inference unit has a machine learning unit that takes the environmental information and the information regarding the type of sheet as input and generates a learning model that outputs the correction parameters.

4. The inference unit includes a result acquisition unit that acquires correctness information regarding whether the correction of the residual toner amount is correct or not. The image forming apparatus according to claim 3, wherein the machine learning unit updates the learning model based on the correct / incorrect information obtained by the result acquisition unit.

5. The image forming apparatus according to claim 3, wherein the machine learning unit further learns information regarding the deterioration of the image carrier as input.

6. The image forming apparatus according to claim 1, further comprising a second estimation unit that estimates toner consumption based on the amount of residual toner estimated by the first estimation unit and the read image data of the toner image formed on the sheet and read by the image reading unit.

7. The image forming apparatus according to claim 1, wherein the first estimation unit estimates the amount of residual toner caused by the identified abnormal image using a calculation method corresponding to the identified type of abnormal image.

8. The image forming apparatus according to claim 1, wherein the first estimation unit estimates the amount of residual toner caused by the vertical streak image by multiplying the travel distance of the image carrier by the width of the vertical streak image when the identified abnormal image is a vertical streak image extending in the transport direction of the sheet.

9. The image forming apparatus according to claim 1, wherein, if the identified abnormal image is not a vertical streak image extending in the sheet transport direction, the first estimation unit estimates the amount of residual toner caused by the abnormal image by subtracting the amount of toner in the image present only in the read image data from a value obtained by dividing the amount of toner in the image present only in the read image data by the transfer rate.

10. The image forming apparatus according to claim 1, wherein the control unit records abnormal image management information for each type of abnormal image, which associates the presence or absence of the abnormal image with the amount of residual toner caused by the abnormal image estimated by the first estimation unit.

11. An image forming method using an image forming apparatus that forms a toner image on a sheet, The aforementioned image forming apparatus The toner image is carried by the image carrier, The cleaning member collects any residual toner that remains on the image carrier without being transferred. The image reading unit reads the toner image formed on the sheet, The control unit controls the operation of the image forming apparatus. The control unit, An image forming method comprising: a first estimation unit identifying the type of abnormal image based on the difference between the formation image data of the toner image formed on the sheet and the read image data of the toner image formed on the sheet and read by the image reading unit, and estimating the amount of residual toner caused by the identified abnormal image.

12. A program that operates in an image forming apparatus that forms a toner image on a sheet, The toner image is carried by the image carrier, The cleaning member collects any residual toner that remains on the image carrier without being transferred. The image reading unit reads the toner image formed on the sheet, The control unit controls the operation of the image forming apparatus. The control unit, The first estimation unit identifies the type of abnormal image based on the difference between the formation image data of the toner image formed on the sheet and the read image data of the toner image formed on the sheet and read by the image reading unit, and estimates the amount of residual toner caused by the identified abnormal image. A program that causes the image forming apparatus to perform the processing.

13. An image forming system comprising an image forming apparatus for forming a toner image on a sheet, and an information processing apparatus that is communicatively connected to the image forming apparatus, The image forming apparatus is An image carrier that carries the aforementioned toner image, A cleaning member for collecting residual toner that remains on the image carrier without being transferred, An image reading unit that reads the toner image formed on the sheet, A control unit that controls the operation of the image forming apparatus, The system includes an information acquisition unit that acquires environmental information within the image forming apparatus and information regarding the type of sheet on which the toner image is formed. The aforementioned information processing device is The system includes an inference unit that uses a learning model that takes the environmental information and information regarding the type of sheet acquired by the information acquisition unit as input and outputs a correction parameter that corrects the estimated amount of residual toner estimated from the formation image data of the toner image formed on the sheet, and infers the correction parameter from the environmental information and information regarding the type of sheet acquired by the information acquisition unit, The control unit, The system includes a first estimation unit that identifies the type of abnormal image based on the difference between the formed image data of the toner image formed on the sheet and the read image data of the toner image formed on the sheet and read by the image reading unit, and estimates the amount of residual toner caused by the identified abnormal image. The first estimation unit is an image forming system that corrects the amount of residual toner estimated from the formed image data using the correction parameters inferred by the inference unit.

Images