Image forming system, control device, and non-transitory computer readable

Abstract

To prevent the occurrence of conveyance failure and image quality failure due to the use of an inappropriate control parameter.SOLUTION: The image forming system includes a detection unit that detects sheet characteristic information corresponding to a characteristic of a sheet, a first output unit that outputs at least one of an attribute of the sheet and a control parameter for forming an image on the sheet based on the detected sheet characteristic information, and a second output unit that outputs a degree of reliability of an output result of the first output unit.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to an image forming system, a control device, and a control program. [Background technology]

[0002] In order to produce prints of consistent quality even when using a variety of paper types, some image forming devices are equipped with sensors that automatically detect the characteristics of the paper used for printing.Then, based on the detected paper characteristics, control parameters for fixing, transfer, transport conditions, etc. during printing are set (for example, see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-089503 Summary of the Invention [Problem to be solved by the invention]

[0004] However, when setting control parameters based on paper characteristics, for example, when estimating using a machine learning learning model, if paper with paper characteristics that deviate significantly from the learning data is used, the control parameters will not be set appropriately. As a result, there is a concern that images will be formed using control parameters that are inappropriate for the paper, resulting in transport problems and poor image quality.

[0005] The present invention has been made in view of the above circumstances, and has an object to prevent transport defects and poor image quality from occurring due to the use of inappropriate control parameters. [Means for solving the problem]

[0006] The above object of the present invention can be achieved by the following means.

[0007] (1) a detection unit for detecting paper characteristic information corresponding to characteristics of paper; a first output unit that outputs at least one of a paper attribute and a control parameter for forming an image on the paper based on the detected paper characteristic information; a second output unit that outputs a degree of certainty regarding the reliability of the output result of the first output unit; An image forming system comprising:

[0008] (2) The image forming system according to (1), wherein the second output unit outputs the degree of accuracy based on the detected paper characteristic information.

[0009] (3) The image forming system according to (1) above, further comprising a control unit that determines whether or not to use the output result of the first output unit based on the accuracy output from the second output unit.

[0010] (4) In the image forming system described in (3) above, if the likelihood is greater than or equal to a threshold value, the control unit sets control parameters for image formation based on the output result of the first output unit.

[0011] (5) The image forming system according to (3) above, wherein if the certainty is lower than a threshold value, the output result of the first output unit is not reflected in the image formation.

[0012] (6) The image forming system according to (3) above, wherein if the certainty is lower than a threshold value, image formation based on the output result of the first output unit is not performed.

[0013] (7) The image forming system according to (5), wherein the control unit receives input of control parameters from a user when the output result of the first output unit is not reflected in the image formation.

[0014] (8) In the image forming system described in (3) above, when the control unit does not reflect the output result of the first output unit, it refers to a paper usage history database, selects usage history data based on the degree of match with the detected paper characteristic information, and sets control parameters for image formation using the control parameters stored in the selected usage history data.

[0015] (9) The image forming system according to (8), wherein the control unit accepts input of control parameters from a user when the degree of match is equal to or less than a predetermined value.

[0016] (10) The image forming system according to (1), wherein the control unit notifies a user of the degree of accuracy output from the second output unit.

[0017] (11) The second output unit is a learning model that outputs the accuracy when the detected paper characteristic information is input, The learning model learns using the paper characteristic information as learning data and a data set in which the presence or absence of a quality defect corresponding to the paper characteristic information is used as a correct answer label, and outputs a reliability that a quality defect will not occur as the accuracy. The image forming system described in (1) above, wherein the quality defect in the data set is a judgment result of at least one of conveying quality and image quality when image formation is performed based on the output result of the first output unit based on the paper characteristic information.

[0018] (12) The image forming system according to (11) above, wherein the transport quality is information on occurrence of transport jams during image formation.

[0019] (13) The image forming system according to (11) above, wherein the image quality is determined by analyzing read data obtained by reading a sheet on which an image has been formed.

[0020] (14) The image forming system according to (11) above, wherein the learning data is composed of data collected from a plurality of image forming systems.

[0021] (15) an acquisition unit that acquires paper characteristic information corresponding to the characteristics of the paper detected by the detection unit; a first output unit that outputs at least one of a paper attribute and a control parameter for forming an image on the paper based on the acquired paper characteristic information; a second output unit that outputs a degree of certainty regarding the reliability of the output result of the first output unit based on the acquired paper characteristic information; A control device comprising:

[0022] (16) The control device according to (15) above, further comprising a control unit that determines whether or not to use the output result of the first output unit based on the accuracy output from the second output unit.

[0023] (17) a step (a) of acquiring paper characteristic information corresponding to the characteristics of the paper detected by the detection unit; a step (b) of outputting at least one of a paper attribute and a control parameter for forming an image on the paper based on the paper characteristic information acquired in the step (a); a step (c) of outputting a degree of certainty regarding the reliability of the output result of the step (b) based on the paper characteristic information acquired in the step (a); A control program for causing a computer to execute a process including the above.

[0024] (18) The control program according to (17) above, wherein the processing further includes a step (d) of determining whether or not to use the output result of step (b) based on the accuracy output in step (c). [Effects of the Invention]

[0025] The image forming system according to the present invention includes a detection unit that detects paper characteristic information corresponding to the characteristics of paper, a first output unit that outputs at least one of paper attributes and control parameters for forming an image on the paper based on the detected paper characteristic information, and a second output unit that outputs a degree of reliability of the output result of the first output unit. This makes it possible to prevent conveyance problems and poor image quality caused by the use of inappropriate control parameters. [Brief explanation of the drawings]

[0026] Advantages and features provided by one or more embodiments of the present invention will be more fully understood from the following detailed description and the accompanying drawings, which are for purposes of illustration only and are not intended to be limiting. [Figure 1] 1 is a diagram showing a schematic configuration of an image forming system according to an embodiment of the present invention; [Figure 2] FIG. 1 is a schematic diagram showing a server communicatively connected to a plurality of image forming systems. [Figure 3] FIG. 1 is a block diagram of an image forming system. [Figure 4] FIG. 2 is a schematic diagram showing a data flow in the image forming system. [Figure 5A] FIG. 2 is a block diagram of a paper characteristic detection device. [Figure 5B] FIG. 2 is a diagram illustrating a schematic configuration of a paper characteristic detection device. [Figure 6A] FIG. 2 is a diagram illustrating a schematic configuration of a size sensor. [Figure 6B] FIG. 2 is a diagram illustrating a schematic configuration of a paper thickness sensor. [Figure 6C] FIG. 2 is a diagram showing a schematic configuration of a basis weight sensor. [Figure 6D] FIG. 1 is a diagram showing a schematic configuration of a moisture percentage sensor. [Figure 6E] FIG. 2 is a diagram showing a schematic configuration of a stiffness sensor. [Figure 6F] FIG. 1 is a diagram showing a schematic configuration of a surface sensor. [Figure 6G] FIG. 1 is a diagram illustrating a schematic configuration of a resistance sensor. [Figure 7] FIG. 10 is a schematic diagram showing a control parameter determination method. [Figure 8] FIG. 10 is a schematic diagram showing a control parameter determination method. [Figure 9] FIG. 10 is a diagram showing an example of paper brand data. [Figure 10] 10 is a flowchart showing a registration process in a paper usage history database. [Figure 11] FIG. 10 is a diagram illustrating an example of paper usage history data. [Figure 12] 10 is a flowchart showing a machine learning method for learning model 2. [Figure 13] FIG. 10 is a diagram illustrating an example of a training data set. [Figure 14] 4 is a flowchart showing a printing process in the first embodiment. [Figure 15] This is an example of the accuracy and its judgment result output. [Figure 16A] 10 is a flowchart showing a printing process in the second embodiment. [Figure 16B] 10 is a flowchart showing a printing process in the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0027] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, the scope of the present invention is not limited to the disclosed embodiments. In the description of the drawings, identical elements are designated by the same reference numerals, and redundant description will be omitted. Furthermore, the dimensional ratios of the drawings are exaggerated for convenience of explanation and may differ from the actual ratios. In the drawings, the up-down direction (vertical direction) is referred to as the Z direction, the front and rear directions of the image forming system or paper characteristic detection device are referred to as the Y direction, and the direction perpendicular to these Y and Z directions is referred to as the X direction. The X direction is also referred to as the paper transport direction. The Y direction is also referred to as the width direction. In this embodiment, paper includes printing paper (hereinafter simply referred to as paper) and various films. In particular, paper includes paper made using plant-derived mechanical pulp and / or chemical pulp. Furthermore, paper types include coated glossy paper and matte paper, and uncoated plain paper and fine paper. Furthermore, in this embodiment, paper attributes include paper type and basis weight.

[0028] In the following description, an electrophotographic method using toner will be taken as an example of the method of the image forming apparatus, but other methods such as an inkjet method may also be applied.

[0029] FIG. 1 is a diagram showing a schematic configuration of an image forming system 100 according to this embodiment. FIG. 2 is a schematic diagram showing a management server 300 connected for communication with a plurality of image forming systems 100. FIG. 3 is a block diagram showing a hardware configuration of the image forming system 100. As shown in FIG. 1, the image forming system 100 includes an image forming apparatus 10, a paper feeder 20, a paper characteristic detection device 30, an inspection device 40, and a post-processing device 50, which are mechanically and electrically connected to one another. The image forming system 100 is also connected to a terminal device 200 such as a PC. The image forming system 100 and the terminal device 200 are also connected to an external network via a router. The terminal device 200 is operated, for example, by an operator who uses the image forming system 100.

[0030] As shown in FIG. 2, multiple image forming systems 100 (100-1 to 100-n) are connected to a management server 300 via a network. The terminal devices 210 are PCs, tablet devices, smartphones, etc., and are used by management users such as service staff management companies that maintain and manage the image forming apparatuses 10 or the image forming systems 100. These devices are connected to each other for communication via the network. The management server 300 is an on-premise server located in the building where the image forming apparatuses 10 are installed, or a cloud server that uses a commercial cloud service. The management server 300 functions as a database server and includes a paper brand database and a paper usage history database (hereinafter simply referred to as the paper brand DB and the usage history DB) (both of which will be described later).

[0031] The management server 300 collects data such as paper usage history data sent periodically (for example, at the end of a job or daily) from each image forming system 100 or image forming device 10, and stores it in a paper history DB. In addition, the "paper brand data" (also called reference data or media bank) stored in the paper brand DB is used to register the characteristics data of paper brands used in the market, and is used to identify paper brands using the paper characteristic data. When a new paper brand is used in the market, the management user measures the paper characteristic data and registers it in the paper brand DB.

[0032] (Image forming apparatus 10) See Figures 1 and 3. Image forming apparatus 10 forms an image on paper 90 sent from upstream paper characteristic detection device 30. Image forming apparatus 10 includes control unit 11, memory unit 12, image forming unit 13, paper feed and transport unit 14, calculation unit 15, printer controller 17, operation panel 18, communication unit 19, etc. These are connected to each other via signal lines such as a bus for exchanging signals.

[0033] (Control unit 11) The control unit 11 is composed of a CPU, ROM, RAM, etc. The control unit 11 executes various processes by executing programs stored in the ROM or in the storage unit 12 (described later), and controls each unit of the device and performs various arithmetic processing in accordance with the programs. The control unit 11 functions as an overall control unit 111, an engine control unit 112, a paper characteristic detection device control unit 113, an other device control unit 114, and a conveyance / image formation control unit 116. The functions of these sub-control units 111 to 116 will be described later.

[0034] (Storage unit 12) The storage unit 12 comprises auxiliary storage units such as a ROM for storing various programs and data in advance, a RAM for temporarily storing programs and data as a working area, and a hard disk for storing various programs and data. The storage unit 12 also stores information about the paper stored in each paper feed tray. The paper information includes information about the paper brand, size (paper width, paper length), basis weight (basis weight), and paper type (plain paper, coated paper (gloss coated paper, matte coated paper), fine paper, rough paper, etc.).

[0035] (Image forming unit 13) The image forming unit 13 forms an image, for example, by electrophotography. The image forming unit 13 includes a writing unit corresponding to each of the basic colors, Y (yellow), M (magenta), C (cyan), and K (black), and a photosensitive drum (not shown). As shown in FIG. 1, the image forming unit 13 also includes multiple developing units 131 containing two-component developers each consisting of a toner of each color and a carrier. The image forming unit 13 also includes an intermediate transfer belt 132, a secondary transfer unit 133, and a fixing unit 134. The toner images formed on the photosensitive drums by the developing units 131 of each color are superimposed on the intermediate transfer belt 132 and transferred to the paper 90 conveyed by the secondary transfer unit 133. The toner images on the paper 90 are fixed to the paper 90 by applying heat and pressure in the fixing unit 134 downstream.

[0036] The fixing unit 134 includes an upper heating unit that contacts the toner image, a lower pressure unit, a non-contact temperature sensor that detects the temperature of the heating unit, and a separation unit 1341 (see Figure 1). The heating unit may be composed of a single roller, or a fixing belt system may be used, consisting of a fixing belt and multiple internal rollers that sandwich the fixing belt. The separation unit 1341 is located near the exit of the fixing nip, which is formed by a pressure unit pressing against the heating unit. This separation unit 1341 assists in separating the paper from the fixing belt. The separation unit 1341 separates the paper 90 from the fixing belt using an air separation system. This separation unit 1341 includes a fan (hereinafter referred to as the fixing separation fan) and a duct, and blows a predetermined amount of air onto the leading edge of the paper (leading edge in the transport direction) in time with the paper 90 passing through the fixing nip. The air volume (fan rotation speed) of the fixing separation fan is variably controlled by setting control parameters.

[0037] (Paper feed conveyance section 14) The paper feed conveyance unit 14 includes conveyance paths 141 and 142, multiple paper feed trays 145, etc. The conveyance path 141 includes multiple pairs of conveyance rollers provided along the conveyance path, and a drive motor (not shown) that drives these pairs of conveyance rollers. The paper feed conveyance unit 14 includes a feed roller that feeds the uppermost sheet of multiple sheets of paper 90 stacked and placed in the paper feed tray 145, and sends (feeds) the sheets of paper 90 in the paper feed tray one by one to the downstream conveyance path. A first conveyance path 341 of the paper characteristic detection device 30 is connected to the upstream side of the conveyance path 141.

[0038] The paper feed conveyance unit 14 conveys paper 90 fed from a paper feed tray 145 or the like. After an image is formed on the paper 90 conveyed along the conveyance path 141 in the image forming unit 13, the paper 90 passes through the subsequent inspection device 40 and post-processing device 50 and is then discharged onto the paper output tray 51. When performing double-sided printing, in which an image is also formed on the back side of the paper 90, the paper 90 with an image formed on one side is conveyed to a conveyance path 142 for double-sided image formation located at the bottom of the device main body. The paper 90 conveyed to this conveyance path 142 is turned over in a switchback path, and then merges with the conveyance path 141 for single side printing, where an image is again formed on the other side of the paper 90 in the image forming unit 13.

[0039] (Computation unit 15) The calculation unit 15 has a first output unit 151 and a second output unit 152. The first output unit 151 includes learning models 1A, 1B, and 1C. The second output unit includes learning model 2. The functions and learning methods of these learning models will be described later.

[0040] (others) Printer controller 17 acquires a print job sent from a terminal device such as a PC (personal computer). The print data (image data) included in this print job, written in PDL (Page Description Language) or PDF format, is then rasterized by printer controller 17 and converted into raster-format image data for each page. The converted image data is temporarily stored in a page memory. The image data from the page memory is read out at a predetermined timing and stored in a buffer, and is output as an exposure signal to the writing unit for each main scanning line in synchronization with the write timing.

[0041] Operation panel 18 is equipped with a touch screen, numeric keypad, start button, stop button, etc., and displays the status of image forming apparatus 10 or image forming system 100, and is used for setting the type of paper placed in paper feed tray 145, etc., and inputting instructions from the user. Furthermore, in the process described below, operation panel 18 displays a warning to the user and displays an input setting screen for control parameters if the reliability of the first output unit is low.

[0042] The communication unit 19 is an interface for communicating with other devices.

[0043] (Sub-control units 111 to 116) When a print job is input, the overall control unit 111 causes the engine control unit 112 to execute the print job based on the print job setting information of the input print job. The print job is input based on instructions sent from the operation panel 18, the terminal device 200 operated by the user, or the like.

[0044] The engine control unit 112 controls the other device control unit 115 and the conveyance / image formation control unit 116 to perform printing processing as shown in FIG. 14 and the like, which will be described later.

[0045] The paper characteristic detection device control unit 113 controls the paper characteristic detection device 30 in response to an execution instruction request from the engine control unit 112, and causes the various sensors included in the paper characteristic detection device 30 to measure the paper characteristics.

[0046] The other device control unit 115 transmits, to the post-processing device 50, the timing of paper transport, setting information for post-processing of the transported paper, etc. The other device control unit 115 also controls the paper feed device 20. Specifically, the other device control unit 115 communicates with the paper feed device 20 to send and receive information about the paper feed tray to be used, the timing of paper transport, etc. The other device control unit 115 also controls the inspection device 40. Specifically, the other device control unit 115 communicates with the inspection device 40 to cause an inspection to be performed using the reading unit 43.

[0047] The conveyance / image formation control unit 116 controls the paper feed / conveyance unit 14 (including drive motors for the conveyance paths 141, 142, the fixing unit, etc.) to control the paper feed / conveyance of the paper 90. The conveyance / image formation control unit 116 also controls the image forming unit 13, and controls the image formation conditions and the image formation timing according to the paper position.

[0048] (Paper feeder 20) As shown in FIG. 1, the paper feeder 20 includes a paper feed conveying section 24. The paper feed conveying section 24 has the same functions as the paper feed conveying section 14 described above. In addition to the paper feed conveying section 24, the paper feeder 20 also includes a control section, a memory section, and a communication section (none of which are shown), which are interconnected via signal lines such as a bus for exchanging signals. The paper feed conveying section 24 includes multiple paper feed trays 245 and a conveying path 241. The conveying path 241 is connected to the conveying path 341. Paper 90 fed from each paper feed tray 245 and conveyed along the conveying path 241 is conveyed to the downstream paper characteristic detection device 30, where the paper characteristics are measured, and an image is formed on the paper by the image forming device 10, which is further downstream. The paper feed conveying section 24 of the paper feeder 20 feeds the topmost paper of a stack of paper sheets stored in the paper feed tray 245, one by one.

[0049] (Inspection device 40) The inspection device 40 includes an inspection and judgment unit including a CPU and a reading unit 43. The reading unit 43 is a scanner that reads an image on a sheet of paper to generate read image data. The reading unit 43 is located on the transport path 441. The reading unit 43 may be configured with two reading units with a common configuration, one above the other and one below the transport path 441, so that images on both sides of the sheet of paper 90 transported along the transport path 441 can be read. The reading unit 43 reads the image on the sheet of paper 90 formed by the image forming unit 13 and generates a read image (read image data). The reading unit includes a sensor array, an optical system, and an LED light source. The sensor array is a color line sensor that has multiple optical elements such as CCDs arranged in a line along the width direction (main scanning direction) and can read the entire width of the sheet of paper 90 in the width direction. The optical system is composed of multiple mirrors and lenses. Light from the LED light source illuminates the surface of the sheet of paper S as it passes through the reading position on the transport path 441. The image of the reading position is guided by an optical system and focused onto the sensor array.

[0050] The inspection and judgment unit of the inspection device 40 performs various inspections of the image quality of printed materials by analyzing the print data and the scanned image data. The inspection and judgment unit also generates input-output correspondence data by comparing and analyzing pixel values ​​of the print data and the scanned image data. For example, the inspection and judgment unit generates correspondence data between image signals and densities, or between specific colors in image signals and output colors. The inspection and judgment unit also compares and analyzes pixel values ​​of the print data and the scanned image data to evaluate defects such as the degree of bleeding, stains, and fireflies (white spots).

[0051] (Post-processing device 50) The post-processing device 50 performs post-processing on and ejects the paper 90 sent from the image forming device 10 according to the print job settings. The post-processing device 50 includes paper output trays 51 and 52, a post-processing unit 53, and a conveying path 541. The post-processing device 50 also includes a control unit, a memory unit, a conveying unit, and a communication unit (none of which are shown), which are interconnected via signal lines such as a bus for exchanging signals. The paper output trays 51 and 52 are selected according to the print job settings. For example, the paper output tray 51 is used as a main tray to which normally printed materials are ejected, and the paper output tray 52 is used as a sub-tray to which defective images formed on the paper 90 are ejected. Paper 90 determined to have poor image quality by the inspection device 40 is treated as waste paper that cannot be used as a product. Waste paper is usually reprinted. The conveying path 541 is connected to the upstream conveying path 441. The post-processing section 53 performs at least one of the following post-processing steps on the paper 90 on which the image has been formed: stapling, punching, cutting, folding, and binding.

[0052] (Data flow in image forming system) An outline of this embodiment will now be described. Details will be described later with reference to FIG. 14 etc., but the outline is as follows. FIG. 4 is a schematic diagram showing the flow of data in image forming system 100. As shown in FIG. 4, paper characteristics 1 to n are detected based on detection by paper characteristic detection device 30. These paper characteristics 1 to n are input to first output unit 151 and second output unit 152. Control parameters 1 to n are output by learning model 1A for control parameter estimation in first output unit 151. Furthermore, paper type is output by learning model 1B for paper type estimation. Furthermore, basis weight is output by learning model 1C for basis weight estimation. Then, control parameters n+1 to m are output using the output paper type and basis weight and a control table.

[0053] Furthermore, the second output unit 152 outputs the reliability (accuracy) of the output result of the first output unit by inputting paper characteristics 1 to n to learning model 2. On the upper side, the control parameters 1 to n, n+1 to m used for image formation, which are the output results output by the first output unit 151 etc., are reflected if the accuracy output from the second output unit 152 is high. On the other hand, if the accuracy is low, the control parameters 1 to n, n+1 to m are discarded without being reflected. This learning model 2 is machine-learned using the image output results (transport, image quality) with the control parameters as a learning data set based on the output result of the first output unit 151. Machine learning will be described in detail later (see FIG. 12 below).

[0054] (Paper characteristic detection device 30) Next, the paper characteristic detection device 30 will be described with reference to Figures 5A to 6G. Figure 5A is a block diagram of the paper characteristic detection device 30, and Figure 5B is a diagram showing the general configuration of the paper characteristic detection device. The paper characteristic detection device 30 includes a control unit 31, a memory unit 32, a transport unit 34, a first detection unit 35, a second detection unit 37, an environmental sensor 38, and a communication unit 39. The environmental sensor 38 detects at least one of the temperature and humidity inside the device body. The communication unit 39 is an interface for communicating with other devices.

[0055] As will be described in detail later, first detection unit 35 includes a size sensor 351, a paper thickness sensor 352, a basis weight sensor 353, and a moisture percentage sensor 354, while second detection unit 37 includes a stiffness sensor 371, a surface property sensor 372, and a resistance sensor 373. As shown in FIG. 9 , which will be described later, paper characteristics 1 and 2 are detected by surface property sensor 372. Paper characteristics 3, 4, 5, and 6 are detected by paper thickness sensor 352, a moisture percentage sensor 354, a stiffness sensor 371, and a resistance sensor 373, respectively. Paper characteristics 7 to 12 are detected by basis weight sensor 353. The sensors of first detection unit 35 are formed on transport path 341, which is connected to the main transport path connected to image forming unit 13, and detect each characteristic of transported paper 90 as it is transported.

[0056] The control unit 31 has a CPU and a memory, similar to the above-described control unit 11. The control unit 31 controls the operations of the first and second detection units 35 and 37, and causes them to detect paper characteristic information corresponding to the paper characteristics of the paper 90.

[0057] The memory unit 32 comprises auxiliary memory units such as a ROM for storing various programs and data in advance, a RAM for temporarily storing programs and data as a working area, and a hard disk for storing various programs and data. The memory unit 32 also stores an environmental correction table that associates the detection values ​​of the environmental sensor 38 with correction values. The control unit 31 corrects the detection results of the first and second detection units 35 and 37 according to the detection values ​​of the environmental sensor 38 and the environmental correction table.

[0058] The transport unit 34 includes a first transport path 341, a second transport path 342, and a purge tray 349 onto which the paper 90 to be purged is discharged. The first and second transport paths 341 and 342 each include a plurality of pairs of transport rollers arranged along the transport path, and a drive motor (not shown) that drives these pairs of transport rollers. The first transport path 341 is the main transport path, and its upstream side is connected to the transport path 241 of the paper feeder 20, and its downstream side is connected to the transport path 141 of the image forming apparatus 10. The second transport path 342 branches off from the first transport path 341 at a branch point s1. The second transport path 342 transports the paper 90 to be purged onto the purge tray 349 without passing through the image forming unit 13 (arranged on the transport path 141). The first transport path 341 extends in a substantially horizontal direction. At least a portion of the second transport path 342 extends in a substantially vertical direction. In particular, in the area where the stiffness sensor 371 (described later) is located, the second transport path 342 extends in a substantially vertical direction, and the paper is transported upward. Note that the entire second transport path 342 does not have to be a straight line. As long as at least the measurement area of ​​the stiffness sensor 371 of the second transport path 342 is straight, the other paths may be partially curved. For example, the second transport path 342 may be a curved transport path that is S-shaped overall.

[0059] (First detection unit 35) 6A to 6D, configuration examples of the size sensor 351, paper thickness sensor 352, basis weight sensor 353, and moisture percentage sensor 354 will be described below. As described above, these sensors 351 to 354 detect paper characteristic information corresponding to the size, paper thickness, basis weight, and moisture percentage while conveying the paper 90 conveyed along the first conveying path 341 without stopping it. In particular, these sensors 351 to 354 detect paper characteristic information while conveying the paper 90 at the conveying speed during image formation (hereinafter also referred to as the normal conveying speed). In this way, paper characteristic information for all sheets of paper 90 can be detected without reducing productivity.

[0060] (Size Sensor 351) The size sensor 351 optically detects the size (shape) of the paper 90. The size sensor 351 is, for example, one or two image sensors. FIG. 6A is a diagram showing a schematic configuration of the size sensor 351. In the example shown in FIG. 6A, the size sensor 351 is two line sensors 511 and 512. Each of the line sensors 511 and 512 is an image sensor in which photoelectric conversion elements, such as CIS (Contact Image Sensor), are arranged in one or more lines, and reads one-dimensional images. The line sensor 171 also has optical elements, such as light-emitting elements and lens arrays, arranged along the line of photoelectric conversion elements. The light-emitting elements irradiate the paper 90 on the first transport path 341 with uniform light in the extension direction of the line. In the example shown in FIG. 6A, each of the line sensors 511 and 512 has a longitudinal length of 200 to 300 mm. These line sensors 511 are arranged adjacent to each other in the transport direction (X direction) so as to overlap in the width direction (Y direction). This allows the entire width of the transported paper 90 to be read, even for paper 90 with widths such as A3 Nobi size. The paper 90, which is transported at a predetermined transport speed, is read by both line sensors 511 and 512, generating read image data. The control unit 31 performs image processing on the obtained read image data for one sheet of paper 90 to detect the edges (positions of the four sides or the outer shape) of the paper 90 and detect its size (shape). Note that the control unit 31 may detect the shape and size of the paper 90 by processing each of the two read image data obtained from the two sensors 511 and 512. Alternatively, the control unit 31 may combine the two read image data into one and process it to detect the shape and size of the paper 90. In addition, in the example shown in FIG. 6A, two sensors 511 and 512 are arranged to overlap in the width direction, but one large sensor may be used to correspond to the size of A3 Nobi or the like.

[0061] (Paper thickness sensor 352) FIG. 6B is a diagram showing the schematic configuration of the paper thickness sensor 352. The paper thickness sensor 352 detects the thickness of the paper 90 by mechanically measuring the amount of displacement. As the paper 90 is transported through the nip of the transport roller pair 521, the axial position of one of the driven rollers of the transport roller pair 521 is displaced depending on the thickness of the paper 90. The thickness of the paper 90 is measured by measuring the height of this displaced axis. The transport roller pair 521 consists of two rollers, the lower of which is a fixed (axial center fixed) drive roller, and the upper of which is a driven roller that is biased toward the drive roller so that it can move toward and away from the drive roller. The height of the upper roller is detected by a displacement sensor. The displacement sensor is composed of an actuator (detection lever) that contacts the upper roller shaft and an encoder that measures the amount of rotation of this actuator. The paper thickness sensor 352 outputs, for example, the paper thickness (microns) as the paper thickness measurement result.

[0062] (Basis weight sensor 353) 6C is a diagram showing a schematic configuration of the basis weight sensor 353. The basis weight sensor 353 is a transmissive and reflective optical sensor that detects the basis weight of the paper, and is equipped with a light-emitting element and a light-receiving element, and detects the basis weight of the paper 90 by measuring the amount of attenuation (transmittance) of light that passes through the paper 90 and the amount of reflected light.

[0063] As shown in FIG. 6C, the basis weight sensor 353 includes multiple light-emitting elements 531 and a single light-receiving element 532. The light-emitting element 531 includes a first light-emitting element 531a, a second light-emitting element 531b, and a third light-emitting element 531c. The first, second, and third light-emitting elements irradiate an irradiation area with first, second, and third irradiation light, respectively. This irradiation area (second irradiation area) is an inner area within the opening a12 when viewed from the Z direction. The opening a12 is provided in the upper guide plate 3411. An opening a22 is also provided in the lower guide plate 3412 at a position opposite the opening a12. The openings a12 and a22 have the same shape, for example, a rectangle. Transparent sheets 534a and 534b made of PET or the like that transmit the wavelengths of the irradiated light are attached to the openings a12 and a22 to prevent foreign matter such as paper dust from the paper 90 passing through the first conveying path 341 from adhering to the openings a12 and a22.

[0064] The first light-emitting unit 531a emits first irradiation light having a first wavelength. The first wavelength is, for example, a near-infrared wavelength that is longer than the wavelength of visible light. More specifically, the first wavelength includes, for example, a wavelength between 750 nm and 900 nm. The second light-emitting unit 531b emits second irradiation light having a second wavelength. The second wavelength is, for example, a wavelength of blue light included in visible light. More specifically, the second wavelength includes, for example, a wavelength between 400 nm and 470 nm. The first light-emitting unit 531a and the second light-emitting unit 531b are both disposed on the opposite side of the first transport path 341 from the light-receiving unit 532, and the third light-emitting unit 531c is disposed on the same side as the light-receiving unit 532 and in the vicinity of the light-receiving unit 532. The third light-emitting unit 531c emits third irradiation light having a third wavelength toward the irradiation region (opening a12). The third wavelength is, for example, the wavelength of green light in visible light. More specifically, the third wavelength includes, for example, a wavelength between 495 nm and 570 nm. The third wavelength is a wavelength different from the first wavelength (for example, a wavelength between 750 nm and 900 nm) and the second wavelength (for example, 400 nm to 470 nm).

[0065] The third irradiation light is irradiated toward the first transport path 341 inside the upper and lower guide plates 3411 and 3412. A reflector 533 is provided on the inside of the lower guide plate 3412, which is provided near the first light emitter 531a and the second light emitter 531b. The reflector 533 is painted, for example, in green, the same color as the third irradiation light, and reflects the third irradiation light. Note that the reflector 533 does not reflect the first irradiation light (near-infrared rays) and the second irradiation light (blue light rays), which are not the same color.

[0066] In this embodiment, during measurement, the control unit 31 controls the first light-emitting unit 531a and the second light-emitting unit 531b to emit first and second irradiation light at different times. The light-receiving unit 532 receives the first and second irradiation light, detects the light intensity of each irradiation light, and outputs the detected light intensity of the first and second irradiation light to the control unit 31. Similarly, the control unit 31 irradiates the paper 90 transported to the position of the opening a12 with the first and second irradiation light. The light-receiving unit 532 receives the transmitted light (first transmitted light, second transmitted light) of the first and second irradiation light, detects the light intensity of each irradiation light, and outputs the detected light intensity of the first transmitted light and the second transmitted light to the control unit 31. That is, the light receiving section 532 detects the first irradiated light and the second irradiated light when the paper 90 is not present, and the first transmitted light and the second transmitted light when the paper 90 is present in the opening a12.

[0067] Similarly, with respect to the third light-emitting unit 531c, the light-receiving unit 532 detects the first reflected light reflected by the reflecting unit 533 when no paper 90 is present, and the second reflected light reflected by the surface of the paper 90 when the paper 90 is in the opening a12.

[0068] The control unit 31 calculates a first transmittance by dividing the amount of the first transmitted light by the amount of the first irradiated light. Similarly, the control unit 31 calculates a second transmittance by dividing the amount of the second transmitted light by the amount of the second irradiated light. The type of paper 90 may then be determined from the first and second transmittances and the determination criteria stored in the memory unit 12.

[0069] Furthermore, in addition to the first and second transmittances, the control unit 31 may calculate the reflectance by dividing the amount of the second reflected light by the amount of the first reflected light, and may take this reflectance into consideration when determining the type of paper 90. Although the third light-emitting unit 531c and the reflecting unit 533 are provided in this embodiment, they may be omitted.

[0070] (Moisture Sensor 354) 6D is a diagram showing a schematic configuration of the moisture percentage sensor 354. The moisture percentage sensor 354 measures the moisture percentage of the paper 90. Note that in this embodiment, a moisture percentage sensor that measures the moisture content of the paper is used as an example of paper characteristic information, but a moisture amount sensor that measures the amount of moisture contained in the paper as paper characteristic information may also be used.

[0071] 6D, the moisture percentage sensor 354 includes a first light-emitting unit 540, a second light-emitting unit 542, a light-receiving unit 543, a temperature detection sensor 544, and lenses 545 and 546. The first light-emitting unit 540 and the second light-emitting unit 542 are light-emitting units that emit light toward the paper.

[0072] The first light emitter 540 emits first near-infrared light (reference light) in a specific wavelength band toward the paper P. A specific example of the first light emitter 540 is an LED (Light Emitting Diode), etc. The first near-infrared light is light whose absorption rate in the paper P when reflected by the paper P does not depend on the moisture content of the paper P. The light receiver 543 receives, via a lens 546, the first near-infrared light emitted from the first light emitter 540 and reflected by the paper P via a lens 545. The light receiver 543 then outputs first received light amount information, which is the amount of received reflected first near-infrared light, to the control unit 31. A specific example of the light receiver 543 is a CCD (Charge-Coupled Device), a CMOS (Complementary Metal-Oxide-Semiconductor), etc.

[0073] The second light emitter 542 emits second near-infrared light of a specific wavelength band toward the paper P. A specific example of the second light emitter 542 is an LED or the like. The second near-infrared light is light whose absorption rate in the paper P when reflected by the paper P varies depending on the moisture content of the paper P. The light receiver 543 receives, via a lens 546, the second near-infrared light emitted from the second light emitter 542 and reflected by the paper P via a lens 545. The light receiver 543 then outputs information on the second received light amount, which is the amount of the reflected second near-infrared light received, to the control unit 31.

[0074] That is, the first light-emitting unit 540 and the second light-emitting unit 542 emit light of wavelengths that are absorbed by the moisture in the paper at different rates. The second near-infrared light emitted by the second light-emitting unit 542 has a wavelength that is more absorbed by the moisture in the paper than the first near-infrared light (reference light) emitted by the first light-emitting unit 540.

[0075] The control unit 31 determines the moisture content of the paper based on the ratio between the first amount of received light and the second amount of received light (the ratio between the output of the light receiving unit 543 for the first near-infrared light and the second near-infrared light). The higher the moisture content of the paper, the greater the amount of second near-infrared light absorbed, and therefore the smaller the amount of second received light. Therefore, the control unit 31 can correspond the ratio between the first amount of received light and the second amount of received light to the moisture content of the paper based on a relational expression or table that shows the relationship between the moisture content of the paper and the ratio between the first amount of received light and the second amount of received light, and calculate the moisture content of the paper from the ratio between the first amount of received light and the second amount of received light.

[0076] (Second detection unit 37) 6E to 6G, configuration examples of the stiffness sensor 371, surface property sensor 372, and resistance sensor 373 will be described below. These sensors 371 to 373 detect sheet characteristic information corresponding to stiffness, surface property, and electrical resistance while stopping the sheet 90 conveyed through the second conveying path 342 or while conveying the sheet 90 at a speed slower than the normal conveying speed.

[0077] (Stiffness Sensor 371) 6E is a diagram showing a schematic configuration of stiffness sensor 371. Stiffness sensor 371 detects the stiffness of paper 90 by mechanically measuring the amount of displacement.

[0078] The stiffness sensor 371 is disposed vertically below a pair of rollers 347 that hold the stopped paper 90. The rollers 347 are controlled by a motor M2 for rotation. The rollers 347 function as a conveying section for conveying the paper 90 through the second conveying path 342, and also function as a holding section during stiffness measurement. The stiffness sensor 371 includes a paper detection sensor 710, a pressing section 711, a pressing force detection section 712, a support mechanism 715, and a motor M1. The motor M1 moves the support mechanism 715 in the horizontal direction (X direction). As a result, the tip of the pressing section 711, which is connected to the support mechanism 715, is positioned at a predetermined position in the X direction during stiffness measurement. The paper detection sensor 710 is a non-contact optical sensor that detects the presence or absence of paper at a detection position (indicated by an arrow in FIG. 6E), i.e., the trailing edge of the paper.

[0079] When measuring stiffness, the paper 90 being transported along the second transport path 342 is stopped so that its trailing edge is positioned at the detection position of the paper detection sensor 710 (or at a position a predetermined distance beyond the detection position). In the stopped state, the trailing edge of the paper 90 becomes a free edge, as shown in FIG. 6E. The pressing portion 711 of the stiffness sensor 371 presses the bottom edge of the paper 90 from the side. More specifically, the stiffness sensor 371 presses the bottom edge of the paper 90 from the horizontal direction at a position a specific distance above the detection position.

[0080] The pressing unit 711 has a blade 711a and a base 711b that is continuous with one end of the blade 711a in the horizontal direction Y. The blade 711a is formed in the shape of a long plate that is long in the width direction (Y direction) so that it can contact the entire width of the paper sheet 90 being transported in the vertical direction (Z direction). The blade 711a comes into contact with a position (measurement point) that is a specific distance vertically above the bottom edge of the paper sheet 90. In other words, the measurement point is located vertically below the portion of the paper sheet 90 that is held by the roller 347.

[0081] The pressing force detection unit 712 is connected to the surface of the base 711b of the pressing unit 711 opposite to the surface continuous with the blade 711a. The pressing force detection unit 712 detects the pressing force when the pressing unit 711 is pressed horizontally due to the repulsive force (rigidity) of the paper 90 when the blade 711a of the pressing unit 711, which is arranged at a predetermined position in the X direction by the motor M1 and the support mechanism 715, presses the paper 90. In other words, the pressing force detection unit 712 detects the pressing force when the pressing unit 711 bends the paper 90. A load cell (pressure sensor), for example, can be used as the pressing force detection unit 712.

[0082] (Surface Sensor 372) 6F is a diagram showing a schematic configuration of the surface property sensor 372. The surface property sensor 372 is a reflective (specular reflection, diffuse reflection) optical sensor that detects the surface property of the paper 90.

[0083] The surface property sensor 372 detects the surface property of the paper 90 based on the absolute values ​​of the intensities of the detected specular reflected light and scattered reflected light, and on the ratio between them.

[0084] An opening a11 is provided in the upper guide plate 3421 located on the right side of the second transport path 342 (upper side in FIG. 6F), and an opening a21 is provided in the lower guide plate 3422 located on the left side (lower side in FIG. 6F). The opening a11 is approximately rectangular and has a hole size of, for example, several tens of millimeters in both length and width (Z and Y directions). The opening a21 is located at a position corresponding to the opening a11 and is slightly larger than the opening a11. A pressing plate 729 of the pressing mechanism is located in the opening a21, and during measurement, it moves from the bottom to the top in FIG. 6F to press and fix the paper 90 against the upper guide plate 3421. When not measuring, the opening a11 is closed by a shutter (not shown). The opening a21 is also closed by the surface of the pressing plate 729, which is slightly retracted.

[0085] The surface property sensor 372 detects the surface property of the stopped paper 90 by locating the surface of the stopped paper 90 as the reference plane of the opening a11, irradiating the opening a11 as the irradiation area, and receiving the specularly reflected light and the scattered reflected light. The reference plane corresponds to the inner surface of the upper guide plate 3421.

[0086] 6F, the surface sensor 372 includes a housing 721, a light-emitting unit 722, a collimating lens 723, and a plurality of light-receiving units 724a and 724b (hereinafter, these are also collectively referred to as light-receiving units 724), etc. The surface sensor 372 detects light irradiated from the light-emitting unit 722 and reflected from the surface of the paper 90 using the light-receiving unit 724a, and detects scattered reflected light using the light-receiving unit 724b, etc.

[0087] The light-emitting unit 722 is positioned so that the incident angle of the irradiated light with respect to the reference plane is 75°. This 75° incident angle is the angle used in measuring white paper glossiness according to the JIS and is an angle that is minimally affected by the color of the object being measured. The reference plane is a virtual plane that includes the lower surface of the upper guide plate 3421. During measurement, the surface of the paper 90 being measured is placed on the reference plane. The light-emitting unit 722 is positioned on the substrate b1. The light-emitting unit 722 includes a light-emitting element serving as a light source, such as an LED, that emits light of a predetermined wavelength. The irradiated light emitted from the light source (point light source) is converted into approximately parallel light by a collimating lens 723 and then irradiated onto the irradiation area. In this embodiment, the wavelength of the light source of the light-emitting unit 722 is preferably in the range of more than 405 nm and less than 525 nm, more preferably in the range of 445 nm to 500 nm, and most preferably around 465 nm. The illumination area (first illumination area) is the inner area of ​​the aperture a11 when viewed from the Z' direction, and the center (optical axis) of the illumination area intersects with a reference plane parallel to the XY' plane at an intersection p1. A surface-emitting LED or a bullet-shaped LED may be used as the light-emitting unit 722. When a bullet-shaped LED is used, a desired illumination diameter (also referred to as beam diameter) can be obtained by designing a lens that matches the directivity of the bullet shape. The light-emitting unit 722 and the light-receiving unit 724 are arranged along the width direction (Y direction), i.e., they are on the same XY plane, and the illumination light from the light-emitting unit 722 is oriented along the width direction.

[0088] Each of the multiple light receiving units 724 includes a light receiving element such as a photodiode or phototransistor, and includes a first light receiving unit 724a that receives specularly reflected light from the illuminated area and one or more second light receiving units 724b that receive diffusely reflected light from the illuminated area. The first light receiving unit 724a is positioned at a reflection angle of 75°, corresponding to the 75° incident angle of the light emitting unit 722, and receives the specularly reflected light. The second light receiving unit 724b can be positioned at any reflection angle between 0° and 90°, excluding 75°, and receives the diffusely reflected light. The preferred positions for the second light receiving unit 724b are at reflection angles of 60°, 30°, and 0°, and more preferably at two positions at 60° and 30°, or one position at 60°. The example in FIG. 6F shows an arrangement of a first light receiving unit 724a for receiving specularly reflected light at a reflection angle of 75° and a second light receiving unit 724b for receiving diffusely reflected light at a reflection angle of 30°. In these figures, light receiving unit 724a is arranged on substrate b2, and light receiving unit 724b is arranged on substrate b3. Openings a3 and a4 are provided in housing 721 on the light receiving paths of light receiving units 724a and 724b. Openings a3 and a4 have the same structure. When viewed from the intersection p1 side, openings a3 and a4 are, for example, circular slits with a diameter of 3 mm.

[0089] (Resistance sensor 373) 6G is a diagram showing a schematic configuration of resistance sensor 373. Resistance sensor 373 applies a high voltage between the front and back of paper 90 in a stationary state, and detects the electrical resistance (volume electrical resistance) of paper 90 from the value of the current that flows.

[0090] As shown in FIG. 6G, the resistance sensor 373 includes a detection roller 732, an opposing roller 731, and a high-voltage power supply unit 733.

[0091] The detection roller 732 is disposed so as to be able to come into contact with one surface of the paper 90. The detection roller 732 is made of an elastic material such as conductive rubber.

[0092] The opposing roller 731 is disposed opposite the detection roller 732 with the paper 90 sandwiched therebetween. The opposing roller 731 is disposed so as to be able to come into contact with the other surface of the paper 90. The opposing roller 731 is made of, for example, a metal material. The opposing roller 731 is grounded.

[0093] The high-voltage power supply unit 733 is a unit for applying a high voltage to the paper 90. The high-voltage power supply unit 733 is electrically connected to the detection roller 732 and the opposing roller 731. This configures an electric circuit including the detection roller 732, the opposing roller 731, and the high-voltage power supply unit 733. The high-voltage power supply unit 733 has an ammeter and a high-voltage power supply circuit. The ammeter is electrically connected to the detection roller 732. The ammeter detects the current that flows due to the voltage applied in the high-voltage power supply circuit.

[0094] The high-voltage power supply circuit is electrically connected to the detection roller 732 via an ammeter. The high-voltage power supply circuit is capable of applying a high voltage. A voltage is applied from the high-voltage power supply circuit to the detection roller 732 via an ammeter. The high-voltage power supply circuit is capable of applying a high voltage of, for example, 1 kV to 5 kV. The method of applying voltage in the high-voltage power supply circuit may involve applying one type of voltage to the paper 90, or may involve applying multiple types of voltage to the paper 90 by controlling the applied voltage in multiple steps.

[0095] (Control parameter determination method) The control unit 11 determines various control parameters using a first example, a second example, or a method that combines these examples (see FIG. 4 above), which will be described below.

[0096] FIG. 7 is a block diagram showing the process of determining control parameters from paper characteristics in the first example. The control unit 11 and the calculation unit 15 determine each control parameter directly from the paper characteristics. Paper characteristics 1 to n (n represents an arbitrary integer; the same applies below) correspond to any of the paper characteristics obtained from the sensors 351 to 354 and 371 to 373 of the paper characteristic detection device 30 described above. For example, the control unit 11 determines fixing control parameters from paper characteristics 1, 2, and 3, and determines transfer control parameters from paper characteristics 1, 3, and n. The control unit 11 and the calculation unit 15 also determine transport and paper feed control parameters from paper characteristics 1 and n, and determine post-processing control parameters from paper characteristics 1 and 3. For example, fixing control parameters include the fixing temperature (fixing control temperature) of the fixing unit 134 and the airflow rate of the fixing separation fan. The transfer control parameter includes the transfer current of the secondary transfer unit 133. The transport and paper feed control parameter includes the transport speed of the paper 90. When determining these control parameters, a trained model trained by machine learning is used (the above-mentioned trained model 1A).

[0097] FIG. 8 is a block diagram showing a process for determining control parameters from paper characteristics in a second example. In the second example, the control unit 11 and the calculation unit 15 determine, based on paper characteristics 1 to n, one of a plurality of paper types and a plurality of grammage types classified by a discrimination process. In contrast to the first example described above, in the second example, the control unit 11 and the calculation unit 15 first classify the paper by paper type and grammage and then determine the control parameters. In the second example, the paper characteristics 1 to n correspond to one of the paper characteristics obtained from the sensors 351 to 354 and 371 to 373 of the paper characteristic detection device 30 described above. The control parameters are then determined based on the determined paper type and grammage. When performing this parameter determination process, the control unit 11 and the calculation unit 15 refer to a correspondence table stored in advance in the storage unit 12, which describes the control values ​​of each parameter for the fixing, transfer, transport / feed, and post-processing processes for each combination of paper type and grammage. When determining the paper type and basis weight, a trained model learned through machine learning is used (the above-mentioned trained models 1B and 1C).

[0098] Control unit 11 controls the fixing process of the fixing unit of image forming unit 13 and the transfer process of the transfer unit using the determined fixing and transfer control parameters. Control unit 11 also controls paper feed conveyance unit 14 using the determined conveyance / paper feed control parameters, and the control unit of paper feeder 20 controls the conveyance and paper feed processes of paper feeder 20. Also, the control unit of post-processing device 50 controls the post-processing process using the determined post-processing control parameters.

[0099] (Paper brand database) FIG. 9A shows an example of brand data recorded in the paper brand database. This brand data is managed by the management server 300 as described above and updated as appropriate. The brand data is sent from the management server 300 to the image forming system 100 at predetermined times, such as when updating. This brand data includes hundreds of registered brands. The control unit 11 normalizes the physical property values ​​1 to n of the target paper's characteristic data based on the maximum / minimum of the physical property values ​​1 to n of the brand data. Then, for each physical property, the control unit 11 calculates the sum of squared differences between the target paper and the reference paper (paper registered as a brand) and calculates the matching rate for each record of the brand data based on the magnitude of the calculated sum. For example, the control unit 11 calculates the root mean square error (RMSE) for each of the multiple records using the following formula (1), and calculates the matching rate f1 based on this. The paper brand with the highest matching rate is then adopted as the determination result.

[0100]

number

[0101] (Paper usage history data) Next, the paper usage history data and its accumulation process will be described with reference to Fig. 10 and Fig. 11. Fig. 10 is a flowchart showing the registration process to the paper usage history database. Fig. 11 is a diagram showing an example of paper usage history data.

[0102] (Step S11) When executing a print job, the image forming system 100 detects the paper characteristics of the paper 90 to be used by the paper characteristic detection device 30. Paper characteristics 1 to n are obtained by the detection.

[0103] (Steps S12 and S13) The paper characteristics 1 to n acquired in step S11 are input to the first output unit 151, and control parameters are output from the first output unit 151. Then, the control parameters 1 to n output from the first output unit 151 of the calculation unit 15 are set as control parameters 1 to n to be used for image formation in the image forming apparatus 10.

[0104] (Steps S14 and S15) The image forming apparatus 10 forms an image on a sheet 90 using the set control parameters. The inspection device 40 performs various inspections related to image quality on the read image data obtained by reading the image on the image-formed sheet 90 with the reading unit 43, and determines quality defects related to multiple quality items.

[0105] (Step S16) If it is determined in step S15 that a quality abnormality in the image quality has occurred, or if a quality abnormality in the conveyance of the paper 90, such as a conveyance jam, has occurred, the control unit 11 advances the process to step S17.

[0106] (Step S17) The image forming system 100 performs error processing for any quality abnormality that occurs. For example, when an image quality abnormality occurs, the control unit 11 displays an error message on the operation panel 18 and causes the sheet 90 with the abnormal quality to be discharged to the paper output tray 52 as waste paper. When a transport quality abnormality occurs, the control unit 11 displays a message on the operation panel 18 to the user indicating that a transport jam has occurred and a warning message urging the user to take action. The user is then prompted to remove the sheet 90 that caused the transport jam.

[0107] (Step S18) If the print job has not ended (NO), the control unit 11 repeats the processing from step S14 onwards, and if the print job has ended (YES), the control unit 11 advances the processing to step S19.

[0108] (Step S19) Image forming system 100 transmits paper usage history data to management server 300. The paper usage history data includes, as the processing results of steps S11 to S18, the device ID that executed the process, the number of printed sheets, paper characteristics, control parameters 1 to n, and information on quality defects related to image quality and transport quality. For example, quality defects include whether or not a quality defect occurred and the number of sheets that did occur (number of printed sheets without jams, number of sheets that jammed, etc.). Figure 11 shows an example of paper usage history data accumulated in the paper usage history DB of management server 300 by this processing.

[0109] (Machine Learning) Next, machine learning for each learning model will be described. The learning device can generate a learning model by a learning method using a neural network configured by combining perceptrons. The learning method is not limited to this, and various supervised learning methods can be used. For example, random forests, support vector machines (SVMs), boosting, Bayesian network linear discriminant analysis, nonlinear discriminant analysis, etc. can be applied. Furthermore, the learning device can be a standalone high-performance computer using a CPU and a GPU (Graphics Processing Unit) processor, or a cloud computer. For example, the management server 300 functions as the learning device. Furthermore, the management server 300 can perform machine learning using paper usage history data aggregated from each image forming system 100 (or image forming apparatus 10) as learning data.

[0110] (Learning Models 1A-1C) The learning model 1A for estimating control parameters used in the first output unit 151 is generated by machine learning using a learning dataset in which multiple paper characteristic data (paper characteristics 1 to n) are input as training data and multiple control parameters are used as correct answer labels. For example, the learning dataset can be paper usage history data in which no quality defects occurred.

[0111] The learning model 1B for paper type estimation used in the first output unit 151 is generated by machine learning using a learning dataset in which paper characteristic data (paper characteristics 1 to n) is input and the paper type information set by the user is used as the correct label.

[0112] The learning model 1C for estimating basis weight used in the first output unit 151 is generated by machine learning using a learning dataset in which paper characteristic data (paper characteristics 1 to n) is input and the basis weight information set by the user is used as the correct answer label.

[0113] (Machine learning for learning model 2) Machine learning of the learning model 2 for determining accuracy (also called reliability or likelihood) used in the second output unit 152 will be described with reference to Figs. 12 and 13. Fig. 12 is a flowchart showing a machine learning method of the learning model 2 used in the second output unit 152. For example, the machine learning shown in Fig. 12 is executed by the management server 300, which functions as a learner. Fig. 13 is a diagram showing an example of a learning dataset.

[0114] (Step S21) The control unit 11 extracts data from paper usage history data such as that shown in Fig. 11 and generates a learning dataset. Fig. 13 is an example of such a learning dataset. The learning dataset is composed of paper characteristic data (paper characteristics 1 to n) as input (explanatory variables) and quality information (presence or absence of defects) as the correct label (objective variable). The quality information is composed of information on image quality and / or conveyance quality as described above.

[0115] (Steps S22 to S23) The explanatory variables are input into the neural network of the learning device, the obtained estimation results are compared with the objective variable (correct label), and the parameters are adjusted based on the comparison results.

[0116] (Steps S24 and S25) The processes of steps S22 and S23 are performed for all data in the training sample data set. When training using all data is completed, training model 2 is updated and stored, and the process ends.

[0117] (Printing process in the first embodiment) Next, a printing process using these learning models will be described with reference to Figures 14 and 15. Figure 14 is a flowchart showing the printing process in the first embodiment.

[0118] (Step S31) When executing a print job, the image forming system 100 detects the paper characteristics of the paper 90 to be used by the paper characteristic detection device 30. Paper characteristics 1 to n are obtained by the detection.

[0119] (Step S32) By inputting the paper characteristics obtained in step S31 into the first output unit 151 (learning models 1A to 1C) of the calculation unit 15, control parameters are obtained as outputs.

[0120] (Step S33) The accuracy c1 is obtained as an output by inputting the paper characteristics obtained in step S31 into the second output unit 152 (learning model 2) of the calculation unit 15. The accuracy c1 can take a value within the range of 0 to 1.

[0121] (Step S34) The control unit 11 notifies the user of the accuracy c1 obtained in step S33, for example by displaying it on the operation panel 18.

[0122] (Steps S35 and S36) The control unit 11 determines whether the probability c1 obtained in step S33 is equal to or greater than a predetermined threshold th1. For example, the threshold th1 is 0.50. FIG. 15 is a table showing examples of probability calculation results for each paper type and the determination results. If the probability c1 is equal to or greater than the threshold th1, the process proceeds to step S36. In this case, the reliability of the output result of the first output unit 151 is deemed high, and the control parameters output by the first output unit 151 are adopted and set as the control parameters of the image forming apparatus 10 (step S36).

[0123] On the other hand, if the accuracy c1 is less than the threshold th1, the process proceeds to step S37. In this case, the reliability of the output result of the first output unit 151 is deemed low, and the control parameters output by the first output unit 151 are not adopted.

[0124] (Step S37) Here, the control unit 11 displays a warning on the operation panel 18 that the reliability is low. Also, a manual reception screen that receives control parameter input from the user is displayed on the operation panel 18. For example, if the paper 90 used for the print job has paper characteristics that deviate from paper that has been used in the past, the reliability c1 is determined to be low, and this warning is displayed. The user manually inputs control parameters appropriate for such paper and causes image formation to be performed using the input control parameters.

[0125] (Step S38) When the control unit 11 receives input settings of control parameters from the user, it sets these settings as the control parameters of the image forming device 10. Furthermore, if there is no input within a predetermined time, or if an instruction to stop printing is received, image formation is stopped.

[0126] (Step S39) The control section causes an image to be formed on the paper 90 according to the control parameters set in step S36 or step S38, and ends the process (END).

[0127] As described above, the image forming system according to the first embodiment includes a detection unit that detects paper characteristic information corresponding to the characteristics of the paper, a first output unit that outputs at least one of the paper attributes and the control parameters for forming an image on the paper based on the detected paper characteristic information, and a second output unit that outputs the accuracy of the output result of the first output unit. This makes it possible to prevent conveyance problems and poor image quality caused by the use of inappropriate control parameters.

[0128] (Printing process in the second embodiment) Next, with reference to Figs. 16A and 16B, a printing process executed in the image forming system 100 according to the second embodiment will be described. Fig. 16A is a flowchart showing the printing process in the second embodiment. Fig. 16B is a flowchart showing the process performed subsequent to Fig. 16A. In the flowcharts shown in Figs. 16A and 16B, the processes of steps S41 to S49 are the same as steps S31 to S39 in the flowchart shown in Fig. 14, respectively, and their explanation will be omitted where appropriate. In Figs. 16A and 16B, steps S501 to S504 are processes that differ from the flowchart in Fig. 14.

[0129] (Steps S41 to S42) When executing a print job, the image forming system 100 detects the paper characteristics of the paper 90 to be used by the paper characteristic detection device 30. Paper characteristics 1 to n are obtained by the detection. In addition, the first output unit 151 outputs control parameters.

[0130] (Step S501) Here, processing is performed to exclude special paper.

[0131] The control unit 11 determines the transmittance from the paper characteristics, and if the transmittance is higher than a predetermined threshold, determines that the paper is a transparent medium such as an OHP sheet.

[0132] In addition, the control unit 11 determines the moisture content and paper thickness from the paper characteristics, and if the moisture content is lower than a predetermined threshold and the paper thickness is thicker than the predetermined threshold, it determines that the paper is synthetic paper such as Yupo paper.

[0133] If the reflectance is higher than a predetermined threshold value based on the characteristics of the paper, the control unit 11 determines that the paper is metallized paper or metal paper, on whose surface a metal such as aluminum is vapor-deposited.

[0134] Furthermore, when light of specific wavelengths corresponding to red, green, and blue is irradiated based on the paper characteristics, if the reflectance is higher than that of other wavelengths, the control unit 11 determines that the paper is red, green, or blue. In the case of such special paper, some paper characteristics deviate significantly from the normal range, so the output of the first output unit 151 is not used.

[0135] (Step S502) See Fig. 16B. If it is determined in step S501 that the paper is special paper by any of the determinations, or if it is determined in step S45 that the accuracy c1 is not equal to or greater than the threshold th1, the process of step S502 is executed.

[0136] In step S502, the control unit 11 calculates the degree of match f1 between the paper characteristics in each data recorded in the paper usage history data in the paper usage history DB and the paper characteristics detected in step S41. The degree of match is calculated using the above-mentioned formula (1).

[0137] (Step S503) From the paper usage history data, the data with the highest degree of match f1 is extracted, and if the degree of match f1 of this data is equal to or greater than the threshold value th2, the process proceeds to step S504. On the other hand, if there is no data in the paper usage history DB with a degree of match f1 equal to or greater than the threshold value th2, the process proceeds to step S47. In this case, as with step S37 and subsequent steps in the first embodiment, the image forming system 100 displays a warning and then accepts control parameter setting input from the user.

[0138] (Step S504) From the paper usage history DB, paper usage history data with the highest matching degree f1 that is equal to or greater than the threshold value th2 is selected, and the control parameters used in that data are obtained. For example, in the example shown in Figure 11, if performance data 18 (data ID: 100018) is the usage history data with the highest matching degree f1 that is equal to or greater than the threshold value th2, the parameters 1 to n used at that time are obtained. Note that when extracting from usage history data, usage history data in which quality defects (zero "0") are recorded is not used.

[0139] Thereafter, the process proceeds to step S49, where image formation is performed using the control parameters set in step S504.

[0140] In this way, in the second embodiment, when the output result of the first output unit is not reflected, the control unit refers to the paper usage history database, selects usage history data based on the degree of match with the detected paper characteristic information, and sets control parameters for image formation using the control parameters stored in the selected usage history data. In this way, appropriate control parameters can be easily set by referring to the control parameters used in data with a past usage history.

[0141] 1 may be included in the image forming system 100. In this case, the terminal device 200 functions as a control device. The control unit and communication unit of the terminal device 200 function as an acquisition unit. The functions of the first and second output units of the calculation unit 15 may be performed on the terminal device 200 side. For example, in the process shown in FIG. 14, the processes of the first and second output units in steps S32 and S33 are performed on the terminal device 200 side, so that the control unit of the terminal device 200 and the control unit 11 cooperate to perform the process of FIG. 14.

[0142] The means and methods for performing various processes in the image forming system 100 according to the above-described embodiment can be realized by either a dedicated hardware circuit or a programmed computer. The program may be provided by a computer-readable recording medium such as a USB memory or a DVD (Digital Versatile Disc)-ROM, or may be provided online via a network such as the Internet. In this case, the program recorded on the computer-readable recording medium is typically transferred to and stored in a storage unit such as a hard disk. The program may be provided as standalone application software, or may be incorporated into the software of the device as a function of the device.

[0143] While embodiments of the present invention have been described and illustrated in detail, the disclosed embodiments are made for purposes of illustration and example only and are not intended to be limiting, and the scope of the present invention should be construed by the language of the appended claims. [Explanation of symbols]

[0144] 100 Image forming system 10 Image forming device 11 Control section 12 Storage section 13 Image forming unit 14 Paper feed transport section 15 Arithmetic section 151 First output section 152 Second output section 17 Printer Controller 18 Operation Panel 19 Communications Department 20 Paper feeder 30 Paper characteristic detection device 31 Control Unit 32 Storage section 34 Conveying section 341 First Transport Path 342 Second transport route 349 Purge Tray s1 Branch 35 First detection unit 351 size sensor 352 Paper thickness sensor 353 Basis weight sensor 354 Moisture Sensor 37 Second detection unit 371 Stiffness Sensor 372 Surface Sensor 373 Resistive Sensor 38 Environmental Sensors 39 Communications Department 40 Inspection equipment 50 Aftertreatment device

Claims

1. a detection unit that detects paper characteristic information corresponding to characteristics of the paper; a first output unit that outputs at least one of a paper attribute and a control parameter for forming an image on the paper based on the detected paper characteristic information; a second output unit that outputs a degree of certainty regarding the reliability of the output result of the first output unit; An image forming system comprising:

2. The image forming system according to claim 1 , wherein the second output unit outputs the degree of certainty based on the detected paper characteristic information.

3. The image forming system according to claim 1 , further comprising a control unit that determines whether or not to use the output result of said first output unit based on the probability output from said second output unit.

4. 4. The image forming system according to claim 3, wherein when the likelihood is equal to or greater than a threshold value, the control unit sets control parameters for forming an image based on the output result of the first output unit.

5. The image forming system according to claim 3 , wherein if the likelihood is lower than a threshold value, the output result of the first output unit is not reflected in the image formation.

6. The image forming system according to claim 3 , wherein if the likelihood is lower than a threshold value, image formation based on the output result of the first output unit is not performed.

7. The image forming system according to claim 5 , wherein the control unit accepts input of control parameters from a user when the output result of the first output unit is not reflected in image formation.

8. 4. The image forming system of claim 3, wherein when the control unit does not reflect the output result of the first output unit, it refers to a paper usage history database, selects usage history data based on the degree of match with the detected paper characteristic information, and sets control parameters for image formation using the control parameters stored in the selected usage history data.

9. 9. The image forming system according to claim 8, wherein the control unit accepts input of control parameters from a user when the degree of match is equal to or less than a predetermined value.

10. The image forming system according to claim 1 , wherein the degree of certainty output from the second output unit is notified to a user.

11. the second output unit is a learning model that receives the detected paper characteristic information and outputs the accuracy; The learning model learns using the paper characteristic information as learning data and a data set in which the presence or absence of a quality defect corresponding to the paper characteristic information is used as a correct answer label, and outputs a reliability that a quality defect will not occur as the accuracy.

2. The image forming system according to claim 1, wherein the quality defect in the data set is a judgment result of at least one of conveying quality and image quality when image formation is performed based on the output result of the first output unit based on the paper characteristic information.

12. The image forming system according to claim 11 , wherein the transport quality is information on occurrence of transport jams during image formation.

13. 12. The image forming system according to claim 11, wherein the image quality is determined by analyzing read data obtained by reading a sheet on which an image has been formed.

14. The image forming system according to claim 11 , wherein the learning data is composed of data collected from a plurality of image forming systems.

15. an acquisition unit that acquires paper characteristic information corresponding to the characteristics of the paper detected by the detection unit; a first output unit that outputs at least one of a paper attribute and a control parameter for forming an image on the paper based on the acquired paper characteristic information; a second output unit that outputs a degree of certainty regarding the reliability of the output result of the first output unit based on the acquired paper characteristic information; A control device comprising:

16. The control device according to claim 15 , further comprising a control unit that determines whether or not to use the output result of the first output unit based on the degree of certainty output from the second output unit.

17. a step (a) of acquiring paper characteristic information corresponding to the characteristics of the paper detected by the detection unit; a step (b) of outputting at least one of a paper attribute and a control parameter for forming an image on the paper based on the paper characteristic information acquired in the step (a); a step (c) of outputting a degree of certainty regarding the reliability of the output result of the step (b) based on the paper characteristic information acquired in the step (a); A control program for causing a computer to execute a process including the above.

18. 18. The control program according to claim 17, wherein the process further includes a step (d) of determining whether or not to use the output result of the step (b) based on the accuracy output in the step (c).

Images