Image forming apparatus, information processing apparatus, and display method

Abstract

The present disclosure relates to a technique for notifying a risk of occurrence of an abnormality in an image forming apparatus.SOLUTION: An image forming device 100 includes image forming parts 5Y, 5M, 5C, and 5K for forming an image on a recording material S, a paper feeding roller 22 for conveying the recording material S, a risk ratio calculation part for acquiring a characteristic value related to conveyance by the paper feeding roller 22, and a display 1401 for notifying a risk of occurrence of jamming on the basis of the characteristic value acquired by the risk ratio calculation part.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a technique for notifying an image forming apparatus of a risk of an abnormality occurring. [Background technology]

[0002] An image forming apparatus includes an image carrier that carries an image and transport parts that transport recording materials on which the image is printed. Image carriers and transport parts can become unable to maintain their original performance due to aging and wear over time. For this reason, these parts are treated as replacement parts that require periodic replacement. The index used to determine whether a replacement part needs to be replaced is the detection result of a sensor that detects the characteristics of the replacement part or a count value from a counter. Patent Document 1 discloses a technology for predicting the end of life of a roller that transports recording materials. In Patent Document 1, the delay rate of transport by the roller is detected from the transport time of the recording material, and the ratio of the current delay rate to the limit delay rate that requires replacement is used as an index (hereinafter referred to as "wear level") for determining whether the roller needs to be replaced. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2003-261237 Summary of the Invention [Problem to be solved by the invention]

[0004] The time it takes for a roller to transport a recording material varies from sheet to sheet, even when transporting the same type of recording material. This causes variations in the delay rate obtained based on the transport time. While it is possible to derive the degree of wear from the maximum or average delay rate, in this case the variation in transport time varies depending on multiple factors, including the type of recording material and environmental conditions. This makes it difficult to accurately obtain the degree of roller wear. This same problem occurs with replacement parts other than rollers. It is also known that the risk of an abnormality occurring in the image forming apparatus increases as the roller wear progresses, but in conventional configurations, there is no way to notify the image forming apparatus of the risk of an abnormality occurring.

[0005] In view of the above-mentioned problems, the present invention has as its main object to notify an image forming apparatus of the risk of an abnormality occurring. [Means for solving the problem]

[0006] The image forming apparatus of the present invention is characterized by having an image forming means for forming an image on a recording material, a roller for transporting the recording material, an acquisition means for acquiring characteristic values ​​related to transport by the roller, and a notification means for notifying of the risk of a jam occurring based on the characteristic values ​​acquired by the acquisition means. The information processing device of the present invention is an information processing device that is communicatively connected to an image forming device that forms an image on a recording material, and is characterized by having an acquisition means that acquires characteristic values ​​related to the transport of rollers that transport the recording material in the image forming device, and a notification means that notifies the image forming device of the risk of a jam occurring based on the characteristic values ​​acquired by the acquisition means. The display method of the present invention is a display method for displaying the status of an image forming device that forms an image on a recording material, and is characterized in that it acquires characteristic values ​​related to the transport of rollers that transport the recording material in the image forming device, and displays the risk of the image forming device jamming based on the characteristic values. [Effects of the Invention]

[0007] According to the present invention, the image forming apparatus can notify the user of the risk of an abnormality occurring. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating the configuration of an image forming apparatus. [Figure 2] 4A to 4C are explanatory diagrams of a paper feeding operation. [Figure 3] Diagram of the machine learning system configuration. [Figure 4] FIG. 2 is a diagram illustrating the hardware configuration of the image forming apparatus. [Figure 5] Diagram of the machine learning server configuration. [Figure 6] Functional block diagram for machine learning. [Figure 7] (a) to (c) are explanatory diagrams of the learning model. [Figure 8] (a) and (b) are illustrations of histograms. [Figure 9] FIG. [Figure 10] FIG. [Figure 11] FIG. 10 is a diagram illustrating a detailed display of a jam risk rate. [Figure 12] FIG. 10 is a diagram illustrating a detailed display of a jam risk rate. DETAILED DESCRIPTION OF THE INVENTION

[0009] Preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be noted that the following embodiments do not limit the scope of the invention. Although the embodiments describe multiple features, not all of these features are necessarily essential to the invention, and multiple features may be combined in any desired manner. Furthermore, in the accompanying drawings, the same reference numerals are used to designate identical or similar components, and redundant explanations will be omitted. The following embodiments will be described using an electrophotographic image forming apparatus as an example.

[0010] FIG. 1 is a diagram illustrating the configuration of an image forming apparatus according to this embodiment. This image forming apparatus 100 employs an intermediate transfer tandem system in which multiple image forming units 5Y, 5M, 5C, and 5K are arranged along an intermediate transfer belt 11. In this embodiment, the image forming apparatus 100 forms (prints) a color image by superimposing toner images of four colors: yellow (Y), magenta (M), cyan (C), and black (K). Such an image forming apparatus 100 is used, for example, in color laser printers, copiers, multifunction peripherals, facsimile machines, and the like. Note that, although this embodiment describes the case in which a color image is formed, the image forming apparatus 100 may also form a monochrome image.

[0011] Hereinafter, the configuration of the parts corresponding to each color will be indicated by adding the suffixes Y, M, C, and K to the reference numerals, such as image forming units 5Y, 5M, 5C, and 5K. However, when it is not necessary to distinguish between the colors yellow, magenta, cyan, and black, the suffixes Y, M, C, and K will be omitted, such as in the image forming unit 5.

[0012] The image forming unit 5 includes a photosensitive drum 1, a charging roller 2, a developing roller 3, a drum cleaner 4, a toner container 6, and a recovered toner container 7. A laser unit 8 is disposed below the image forming unit 5. An intermediate transfer belt 11 is disposed above the image forming unit 5.

[0013] The photosensitive drum 1 is a drum-shaped photosensitive element with a photosensitive layer on its surface, and functions as an image carrier. The photosensitive drum 1 rotates around its drum axis during image formation. The charging roller 2 is a charger that uniformly charges the surface of the rotating photosensitive drum 1 to a predetermined potential with a predetermined polarity. The laser unit 8 irradiates the uniformly charged surface of the photosensitive drum 1 with laser light based on image data. As the potential at the position irradiated by the laser light changes, an electrostatic latent image corresponding to the image data is formed on the surface of the photosensitive drum 1. The developing roller 3 develops the electrostatic latent image by attaching toner contained in a toner container 6 to the electrostatic latent image, forming a toner image on the surface of the photosensitive drum 1. The developing roller 3 and the toner container 6 constitute a developing unit.

[0014] A yellow toner image is formed on the surface of the photosensitive drum 1Y of the image forming unit 5Y. A magenta toner image is formed on the surface of the photosensitive drum 1M of the image forming unit 5M. A cyan toner image is formed on the surface of the photosensitive drum 1C of the image forming unit 5C. A black toner image is formed on the surface of the photosensitive drum 1K of the image forming unit 5K.

[0015] The intermediate transfer belt 11 is an endless belt member that is wound around a drive roller 12, a tension roller 13, and an opposing roller 15. The outer side of the intermediate transfer belt 11 contacts the photosensitive drums 1 of each color. On the inner side of the intermediate transfer belt 11, a primary transfer roller 10 is disposed in a position facing the photosensitive drum 1. When a transfer voltage is applied, the primary transfer roller 10 transfers a toner image from the corresponding photosensitive drum 1 to the intermediate transfer belt 11. The intermediate transfer belt 11 rotates in the direction of the arrow in the figure.

[0016] The toner image is negatively charged, for example, and is transferred to the intermediate transfer belt 11 by applying a positive voltage to the primary transfer roller 10. The transfer of the toner image by the primary transfer roller 10 is performed so that the toner images of each color are superimposed on the intermediate transfer belt 11 at a timing determined by the rotation speed of the intermediate transfer belt 11 and the intervals between the photosensitive drums 1Y, 1M, 1C, and 1K of each color. The toner images are transferred in the order of yellow (Y), magenta (M), cyan (C), and black (K).

[0017] The intermediate transfer belt 11 rotates to transport the transferred toner images of each color to an opposing roller 15. The opposing roller 15 forms a secondary transfer section with a secondary transfer roller 14 disposed opposite the intermediate transfer belt 11. In the secondary transfer section, the toner images of each color carried on the intermediate transfer belt 11 are transferred all at once to a recording material.

[0018] The image forming apparatus 100 includes a paper feed mechanism 20 that feeds sheet-like recording materials S, and a conveying path 34 that conveys the recording materials S fed from the paper feed mechanism 20. The paper feed mechanism 20 includes a paper feed cassette 21, a paper feed roller 22, a conveying roller 23, and a separation roller 24. The paper feed cassette 21 stores a stack of recording materials S. The paper feed roller 22 feeds the recording materials S stored in the paper feed cassette 21. The conveying roller 23 conveys the recording materials S fed by the paper feed roller 22 to the conveying path 34. The conveying roller 23 and the separation roller 24 form a pair and separate and convey the recording materials S one by one.

[0019] The conveying path 34 is provided with a pair of registration rollers 25, a secondary transfer roller 14, a fixing device 30, and a discharge roller 33. The pair of registration rollers 25 corrects any skew of the recording material S conveyed from the paper feed mechanism 20. The pair of registration rollers 25 temporarily stops the conveyance of the recording material S and conveys the recording material S to the secondary transfer section (secondary transfer roller 14) in accordance with the timing at which the toner image carried on the intermediate transfer belt 11 is conveyed to the secondary transfer section. The secondary transfer roller 14 transfers the toner images of each color from the intermediate transfer belt 11 to the recording material S all at once by applying, for example, a positive voltage.

[0020] The secondary transfer roller 14 transports the recording material S onto which the toner image has been transferred to the fixing device 30. The fixing device 30 includes a fixing film 31 having a heat source such as a heater, and a pressure roller 32. The fixing device 30 fixes the toner image onto the recording material S by sandwiching and transporting the recording material S between the fixing film 31 and the pressure roller 32. When sandwiching and transporting the recording material S, the fixing device 30 heats the toner image with the fixing film 31 (heat source), and applies pressure by pressing the recording material S towards the fixing film 31 with the pressure roller 32. The toner image melts and mixes colors when heated, and is fixed to the recording material S by applying pressure. The discharge roller 33 discharges the recording material S onto which the image has been fixed by the fixing device 30 out of the image forming apparatus 100.

[0021] The image forming apparatus 100 includes an operation unit 140 as a user interface. The operation unit 140 includes an input interface for receiving instructions and input of setting values ​​from the user, and an output interface for outputting various information to the user. The input interface is, for example, key buttons, a touch panel, etc. The output interface is, for example, a display 1401, a speaker, etc. The operation unit 140 is provided, for example, on the top of the image forming apparatus 100. Details of the operation unit 140 will be described later.

[0022] A plurality of conveying path sensors 27 (27a, 27b, 27c) are arranged along the conveying path 34 to detect the recording material S being conveyed along the conveying path 34. The conveying path sensor 27a is provided between the conveying roller 23 and the pair of registration rollers 25. The conveying path sensor 27b is provided between the pair of registration rollers 25 and the secondary transfer roller 14. The conveying path sensor 27c is provided between the secondary transfer roller 14 and the fixing device 30.

[0023] The image forming apparatus 100 determines whether or not a transport abnormality such as early arrival, delay, or jam of the recording material S has occurred based on the detection result of the transport path sensor 27. If it is determined that a transport abnormality has occurred, the image forming apparatus 100 displays a message on the display 1401 informing the user that a transport abnormality has occurred. Furthermore, the image forming apparatus 100 provides guidance on a method for resolving the transport abnormality as necessary.

[0024] 2 is an explanatory diagram of the paper feeding operation by the paper feeding mechanism 20. FIG. 2 shows the state in which the recording material S is fed from the paper feed cassette 21 and conveyed to the pair of registration rollers 25.

[0025] 2A illustrates a state in which the uppermost recording material S1 is being fed out of the multiple recording materials S stacked in the paper feed cassette 21. The multiple recording materials S are positioned by having their ends pressed against a trailing end regulating plate 26 provided in the paper feed cassette 21. When feeding of the recording material S1 begins, the end (leading end) opposite the trailing end regulating plate 26 is at position Ps.

[0026] When the paper feeding operation starts, the paper feed roller 22 and the conveying roller 23 each start rotating. As the paper feed roller 22 rotates, the recording material S starts moving to the right (paper feeding direction) in FIG. 2A due to the frictional force between the paper feed roller 22 and the recording material S. Having started moving, the recording material S1 reaches the separation nip Pn formed by the conveying roller 23 and the separation roller 24.

[0027] 2B illustrates a state in which the leading edge of recording material S1 has reached the separation nip Pn. During sheet feeding, frictional force is generated between recording material S1 and recording material S2, which is the second-highest sheet. This frictional force may cause recording material S2 to move together with recording material S1.

[0028] At the separation nip Pn, when two or more sheets of recording material S1 and S2 are conveyed by the rotation of the paper feed roller 22, recording material S2 is separated and only recording material S1 is conveyed downstream. A torque limiter (not shown) is connected to the separation roller 24, and torque is applied as a resistance force in the direction opposite to the conveyance direction of the recording material S1. This torque is set so that when only one sheet of recording material S is conveyed to the separation nip Pn, the separation roller 24 rotates in response to the conveyance roller 23, and when two or more sheets of recording material S are conveyed to the separation nip Pn, the separation roller 24 stops. With this setting, the recording materials are separated one by one at the separation nip Pn and conveyed downstream.

[0029] As the paper feed roller 22 and the conveyance roller 23 continue to rotate, the leading edge of the recording material S1 that has passed through the separation nip portion Pn reaches the detection position Pra of the conveyance path sensor 27a. FIG. 2(c) illustrates a state in which the leading edge of the recording material S1 has reached the detection position Pra. The time from the start of the paper feed operation until the leading edge of the recording material S1 reaches the detection position Pra is referred to as the "conveyance time." Here, the start of the paper feed operation is the timing at which the paper feed roller 22 changes from a stopped state to a rotating state. The paper feed roller 22 starts rotating based on a rotation start signal. Therefore, the start of the paper feed operation may be the timing at which the rotation start signal is output.

[0030] (machine learning system) 3 is a configuration diagram of a machine learning system including an image forming apparatus 100 of this embodiment. The machine learning system 500 is configured by connecting the image forming apparatus 100, a machine learning server 102, a data server 105, a general-purpose computer 103, etc. so that they can communicate with each other via a network 104. The general-purpose computer 103 transmits image data to the image forming apparatus 100, etc. A plurality of image forming apparatuses 100 and a plurality of general-purpose computers 103 may be connected to the network 104. The network 104 is, for example, a wired local area network (LAN), a wireless LAN, a public communication line, etc.

[0031] The image forming apparatus 100 is equipped with an AI (Artificial Intelligence) function. The machine learning server 102 is an information processing apparatus that generates a trained model used in the AI ​​function. The data server 105 is an information processing apparatus that collects training data used by the machine learning server 102 to perform machine learning from an external device and stores the data to provide to the machine learning server 102. In this case, the external device is the image forming apparatus 100 (or a general-purpose computer 103) connected to the network 104.

[0032] The image forming apparatus 100 realizes a specific AI function by acquiring a generated trained model from the machine learning server 102 as needed. The machine learning server 102 acquires training data necessary for training the trained model to realize the specific AI function from external devices such as the data server 105, the image forming apparatus 100, and the general-purpose computer 103. The machine learning server 102 is capable of generating a trained model by performing machine learning using at least a portion of the training data acquired from the external devices.

[0033] 4 is a hardware configuration diagram of the image forming apparatus 100. The image forming apparatus 100 includes an operation unit 140, a controller 1200, a reader 250, and a printer 210. The operation unit 140, the reader 250, and the printer 210 are connected to the controller 1200. The controller 1200 controls the operations of the operation unit 140, the reader 250, and the printer 210, and communicates with the machine learning server 102, the data server 105, and the general-purpose computer 103 via the network 104.

[0034] The reader 250 is an image reading device that reads an image in response to an instruction from the operation unit 140. The reader 250 has a processor that controls the reader 250, a light source for reading the image, a scanning mirror, and a light receiving unit. The printer 210 has a configuration that prints an image on the lower recording material S.

[0035] The controller 1200 includes a system bus 1207 and an image bus 2008. The system bus 1207 and the image bus 2008 are communicatively connected via a bus interface (I / F) 1205. The bus I / F 1205 is a bus bridge that performs processes such as data structure conversion between the system bus 1207 and the image bus 2008.

[0036] A CPU (Central Processing Unit) 1201, RAM (Random Access Memory) 1202, ROM (Read Only Memory) 1203, and storage 1204 are connected to a system bus 1207. The CPU 1201 controls the operation of the image forming apparatus 100 by executing computer programs stored in the ROM 1203 and storage 1204. A boot program is stored in the ROM 1203. The storage 1204 stores system software, image data, software counter values, etc.

[0037] The RAM 1202 provides a work area when the CPU 1201 executes processing, and stores temporary data, etc. The RAM 1202 stores image formation conditions, control tables, conversion tables, etc. The storage 1204 is a large-capacity storage device, such as an HDD (Hard Disk Drive) or SSD (Solid State Drive). The RAM 1202 or the storage 1204 records output attribute information, including the user name, number of copies, color printing, etc., when a print job or copy job is executed, as well as the job execution history, as job log information.

[0038] The system bus 1207 is connected to interfaces including an operation unit I / F 1206, a wired communication I / F 1210, a modem 1211, a wireless communication I / F 1270, and a communication I / F 1208. The operation unit I / F 1206 is connected to the operation unit 140, receives instructions from the operation unit 140, transmits them to the CPU 1201, and outputs various information from the operation unit 140 (display 1401) in response to instructions from the CPU 1201. The wired communication I / F 1210 and the wireless communication I / F 1270 are communication interfaces for communicating via the network 104. The wireless communication I / F 1270 can control communication with the network 104 via a wireless line 106. The modem 1211 is connected to a public line 3001, and communicates (sends and receives) data with an external facsimile machine (not shown). The communication I / F 1208 controls communication between the reader 250 and the printer 210.

[0039] A GPU (Graphics Processing Unit) 1291 and a timer 1209 are connected to the system bus 1207. The GPU 1291 is capable of performing efficient calculations by processing large amounts of data in parallel, and is therefore effective when performing learning multiple times using a learning model such as deep learning. In this embodiment, when performing machine learning, the CPU 1201 and the GPU 1291 cooperate to execute the process. Note that, when the processing capabilities of the CPU 1201 and the GPU 1291 are high, the machine learning may be performed independently by the CPU 1201 or the GPU 1291.

[0040] To the image bus 2008, a RIP (Raster Image Processor) unit 1260, a reader image processing unit 1280, a printer image processing unit 1290, an image rotation unit 1230, an image compression unit 1240, and a device I / F 1220 are connected.

[0041] The RIP unit 1260 converts a PDL (Page Description Language) record included in a print job acquired from the general-purpose computer 103 into a bitmap image. The reader image processing unit 1280 performs image processing such as correction, processing, and editing on image data acquired from the reader 250. The image data acquired from the reader 250 is read data representing an image read from an original by the reader 250. The printer image processing unit 1290 performs image processing such as correction and resolution conversion on image data representing an image to be output (printed) by the printer 210. The image rotation unit 1230 performs image rotation on the image data. The image compression unit 1240 performs image compression and expansion processing. For example, the image compression unit 1240 performs expansion and compression processing on multi-value image data based on the JPEG standard and on binary image data based on the JBIG, MMR, or MH standard. The device I / F 1220 converts image data between synchronous and asynchronous systems between the reader 250, printer 210, and controller 1200.

[0042] (machine learning server) 5 is a configuration diagram of the machine learning server 102. The machine learning server 102 includes a CPU 1301, RAM 1302, ROM 1303, storage 1304, an IO unit 1305, a GPU 1306, and a communication I / F 1310. These components are connected to a system bus 1307. The machine learning server 102 is connected to an operation unit 1311 that includes a display 1312 such as a touch panel and an input device.

[0043] The CPU 1301 controls the operation of the machine learning server 102 by executing computer programs stored in the ROM 1303 and storage 1304. The RAM 1302 provides a work area when the CPU 1301 executes processing, and stores temporary data, etc. The ROM 1303 stores a BIOS (Basic Input Output System), an OS (Operating System) startup program, setting files, etc. The storage 1304 is a large-capacity storage device such as an HDD or SSD. The storage 1304 stores system software, etc. The communication I / F 1310 is connected to the network 104 and controls communication with other devices connected to the network 104, such as the image forming apparatus 100.

[0044] The IO unit 1305 is an interface with the operation unit 1311. Predetermined information is displayed on a display 1312 of the operation unit 1311 at a predetermined resolution, number of colors, etc. For example, a GUI (Graphical User Interface) screen is formed on the display 1312 of the operation unit 1311, and various windows, data, etc. required for operation are displayed.

[0045] The GPU 1306 is capable of performing efficient calculations by processing large amounts of data in parallel, and is therefore effective when performing learning multiple times using a learning model such as deep learning. In this embodiment, when performing machine learning, the CPU 1301 and the GPU 1306 cooperate to execute processing. Specifically, when executing a learning program including a learning model, the CPU 1301 and the GPU 1306 cooperate to execute processing, thereby performing learning. If the processing capabilities of the CPU 1301 and the GPU 1306 are each high, the machine learning may be performed independently by the CPU 1301 or the GPU 1306.

[0046] The following describes how to use the GPU 1291 of the image forming apparatus 100 and the GPU 1306 of the machine learning server 102. The computational resources of the GPUs 1291 and 1306 are effectively utilized depending on the communication load of the network 104, the processing load of each GPU 1291 and 1306, the power saving mode of the image forming apparatus 100, and the like. For example, when the image forming apparatus 100 transitions to the power saving mode, the GPU 1306 on the machine learning server 102 side is actively utilized. When the communication load is heavy, the GPU 1291 on the image forming apparatus 100 side is utilized.

[0047] (function block) 6 is a functional block diagram for performing machine learning using the machine learning system 500 of this embodiment. The machine learning system 500 learns information for the image forming apparatus 100 to feed the recording material S, and performs processing for estimating the state of the paper feed mechanism 20 due to the feeding operation of the recording material S. The functional block diagram of FIG. 6 shows the functional blocks for performing such processing. The machine learning system 500 is configured to include the image forming apparatus 100, a data server 105, and a risk rate calculation unit 107.

[0048] Each function of the image forming apparatus 100 is realized, for example, by the CPU 1201 and GPU 1291 working together to execute a computer program in the hardware configuration of Fig. 4. The risk rate calculation unit 107 is realized by the machine learning server 102. Each function of the risk rate calculation unit 107 of the machine learning server 102 is realized, for example, by the CPU 1301 and GPU 1306 working together to execute a computer program in the hardware configuration of Fig. 5. The same is true for each function of the data server 105, which is realized by a CPU (not shown) included in the data server 105 executing a computer program.

[0049] The image forming apparatus 100 functions as a paper feed unit 501, a drive unit 502, a measurement unit 503, and a detection unit 504. The image forming apparatus 100 includes a paper feed motor 90 and a paper feed solenoid 91 for performing paper feed operations. The data server 105 functions as a data collection and provision unit 510 and a data storage unit 512. The risk rate calculation unit 107 functions as a learning data generation unit 513, a machine learning unit 514, and a data storage unit 515.

[0050] When image forming apparatus 100 receives a print instruction from operation unit 140 or general-purpose computer 103, paper feed unit 501 instructs drive unit 502 to start paper feed operation. Paper feed unit 501 instructs drive unit 502 to start paper feed operation by sending a rotation start signal to drive unit 502. When drive unit 502 receives the instruction to start paper feed operation from paper feed unit 501, it rotates paper feed motor 90 to rotate conveyance roller 23 and separation roller 24. At the timing to start paper feed, drive unit 502 drives paper feed solenoid 91 to rotate paper feed roller 22 one rotation.

[0051] By such operation of the paper feed motor 90 and the paper feed solenoid 91, the recording materials S pushed up in the paper feed cassette 21 are separated and fed one by one and conveyed to the conveying path 34. The recording materials S conveyed along the conveying path 34 pass through the detection position Pr of the conveying path sensor 27 and are conveyed to the secondary transfer roller 14.

[0052] The measuring unit 503 and the detecting unit 504 are used to measure the conveying time. The detecting unit 504 determines whether the leading edge of the recording material S has reached the detection position Pra of the conveying path sensor 27a based on a signal (detection signal) indicating the detection result obtained from the conveying path sensor 27a. The detecting unit 504 detects that the leading edge of the recording material S has reached the detection position Pra of the conveying path sensor 27a when the detection signal obtained from the conveying path sensor 27a changes from a state in which the recording material S is not detected to a state in which the recording material S is detected.

[0053] The measurement unit 503 measures the transport time from the timing when the paper feed unit 501 issues a command to start the paper feed operation until the leading edge of the recording material S reaches the detection position Pra of the transport path sensor 27a. Specifically, the measurement unit 503 uses the timer 1209 to measure the time from the timing when the rotation start signal is received from the paper feed unit 501 until the timing when the measurement unit 503 receives a signal from the detection unit 504 indicating that the leading edge of the recording material S has reached the detection position Pra. This measurement is performed each time one sheet of recording material S is fed. The measured time is stored in the RAM 1202 as transport time data. The measurement unit 503 is implemented by, for example, the CPU 1201 and the timer 1209. The transport time data stored in the RAM 1202 is collected by a data collection and provision unit 510 of the data server 105 and also stored in the data storage unit 512.

[0054] The machine learning unit 514 classifies a set of transportation time data stored in the data storage unit 512 into a plurality of subsets based on a predetermined criterion. The machine learning unit 514 performs machine learning using the learning data generated by the learning data generation unit 513 as input. The machine learning unit 514 performs machine learning based on a learning method using a learning model, which will be described later with reference to FIG. 7.

[0055] (Learning model) Fig. 7 is an explanatory diagram of a learning model of machine learning performed by the machine learning unit 514 of the machine learning server 102. Fig. 7 shows the input / output structure using the learning model by the machine learning unit 514, and illustrates a learning model using a neural network.

[0056] In the neural network shown in Fig. 7(a), set values ​​or measured values ​​that can be obtained in the image formation state and the non-image formation state are used as input data X. Here, examples of input data X include X1 to X7 related to the generation of a learning model for predicting the state of the paper feed roller 22. In the neural network shown in Fig. 7(b), examples of input data X include X1 to X11 related to the generation of a learning model for predicting the jam risk rate of the paper feed roller 22. Here, the jam risk rate is the risk of a jam occurring expressed as a percentage.

[0057] The elements of the learning data are not limited to data related to the state of the paper feed roller 22, and may also include data obtainable from sensors provided in the image forming apparatus 100. When data expressed as categorical variables, such as paper settings, double-sided printing, and continuous or intermittent operation, are handled as numerical values ​​in machine learning, the data is preprocessed by converting the expression into numerical values ​​using a known method such as one-hot encoding.

[0058] Specific examples of machine learning algorithms include neural networks, nearest neighbor methods, naive Bayes methods, decision trees, and support vector machines. Deep learning, which uses neural networks to generate features and connection weighting coefficients for learning, is also an example. Any of the above algorithms that can be used can be used as appropriate and applied to this embodiment.

[0059] As shown in FIG. 7(c), the learning model (W) may include an error detection unit and an update unit. The error detection unit, for example, uses a loss function to derive a loss (L) representing the error between the training data T and output data Y (4) output from the output layer of the neural network in response to input data X (2) input to the input layer. The update unit updates the connection weighting coefficients between the nodes of the neural network so as to reduce the loss (L) obtained by the error detection unit. The update unit updates the connection weighting coefficients, for example, using backpropagation. The backpropagation is a technique for adjusting the connection weighting coefficients between the nodes of each neural network so as to reduce the error between the output data Y and the training data T.

[0060] The learning model (W) prepares a large amount of training data, each pair consisting of "input data with known correct values" and "correct values," and adjusts the weighting coefficients within the learning model (W) so that when input data corresponding to this correct value is input, the output comes as close as possible to the correct value. By performing this type of processing, the learning model (W) becomes a highly accurate learning model (W). This type of processing is called the "learning process," and the learning model that has been adjusted through the learning process is called the "trained model."

[0061] The prepared training data T is a set of "input data with known correct values" and "correct values." The learning model in the machine learning unit 514 is not limited to the deep learning system described above, and a model based on linear regression or nonlinear regression may also be applied. There is no problem if the learning model calculates the correct value by multiplying the input data by a known coefficient.

[0062] (Determine the condition of the paper feed roller) The risk rate calculation unit 107 acquires characteristic values ​​for determining the state of the paper feed roller 22. The characteristic values ​​are, for example, the transport time from when the paper feed roller 22 starts feeding the recording material S until the transport path sensor 27a detects the leading edge of the recording material S, and the drive current value (torque) generated in the paper feed motor 90 that drives the paper feed roller 22. The transport time is a characteristic value related to transport (paper feeding) by the paper feed roller 22. Similarly, the drive current value (torque) is also a characteristic value related to transport (paper feeding) by the paper feed roller 22.

[0063] The risk rate calculation unit 107 collects statistics on the characteristic values ​​and creates a histogram for every certain number of sheets (every 1000 sheets in this embodiment), and calculates the transport time histogram, summary statistics, histogram evaluation index, and histogram-derived feature amount, which are the input data X shown in FIG. 7(a), as explanatory variables. Based on the calculated explanatory variables, the risk rate calculation unit 107 determines the state of the sheet feed roller 22 using a machine learning model, LGBTC (Light Gradient Boosted Trees Classifier). The summary statistics are statistical data such as the maximum value, minimum value, mean value, standard deviation, variance, skewness, kurtosis, median, first quartile, and third quartile, which are obtained from the histogram of the characteristic values.

[0064] The risk rate calculation unit 107 classifies the state of the paper feed roller 22 into normal / worn / contaminated / damaged / paper based on the machine learning model LGBTC. The risk rate calculation unit 107 notifies the customer engineer of the percentage probability of each classified state. The notification is performed, for example, by displaying the information on the display 1312 of the operation unit 1311 or the display 1401 of the image forming apparatus 100. The machine learning model LGBTC can calculate the probability that a delay in transport time occurs due to wear or contamination, as well as the probability that a delay in transport time occurs due to damage to parts or that transport time varies due to improper loading of the recording material S.

[0065] (Determine the condition of the paper feed roller, transport roller, and separation roller) As described above, the paper feed mechanism 20 includes the paper feed roller 22, the conveying roller 23, and the separation roller 24. The risk rate calculation unit 107 acquires, as characteristic values, the conveying time from the start of the paper feed operation until the conveying path sensor 27a detects the leading edge of the recording material S, and the driving current value (torque) of the paper feed motor 90 from the start of driving each roller until the conveying path sensor 27a detects the leading edge of the recording material S.

[0066] The risk rate calculation unit 107 aggregates the characteristic values ​​for each set number of sheets (every 1000 sheets in this embodiment), creates a histogram for each roller, and calculates the input data X in Fig. 7(a) as summary statistics for each roller. The risk rate calculation unit 107 uses the calculated summary statistics to determine the state of each of the paper feed roller 22, the conveyance roller 23, and the separation roller 24 using the machine learning model LGBTC.

[0067] The risk rate calculation unit 107 classifies the determined states of the paper feed roller 22, the conveyance roller 23, and the separation roller 24 into normal / worn / contaminated / damaged / paper. The risk rate calculation unit 107 calculates the probability of each state of the paper feed roller 22, the conveyance roller 23, and the separation roller 24, and notifies the customer engineer of the calculated state probability. The display 1312 of the operation unit 1311 and the display 1401 of the image forming apparatus 100 display the calculated state probability based on the notification. Alternatively, the display 1312 of the operation unit 1311 and the display 1401 of the image forming apparatus 100 may be configured to display the state with the highest probability.

[0068] (Calculation of the deterioration (wear) level of the paper feed roller) The risk rate calculation unit 107 calculates the wear level of the paper feed roller 22 when the probability that a delay in transport time is occurring due to wear or contamination of the paper feed roller 22 is higher than a predetermined threshold (for example, 50%). For example, when the probability that a delay in transport time is occurring is higher than the threshold, the risk rate calculation unit 107 calculates the difference between each of the summary statistics and a corresponding reference value based on a machine learning model that calculates the wear level. The risk rate calculation unit 107 calculates the average value of the ratio of the difference for each of the calculated summary statistics as the wear level of the paper feed roller 22. The risk rate calculation unit 107 determines the risk of a jam occurring (jam risk) based on the wear level of the paper feed roller 22.

[0069] Summary statistics include the maximum value, minimum value, mean value, standard deviation, variance, skewness, kurtosis, median, first quartile, third quartile, etc., obtained from a histogram. Note that the input data X for the model to calculate the wear level may include the cumulative number of retries, the cumulative number of jams, and a parts counter. For example, XGBTR (eXtreme Gradient Boosted Trees Regressor with Early Stopping) is used as the machine learning model to calculate the wear level.

[0070] The risk rate calculation unit 107 notifies the display 1401 of the operation unit 140 of the jam risk rate of the paper feed roller 22 calculated by machine learning. This notifies the customer engineer of the jam risk rate. The notification of the jam risk rate enables the customer engineer to determine the timing of replacing the paper feed roller 22. Furthermore, by calculating the jam risk rates for the transport roller 23 and the separation roller 24, it is also possible to notify the customer of the jam risk rate of the paper feed mechanism 20 in more detail.

[0071] (Determining the index for determining whether or not the paper feed roller needs to be replaced) The risk rate calculation unit 107 determines an index for determining whether or not the paper feed roller 22 needs to be replaced. The paper feed roller 22 undergoes deterioration over time as the number of sheets of recording material S fed increases, and it becomes necessary to replace it. As the paper feed roller 22 deteriorates over time, for example, the frictional force on the surface of the paper feed roller 22 changes, causing the conveying time to increase. Therefore, whether or not the paper feed roller 22 needs to be replaced is determined based on the conveying time.

[0072] For example, the risk rate calculation unit 107 calculates (acquires) at least two statistics (here, a first statistic and a second statistic) from the statistical results of the transport time by performing different arithmetic processing. Based on the two calculated statistics, the risk rate calculation unit 107 determines an index for determining whether or not the paper feed roller 22 needs to be replaced. The statistics are, for example, summary statistics obtained from a histogram of the transport time, such as maximum value, minimum value, mean value, standard deviation, variance, skewness, kurtosis, median, first quartile, third quartile, mode, outlier, etc. The first statistic and second statistic are a combination of two predetermined statistics from these statistics.

[0073] Here, we will explain the case where "median" and "outlier" are used as statistical quantities. Figure 8 is an example diagram of a histogram showing the statistical results of transport time. Figure 8(a) is a histogram showing the statistical results of the transport time for the most recent 1000 sheets (4001st to 5000th sheets) when the cumulative number of printed sheets is 5000. Figure 8(b) is a histogram showing the statistical results of the transport time for the most recent 1000 sheets (19001st to 20000th sheets) when the cumulative number of printed sheets is 20000. In Figures 8(a) and 8(b), a design value and a threshold time that serves as a criterion for determining whether replacement is necessary are set for the statistical quantity. If the transport time exceeds the threshold time, it is determined that the paper feed roller 22 needs to be replaced.

[0074] In FIG. 8(a), the number of conveyed recording materials S is small, so there is little wear on the surface of the paper feed roller 22 and a small decrease in frictional force. As a result, the median value of the conveyance time is shifted toward the threshold time from the design value of the conveyance time (target conveyance time), but the time difference from the threshold time is sufficiently large. The time difference from the threshold time for the outliers is also sufficiently large. The time difference between the outliers and the threshold time is called the margin.

[0075] In Figure 8(b), the number of conveyed recording materials S is large, which causes wear on the surface of the paper feed roller 22 and significantly reduces the frictional force. As a result, the median value of the conveyance time is shifted closer to the threshold time than in Figure 8(a), and the time difference from the threshold time is smaller than in Figure 8(a). For the outliers, the time difference from the threshold time (margin) is also smaller than in Figure 8(a).

[0076] The index for determining whether or not replacement of the paper feed roller 22 is necessary is determined from the relationship between the statistical results (statistical values) of the transport time and the threshold time. As an example, a method for calculating the index will be described below.

[0077] The risk rate calculation unit 107 calculates the difference (first difference) between the median and the threshold time. The risk rate calculation unit 107 calculates a first ratio from the first difference. The first ratio is calculated by the following formula. (First ratio) = {(First difference) / |Threshold time - Design value|} × 100

[0078] The risk rate calculation unit 107 calculates the difference (second difference) between the outlier and the threshold time. The risk rate calculation unit 107 calculates the second ratio from the second difference. The second ratio is calculated by the following formula. (Second ratio) = {(Second difference) / |Threshold time - Design value|} × 100

[0079] The risk rate calculation unit 107 determines the average value of the calculated first rate and second rate or (first rate x α + second rate x β) as an index for determining whether or not replacement of the paper feed roller 22 is necessary. The index determined in this manner is notified to a customer engineer. The notification is performed, for example, by displaying it on the display 1312 of the operation unit 1311 or the display 1401 of the image forming apparatus 100.

[0080] As described above, the combination of the first statistic and the second statistic may be any two of the maximum value, minimum value, mean value, standard deviation, variance, skewness, kurtosis, median, first quartile, third quartile, mode, outlier, etc. In any case, a first ratio is calculated from the first statistic and the threshold time, and a second ratio is calculated from the second statistic and the threshold time. An index for determining whether or not the paper feed roller 22 needs to be replaced is determined based on the first ratio and the second ratio. Also, the case where an index is determined to determine whether or not replacement of the paper feed roller 22 is necessary has been described above. Similar processing can be used to determine indexes to determine whether or not replacement of the conveying rollers that convey the recording material S, such as the conveying roller 23, separation roller 24, registration roller pair 25, and discharge roller 33, is necessary.

[0081] The above-described processes of determining the state of the paper feed roller 22, determining the states of the paper feed roller 22, the conveying roller 23, and the separation roller 24, calculating the deterioration level (wear level) of the paper feed roller 22, and determining an index for determining whether or not the paper feed roller 22 needs to be replaced may be performed by the image forming apparatus 100. In this case, the image forming apparatus 100 includes all the functions of the risk rate calculation unit 107. Furthermore, the image forming apparatus 100 and the risk rate calculation unit 107 may cooperate to perform each process.

[0082] The processes of determining the state, calculating the degree of wear, and determining the index for determining whether replacement is necessary may be performed on other rollers that transport the recording material S, such as the registration roller pair 25. When performed on the registration roller pair 25, the transport time is obtained, for example, from the detection results of the transport path sensor 27a and the transport path sensor 27b. For example, the transport time is the time from when the transport path sensor 27a no longer detects the recording material S to when the transport path sensor 27b detects the recording material S.

[0083] The processes of determining the state, calculating the degree of wear, and determining an index for determining whether replacement is necessary can be performed not only on the rollers that transport the recording material S, but also on the photosensitive drum 1 and intermediate transfer belt 11. When processing is performed on the photosensitive drum 1, for example, image density is used as the characteristic value. An image formed on the photosensitive drum 1 under predetermined image formation conditions (charge potential, laser light amount, toner concentration, etc.) is detected on the photosensitive drum 1, and the image density becomes the characteristic value. First and second statistics obtained from the characteristic values ​​of a predetermined number of sheets are compared with threshold values ​​that serve as criteria for determining whether replacement is necessary. Based on the comparison result, an index for determining whether replacement is necessary is determined. Similar processes are performed on the intermediate transfer belt 1.

[0084] In this way, the processing of this embodiment is effective for replacement parts that require replacement due to image formation. An index for determining whether or not the replacement part needs to be replaced is determined based on a plurality of statistics obtained from characteristic values ​​that represent the operating state of the replacement part and threshold values ​​that serve as criteria for determining whether or not the replacement is necessary.

[0085] (Operation unit) 9 is an explanatory diagram of the operation unit 140. As described above, the operation unit 140 includes a display 1401 which is an input interface and an output interface. In this embodiment, various key buttons and a touch panel 1411 are provided as the input interface. The key buttons include a setting key 1403, a power saving key 1404, a hard key group 1405, a reset key 1406, a stop key 1407, and a start key 1408. The touch panel 1411 is provided on the display 1401. An operation screen is displayed on the display 1401 under the control of the CPU 1201. In this embodiment, an operation screen including software keys for selecting whether to enable or disable jam risk rate calculation is displayed on the display 1401.

[0086] When a key button or software key is operated, information corresponding to the operated key is sent to the CPU 1201 via the operation unit I / F 1206. A start key 1408 is used to issue an instruction to start a process such as a copy process or a print process. The start key 1408 is equipped with two LEDs (light-emitting diodes) in green and red (not shown). The LED indicates that the process can be started when lit green, and that the process cannot be started when lit red. A stop key 1407 is used to stop an operation that is currently running. The hard key group 1405 includes a numeric keypad, a clear key, and an authentication key.

[0087] The power saving key 1404 is used to switch the image forming apparatus 100 into sleep mode or to return from sleep mode. The image forming apparatus 100 switches into sleep mode when the power saving key 1404 is pressed in normal mode, and switches back to normal mode when the power saving key 1404 is pressed in sleep mode. The setting key 1403 is used to set AI function settings and the like. The operation unit 140 is also used to input information necessary for creating job information, such as a user name, number of copies to be printed, and output attribute information.

[0088] 10 is a diagram showing an example of an operation screen displayed on the display 1401. This operation screen shows an example of a selection screen for selecting whether to enable or disable the jam risk rate calculation. The selection screen is displayed, for example, by pressing a software key for starting the selection of the jam risk rate display from the menu screen, which is the initial screen.

[0089] The selection screen displays a selection button 1402 that allows the selection of whether to enable (ON) or disable (OFF) the calculation of the jam risk rate. The selection button 1402 is used to select the setting (enabled / disabled) for each trained model. The user selects the selection button 1402 and presses the OK button 1412 to select either enabling or disabling the calculation of the jam risk rate. The selection result is sent to the CPU 1201. The CPU 1201 saves the selection result in the RAM 1202. The CPU 1201 executes processing based on the content saved in the RAM 1202. Note that the index determination process for determining whether replacement of a replacement part is necessary can also be set on the same selection screen.

[0090] 11 is an example of a detailed display of the jam risk rate for each roller. The detailed display makes it possible to display the jam risk rate for each roller status classification. Note that the information displayed on the display 1401 can also be disclosed only to customer engineers, and not to users.

[0091] The display on the display 1401 can also be performed by an external terminal other than the display 1401. FIG. 12 is a diagram illustrating an example of detailed display of the jam risk rate on an external terminal. The external terminal can communicate with the image forming apparatus 100 via a predetermined network. An application for displaying an operation screen and detailed display of the jam risk rate is installed in the external device. The image forming apparatus 100 transmits data for displaying the jam risk rate for each roller condition classification to the external device. The external device displays detailed information about the jam risk rate based on data acquired from the image forming apparatus 100.

[0092] Alternatively, the external device may be configured to include a risk rate calculation unit 107, which acquires the transport time (or drive current value) and notifies the jam risk rate based on the transport time (or drive current value) based on the above-mentioned processing. In this case, the external device functions as an information processing device that notifies the jam risk rate.

[0093] According to the present embodiment as described above, customer engineers can grasp the jam risk rate, and as a result, it becomes possible to improve the efficiency of roller maintenance planning.

[0094] 11 and 12, it is also possible to display an indicator for determining whether a replacement part is necessary. Furthermore, the indicator for determining whether a replacement part is necessary allows the customer engineer to determine whether a replacement part is necessary.

Claims

1. an image forming means for forming an image on a recording material; a roller for conveying the recording material; an acquisition means for acquiring a characteristic value related to the conveyance by the roller; and a notification unit that notifies a user of a risk of jamming based on the characteristic value acquired by the acquisition unit.

2. further comprising a display means for displaying the status of the image forming apparatus; 2. The image forming apparatus according to claim 1, wherein the notification unit notifies the risk of jamming to the display unit.

3. The image forming apparatus according to claim 1, characterized in that the notification means acquires statistical data of the characteristic values, calculates a first value from the statistical data by a first calculation process, calculates a second value from the statistical data by a second calculation process different from the first calculation process, and acquires an index indicating the risk of a jam occurring based on the first value and the second value.

4. 2. The image forming apparatus according to claim 1, wherein the notification unit acquires statistical data obtained by collecting statistics on the characteristic values, acquires at least two statistical quantities, namely, the maximum value of the statistical data, the minimum value of the statistical data, the average value of the statistical data, the standard deviation of the statistical data, the variance of the statistical data, the skewness of the statistical data, the kurtosis of the statistical data, the median of the statistical data, the first quartile of the statistical data, and the third quartile of the statistical data, and notifies the user of the risk of a jam occurring based on the acquired statistical quantities.

5. a sensor for detecting the recording material conveyed by the roller; 2. The image forming apparatus according to claim 1, wherein the characteristic value is a conveying time of the recording material detected by the sensor.

6. 2. The image forming apparatus according to claim 1, wherein the characteristic value is a driving current of a motor used to drive the roller.

7. 2. The image forming apparatus according to claim 1, wherein the risk is expressed as a percentage.

8. An information processing apparatus communicably connected to an image forming apparatus that forms an image on a recording material, an acquiring unit for acquiring a characteristic value relating to conveyance of a roller that conveys the recording material in the image forming apparatus; and a notification unit that notifies a user of a risk of a jam occurring in the image forming apparatus based on the characteristic value acquired by the acquisition unit.

9. further comprising a display means for displaying the status of the image forming apparatus; 9. The information processing apparatus according to claim 8, wherein the notification means notifies the display means of the risk of jamming.

10. The information processing device according to claim 8, characterized in that the notification means acquires statistical data obtained by calculating the characteristic values, calculates a first value from the statistical data by a first calculation process, calculates a second value from the statistical data by a second calculation process different from the first calculation process, and acquires an index indicating the risk of a jam occurring based on the first value and the second value.

11. The information processing device according to claim 8, characterized in that the notification means acquires statistical data obtained by collecting statistics on the characteristic values, acquires at least two statistical quantities, namely, a maximum value of the statistical data, a minimum value of the statistical data, an average value of the statistical data, a standard deviation of the statistical data, a variance of the statistical data, a skewness of the statistical data, a kurtosis of the statistical data, a median of the statistical data, a first quartile of the statistical data, and a third quartile of the statistical data, and notifies the risk of a jam occurring based on the acquired statistical quantities.

12. 9. The information processing apparatus according to claim 8, wherein the characteristic value is a conveying time of the recording material.

13. 9. The information processing apparatus according to claim 8, wherein the characteristic value is a driving current of a motor used to drive the roller.

14. 9. The information processing apparatus according to claim 8, wherein the risk is expressed as a percentage.

15. A display method for displaying a status of an image forming apparatus that forms an image on a recording material, comprising: acquiring a characteristic value relating to conveyance of a roller that conveys the recording material in the image forming apparatus; A display method comprising displaying a risk of jamming in the image forming apparatus based on the characteristic value.

Images