Image forming apparatus

Abstract

To solve the problem in which: when a density variation model is corrected, data acquired for the correction also has a variation, which reduces the accuracy of the model.SOLUTION: An image forming apparatus is provided which forms an image on a sheet through an intermediate transfer body based on an image forming condition. The apparatus measures a first image for measurement formed on the intermediate transfer body with a first sensor, and measures a second image for measurement formed on a sheet with a second sensor. The apparatus acquires variation correlation information correlated to a variation in the density of an image to be formed, determines the density of the image to be formed based on a determination condition from the acquired variation correlation information, and creates the image forming condition based on the determined density. The apparatus updates the determination condition based on a result of measurement of the first image for measurement, a result of measurement of the second image for measurement, and the variation correlation information.SELECTED DRAWING: Figure 17

Description

Technical Field

[0001] The present invention relates to an image forming apparatus, and more particularly to an image forming apparatus using, for example, an electrophotographic process.

Background Art

[0002] Due to short-term variations caused by changes in the environment where the apparatus is installed or within the apparatus, and long-term variations caused by changes over time (aging deterioration) of the photoreceptor and developer, etc., the density and density gradation of the output image may differ from the desired density and gradation. Therefore, in an image forming apparatus, it is necessary to correct the image forming conditions as needed in consideration of various such variations in order to match the density and gradation of the output image to the desired density and gradation.

[0003]

[0004] Conventionally, in order to stabilize the density and gradation of the output image described above, for example, as in Patent Document 1, a specific correction pattern such as a gradation pattern is formed on a sheet of paper. The formed pattern is read by an image reading unit, and the read gradation pattern information is fed back to image forming conditions such as γ (gamma) correction, thereby improving the stability of image quality.

[0005] ​Also, the timing when calibration is required varies depending on various situations, including environmental changes and long-term idle conditions as described above, and appropriate tone correction is necessary. For example, especially when powering on in the early morning when environmental changes are likely to occur, when resuming from the power-saving mode, or when the toner supply amount increases due to a high output image DUTY, or conversely, when jobs with a low output image DUTY are continuously performed. As a technique for performing such calibration, for example, a technique such as Patent Document 2 has been proposed.

[0006] In recent years, there has been an increasing demand for improving image quality stability, user-friendliness, especially productivity improvement by reducing waiting time and downtime. There is also a strong demand for controlling calibration for image quality stabilization in a shorter time. As a technique corresponding to such a demand, for example, as in Patent Document 3, a model is created using fluctuations in the external environment, image output conditions, and various sensor values as input values, and fluctuations in calibration patches are predicted from the model. By doing so, a technique has been proposed that omits the image formation process of patches that consume a large amount of calibration time.

[0007] Furthermore, as a method of performing control in a model for predicting fluctuations so that it becomes an optimal operation value depending on the usage environment and usage situation, a technique such as Patent Document 4 has been proposed. Patent Document 4 proposes a technique of learning the characteristics of an image forming apparatus using a neural network and determining an operation amount from a state prediction value and a target value.

Prior Art Documents

Patent Documents

[0008]

Patent Document 1

Patent Document 2

Patent Document 3

Patent Document 4

Summary of the Invention

Problems to be Solved by the Invention

[0009] However, in the calibration method of predicting variations in color and density using a model in this way, the following problems occur.

[0010] When performing calibration control for density adjustment using an optimal density prediction model that individually corresponds to the usage environment, output conditions, and usage status, it is necessary to modify the current prediction model. This is because, usually in the initial stage, it is common to use an average model that can cover a certain range of usage environments and situations, and it is not always optimal for individual usage environments.

[0011] To modify the prediction model, data that combines actual density variations with the environment, output conditions, etc. is required. Therefore, usually, control for actually forming a calibration patch and performing density adjustment is used in combination, and at the timing of executing calibration control using the patch, data for modifying the prediction model is simultaneously acquired.

[0012] However, to modify the prediction model, a considerable amount of data is required, and it takes a lot of time to calculate the optimal model. This is because if the model is modified with a small amount of data, the model will be greatly biased towards the acquired data only, or the acquired data for modification will deviate significantly from the center of the assumed density distribution, and as a result, a model with poor prediction accuracy may be formed instead.

[0013] Also, it is necessary to consider the variation in the data itself used to modify the prediction model. The accuracy of the actual density variation data that can be acquired depends on the accuracy of the density detection system. However, in order to quickly and accurately modify the prediction model, it is important to use a lot of data that is close to the true value for the density data used.

[0014] The present invention has been made in view of the above circumstances. An object thereof is to provide an image forming apparatus capable of modifying a prediction model in a usage environment in a short period of time with high accuracy in calibration for stabilizing color tone and density gradation control.

Means for Solving the Problems

[0015] In order to achieve the above object, the present invention has the following configuration. That is, according to one aspect of the present invention, an image forming unit that forms an image on a sheet via an intermediate transfer body based on image forming conditions, a first measuring unit that measures a first measurement image formed on the intermediate transfer body by the image forming unit, a second measuring unit that measures a second measurement image formed on the sheet by the image forming unit, an acquisition unit that acquires variation correlation information correlated with variation in density of an image formed by the image forming unit, a generation unit that determines the density of an image formed by the image forming unit based on determination conditions from the variation correlation information acquired by the acquisition unit, and generates the image forming conditions based on the determined density, and an update unit that updates the determination conditions based on the measurement result of the first measurement image by the first measuring unit, the measurement result of the second measurement image by the second measuring unit, and the variation correlation information acquired by the acquisition unit. and the update means updates the determination condition by weighting the measurement result of the second measurement image by the second measurement means more heavily than the measurement result of the first measurement image by the first measurement means An image forming apparatus characterized by the above is provided.

Effects of the Invention

[0016] According to the present invention, in calibration for stabilizing color tone and density gradation control, it becomes possible to modify an optimal prediction model in a usage environment in a short period of time with high accuracy.

Brief Description of the Drawings

[0017]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22

Figure 23

Figure 24

Mode for Carrying Out the Invention

[0018] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the invention according to the claims. Although a plurality of features are described in the embodiments, not all of these plurality of features are essential to the invention, and the plurality of features may be arbitrarily combined. Further, in the accompanying drawings, the same or similar configurations are denoted by the same reference numerals, and duplicate explanations are omitted.

[0019] [Embodiment 1] First, a first embodiment of the present invention will be described. In this embodiment, a method for solving the above problems will be described using an image forming apparatus of an electrophotographic system (or an electrophotographic process). Although the description is made in the electrophotographic system, the characteristic points of control, particularly the matters described in the claims, have the same problems in an inkjet printer, a sublimation printer, etc., and the problems can be solved using the methods described below. Therefore, it is claimed that each image forming apparatus is also included in the invention according to the above claims.

[0020] (Image Forming Apparatus) (Reader Unit) As shown in FIG. 1, the image forming apparatus 100 includes a reader unit A. The document placed on the document table glass 102 of the reader unit A is illuminated by a light source 103, and the reflected light from the document forms an image on a CCD sensor 105 via an optical system 104. The CCD sensor 105 consists of red, green, and blue CCD line sensor groups arranged in three columns, and generates red, green, and blue color component signals for each line sensor. These reading optical system units are moved in the direction of arrow R103 shown in FIG. 1 to convert the image of the document into an electrical signal for each line. On the document table glass 102, there are a positioning member 107 that abuts on one side of the document to prevent the document from being placed obliquely, and a reference white plate 106 for determining the white level of the CCD sensor 105 and performing shading correction in the thrust direction of the CCD sensor 105. The image signal obtained by the CCD sensor 105 is A / D converted, subjected to shading correction using the reading signal of the reference white plate 106, and color-converted by a reader control unit 108, and then sent to the printer unit for processing by a printer control unit. In addition, an operation unit 20 and a display 218 for an operator to perform operations such as copy start and various settings are connected to the reader unit A. The reader unit A may also be provided with a CPU, a RAM 215, and a ROM 216 for control. These control the reader unit A.

[0021] (Printer unit) As shown in FIG. 1, the image forming apparatus 100 is a tandem type intermediate transfer full-color printer in which yellow, magenta, cyan, and black image forming units PY, PM, PC, and PK are arranged along an intermediate transfer belt 6.

[0022] In the image forming unit PY, a yellow toner image is formed on a photosensitive drum 1Y and is primarily transferred to the intermediate transfer belt 6. In the image forming unit PM, a magenta toner image is formed on a photosensitive drum 1M and is primarily transferred onto the yellow toner image on the intermediate transfer belt 6. In the image forming units PC and PK, a cyan toner image and a black toner image are formed on photosensitive drums 1C and 1K, respectively, and are similarly sequentially overlaid and primarily transferred to the intermediate transfer belt 6.

[0023] The four-color toner images primarily transferred onto the intermediate transfer belt 6 are conveyed to the secondary transfer unit T2 and collectively secondarily transferred onto the recording material P. The recording material P onto which the four-color toner images have been secondarily transferred is conveyed by the conveyance belt 10, heated and pressurized by the fixing device 11 to fix the toner images on the surface, and then discharged to the outside of the machine body.

[0024] The intermediate transfer belt 6 is supported by being wound around the tension roller 61, the drive roller 62, and the opposing roller 63, and is driven by the drive roller 62 to rotate in the direction of arrow R2 at a predetermined process speed.

[0025] The recording material P pulled out from the recording material cassette 65 is separated one by one by the separation roller 66 and sent to the registration roller 67. The registration roller 67 receives and waits for the recording material P in a stopped state, and feeds the recording material P into the secondary transfer unit T2 in synchronization with the toner image on the intermediate transfer belt 6.

[0026] The secondary transfer roller 64 abuts on the intermediate transfer belt 6 supported by the opposing roller 63 to form the secondary transfer unit T2. When a positive-polarity DC voltage is applied to the secondary transfer roller 64, the toner image charged negatively and carried on the intermediate transfer belt 6 is secondarily transferred onto the recording material P.

[0027] The image forming units PY, PM, PC, PK are substantially configured identically except that the colors of the toners used in the developing devices 4Y, 4M, 4C, 4K are different, being yellow, magenta, cyan, and black respectively. Hereinafter, when no particular distinction is required, the subscripts Y, M, C, K attached to the symbols to indicate that they are for any one of the colors are omitted and a general description is given.

[0028] As shown in FIG. 1, around the photosensitive drum 1 of the image forming unit, a charging device 2, an exposure device 3, a developing device 4, a primary transfer roller 7, and a cleaning device are arranged.

[0029] The photosensitive drum 1 has a photosensitive layer with a negative charging polarity formed on the outer peripheral surface of an aluminum cylinder, and rotates in the direction of the arrow at a predetermined process speed. The photosensitive drum 1 is an OPC photosensitive member with a reflectivity of approximately 40% for near-infrared light (960 nm). However, an amorphous silicon-based photosensitive member or the like having a similar reflectivity may also be used.

[0030] The charging device 2 uses a scorotron charger, irradiates the photosensitive drum 1 with charged particles generated by corona discharge, and charges the surface of the photosensitive drum 1 to a uniform negative potential. The scorotron charger has a wire to which a high-voltage is applied, a shield portion connected to the ground, and a grid portion to which a desired voltage is applied. A predetermined charging bias is applied to the wire of the charging device 2 from a charging bias power source (not shown). A predetermined grid bias is applied to the grid portion of the charging device 2 from a grid bias power source (not shown). Depending on the voltage applied to the wire, the photosensitive drum 1 is charged to approximately the voltage applied to the grid portion.

[0031] The exposure device 3 scans a laser beam with a rotating mirror and writes an electrostatic image of an image on the surface of the charged photosensitive drum 1. A potential sensor (not shown), which is an example of potential detection means, can detect the potential of the electrostatic image formed by the exposure device 3 on the photosensitive drum 1. The developing device 4 attaches toner to the electrostatic image on the photosensitive drum 1 and develops it into a toner image.

[0032] The primary transfer roller 7 presses against the inner surface of the intermediate transfer belt 6 to form a primary transfer portion between the photosensitive drum 1 and the intermediate transfer belt 6. By applying a positive DC voltage to the primary transfer roller 7, the negative-polarity toner image carried on the photosensitive drum 1 is primarily transferred to the intermediate transfer belt 6 passing through the primary transfer portion T1.

[0033] The first density sensor (patch detection sensor) 200 is arranged to face the intermediate transfer belt 6 and measures the image density of unfixed toner. The first density sensor 200 includes a light-emitting diode (hereinafter referred to as LED), which is a light source that irradiates infrared rays onto the intermediate transfer belt. The first density sensor 200 further includes an optical sensor, such as a photodiode (hereinafter referred to as PD), that receives the reflected light of the light irradiated from the light source onto the intermediate transfer belt and the patch image at the position of the specular reflection angle, and an optical sensor composed of a PD that receives the diffused reflection light at the position of the diffused reflection. The LED and the optical sensor are mounted on an electric substrate, and the first density sensor 200 is configured including them. Here, at the position of the optical sensor 200, during image formation, a toner image, for example, a patch image, is formed on the intermediate transfer belt 6 by the image forming units PY, PM, PC, and PK for each color component.

[0034] Regarding the black toner, the detection result of the specular reflection light by the first density sensor 200 is used, and regarding cyan, magenta, and yellow, the detection result of the diffused reflection light by the first density sensor 200 is used to convert them into density values. At this time, the relationship between the signal value of the output signal of the first density sensor 200 and the density value is acquired in advance and stored in the main body of the image forming apparatus as a LUT. Then, according to the LUT, the signal value of the first density sensor 200 is converted into the density value of each color. In this embodiment, the first density sensor 200 is arranged to face the intermediate transfer belt 6, but it can also be arranged as appropriate, including a configuration arranged to face the photosensitive drum 1. In this example, there are multiple colors other than black. For example, by measuring the patch images of each color component at the timing determined for each color, the density of each color can be detected by one sensor.

[0035] On the other hand, as an image density sensor for measuring the fixed pattern image, a line sensor is arranged as the second density sensor 500 on the downstream side of the fixing device. The second density sensor 500 is an optical sensor such as a CMOS line sensor or a CCD line sensor, reads the image formed on the paper, and outputs read signals for each color of R, G, and B. A white LED or the like may be provided as a light source for irradiating the toner image formed on the sheet near the second density sensor 500.

[0036] This read signal value is converted into density values for each of cyan (C), magenta (M), yellow (Y), and black (K) and then used. Generally, C is calculated from the luminance value of the R sensor, M is calculated from the luminance value of the G sensor, Y is calculated from the luminance value of the B sensor, and K is calculated from the luminance value of the G sensor. At this time, the relationship between the luminance values of each RGB sensor and the density values of each color is obtained in advance and stored in the main body as a LUT, and the density values of each color are converted from the respective luminance values according to the LUT.

[0037] The cleaning device rubs a cleaning blade against the photosensitive drum 1 to recover the transferred residual toner remaining on the photosensitive drum 1, bypassing the transfer to the intermediate transfer belt 6.

[0038] The belt cleaning device 68 rubs a cleaning blade against the intermediate transfer belt 6 to recover the transferred residual toner remaining on the intermediate transfer belt 6, bypassing the transfer to the recording material P and passing through the secondary transfer section T2.

[0039] Note that a potential sensor for measuring the potential on the surface of the photosensitive drum 1 for each color component may be provided and configured to output a signal indicating the potential.

[0040] (Image processing unit) FIG. 2 is a diagram showing the configuration of the printing system according to the present invention. In the figure, 301 is a host computer, and 100 is an image forming apparatus. The host computer 301 and the image forming apparatus 100 are connected by a communication line such as USB2.0 High-Speed, 1000Base-T / 100Base-TX / 10Base-T (conforming to IEEE 802.3).

[0041] In the image forming apparatus 100, the printer controller 300 controls the operation of the entire printer. The printer controller 300 has the following configuration. A host I / F unit 302 that controls input / output with the host computer 301. An input / output buffer 303 for performing transmission and reception of control codes from the host I / F unit 302 and data from each communication means. A printer controller CPU 313 that controls the operation of the entire controller 300. A program ROM 304 in which a control program and control data of the printer controller CPU 313 are built-in. A RAM 309 used as a work memory for interpreting the control codes and data, performing calculations necessary for printing, or processing print data. An image information generation unit 305 that generates various image objects based on settings of data received from the host computer 301. A RIP (Raster Image Processor) unit 314 that expands the image object into a bitmap image. A color processing unit 315 that performs color conversion processing for multi-color. A tone correction unit 316 that executes tone correction for single color. A pseudo halftone processing unit 317 that executes pseudo halftone processing such as a dither matrix or an error diffusion method. An engine I / F unit 318 that transfers the converted image to the image forming engine unit. An image forming engine unit 101 that forms the converted image data as an image. The above is the flow of image processing of the printer controller during basic image formation, which is shown by thick solid lines.

[0042] The printer controller 300 is in charge of not only image formation but also various control operations. It has a control program for that in the program ROM 304. The following are included as the control program and data. · A maximum density condition determination unit 306 that performs maximum density adjustment. · A predicted density calculation unit 307 that predicts the density based on the output value from the sensor or the like. · A tone correction table generation unit (γLUT) 308 that performs density tone correction. The generated tone correction table includes, for example, an output density value corresponding to the input density value as a correction value. · A prediction model correction unit 350 that corrects a model for calculating a predicted density. Note that detailed descriptions of various control operations in the printer controller will be described later. Note that the gradation correction table may also be referred to as an image correction condition.

[0043] In addition, it has a table storage unit 310 that temporarily stores the adjustment results from the maximum density condition determination unit 306 to the gradation correction table generation unit 308. Furthermore, it has an operation panel 218 that gives execution instructions for the operations of the printing apparatus and the above correction process, and a panel I / F unit 311 that connects the printer controller 300 and the operation panel 218. Furthermore, it is composed of an external memory unit 181 used for storing print data and information on various printing apparatuses, a memory I / F unit 312 that connects the controller 300 and the external memory unit 181, and a system bus 319 that connects each unit.

[0044] Furthermore, the image forming apparatus 100 includes an image forming engine unit 101, which is controlled by an engine control CPU 1012. In addition, the image forming engine unit 101 also includes a first density sensor 200, a second density sensor 500, a timer 201, a counter 202, etc.

[0045] (Density prediction unit) Next, with reference to FIG. 3, the predicted density calculation unit in the printer controller 300 will be described. Various signal values from the image density sensor 200, the timer 201, and the counter 202 provided in the image forming apparatus 100, and the current image forming conditions 203 are input to the predicted density calculation unit 307 in the printer controller 300. The image forming conditions 203 include the current exposure intensity (hereinafter LPW) and charging potential (hereinafter Vd) in the image forming apparatus 100, etc. Furthermore, it may include the temperature inside the machine, etc. At this time, first, the signal values are input to the input signal value processing unit 320 in the predicted density calculation unit 307. This input signal value processing unit 320 includes a signal value storage unit 321 that stores basic signal values, and a difference calculation unit 322 that calculates the difference between the input signal values and the signal values stored in the signal value storage unit 321.

[0046] The signal value processed by the input signal value processing unit 320 is input to the density prediction unit 330. The density prediction unit 330 includes a density storage unit 331 that stores the basic density, and a prediction function unit 332 that predicts the density from the input value from the input signal processing unit 320. The prediction function unit 332 has an image density prediction model (also referred to as a prediction model) 3321 that calculates the density change amount from the basic density from the input value. The prediction model 3321 includes, for example, a matrix of partial regression coefficients of a multiple regression model. The prediction function unit 332 adds the density change amount calculated using the image density prediction model 3321 and the basic density stored in the density storage unit 331 to calculate the current predicted density. Note that the image density prediction model 3321 will be described later. Also, the acquisition of the basic signal value and the acquisition of the basic density will be described later.

[0047] The calculated predicted density is input to the gradation correction table generation unit 308. The gradation correction table generation unit 308 creates a γLUT for input to the gradation correction unit 316 based on the predicted density. Note that the gradation correction method will be described later.

[0048] (Prediction Model Correction Unit) Next, the prediction model correction unit 350 that corrects the model for calculating the predicted density will be described with reference to FIG. 4. The correction of the prediction model is performed, as will be described later, by adding correction data to the data used to create the current model. That is, correction data is added to create a corrected model. Therefore, the model creation data storage unit 351 that stores the data when the current model was created includes a signal value storage unit that stores signal values such as sensors and conditions for model creation, and a corresponding density value storage unit. Note that the current model refers to the initially created basic model (or initial model) when no correction has been applied, and the corrected latest model when correction has been applied.

[0049] In addition, the model correction data storage unit 352 stores the newly acquired correction data. The model correction data storage unit 352 includes a signal value storage unit that stores signal values, and a density value storage unit that stores density values corresponding to the stored signal values. The signal value storage unit stores signal values obtained from the first density sensor 200, the timer 201, the counter 202, and the image formation conditions 203. In addition, signal values obtained from a sensor 299 such as a potential sensor that measures the potential on the surface of each photosensitive drum 1 may be stored. The density value storage unit stores density values obtained from the first density sensor 200 and the second density sensor 500, respectively. The first density sensor 200 corresponds to an image density sensor (patch detection sensor) 200. The second density sensor 500 is a line sensor provided in the sheet conveyance path in the present embodiment, but any sensor that can measure the density on the recording material, such as the reader unit A, may be used. In the present embodiment, the case where the reader unit A is used as the density sensor for the image on the sheet will be described.

[0050] Furthermore, the model calculation unit 353 that determines a new model using these data includes a calculation unit that newly creates a model and a model storage unit that stores the created model. When the model correction is completed, the relationship between the signal value and the density value is stored in the model creation data storage unit as a data set. The prediction model correction unit 350 described here can be realized by being included in the image forming apparatus or in a device connected to the image forming apparatus via a network.

[0051] (Obtaining Density Prediction Reference Value) Next, the acquisition methods of the basic signal values stored in the signal value storage unit 321 and the basic concentrations stored in the concentration storage unit 331, which were described in the aforementioned concentration prediction unit 330, will be explained. As an example, the basic concentration used in this embodiment is obtained by automatic gradation correction using an output image (toner image after fixing) formed on a sheet that is periodically performed as shown in FIG. 5. In this embodiment, a system having a potential sensor for measuring the potential on the drum surface will be described, but the present invention is not limited to this. Also, regarding the acquisition timing, it is also possible to acquire in the same manner at the control timing for creating sufficient gradation patches.

[0052] (Potential Control) When the automatic gradation correction control is started arbitrarily by the user, first, the potential control process (S201) starts. The engine control unit CPU1012 determines the target charging potential (VdT), grid bias (Y), and development bias (Vdc) by potential control before printing on a sheet (a medium such as paper). By the potential control process, it is possible to determine the charging potential and the like according to the environmental conditions (including temperature and humidity conditions) in which the image forming apparatus 100 is installed. The engine control unit CPU1012 may also be referred to as the engine control unit 1012.

[0053] In this embodiment, the engine control unit 1012 performs potential control called two-point potential control. FIG. 6 is a diagram for explaining the concept of potential control by two-point potential control. In FIG. 6, the horizontal axis represents the grid bias, and the vertical axis represents the photoreceptor surface potential. VD1 indicates the charging potential under the first charging condition (grid bias 400V), and Vl1 indicates the potential of the exposed portion formed with the standard laser power. Also, Vd2 indicates the charging potential under the second charging condition (grid bias 800V), and Vl2 is the potential of the exposed portion formed with the standard laser power at that time. At this time, the contrast potentials (Cont1, Cont2) at grid biases of 400V and 800V can be calculated from equations (1) and (2).

[0054] (Cont1)=(Vd1―Vl1) ···(1) (Cont2) = (Vd2 - Vl2) ···(2) Here, the increase amount of the contrast potential (ContΔ) every 1 V of the charging potential can be calculated by Equation (3) based on the results of Equations (1) and (2).

[0055] (ContΔ) = ((Cont2 - Cont1) / (Vd2 - Vd1))···(3).

[0056] On the other hand, an environmental sensor (not shown) is provided in the image forming apparatus 100, and the environmental sensor measures the environmental conditions such as the temperature and humidity inside the image forming apparatus 100. The engine control unit 1012 obtains the environmental conditions (for example, the absolute moisture content) inside the image forming apparatus 100 based on the measurement results of the environmental sensor. Then, the target contrast potential (ContT) corresponding to the environmental conditions is referred to from a pre-registered environmental table.

[0057] The relationship between the target contrast potential (ContT) and the increase amount of the contrast potential (ContΔ) can be calculated by Equation (4). ContT = Cont1 + X · ContΔ ···(4).

[0058] If the parameter "X" that satisfies the relationship of Equation (4) is calculated, the target charging potential (VdT) (hereinafter, this is also referred to as the "target potential") can be calculated by Equation (5). VdT = Vd1 + X ···(5).

[0059] The change amount of the charging potential (VdΔ) per 1 V of the grit bias can be calculated by Equation (6). (VdΔ) = (Vd2 - Vd1) / (800 - 400) ···(6).

[0060] The grit bias (Y) that gives the target potential (VdT) can be calculated from Equation (7). Target VdT = 400 + Y · VdΔ ···(7).

[0061] In formula (7), VdΔ can be calculated by formula (6), and VdT can be calculated from formula (5). Therefore, by substituting the potential known from formulas (5) and (6), the grid bias (Y) that satisfies the relationship of formula (7) can be finally determined.

[0062] Through the above processing, the target potential (VdT) and grid bias (Y) according to the environmental conditions can be determined. The development bias (Vdc) has a specified potential difference with respect to the target potential (VdT), and it can be calculated by subtracting the specified potential from the determined target potential (VdT). Image formation is performed hereafter with the determined development bias (Vdc). Note that the potential on each drum is negative, but the minus sign is omitted here for the sake of easy understanding of the calculation process. Through the above processing, the potential control process of step S201 in FIG. 5 is terminated.

[0063] (Maximum toner loading adjustment) Next, the process proceeds to step S202, and a patch image for adjusting the maximum toner loading is formed (S202) using the grid bias (Y) determined by the potential control in the previous step S201 and the development bias (Vdc).

[0064] In printers that emphasize productivity, the following flow is omitted, and a flow for adjusting the maximum loading amount only by potential control is also disclosed. However, since the charge holding amount of the colorant in the developing device, the mixing ratio of toner and carrier, etc. also change depending on the environment and durability, control only by potential has low accuracy. Therefore, in this embodiment, a patch image with the exposure intensity (hereinafter, LPW) changed in several steps is formed, and the LPW used for normal image formation is determined.

[0065] The image forming apparatus 100 in which the grit bias (Y) and the development bias (Vdc) are determined forms five patch images ((1) to (5)) for each of black, cyan, yellow, and magenta as shown in FIG. 7 in order to adjust the maximum load. Note that the number of patches is not limited to this. The formation conditions of the five patch images are different in LPW, and are LPW1, LPW2, LPW3 (corresponding to the standard laser power used for potential control), LPW4, and LPW5 in order from the left. The laser power increases from LPW1 to LPW5 in order. Also, the number of patch colors may follow the number of color components used in the image forming apparatus 100 and is not limited to four colors.

[0066] The output image is set by the user in the reader unit, and the density of the image pattern is automatically detected (S203). FIG. 8 is a diagram showing the relationship between the density value of each patch image and LPW. By controlling LPW so that the detected density value matches the target density target value (hereinafter, also referred to as the "maximum load target density value"), it is possible to adjust the toner load.

[0067] (Tone correction and basic value acquisition) When the adjustment of the maximum toner load is completed, tone correction is then performed. Here, using the grid bias (Y) determined previously, the development bias (Vdc), and the LPW level, an image pattern of 64 tones for each color is formed and output onto paper (S204). Note that the number of tones is not limited to this.

[0068] The output image is set by the user in the reader unit, and the density of the image pattern is automatically detected (S205).

[0069] From the density obtained from the image pattern, interpolation processing and smoothing processing are performed to obtain the engine γ characteristics in the entire density range. Next, using the obtained engine γ characteristics and a preset gradation target, a gradation correction table for converting the input image signal into an output image signal is created (S206). In the present embodiment, as shown in FIG. 9, an inverse conversion process is performed to match the gradation target to create a gradation correction table. When this operation is completed, the density on paper will match the gradation target in the entire density range.

[0070] Apply the target LPW determined by the above procedure, and using the gradation correction table, form a toner image pattern including test images (also referred to as measurement images) of a plurality of gradations for each color component (S207). If the density of the test image is detected using the first density sensor 200 on the intermediate transfer member (S208), the density value becomes the target density on the intermediate transfer member and is stored in the density storage unit 331 as the basic density (S209). The intermediate transfer member may be an intermediate transfer belt, a photoreceptor, or the like. In the present embodiment, after the gradation correction table is created, test images of 10 gradations are formed for each color component, the test images are measured using the first density sensor 200, and the results (for example, measurement values) are stored in the density storage unit 331 as the basic density. The density storage unit 331 stores the measurement results of the first density sensor 200 that vary according to the density of the test image. In this case, the data stored in the density storage unit 331 is the density value of the test image. Note that the density value may be stored together with the density value before or after gradation correction corresponding to the density. However, it is necessary to determine which one it is. Also, if the test images to be formed are determined in advance, the density value for each detected test image may be stored without being associated with the density value. The basic density value is referred to during calibration.

[0071] Also, when performing this automatic gradation correction and obtaining the base density, the sensor, counter, timer values, and image forming conditions such as grid bias, developing bias, and LPW level are stored in the signal value storage unit 321 as basic signal values (S210). Referring to the base density, engine γ characteristics, and basic signal values thus obtained, the gradation correction table (LUT) is updated in the manner described below.

[0072] In this embodiment, since the image density prediction model is a model for predicting the density of test images such as patches on the intermediate transfer body, the base density value stores the density value measured on the intermediate transfer body. However, for example, when using a model for predicting the density of test images on the recording medium, the density of the test image on the recording medium is measured and stored by the reader unit A as the base density value (base density). The base density may be appropriately selected according to which patch density the image density prediction model deals with, and is not limited to the above. Note that the second density sensor 500 may be used instead of the reader unit A. When the density of the test image is measured by the reader unit A, the second density sensor may refer to the reader unit A.

[0073] (Density correction control) (Outline of control timing of actual measurement control and prediction control) The basic gradation correction table was created according to the procedure of FIG. 5, and the base density and basic signal values were also stored. The gradation correction table needs to be updated according to the color change and density change that occur according to the degree of use of the image forming apparatus. Therefore, in this embodiment, density correction by actual measurement control and density correction by prediction control are used in combination.

[0074] A density correction sequence by forming a density patch on an intermediate transfer belt and reading the density patch with an image density sensor such as a first density sensor is generally often executed by interrupting an image formation sequence which is a printing operation, contributing to a decrease in productivity. On the other hand, performing the actual measurement control at a low frequency out of concern for a decrease in productivity leads to deterioration of image quality due to neglect of variations in color tone and density or either of them. Based on this background, in a conventional image forming apparatus, the control timing of the actual measurement control is set in consideration of the balance between color tone / density variations and productivity. Depending on the main body configuration, it is possible to improve the frequency of the actual measurement control by forming a density patch outside the image formation range. However, since performing the actual measurement control at a high frequency may also lead to an increase in toner usage, that is, an increase in cost, it is difficult at present to increase the frequency of the actual measurement control.

[0075] However, by performing predictive control of density, it becomes possible to supplement density correction between the controls of the actual measurement control and suppress color tone / density variations. An overview diagram of the control timings of the actual measurement control and the predictive control is shown in FIG. 24. FIG. 24(a) shows the density correction control timing when only the conventional actual measurement control was performed, and the color tone variation strength at that time. On the other hand, FIG. 24(b) shows the density correction control timing and the color tone variation strength when the actual measurement control and the predictive control proposed in this case are intertwined and controlled. As a result, since the density correction shown in FIG. 24(b) can perform density correction at a higher frequency, it has been realized that color tone variations can be more suppressed.

[0076] Note that, as will be described later, a data set for correcting the density prediction model is acquired simultaneously at the timing of control for actually forming a patch image and measuring the density, including correction control performed by forming a density patch on such a transfer belt.

[0077] (Method for Creating (Updating) LUT at the Time of Predictive Density Correction) Next, in predictive control, a method of reflecting the calculated density value in the LUT will be described. First, at the time of automatic gradation correction (Fig. 5) arbitrarily performed by the user, a gradation correction table (hereinafter referred to as the basic correction LUT) is formed in accordance with the engine γ characteristic so as to become a preset gradation target (hereinafter referred to as the gradation LUT). Then, the basic density values of 10 gradations for each color described above are obtained. After automatic gradation correction, the input image data is converted by this initial correction LUT and input to the engine, and is output in combination with the engine γ characteristic so as to become the target gradation LUT.

[0078] Thereafter, for example, at the timing when the activation conditions of density correction control are satisfied, such as when the power is turned on, when waking up from sleep, when the environment changes, or at a preset timing, the density value is acquired, and the acquired density value is used to create an LUT (hereinafter referred to as the composite correction LUT) at the time of image output. The method of creating the composite correction LUT will be described with reference to Figs. 10, 11, 12, and 13. Fig. 10 is a flowchart of creating the composite correction LUT. The process of Fig. 10 is executed, for example, by the printer controller CPU 313. The density curve in the following description is a curve showing the correspondence between the input signal value representing the density and the recorded density value (or predicted density value). The density curve may be realized, for example, by a table associating the input value and the density value. Also, the process of Fig. 10 is executed at the predictive control timing shown in Fig. 24. Specifically, it may be executed every time printing on a predetermined number (or number of pages) of sheets is completed.

[0079] First, the predicted density value of the test image is acquired (S301). The acquisition of the predicted density will be described later with reference to Fig. 15. Next, the acquired predicted density values are plotted for each gradation, and a density curve (broken line) for the predicted density values shown as ○ points in Fig. 11 is created (S302). An inverse transformation is performed to correct this density curve of the predicted density value to create a prediction-time LUT as shown by the long broken line in Fig. 12 (S303).

[0080] Here, the initial concentration curve corresponds to the concentration curve at the time of obtaining the basic concentration indicated by ● in FIG. 12. This may be realized by a table associating the input signal value with the basic concentration value stored in the concentration storage unit. Also, the curves of the initial correction LUT shown in FIGS. 11 and 13 indicate the characteristic of correcting the input signal value so that the relationship between the input signal value and the concentration becomes the initial concentration curve when image formation is performed based on the output signal value obtained by converting the input signal value by the initial correction LUT. On the other hand, the prediction-time LUT shown in FIG. 12 is a LUT for converting the predicted concentration curve (characteristic) corresponding to the input value into the basic concentration curve (characteristic).

[0081] Finally, a combined correction LUT as shown by the long two-dot chain line in FIG. 13, which is obtained by multiplying (i.e., combining) the prediction-time LUT and the initial correction LUT, is created (S304). The created combined correction LUT is passed to, for example, the gradation correction unit 316 and used for gradation correction. The input signal is converted into an output signal by this combined correction LUT and output by reflecting it on the output image. Note that the method of creating the concentration curve may be a generally used approximation method such as using an approximation formula connecting 10 points.

[0082] (Predicted Concentration Calculation) The flow of calculating the predicted concentration value in S301 is as shown in FIG. 15. Here, in the method of FIG. 5, a flow of predicting the concentration when the activation condition of the predicted concentration correction control is satisfied in a state where the basic signal value and the basic concentration have been obtained in advance will be described.

[0083] First, when the predicted concentration correction control is activated, information such as the environmental value, the elapsed time, and the number of toner replenishments at the time of activation, and information on the image formation conditions for performing image formation are obtained as input signal values from the sensors, timers, and counters provided in the image forming apparatus (S401). The difference between the obtained signal value and the basic signal value stored in advance is extracted (S402).

[0084] Next, substitute the extracted difference value into the image density prediction model formula created in advance based on considerations (S403), and calculate the difference value from the basic density of the current density as a predicted value (S404). Calculate the predicted density value at the current time from the sum of this difference predicted value and the basic density value, and obtain the γ characteristic (S405). Note that the creation process of the image density prediction model will be described later with reference to FIG. 16.

[0085] (LUT Creation Method during Measured Density Correction) The method for creating a patch image for density correction and the method for creating a composite correction LUT when the density is detected will be described using the processing flow of FIG. 20 and the density characteristic diagrams of FIGS. 21, 22, and 23. In this embodiment, a method of sequentially rotating and correcting patch images at five points of input values 30H, 60H, 90H, C0H, and FFH will be described, but it is not limited to this. The processing of FIG. 20 is executed by, for example, the printer controller CPU 313. Also, the processing of FIG. 20 is executed at the measured control timing shown in FIG. 24. Specifically, it may be executed every time printing on a predetermined number (or number of sides) of sheets is completed. However, the interval may be longer than the interval of density correction by prediction control, and desirably about several times (five times in the example of FIG. 24).

[0086] The patch image is created by applying the current correction LUT. After automatic gradation correction, for a determined gradation for density correction, for example, for each color component, a pattern with a density value of 30H is used as a test image, and it is created by applying the initial correction LUT as shown in Fig. 21 obtained during automatic gradation correction (S901, S902). This created pattern is formed into an image and detected by a density detection sensor (for example, the first density sensor 200), and the detection result is plotted as a detection density of 30H (S903). If the density value is detected, it is newly plotted at the 30H portion of the initial target density value as shown by the ○ mark in Fig. 22. That is, the input value of 30H and the detected density value are associated with each other. For the other 60H, 90H, C0H, and FFH, the density target value immediately after creating the initial correction LUT is used. Using this newly plotted 30H measured density value and the five basic density values of the initially measured density values 60H, 90H, C0H, and FFH, a density curve as shown by the long two-dot chain line in Fig. 23 is created (S904). The basic density values can be obtained from the density storage unit 331. The method of creating this density curve may be a generally used approximation method such as using an approximation formula that connects the five points.

[0087] Next, in order to correct the current density curve created in S904 to the initial density curve, an inverse transformation is performed to create a sequential correction LUT as shown by the broken line in Fig. 23 (S905).

[0088] Finally, a composite correction LUT as shown by the solid line in FIG. 22 obtained by multiplying the sequential correction LUT and the initial correction LUT is created (S906), reflected in the output image, and output. The output composite correction LUT is passed to, for example, the gradation correction unit 316 and used for gradation correction. After reflecting this composite correction LUT, the output image and the gradation pattern for image density correction in the next intersheet portion are output with image correction by this composite correction LUT. Thereafter, for example, after printing a predetermined number of pages, a pattern image of another gradation is continuously created, density detection is performed, and a composite correction LUT is sequentially created in the same procedure. The pattern image of another gradation may be patches of each gradation of 60H, 90H, C0H, and FFH in the above example. For densities other than the density of the actually measured pattern, the basic density may be used in the same manner as in the above example.

[0089] (Normal density calculation) Next, in the normal (measurement-based) density correction control for forming a patch image for density correction, a flow (S903) for acquiring the density value in the current image forming apparatus is shown in FIG. 14. FIG. 14 corresponds to S901 - S903 in FIG. 20.

[0090] When the activation conditions are satisfied, information such as environmental values, elapsed time, and toner replenishment times during the control operation and information on image forming conditions for performing image formation are acquired as input signal values from sensors, timers, and counters provided in the image forming apparatus (S501). The activation conditions are, for example, activation conditions for density correction control, such as power-on or reaching a specified number of sheets.

[0091] Next, a plurality of toner image patterns are formed under image forming conditions according to the acquired information (S502). In the present embodiment, patterns of 30H, 60H, 90H, C0H, and FFH are sequentially formed, but the present invention is not limited to this.

[0092] Next, the formed patch image is subjected to density detection (S503) using the first density sensor 200 on the intermediate transfer body, and the density value (γ characteristic) at the correction time is acquired.

[0093] (Creation of Density Prediction Model) The image density prediction model is obtained by formulating based on experimental results, taking information correlated with density fluctuations in the image (fluctuation correlation information) as input information and image density information as output information. For this reason, this formula itself may also be referred to as a prediction model, a prediction condition, or a determination condition. The input information includes environmental information that can be obtained from sensor 200 immediately after the power-on or return of the image forming apparatus, and time information such as the elapsed time since the previous print obtained from timer 201. Further, the input information includes count information such as the number of toner replenishments and the number of idle rotations obtained from counter 202, and the image forming conditions 203, etc. before the image forming apparatus is left idle. The density prediction model in this embodiment is a multiple regression model, and in its creation, the partial regression coefficients corresponding to each of the predetermined input information, which are explanatory variables, are determined. Also, in this example, as explanatory variables, the charging potential Vd, exposure intensity LPW, toner density in the developing unit, and environmental temperature during printing are used.

[0094] Hereinafter, the procedure for preliminarily creating the image density prediction model used in this embodiment will be described with reference to the flowchart of FIG. 16. The procedure of this flowchart may be executed by the prediction model correction unit 350 in software (or firmware). Hardware-wise, it is executed by the printer controller CP313. In this description, the explanation will proceed using a multiple regression model as an example, but the present invention is not limited to this multiple regression model, and a regression model by other means may also be used. Also, as input values (explanatory variables), some of the exemplified variables may be used, or other variables may be included. The creation of the prediction model may be performed individually for each machine body, or may be performed for the machine bodies serving as samples. In the latter case, a prediction model may be created for the sample machine bodies and applied to image forming apparatuses of the same type as the initial prediction model. Also, there may be a plurality of sample machine bodies. Note that the prediction model created here is an initial prediction model installed in a newly produced image forming apparatus in which parts and the like are not worn out, and is updated by the procedure described later in FIG. 17 and the like according to use.

[0095] First, prepare a large number of environmental condition variation patterns and image formation condition variation patterns, print a predetermined test image under those conditions, and measure the environmental conditions and image density (S101). The test image may be an image in which patterns of predetermined densities are arranged in a predetermined layout. The environmental conditions include the toner density in the developing unit during printing, the temperature and humidity at various locations, the toner density in the developing unit during the previous printing, the elapsed time since the previous printing, etc. These are environmental information that can be obtained immediately after power-on. The image formation conditions include the charging potential (hereinafter Vd) on the photosensitive drum, the exposure intensity (hereinafter LPW), the development contrast (hereinafter Vcont) in the developing unit, etc. The environmental conditions and image formation conditions to be measured may be those selected as explanatory variables. Also, the image density is the density of the test image, and for example, it may be the density on the photoreceptor of the toner patch, the density on the intermediate transfer body, or the density on the printing medium. In this example, for the creation of the initial prediction model, an example using the density on the intermediate transfer body will be described, but other densities may also be used. Alternatively, a combination of measurement values of multiple densities, such as a combination of the density on the intermediate transfer body and the density on the printing medium, may be used.

[0096] Next, classify the measurement data into identification data and verification data (S102). The identification data is used for determining the provisional coefficients, and the verification data is used for verifying the predicted density values using the provisional coefficients and for determining the actual coefficients. The actual coefficients become the partial regression coefficients of the generated prediction model. Therefore, it is desirable that the identification data and the verification data be randomly selected from the measurement values. Alternatively, the identification data and the verification data may be measured using different machines.

[0097] Next, using the first measurement data as a reference value, calculate the variation from the reference value for the values of each measurement item of environmental variation, image formation condition change, and image density variation (S103).

[0098] Next, the measured values of each environmental condition and each image forming condition classified as identification data are used as input data (explanatory variables), and the coefficients of the multiple regression model are obtained using the actually measured density values measured under each environmental condition and each image forming condition as teacher data (S104). The coefficients to be obtained are the coefficients such that the error between the predicted density value and the actually measured density value is minimized when the predicted density value is obtained using each environmental condition and each image forming condition included in the identification data as explanatory variables. In other words, in step S104, curve fitting of the regression model is performed. A detailed explanation of this will be given after the explanation of FIG. 16.

[0099] Next, the measured values of each environmental condition and each image forming condition designated and classified as verification data are used as input data to calculate the predicted density value. At this time, provisional coefficients are used for the prediction model. Then, the difference, that is, the prediction error, between the predicted density value and the actually measured density value measured under the measured values of each environmental condition and each image forming condition designated and classified as verification data is calculated (S105).

[0100] Finally, the provisional coefficients are corrected to determine the actual coefficients so as to minimize the prediction error or its average value (S106). That is, as the regression model, a linear function model in which coefficients are multiplied and added to the measurement items of each environmental condition and each image forming condition is determined.

[0101] In the above manner, a multiple regression model is created. In the above example, the measurement data is divided into identification data and verification data, but all of them may be used as identification data, and the provisional coefficients determined in step S104 may be used as the coefficients of the final prediction model. In this case, S105 and S106 do not need to be executed.

[0102] ● Determination of coefficients For example, in the following, the input signal values, i.e., the charging potential Vd during printing, the exposure intensity LPW, the toner concentration in the developing device, and the environmental temperature, are described as variation correlation information correlated with the variation of the image density, but it is not limited thereto. Note that the items included in this variation correlation information may be included in the basic signal values or may be the same. Also, for the above sensor input values, an explanation up to a four-input linear function model is given, but even when using five or more sensor inputs or image formation condition inputs, a regression model can be created by performing the same processing, and it is not limited thereto.

[0103] Create a linear function model that predicts the image density variation y as the output variable from combinations of four types of input variables. Here, the input variable x n_train is the LPW variation x i(n) during printing, the charging potential variation x 1(n) , the toner concentration variation x 2(n) in the developing device, and the environmental temperature variation x 3(n) . 4(n) Four-input model: y n_train = a1 × x 1(n) + a2 × x 2(n) + a3 × x 3(n) + a4 × x 4(n) (i = 1, 2, 3, 4, n = 1,..., number of data) More generally, y n_train = Σ i a i × x i(n) .

[0104] For this input model, the actually measured data of the image density variation, which is the output variable, is used as the teacher data y n_teach , and curve fitting is performed on this value. As an example of the curve fitting method, for the coefficients (a1, a2, a3, a4) of the linear function model, the sum of squares L of the prediction error represented by the following equation between the predicted value and the measured value is calculated, and the coefficients that minimize this are derived. The derivation method will be explained. First, each variable is represented by a matrix as follows.

[0105] ​ [Number]

[0106] Then, as described above, the sum of the squares of the differences between the predicted value and the measured value is obtained.

[0107] [Number]

[0108] This expansion formula is the sum of the squares of the prediction errors L. The objective is to find the matrix a that minimizes this L, that is, the coefficients (a1, a2, a3, a4) of the linear function model. That is, y = y n_teach , y n_train = xa, L = y T y - 2y T xa + a T x T xa Find the coefficient matrix a that gives the minimum value of. Therefore, set L as the objective variable, set the equation obtained by differentiating L with respect to a to 0, and solve it to derive the optimal coefficients of the regression model. First, find the differential formula.

[0109] [Number]

[0110] Then, set this solution to 0.

[0111] ―2y T X + a T (X T X + (X T X) T ) = 0 Then, perform the formula expansion with a on the left side, and a is obtained as follows.

[0112] a = ((X T X) T X T y n_teach) By obtaining the coefficient a matrix of the multiple regression model as an example of the image density prediction model in this way, the multiple regression model can be created.

[0113] In this embodiment, the input variables are x 1(n) , x 2(n) , x 3(n) , x 4(n) which are simple ones, but by preparing products or quotients of environmental conditions and image formation conditions such as x 1(n) ×x 2(n) , complex models can also be considered. For example, an input variable that can represent the change in toner charge amount considering the toner density in the developing unit and the standing time can be created, and the prediction model can be considered.

[0114] (Modification of the density prediction model) Using FIG. 17, the flow of modifying the density prediction model will be described. The procedure of this flowchart may be executed by the prediction model modification unit 350 in software (or firmware). On hardware, it is executed by the printer controller CP313. As described above, when performing calibration control for density adjustment using an optimal density prediction model corresponding individually to the usage environment, output conditions, and usage status, it is necessary to modify the prediction model to be used. This is because, generally, an average model that can cover a certain range of usage environments and situations is used for the prediction model set at the time of normal shipment, and it is not always optimal for individual usage environments.

[0115] To correct the prediction model, data (measurement values) combined with actual density fluctuations, environmental conditions, image formation conditions, etc. are required. In this embodiment, it is used in combination with control for forming a calibration patch and performing density adjustment, and at the same time, data for correcting the predicted density is acquired (S701). The correction of the predicted density is performed by correcting the coefficients of the prediction model. For this purpose, the density value of the patch image formed on the transfer belt (or on the photosensitive drum) which is an intermediate transfer member is measured using the first density sensor 200 at the timing of executing density correction control. Then, the density value, the output values of various sensors such as the in-machine temperature sensor, the timer value, the counter value, and the image formation conditions at that time are acquired as a set and stored as data for correcting the density prediction model. The patch image which is the measurement image formed by the intermediate transfer member may be referred to as the first measurement image. Also, using the second density sensor 500 for detecting the density of the patch image formed on the recording material, the density value is measured at the timing of executing density correction control. The timing here may be the timing of detecting the density by the reader unit during the automatic gradation correction performed periodically as described above. Then, the density value at that time, the various sensor values such as the in-machine temperature sensor, the timer value, the counter value, and the image formation conditions are acquired as a set and stored as data for correcting the density prediction model. Then, the number of data n is increased and added to the following matrix data. The density value measured here becomes the teacher data. The patch image which is the measurement image formed on the recording material, that is, the sheet may be referred to as the second measurement image.

[0116]

Number

[0117] Data is added until the number of added data n reaches a specified number (S702). When the specified number is reached, a new multiple regression model is created by obtaining the coefficients a of the multiple regression model again in the same manner as the above-described process using each of the variables updated by addition (S703). That is, the coefficient matrix a is updated. The above-described process may be, for example, adding new data to the original data and executing steps S101 to S104 in FIG. 16. Alternatively, the steps S105 to S106 in FIG. 16 may be executed using the new data as verification data.

[0118] In addition, when correcting the density prediction model, it is also conceivable to correct the model during actual density prediction control at any time, or to have a plurality of density prediction models and separately have a model for actually performing density prediction and a density prediction model for which correction is advanced. Further, as described above, data accumulation for correcting the density prediction model and execution of an operation for actually obtaining the corrected density prediction model can be realized by performing them in the image forming apparatus or in an apparatus connected to the image forming apparatus via a network. The place where the operation is performed does not limit the present invention.

[0119] (Effect of density measurement value on the recording material) Next, the effect of executing density prediction model correction using the first density sensor 200 (first density detection sensor) and the second density sensor 500 (second density detection sensor), which are features of this embodiment, will be described.

[0120] As described above, the first density detection sensor detects the density of a patch image formed on the transfer belt (or on the photosensitive drum). That is, when predetermined conditions such as the number of sheets passed, the image DUTY, or environmental changes are satisfied during the operation of the image forming apparatus, the detection value of a test image such as a patch formed on the belt or on the photosensitive drum is measured by the first density detection sensor, and density correction control is performed using the same. Therefore, as the image forming apparatus operates, a data set measured by the first density detection sensor is accumulated.

[0121] On the one hand, the second density detection sensor detects the density of a test image formed on a recording material, and can acquire a data set during automatic gradation correction arbitrarily performed by the user as described above. Therefore, usually, the number of data sets detected by the first density detection sensor is larger than that detected by the second density sensor.

[0122] However, from the viewpoint of the plausibility (accuracy) as data for model correction, the second density detection sensor can acquire a density value closer to the true value (here, the output density of each image forming apparatus) than the first density detection sensor.

[0123] The density value obtained from the first density detection sensor is obtained by converting the detection result of regular reflection light or diffused reflection light from a patch image formed on the belt into a density value from the relationship between the detection signal value and density (hereinafter referred to as the first ID conversion table) obtained in advance.

[0124] The first ID conversion table is a table that converts the patch image signal value on the intermediate transfer belt into the density of an image formed on paper. Therefore, usually, it includes variations when transferring a patch image from the intermediate transfer belt onto the recording material, variations in fixing properties in the fixing unit, etc. Also, since the intermediate transfer belt itself is rotating and running, the signal value obtained from the patch image on the belt also includes variations in the transportability of the belt itself.

[0125] On the other hand, since the density value obtained from the second density detection sensor is acquired by measuring the patch image on the recording material as described above, it does not include variations due to transfer and fixing. Also, since the second density detection sensor measures the density information of an image formed on a medium that is stationary in the leader unit A, there are few variations in the conveyance of the measurement surface. Therefore, the density data that can be acquired from the second density detection sensor can acquire a density value closer to the true value than the density data that can be acquired from the first density detection sensor, and high-precision data can be obtained as data for model correction.

[0126] In addition, since the model is modified when a certain amount of the dataset used for model modification has been accumulated, increasing the frequency of acquiring the dataset increases the rate at which the accumulated data grows. Therefore, by obtaining the density value with the first density sensor 200, the frequency of acquiring the dataset increases, and the model can be modified earlier. Furthermore, since the density data acquired by the second density sensor is close to the true value as described above, it becomes possible to improve the convergence to the individual models of each image forming apparatus.

[0127] From the above, the dataset of the signal value obtained from the second density detection sensor becomes a value closer to the output density of the image forming apparatus in use than the dataset of the first density detection sensor. Thereby, by using not only the dataset of the first density detection sensor but also the dataset of the signal value obtained from the second density detection sensor, it becomes possible to realize the reconstruction (or calibration) of the density prediction model faster and with higher accuracy. Also, by using the measured density value for the calibration of the LUT for density correction, the calibration of the LUT can be performed more frequently and with higher accuracy.

[0128] [Modification Example 1] In Embodiment 1, the case where a reader is used as the second density detection sensor and data for model modification is acquired by acquiring a dataset during automatic gradation correction arbitrarily performed by the user was described.

[0129] In this Modification Example 1, as the first density detection sensor, the first density sensor 200 that measures the patch image on the same belt as in Embodiment 1, and as the second density detection sensor, the second density sensor 500 that measures the patch image after fixing on the recording material are used. Then, the case of acquiring a dataset for modifying the density prediction model by these density sensors will be described. Note that the configuration and flow of the other image forming apparatuses are the same as those in Embodiment 1.

[0130] The test image such as the patch image of the detection target by the second density sensor 500 is formed on the recording material. The second density sensor 500 measures the density information of the image formed on the medium in the conveyed state. The timing of density control (or calibration) of the density prediction model using the measured value may be the same as the density control based on the density of the test image on the intermediate transfer belt. That is, when certain conditions such as the number of sheets passed, the image duty, or environmental changes are satisfied during the operation of the image forming apparatus, a patch image may be formed on the recording material separately from the actual output image, and its density may be measured and calibrated. The patch image on the recording material may be formed on the image area of the actual output image. In this case, the test image will be output between the production of printed materials. Alternatively, the patch image may be formed using the cutting portion that is cut after printing. When the patch image is formed and detected using the cutting portion, the test image is formed together with the production of the actual printed material, so the productivity does not decrease. Therefore, it is possible to form the patch image frequently and perform calibration of the density prediction model and calibration of the LUT for density correction. Note that the present invention is not limited to the above, and it is possible to execute at the timing of detecting the patch image formed on the recording material.

[0131] Here, an explanation will be given from the viewpoint of plausibility (accuracy) as data for model correction. The density data that can be obtained from the second density detection sensor can obtain a density value closer to the true value (here, the output density of each image forming apparatus) than the density data that can be obtained from the first density detection sensor.

[0132] The density value obtained from the post - fixing image density sensor as the second density detection sensor measures and acquires the patch image formed on the recording material while conveying the recording material. Therefore, while measurement value variations due to conveyance variations occur, variations due to transfer and fixing do not occur.

[0133] As shown in Embodiment 1, the density value obtained from the first density sensor includes variations due to conveyance and variations due to transfer and fixing. Therefore, the density data that can be obtained from the second density detection sensor can obtain a density value closer to the true value than the density data that can be obtained from the first density detection sensor, and highly accurate data can be obtained as data for model correction.

[0134] Also, when performing correction control by forming patch images regularly or frequently on the recording material as in this modified example, the frequency of obtaining the data set becomes high, and it becomes possible to correct the model earlier. Furthermore, since the density data obtained by the second density sensor is closer to the true value as described above, it becomes possible to improve the convergence to the individual model of each image forming apparatus.

[0135] From the above, the data set of the signal value obtained from the second density detection sensor becomes a value closer to the output density of the image forming apparatus in use than the data set of the first density detection sensor. By using not only the data set of the first density detection sensor but also the data set of the signal value obtained from the second density detection sensor, it becomes possible to reconstruct the density prediction model faster (or more frequently) and with higher accuracy.

[0136] [Embodiment 2] In Embodiment 1, a method of detecting the density of the patch image formed on the transfer belt by the first density sensor, detecting the density of the patch image formed on the recording material by the second density sensor, and correcting the density prediction model using the data set of the image forming conditions including the density value was explained.

[0137] In the second embodiment, a method for correcting a density prediction model by weighting a data set obtained from a first density sensor and measurement values obtained from each of second density sensors will be described with reference to FIG. 18. In this embodiment as well, the density of a test image (patch image) on paper is measured by the reader unit A. The procedure of FIG. 18 is executed by the prediction model correction unit 350 as in the first embodiment, but is executed by the printer controller CPU 313 in terms of hardware.

[0138] First, in the same manner as in the first embodiment, at the timing of each density control, a data set such as a calculated density value and a sensor value is acquired (S801). This may be the same as S701 in FIG. 17. Next, it is determined whether the acquired data set is a density measurement value formed on paper (S802). That is, it is determined whether the data set corresponds to the density value measured by the second density sensor. As described in the first embodiment, from the viewpoint of the plausibility (accuracy) as data for model correction, the density data that can be acquired from the second density sensor is closer to the true value (here, the output density of each image forming apparatus) than the density data that can be acquired from the first density sensor. Therefore, the data set acquired from the second density sensor is treated as data with high importance (S803), and the data set acquired from the first density sensor is treated as normal data (S804). Here, for example, information indicating the difference in importance may be associated and stored in the data set.

[0139] Next, it is determined whether the number of data sets combining the important data and the normal data collected in S801 is equal to or greater than a specified number (S805). If the specified number has not been reached, data set collection is performed again (S801), and if the specified number has been reached, creation of a correction model is carried out (S806).

[0140] As a method of treating important data, for example, when it is determined as important data, a method of increasing the number of the data itself can be mentioned. The data determined as important data, for example, replicates the same data set three times. Replicating three times means replicating one data set twice. In this way, by replicating a data set including density information and return correlation information a predetermined number of times, weighting is performed on the data actually measuring the paper density. As a result, data sets closer to the true value increase, and it becomes possible to correct the optimal density prediction model of each image forming apparatus more quickly and with high accuracy.

[0141] [Modification Example 2] Also, as shown in Modification Form 1, weighting is performed including the case of using the post-fixing density sensor (second density sensor 500). An example thereof is shown in FIG. 19. The procedure of FIG. 19 is executed by the prediction model correction unit 350 in the same manner as in Embodiment 1, but is executed by the printer controller CPU 313 in terms of hardware.

[0142] As shown in FIG. 19, the difference from FIG. 19 is that S805-S805 is replaced with S1003-S1007. Therefore, an explanation will be made centering on this difference.

[0143] If a data set including the measured density value is acquired, it is determined whether the density data (that is, the density value) included in the data set is acquired by the reader unit ( S1003). If so, considering the variation of the acquired density data, the data set associated with the detected density by the reader unit is replicated five times (S1005). On the other hand, the data set of the detected density by the post-fixing image density sensor, that is, the second density sensor 500, is replicated twice (S1006). The data set of the detected density by the first density sensor 200 on the transfer belt is left as it is (S1007). Nothing needs to be done in S1007. If the total number of data sets including replication exceeds the specified number, the model is corrected (S1009). By doing so, it is possible to correct the optimal density prediction model of each image forming apparatus even more quickly and with high accuracy.

[0144] As described above, by weighting the signal values from a plurality of types of density detection sensors and using them as correction data for the density prediction model, it becomes possible to correct the density prediction model faster and with higher accuracy.

[0145] [Other Embodiments] The present invention can also be realized by supplying a program that realizes one or more functions of the above-described embodiments to a system or apparatus via a network or a storage medium, and having one or more processors in a computer of the system or apparatus read and execute the program. Further, it can also be realized by a circuit, for example, an ASIC, that realizes one or more functions.

[0146] The invention is not limited to the above-described embodiments, and various changes and modifications can be made without departing from the spirit and scope of the invention. Therefore, the claims are attached to disclose the scope of the invention.

Description of Reference Numerals

[0147] 1: Photoconductor drum, 2: Charging device, 3: Exposure device, 4: Developing device, 6: Transfer device, 200: Intermediate transfer image density sensor, 300: Printer controller

Claims

1. Image forming means for forming an image on a sheet via an intermediate transfer member based on image forming conditions; First measuring means for measuring a first measurement image formed on the intermediate transfer member by the image forming means; Second measuring means for measuring a second measurement image formed on the sheet by the image forming means; Obtaining means for obtaining variation correlation information correlated with variation in density of an image formed by the image forming means; Generating means for determining the density of an image formed by the image forming means based on determination conditions from the variation correlation information obtained by the obtaining means, and generating the image forming conditions based on the determined density; Updating means for updating the determination conditions based on the measurement result of the first measurement image by the first measuring means, the measurement result of the second measurement image by the second measuring means, and the variation correlation information obtained by the obtaining means; The updating means updates the determination conditions by weighting the measurement result of the second measurement image by the second measuring means more heavily than the measurement result of the first measurement image by the first measuring means An image forming apparatus characterized by the above.

2. The image forming apparatus according to claim 1, The updating means performs the weighting by replicating a predetermined number of the measurement result of the second measurement image by the second measuring means and the variation correlation information related to the measurement result An image forming apparatus characterized by the above.

3. The image forming apparatus according to claim 1 or 2, The generating means determines the density using a multiple regression model with the variation correlation information as an input value as the determination condition, The updating means updates the coefficients of the multiple regression model based on the measurement result of the first measurement image by the first measuring means, the measurement result of the second measurement image by the second measuring means, and the variation correlation information related to the measurement result An image forming apparatus characterized by the above.

4. The image forming apparatus according to any one of claims 1 to 3, The image forming conditions are a tone correction table used for converting image data, The image forming means forms the image based on the image data converted based on the tone correction table An image forming apparatus characterized by the above.

5. The image forming apparatus according to any one of claims 1 to 4, The image forming apparatus is an electrophotographic system, The first measuring means measures density information of an image formed on either an intermediate transfer belt or a photoreceptor as the intermediate transfer member, and the second measuring means measures density information of an image formed on the sheet in either a conveyed state or a stationary state. An image forming apparatus characterized by the above. **Claim 6** A control method for an image forming apparatus, wherein the image forming apparatus includes an image forming means for forming an image on a sheet via an intermediate transfer member based on image forming conditions, a first measuring means for measuring a first measurement image formed on the intermediate transfer member by the image forming means, a second measuring means for measuring a second measurement image formed on the sheet by the image forming means, an acquisition means, a generation means, and an update means, and the control method of the image forming apparatus includes an acquisition step in which the acquisition means acquires variation correlation information correlated with variation in density of an image formed by the image forming means, a generation step in which the generation means determines the density of an image formed by the image forming means based on determination conditions from the variation correlation information acquired by the acquisition means, and generates the image forming conditions based on the determined density, and an update step in which the update means updates the determination conditions based on a measurement result of the first measurement image by the first measuring means, a measurement result of the second measurement image by the second measuring means, and the variation correlation information acquired by the acquisition means. In the update step, the determination conditions are updated by weighting the measurement result of the second measurement image by the second measuring means more heavily than the measurement result of the first measurement image by the first measuring means. A control method for an image forming apparatus characterized by the above. **Claim 7** A control method for an image forming apparatus according to claim 6, wherein in the update step, the weighting is performed by replicating a predetermined number of the measurement result of the second measurement image by the second measuring means and the variation correlation information related to the measurement result. A control method for an image forming apparatus characterized by the above. **Claim 8** A control method for an image forming apparatus according to claim 6 or 7, wherein in the generation step, the density is determined using a multiple regression model with the variation correlation information as an input value as the determination condition. In the update process, the coefficients of the multiple regression model are updated based on the measurement result of the first measurement image by the first measurement means, the measurement result of the second measurement image by the second measurement means, and the variation correlation information related to the measurement result. A control method for an image forming apparatus, characterized by the above.

9. A control method for an image forming apparatus according to any one of Claims 6 to 8, wherein the image forming condition is a gradation correction table used for converting image data, and the image is formed by the image forming means based on the image data converted based on the gradation correction table. A control method for an image forming apparatus, characterized by the above.

10. A control method for an image forming apparatus according to any one of Claims 6 to 9, wherein the image forming apparatus is an electrophotographic system, the density information of the image formed on either the intermediate transfer belt or the photoreceptor as the intermediate transfer body is measured by the first measurement means, and the density information of the image formed on the sheet in either a conveyed state or a stationary state is measured by the second measurement means. A control method for an image forming apparatus, characterized by the above.

Images