Failure prediction system

Abstract

To provide a failure prediction system capable of performing abnormality prediction for each abnormality that occurs in an image formation apparatus that can suppress the occurrence of failures by determining signs of failure.SOLUTION: A failure prediction system comprises a plurality of image formation apparatuses and a server. The image formation apparatus includes a first storage unit that stores sensor information detected by sensors installed in the image formation apparatus and operation information indicating the operating status of the image formation apparatus. The server includes a first acquisition unit that acquires the sensor information and operation information, and a first calculation unit that calculates abnormality sign information indicating the degree of signs of abnormality for each abnormality that occurs in the image formation apparatus on the basis of the sensor information and operation information acquired by the first acquisition unit.SELECTED DRAWING: Figure 7

Description

Technical Field

[0001] The present invention relates to a failure prediction system.

Background Art

[0002] There is known a system that predicts a failure of an image forming apparatus using a learning model constructed by machine learning such as supervised learning.

[0003] As a technique for predicting a failure of such an image forming apparatus, state data collection means for receiving a plurality of types of state data from the image forming apparatus and storing them in a state database, and a plurality of types of target data for determining an abnormal sign based on the plurality of types of state data are generated. Target data generation means, first discrimination means for discriminating whether a plurality of types of target data are below or exceed each reference value set for each destination, and discrimination results for each type of state data destination of the first discrimination means, A management device is disclosed that includes second discrimination means for determining the presence or absence of an abnormal sign as a whole of several types of state data by attaching weights set for each state data destination and performing a majority vote (for example, Patent Document 1).

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the technique described in Patent Document 1 has a problem in that it can only determine an abnormal sign as a whole of state data and cannot perform an abnormality prediction for each abnormality that occurs in the image forming apparatus.

[0005] The present invention has been made in view of the above, and an object thereof is to provide a failure prediction system capable of performing an abnormality prediction for each abnormality that occurs in an image forming apparatus.

Means for Solving the Problems

[0006] In order to solve the above-described problems and achieve the object, the present invention is a failure prediction system including a plurality of image forming apparatuses and a server, wherein the image forming apparatus includes a first storage unit that stores sensor information detected by a sensor mounted on the image forming apparatus and operation information indicating an operation state of the image forming apparatus, and the server includes a first acquisition unit that acquires the sensor information and the operation information, and a first calculation unit that calculates abnormality prediction information indicating a degree of a sign of the abnormality for each abnormality occurring in the image forming apparatus based on the sensor information and the operation information acquired by the first acquisition unit.

Effect of the Invention

[0007] According to the present invention, it is possible to perform abnormality prediction for each abnormality occurring in the image forming apparatus.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Embodiments for Carrying Out the Invention

[0009] Hereinafter, embodiments of a failure prediction system according to the present invention will be described in detail with reference to the drawings. Note that the present invention is not limited by the following embodiments, and the constituent elements in the following embodiments include those that can be easily conceived by those skilled in the art, substantially identical ones, and those within the so-called equivalent range. Furthermore, various omissions, substitutions, changes, and combinations of the constituent elements can be made without departing from the gist of the following embodiments.

[0010] (Overall Configuration of Failure Prediction System) FIG. 1 is a diagram showing an example of the overall configuration of a failure prediction system according to an embodiment. With reference to FIG. 1, the overall configuration of the failure prediction system 1 according to the present embodiment will be described.

[0011] The failure prediction system 1 shown in FIG. 1 is a system capable of performing anomaly prediction for each anomaly that occurs in MFPs (Multifunction Peripherals) 2a to 2c. As shown in FIG. 1, the failure prediction system 1 includes MFPs 2a to 2c, a server 3, and a PC (Personal Computer) 4 for the person in charge. These can communicate with each other via a network N. Note that the network N is a network such as a LAN (Local Area Network) or the Internet.

[0012] MFP2a to 2c are image forming apparatuses that perform image formation on a recording medium by, for example, an electrophotographic method. Here, an MFP is a multifunction peripheral having at least two functions among a copying function, a printer function, a scanner function, and a fax function. Note that for MFP2a to 2c, when indicating an arbitrary MFP or referring to them generically, they shall simply be referred to as "MFP2". Also, in the example of the failure prediction system 1 shown in FIG. 1, three MFPs 2a to 2c are shown, but the number of units is not limited to three. Further, MFP2a to 2c are not limited to electrophotographic image forming apparatuses, and at least one of them may be, for example, an inkjet image forming apparatus. Also, MFP2a to 2c are not limited to multifunction peripherals and may be ordinary printers.

[0013] The server 3 is an information processing apparatus that constructs a learning model by machine learning such as supervised learning using various sensor information and operation information received from MFP2a to 2c as teacher data, and performs anomaly prediction for each anomaly occurring in MFP2a to 2c using the learning model.

[0014] The operator's PC 4 is an information terminal such as a PC or a tablet terminal used by a customer engineer (service technician) in charge of MFP2a to 2c. The operator's PC 4 receives and displays the anomaly prediction results for each anomaly of MFP2 in charge of the customer engineer from the server 3. Note that MFP2a to 2c may each be in charge of a different customer engineer, and in that case, each customer engineer may own an operator's PC 4.

[0015] (Overall Structure of the Image Forming Apparatus) FIG. 2 is a diagram showing an example of the overall structure of the MFP according to the embodiment. FIG. 3 is a diagram showing an example of the configuration of the fixing device of the MFP according to the embodiment. The structure of MFP2 according to the present embodiment will be described with reference to FIGS. 2 and 3.

[0016] As shown in FIG. 2, the MFP2 includes an ADF (Auto Document Feeder) 13, a reading device 25, a paper discharge tray 14, an image forming unit 12, and a paper discharge tray 20.

[0017] The ADF 13 is a device that automatically sends the document D placed on the document table 21 to the contact glass 24. The ADF 13 includes a document table 21, a pickup roller 22, and a conveyance belt 23.

[0018] When an operation such as copy execution is performed with the document D placed on the document table 21 of the ADF 13, the uppermost document D placed on the document table 21 is sent out in the direction of arrow B1 by the rotation of the pickup roller 22. The document D sent out in the direction of arrow B1 is supplied onto the contact glass 24 fixed to the reading device 25 by the rotation of the conveyance belt 23 and stops there.

[0019] The reading device 25 is a device that is arranged between the image forming unit 12 and the contact glass 24 and reads the image of the document D supplied onto the contact glass 24. The reading device 25 includes a contact glass 24, a light source 26, an optical system 27, and a photoelectric conversion element 28.

[0020] The contact glass 24 is a glass onto which the document D is automatically supplied by the ADF 13. The light source 26 is a light source that irradiates light onto the document D supplied onto the contact glass 24. The optical system 27 is an optical system that forms an image of the light reflected from the document D irradiated by the light source 26. The photoelectric conversion element 28 is a solid-state imaging device such as a CCD (Charge-Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor) that detects the light imaged by the optical system 27 as a document image.

[0021] The original document D from which an image has been read by the reading device 25 is conveyed in the direction of arrow B2 by the rotation of the conveyance belt 23 and discharged onto the paper discharge tray 14. In this way, the original documents D are conveyed one by one onto the contact glass 24, and the reading operation by the reading device 25 is performed.

[0022] The image forming unit 12 forms an image on a recording medium P such as paper based on the image read by the reading device 25. The image forming unit 12 includes a paper feeding unit 15, an image forming unit 30, a fixing device 40 (fixing unit), and a paper discharge roller pair 50.

[0023] The paper feeding unit 15 is a part that feeds out a recording medium P such as paper in the direction of arrow B3 and feeds it to the image forming unit 30. The paper feeding unit 15 includes paper feeding cassettes 16 to 19 which are a plurality of paper feeding cassettes. The paper feeding cassettes 16 to 19 accommodate recording media having different sizes, paper thicknesses, etc.

[0024] The image forming unit 30 is a device that forms an image by transferring the toner image formed on the photoreceptor 31 to the recording medium P. The image forming unit 30 includes a photoreceptor 31, a charging device 32, a writing device 33, a developing device 34, a transfer device 35, and a cleaning device 36.

[0025] The photoreceptor 31 is, for example, a drum-shaped member in which a photosensitive layer made of an organic photosensitive material having photosensitivity is coated on a base tube made of aluminum or the like, and is rotationally driven.

[0026] The charging device 32 is a charging roller to which an alternating voltage is applied, and charges the photoreceptor 31 abnormally by making sliding contact with it.

[0027] The writing device 33 is a device that forms an electrostatic latent image on the surface of the uniformly charged photoreceptor 31 by irradiating laser light that has been optically modulated based on the image read by the reading device 25 and exposing the surface of the photoreceptor 31.

[0028] The developing device 34 is a device that supplies toner to the photoreceptor 31 on which an electrostatic latent image has been formed, develops the electrostatic latent image, and forms a toner image.

[0029] When the toner image formed on the surface of the photoreceptor 31 comes to a position facing the photoreceptor 31 due to the rotation of the photoreceptor 31, the transfer device 35 transfers the toner image to the recording medium P conveyed between the photoreceptor 31 and the transfer device 35 by the transfer bias between the photoreceptor 31 and the transfer device 35.

[0030] The cleaning device 36 is a device that removes and cleans the toner remaining on the surface of the photoreceptor 31 after the toner image has been transferred by the transfer device 35.

[0031] The fixing device 40 is a device that fixes the toner image to the recording medium P by the action of heat and pressure on the recording medium P to which the toner image has been transferred by the image forming unit 30 conveyed in the direction of arrow B4. As shown in FIG. 3, the fixing device 40 includes a fixing heater 41, a heating roller 42, a pressure roller 43, and a contact thermistor 45.

[0032] The fixing heater 41 is a heater device installed inside the heating roller 42 and heats the heating roller 42 by energization based on a fixing lighting duty described later. As shown in FIG. 3, when the heating roller 42 and the pressure roller 43 are rotationally driven in the direction of the arrow, the recording medium P is conveyed in the direction of the arrow (upward in the plane of the paper), and the toner image transferred to the recording medium P is fixed by the action of heat and pressure by the heating roller 42 and the pressure roller 43.

[0033] The contact thermistor 45 is a sensor that detects the temperature of the heating roller 42 by directly contacting the heating roller 42 using an electric resistance that changes greatly with temperature changes.

[0034] The recording medium P that has passed through the fixing device 40 is conveyed by the paper discharge roller pair 50 and discharged to the paper discharge tray 20 and stacked as shown by the arrow B5.

[0035] (Outline of the overall operation of the failure prediction system) FIG. 4 is a diagram for explaining an overview of the overall operation of the failure prediction system according to the embodiment. While referring to FIG. 4, an overview of the overall operation of the failure prediction system 1 according to the present embodiment will be described.

[0036] First, the MFPs 2a to 2c transmit, as learning data, sensor information (for example, temperature data of the fixing device 40, rotational torque of the fixing device 40, ambient temperature data, ambient humidity data, power supply voltage data, etc.) and operation information (for example, operation time, printing time, number of prints, number of printed sheets, printing stop time, operation time of the fixing device 40, etc.) detected by various sensors mounted thereon to the server 3. Based on the sensor information and operation information, which are the learning data received from the MFPs 2a to 2c, the server 3 constructs a learning model for outputting a failure prediction score (an example of abnormal prediction information) that indicates the degree of the sign of an abnormality for each abnormality as a continuous score by machine learning such as supervised learning. Therefore, when constructing the learning model by supervised learning, some label (such as a flag indicating normal) may be assigned to the sensor information and operation information to obtain teacher data. Note that the failure prediction score is not limited to being represented by a score, and may be represented by other information (an example of abnormal prediction information) as long as it indicates the degree of the sign of an abnormality.

[0037] And during operation, MFPs 2a to 2c each transmit the real-time sensor information and operation information detected by various sensors to server 3 (Fig. 4(1)). Then, server 3 uses the sensor information and operation information received from MFPs 2a to 2c as inputs to the constructed learning model, and calculates a failure prediction score for each possible abnormality occurring in MFPs 2a to 2c based on the information output from the learning model (Fig. 4(2)). Here, server 3 may calculate the failure prediction score using the information regarding the failure prediction score output from the learning model by providing the sensor information and operation information as inputs to the learning model, or may obtain the one in which continuous failure prediction scores are directly output as a regression process from the learning model. For example, server 3 assigns an identification number uniquely identified for each abnormality of MFP 2, and calculates a failure prediction score for each abnormality identified by the identification number. Fig. 4 shows an example in which identification numbers such as "SC001", "SC002", "SC003",... are assigned as identification numbers for identifying each abnormality. Then, server 3 transmits the calculated failure prediction score for each abnormality to the corresponding MFP 2 (Fig. 4(3)). MFP 2 stores the failure prediction score received from server 3 in a mounted storage device (e.g., HD909 shown in Fig. 6 described later), and displays the failure prediction score on a display device (e.g., panel display unit 940a shown in Fig. 6 described later) as needed. Thus, it is possible to present a failure prediction score indicating the degree of prediction of an abnormality such as a failure of each device / component such as fixing device 40 mounted on MFP 2. That is, although it does not reach the point of being determined as a failure with respect to each device / component such as fixing device 40, there may be a case where it is transitioning near the threshold value. Even in such a case, the user of MFP 2 or a customer engineer can confirm the failure prediction score as a continuous numerical value as the degree of prediction of an abnormality such as a failure. And it becomes possible to take corresponding actions such as changing soft control according to the presented failure prediction score before an actual abnormality such as a failure occurs in each MFP 2. Note that the failure prediction score indicates, for example, that 100 points represent the normal state of a new product, and 0 points represent a failure.

[0038] When there is a decreasing predicted failure score among the calculated predicted failure scores, the server 3 transmits a notice indicating that the predicted failure score has decreased to the dedicated PC 4 of the customer engineer in charge of the corresponding MFP2 (item (4) in Fig. 4). Here, the situation where the predicted failure score has decreased may be defined as, for example, the case where the predicted failure score has become equal to or lower than a predetermined threshold. As a result, while in the past it was only possible to determine whether or not there was a failure, the customer engineer can recognize signs of an abnormality in the corresponding MFP2 and can take early action. That is, once an abnormality such as a failure occurs, the customer engineer's response is always necessary, resulting in downtime on the user side of the MFP2. However, by grasping signs of abnormalities such as failures in advance, proactive responses become possible, and downtime on the user side can be reduced. Note that the threshold value may be different for each predicted failure score.

[0039] Further, the server 3 calculates so that parameters such as a threshold value for determining whether or not there is an abnormality corresponding to the calculated predicted failure score are optimized, and transmits the calculated parameters to the MFP2 (item (5) in Fig. 4). As a result, each MFP2 can perform abnormality determination using the optimized parameters, and downtime on the user side of the MFP2 can be reduced.

[0040] Note that even after constructing the learning model, the server 3 may accumulate the sensor information and operation information received from each MFP2 and update the learning model by re-learning from the sensor information and operation information.

[0041] (Hardware configuration of server, etc.) Fig. 5 is a diagram showing an example of the hardware configuration of the server according to the embodiment. With reference to Fig. 5, the hardware configuration of the server 3 according to the present embodiment will be described. Note that the hardware configuration of the dedicated PC 4 for the person in charge also conforms to the configuration shown in Fig. 5.

[0042] As shown in FIG. 5, the server 3 includes a CPU (Central Processing Unit) 601, a ROM (Read Only Memory) 602, a RAM (Random Access Memory) 603, an auxiliary storage device 605, a media drive 607, a display 608, a network I / F 609, a keyboard 611, a mouse 612, and a DVD (Digital Versatile Disc) drive 614.

[0043] The CPU 601 is an arithmetic unit that controls the operation of the entire server 3. The ROM 602 is a non-volatile storage device that stores programs for the server 3. The RAM 603 is a volatile storage device used as a work area for the CPU 601.

[0044] The auxiliary storage device 605 is a storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive) that stores various data and programs. The media drive 607 is a device that controls the reading and writing of data to a recording medium 606 such as a flash memory according to the control of the CPU 601.

[0045] The display 608 is a display device composed of, for example, a liquid crystal or an organic EL (Electro Luminescence) that displays various information such as a cursor, a menu, a window, characters, or an image.

[0046] The network I / F 609 is an interface for communicating data with external devices such as the MFP 2 and the operator's PC 4 using the network N. The network I / F 609 is compatible with, for example, Ethernet (registered trademark) or Wi-Fi (registered trademark) and enables wired or wireless communication compliant with TCP (Transmission Control Protocol) / IP (Internet Protocol).

[0047] The keyboard 611 is an input device for performing operations such as selecting characters, numbers, various instructions, and moving the cursor. The mouse 612 is an input device for selecting and executing various instructions, selecting a processing target, and moving the cursor.

[0048] The DVD drive 614 is a device that controls reading and writing of data to a DVD 613 such as a DVD-ROM or a DVD-R (Digital Versatile Disk Recordable), which is an example of a removable storage medium.

[0049] The above-mentioned CPU 601, ROM 602, RAM 603, auxiliary storage device 605, media drive 607, display 608, network I / F 609, keyboard 611, mouse 612, and DVD drive 614 are communicably connected to each other by a bus 610 such as an address bus and a data bus.

[0050] Note that the hardware configuration of the server 3 shown in FIG. 5 is an example, and it is not necessary to include all the components shown in FIG. 5, or other components may be included.

[0051] Also, the server 3 is not limited to being configured by a single information processing device, and may be an information processing system configured by a plurality of information processing devices.

[0052] (Hardware Configuration of MFP) FIG. 6 is a diagram showing an example of the hardware configuration of an MFP according to an embodiment. With reference to FIG. 6, the hardware configuration of the MFP 2 according to this embodiment will be described.

[0053] As shown in FIG. 6, the MFP 2 includes a controller 910, a short-range communication circuit 920, an antenna 920a, an engine control unit 930, a cartridge 935, an operation panel 940, and a network I / F 950.

[0054] The controller 910 includes a CPU 901 which is the main part of the computer, a system memory (MEM-P) 902, a north bridge (NB) 903, a south bridge (SB) 904, an ASIC (Application Specific Integrated Circuit) 906, a local memory (MEM-C) 907 which is a storage unit, an HDD controller 908, and an HD 909 which is a storage unit. It is configured such that the NB 903 and the ASIC 906 are connected by an AGP (Accelerated Graphics Port) bus 921.

[0055] The CPU 901 is a control unit that performs overall control of the MFP 9. The NB 903 is a bridge for connecting the CPU 901 to the MEM-P 902, the SB 904, and the AGP bus 921, and has a memory controller that controls read / write operations on the MEM-P 902, a PCI (Peripheral Component Interconnect) master, and an AGP target.

[0056] The MEM-P 902 consists of a ROM 902a which is a memory for storing programs and data for realizing the functions of the controller 910, and a RAM 902b which is used as a memory for program and data expansion, and drawing during memory printing. Note that the program stored in the RAM 902b may be provided by recording it in an installable or executable format file on a computer-readable recording medium such as a CD-ROM, CD-R, or DVD.

[0057] SB904 is a bridge for connecting NB903 with a PCI device and a peripheral device. ASIC906 is an IC (Integrated Circuit) for image processing applications having hardware elements for image processing, and serves as a bridge for connecting an AGP bus 921, a PCI bus 922, an HDD controller 908, and a MEM-C907 respectively. This ASIC906 consists of a PCI target and an AGP master, an arbiter (ARB) forming the core of the ASIC906, a memory controller for controlling MEM-C907, a plurality of DMACs (Direct Memory Access Controllers) for performing rotation etc. of image data by means of hardware logic etc., and a PCI unit for performing data transfer via the PCI bus 922 between a scanner unit 931 and a printer unit 932. Note that an interface for USB (Universal Serial Bus) or an interface for IEEE1394 (Institute of Electrical and Electronics Engineers 1394) may be connected to the ASIC906.

[0058] MEM-C907 is a local memory used as a copy image buffer and a code buffer. HD909 is a storage for accumulating image data, accumulating font data used at the time of printing, and accumulating forms. The HD controller 908 controls reading or writing of data to / from the HD909 according to the control of the CPU901.

[0059] The AGP bus 921 is a bus interface for a graphics accelerator card proposed for speeding up graphic processing, and can speed up the graphics accelerator card by directly accessing the MEM-P902 with high throughput.

[0060] The short-range communication circuit 920 is a communication circuit that performs data communication using an antenna 920a in accordance with NFC (Near Field Communication) or Bluetooth (registered trademark) etc.

[0061] The engine control unit 930 includes a scanner unit 931 and a printer unit 932. The printer unit 932 is a device that forms an image on a recording medium using ink or toner supplied by a cartridge 935.

[0062] The cartridge 935 is an ink cartridge or toner cartridge that supplies ink or toner to the printer unit 932. The cartridge 935 includes a memory 935a. The memory 935a is a storage device that stores the remaining amount of ink or toner and the like.

[0063] The operation panel 940 includes a panel display unit 940a such as a touch panel that displays current setting values, selection screens, etc. and receives inputs from an operator, and a key operation unit 940b that includes numeric keys that receive setting values for conditions related to image formation such as density setting conditions and a start key that receives a copy start instruction.

[0064] The controller 910 controls the entire MFP2, and controls, for example, drawing, communication, inputs from the operation panel 940, etc. The scanner unit 931 or the printer unit 932 includes an image processing part such as error diffusion and gamma conversion.

[0065] Note that the MFP2 can sequentially switch and select a document box function, a copy function, a printer function, and a facsimile function by an application switching key on the operation panel 940. When the document box function is selected, it becomes the document box mode, when the copy function is selected, it becomes the copy mode, when the printer function is selected, it becomes the printer mode, and when the facsimile mode is selected, it becomes the facsimile mode.

[0066] The network I / F 950 is an interface for performing data communication using the network N.

[0067] The short-range communication circuit 920 and the network I / F 950 are electrically connected to the ASIC 906 via the PCI bus 922.

[0068] (Configuration and Operation of Fault Prediction System Functional Blocks) FIG. 7 is a diagram showing an example of the configuration of the functional blocks of the fault prediction system according to the embodiment. FIG. 8 is a diagram showing an example of the detection conditions for each abnormality. With reference to FIGS. 7 and 8, the configuration and operation of the functional blocks of the fault prediction system 1 according to the present embodiment will be described.

[0069] As shown in FIG. 7, the MFP 2 includes a communication unit 201, an information transmission unit 202 (transmission unit), an acquisition unit 203 (second acquisition unit), a determination unit 204, a display control unit 205, and a storage unit 206 (first storage unit).

[0070] The communication unit 201 is a functional unit that performs data communication with external devices such as the server 3 via the network N and the network I / F 950.

[0071] The information transmission unit 202 collects sensor information (e.g., temperature data of the fixing device 40, rotational torque of the fixing device 40, ambient temperature data, ambient humidity data, power supply voltage data, etc.) and operation information (e.g., operation time, printing time, number of prints, number of printed sheets, printing stop time, operation time of the fixing device 40, etc.) detected by various sensors mounted on the MFP 2, and transmits the collected information to the server 3 via the communication unit 201. Note that the information transmission unit 202 may transmit, as teacher data with the label of normal or abnormal, for example, sensor information and operation information in a normal state, or sensor information and operation information when an abnormality occurs, to the server 3. Also, the sensor information and operation information detected by various sensors may be stored in the memory 935a of the cartridge 935, and the sensor information and operation information may be transmitted to the server 3 via the cartridge 935.

[0072] The acquisition unit 203 is a functional unit that acquires, from the server 3 via the communication unit 201, the failure omen scores for each abnormality calculated by the server 3 and parameters such as threshold values used for each abnormality determination. Note that at least one of the failure omen scores for each abnormality calculated by the server 3 and parameters such as threshold values used for each abnormality determination may be transmitted to the MFP 2 by supplying and setting the cartridge 935 equipped with the memory 935a to the MFP 2.

[0073] The determination unit 204 is a functional unit that determines the presence or absence of occurrence of each abnormality based on the threshold value included in the parameters acquired by the acquisition unit 203. Fig. 8 shows detection conditions (determination conditions) of abnormalities that may occur in the MFP 2. For example, for the abnormality identified by the identification number "SC001", the abnormality name is "Do not reload the fixing center thermopile", the monitoring start trigger for the abnormality is "Heater A ON", the monitoring end trigger is "TA [°C] reached", the target (detection target) used for the abnormality determination is "Sensor B", the detection temperature serving as the threshold value for the abnormality determination is "TA [°C]", the detection time serving as the threshold value for the abnormality determination is "ta [seconds]", and the abnormality detection condition (abnormality determination condition) is "when Sensor B continuously detects that it is below TA [°C] for ta [seconds] after the monitoring start trigger". In this case, the threshold values used for the determination of the abnormality are the temperature "TA [°C]" and the time "ta [seconds]".

[0074] The display control unit 205 is a functional unit that controls the display operation of the panel display unit 940a. The display control unit 205 causes the panel display unit 940a to display, for example, the failure omen scores of each abnormality acquired by the acquisition unit 203 and the details of the abnormalities determined by the determination unit 204. That is, although it does not reach the point of being determined as a failure or a threshold value for each device and member such as the fixing device 40, there may be cases where it is transitioning near the threshold value. Even in such cases, the user of the MFP 2 or the customer engineer can confirm the failure omen score as a continuous numerical value as the degree of omen of an abnormality such as a failure. And it becomes possible to take corresponding actions such as changing the soft control according to the presented failure omen score before an actual abnormality such as a failure occurs in each MFP 2.

[0075] The storage unit 206 is a functional unit that stores sensor information and operation information detected by various sensors mounted on the MFP2, as well as the failure omen scores and parameters obtained by the acquisition unit 203. The storage unit 206 is realized by at least one of the HD909 and the memory 935a shown in FIG. 6.

[0076] The above-mentioned communication unit 201, information transmission unit 202, acquisition unit 203, determination unit 204, and display control unit 205 are realized by executing a program by the CPU901 shown in FIG. 6. Note that at least a part of the communication unit 201, information transmission unit 202, acquisition unit 203, determination unit 204, and display control unit 205 may be realized by a hardware circuit such as an ASIC.

[0077] Note that each functional unit of the MFP2 shown in FIG. 7 conceptually shows the functions and is not limited to such a configuration. For example, a plurality of functional units illustrated as independent functional units in the MFP2 shown in FIG. 7 may be configured as one functional unit. On the other hand, the functions of one functional unit in the MFP2 shown in FIG. 7 may be divided into a plurality of functions and configured as a plurality of functional units. In addition, each functional unit of the MFP2 does not have to be configured as a clear software module as the block shown in FIG. 7, and it is sufficient that the functions of each functional unit are realized as a whole when a program is executed in the MFP2.

[0078] As shown in FIG. 7, the server 3 includes a communication unit 301, an acquisition unit 302 (first acquisition unit), a learning unit 303, a first calculation unit 304, a second calculation unit 305, an output unit 306, a notification unit 307, and a storage unit 308 (second storage unit).

[0079] The communication unit 301 is a functional unit that performs data communication with external devices such as the MFP2 and the operator's PC4 via the network N and the network I / F609.

[0080] The acquisition unit 302 is a functional unit that acquires sensor information (e.g., temperature data of the fixing device 40, rotational torque of the fixing device 40, ambient temperature data, ambient humidity data, power supply voltage data, etc.) and operation information (e.g., operation time, printing time, number of prints, number of printed sheets, printing stop time, operation time of the fixing device 40, etc.) detected by various sensors mounted on the MFP 2 from the MFP 2 via the communication unit 201. The acquisition unit 302 stores the acquired sensor information and operation information in the storage unit 308. In the learning stage of the learning model by the learning unit 303, the acquisition unit 302 acquires the sensor information and operation information as learning data. Also, when the learning model is constructed by supervised learning by the learning unit 303, teacher data with some label (such as a flag indicating normal or abnormal) attached to the sensor information and operation information is acquired as learning data by the acquisition unit 302. Note that the sensor information and operation information may be stored in the memory 935a of the cartridge 935, and the sensor information and operation information may be acquired by the acquisition unit 302 via the cartridge 935.

[0081] The learning unit 303 is a functional unit that constructs a learning model for outputting a failure prediction score that indicates, for each abnormality, a sign of an abnormality occurring as a continuous score based on the sensor information and operation information, which are the learning data acquired from the acquisition unit 302, by machine learning such as supervised learning. Note that the learning unit 303 may construct the learning model using, for example, any of the learning data acquired in the short term, medium term, or long term by the acquisition unit 302 as the learning data used for the learning process by machine learning. The learning unit 303 stores the constructed learning model in the storage unit 308.

[0082] The first calculation unit 304 is a functional unit that gives the sensor information and operation information acquired by the acquisition unit 302 as inputs to the learning model constructed by the learning unit 303, and calculates a failure prediction score for each possible abnormality occurring in the MFP2 based on the information output from the learning model. Note that the first calculation unit 304 may calculate the failure prediction score using the information output from the learning model by giving the sensor information and operation information as inputs to the learning model, or may obtain a continuous failure prediction score directly output as a regression process from the learning model.

[0083] The second calculation unit 305 is a functional unit that calculates parameters such as a threshold value for determining whether or not an abnormality corresponding to the failure prediction score is an abnormality according to the failure prediction score calculated by the first calculation unit 304 so as to be optimal. As a result, parameters corresponding to aging deterioration or the usage environment can be calculated from the tendency of the abnormality prediction indicated by the failure prediction score. For example, if the usage environment is a cold region, fine adjustment can be made in the direction of relaxing the abnormality determination conditions. In the case of the abnormality shown in FIG. 8 identified by the above identification number "SC001", the detection temperature TA, which is the threshold value, is decreased and the detection time ta is increased to relax the abnormality determination conditions. Note that the timing at which the parameter is calculated by the second calculation unit 305 may be, for example, when the failure prediction score calculated by the first calculation unit 304 becomes equal to or less than a predetermined value.

[0084] The output unit 306 is a functional unit that outputs (transmits) the failure prediction score calculated by the first calculation unit 304 and parameters such as the threshold value calculated by the second calculation unit 305 to the MFP2 via the communication unit 301. As a result, each MFP2 can perform abnormality determination using the optimized parameters, and the downtime on the user side of the MFP2 can be reduced. Note that the output unit 306 may store at least any one of the failure prediction score calculated by the first calculation unit 304 and the parameters such as the threshold value calculated by the second calculation unit 305 in the memory 935a of the cartridge 935. As a result, at least any one of the failure prediction score for each abnormality and the parameters such as the threshold value used for each abnormality determination can be transmitted to the MFP2 when the cartridge 935 equipped with the memory 935a is supplied and set to the MFP2.

[0085] The notification unit 307 determines whether there is a decreased failure prediction score among the failure prediction scores calculated by the first calculation unit 304. If there is a decreased failure prediction score, the notification unit 307 notifies (transmits) to the dedicated PC 4 of the person in charge of the customer engineer in charge of the corresponding MFP2 via the communication unit 301 that the failure prediction score has decreased. As a result, while conventionally it was only possible to grasp whether there was a failure or not, the customer engineer can recognize the sign of an abnormality in the MFP2 in charge and can take early measures. That is, once an abnormality such as a failure occurs, the customer engineer's response is always necessary, so downtime occurs on the user side of the MFP2. However, by grasping the sign of an abnormality such as a failure in advance, proactive response becomes possible and the downtime on the user side can be reduced. Here, that the failure prediction score has decreased may mean, for example, that the failure prediction score has become equal to or less than a predetermined threshold value.

[0086] The storage unit 308 is a functional unit that stores the sensor information and operation information acquired by the acquisition unit 302, and the learning model and the like constructed by the learning unit 303. The storage unit 308 is realized by the auxiliary storage device 605 shown in FIG. 5.

[0087] The above communication unit 301, acquisition unit 302, learning unit 303, first calculation unit 304, second calculation unit 305, output unit 306, and notification unit 307 are realized by a program being executed by the CPU 601 shown in FIG. 5. Note that at least a part of the communication unit 301, acquisition unit 302, learning unit 303, first calculation unit 304, second calculation unit 305, output unit 306, and notification unit 307 may be realized by a hardware circuit such as an ASIC.

[0088] Note that each functional unit of the server 3 shown in FIG. 7 conceptually shows the functions and is not limited to such a configuration. For example, a plurality of functional units illustrated as independent functional units in the server 3 shown in FIG. 7 may be configured as one functional unit. On the other hand, the functions of one functional unit in the server 3 shown in FIG. 7 may be divided into a plurality of functions and configured as a plurality of functional units. Further, each functional unit of the server 3 does not necessarily need to be configured as a clear software module as the block shown in FIG. 7, and it is sufficient that the functions of each functional unit are realized as a whole when a program is executed in the server 3.

[0089] As described above, in the failure prediction system 1 according to the present embodiment, the MFP 2 includes a storage unit 206 that stores sensor information detected by a sensor mounted on the MFP 2 and operation information indicating the operation status of the MFP 2, and the server 3 includes an acquisition unit 302 that acquires the sensor information and the operation information, and a first calculation unit that calculates a failure prediction score indicating the degree of a sign of an abnormality for each abnormality occurring in the MFP 2 based on the sensor information and the operation information acquired by the acquisition unit 302. Accordingly, an abnormality prediction can be performed for each abnormality occurring in the MFP 2.

[0090] Note that each function of the above-described embodiments can be realized by one or more processing circuits. Here, the "processing circuit" includes a processor programmed to execute each function by software, such as a processor implemented by an electronic circuit, an ASIC, a DSP (Digital Signal Processor), an FPGA (Field-Programmable Gate Array), a SoC (System on a Chip), a GPU (Graphics Processing Unit), and devices such as conventional circuit modules designed to execute the above-described functions.

[0091] Also, in the above-described embodiments, when at least any one of the functional units of the MFP2 and the server 3 is realized by executing a program, the program is provided by being pre-embedded in a ROM or the like. Further, in the above-described embodiments, the programs executed in the MFP2 and the server 3 may be configured to be recorded on a computer-readable recording medium such as a CD-ROM (Compact Disc Read Only Memory), a flexible disk (FD), a CD-R (Compact Disk-Recordable), or a DVD (Digital Versatile Disc) in an installable format or an executable format file and provided. Also, in the above-described embodiments, the programs executed in the MFP2 and the server 3 may be configured to be stored on a computer connected to a network such as the Internet and downloaded via the network for providing. Also, in the above-described embodiments, the programs executed in the MFP2 and the server 3 may be configured to be provided or distributed via a network such as the Internet. Also, in the above-described embodiments, the programs executed in the MFP2 and the server 3 have a module configuration including at least any one of the above-described functional units, and as actual hardware, the CPU reads the program from the above-described storage device and executes it, so that the above-described functional units are loaded and generated on the main storage device.

[0092] Aspects of the present invention are as follows. <1>A failure prediction system including a plurality of image forming apparatuses and a server, wherein the image forming apparatus includes a first storage unit that stores sensor information detected by a sensor mounted on the image forming apparatus and operation information indicating an operation state of the image forming apparatus; the server has a first acquisition unit that acquires the sensor information and the operation information; and a first calculation unit that calculates abnormality prediction information indicating a degree of a sign of an abnormality for each abnormality occurring in the image forming apparatus based on the sensor information and the operation information acquired by the first acquisition unit. The failure prediction system is provided with these components. <2>The image forming apparatus further includes a transmission unit that transmits the sensor information and the operation information to the server. The server further includes an output unit that outputs the abnormality prediction information calculated by the first calculation unit to the image forming apparatus corresponding to the abnormality prediction information. The failure prediction system according to <1> above is provided with these components. <3>The image forming apparatus further includes an ink or toner cartridge having a memory. The memory stores the sensor information and the operation information of the image forming apparatus. The first acquisition unit acquires the sensor information and the operation information stored in the memory. The failure prediction system according to <1> or <2> above is provided with these components. <4>The server further includes an output unit that stores the abnormality prediction information calculated by the first calculation unit in a memory provided in an ink or toner cartridge. The image forming apparatus further includes a second acquisition unit that acquires the abnormality prediction information stored in the memory when the cartridge is mounted. The failure prediction system according to any one of <1> to <3> above is provided with these components. <5>The abnormal sign information is the failure prediction system according to any one of <1> to <4> above, which represents the degree of the sign of the abnormality for each abnormality occurring in the image forming apparatus as a continuous score. <6>The server A second storage unit that stores the sensor information and the operation information acquired by the first acquisition unit; A learning unit that constructs a learning model for outputting information related to the abnormal sign information based on the sensor information and the operation information stored in the second storage unit; further includes The first calculation unit is the failure prediction system according to any one of <1> to <5> above, which gives the sensor information and the operation information acquired by the first acquisition unit as an input to the learning model, and calculates the abnormal sign information based on the information output from the learning model. <7>The server further includes a second calculation unit that calculates a threshold value for determining whether there is an abnormality corresponding to the abnormal sign information according to the abnormal sign information calculated by the first calculation unit. The image forming apparatus is the failure prediction system according to any one of <1> to <6> above, further including a determination unit that determines whether there is an abnormality corresponding to the threshold value using the threshold value calculated by the second calculation unit. <8>The server further includes a notification unit that determines whether the abnormal sign information calculated by the first calculation unit is equal to or less than a predetermined value, and when it is equal to or less than the predetermined value, notifies the image forming apparatus that the abnormal sign information has decreased. The failure prediction system according to any one of <1> to <7> above. <9>The sensor information is the failure prediction system according to any one of <1> to <8> above, including at least any one of temperature data of a fixing device mounted on the image forming apparatus, rotational torque of the fixing device, environmental temperature data, environmental humidity data, and power supply voltage data.

Description of Signs

[0093] 1 Failure prediction system 2, 2a to 2c MFP 3 Server 4 Operator's PC 12 Image Forming Unit 13 ADF 14 Paper Output Tray 15 Paper Feeding Unit 16 - 19 Paper Feeding Cassettes 20 Paper Output Tray 21 Document Table 22 Pickup Roller 23 Conveyor Belt 24 Contact Glass 25 Reading Device 26 Light Source 27 Optical System 28 Photoelectric Conversion Element 30 Image Forming Section 31 Photoconductor 32 Charging Device 33 Writing Device 34 Developing Device 35 Transfer Device 36 Cleaning Device 40 Fixing Device 41 Fixing Heater 42 Heating Roller 43 Pressing Roller 45 Contact Thermistor 50 Paper Output Roller Pair 201 Communication Section 202 Information Sending Section 203 Acquisition Section 204 Judgment Section 205 Display Control Section 206 Memory Section 301 Communication Section 302 Acquisition Section 303 Learning Section 304 First Calculation Section 305 Second Calculation Section 306 Output Section 307 Notification Section 308 Memory Section 601 CPU 602 ROM 603 RAM 605 Auxiliary Storage Device 606 Recording Medium 607 Media Drive 608 Display 609 Network I / F 610 Bus 611 Keyboard 612 Mouse 613 DVD 614 DVD Drive 901 CPU 902 MEM-P 902a ROM 902b RAM 903 NB 904 SB 906 ASIC 907 MEM-C 908 HD Controller 909 HD 910 Controller 920 Short-Range Communication Circuit 920a Antenna 921 AGP Bus 922 PCI Bus 930 Engine Control Unit 931 Scanner Unit 932 Printer Unit 935 Cartridge 935a Memory 940 Operation Panel 940a Panel Display Section 940b Key Operation Section 950 Network I / F N Network

Prior Art Documents

Patent Documents

[0094]

Patent Document 1

Claims

1. A failure prediction system including a plurality of image forming apparatuses and a server, wherein the image forming apparatus includes a first storage unit that stores sensor information detected by a sensor mounted on the image forming apparatus and operation information indicating an operation state of the image forming apparatus, and the server, a first acquisition unit that acquires the sensor information and the operation information, a first calculation unit that calculates abnormality prediction information indicating the degree of a sign of an abnormality for each abnormality occurring in the image forming apparatus based on the sensor information and the operation information acquired by the first acquisition unit, and the failure prediction system is provided with.

2. The image forming apparatus further includes a transmission unit that transmits the sensor information and the operation information to the server, and the server further includes an output unit that outputs the abnormality prediction information calculated by the first calculation unit to the image forming apparatus corresponding to the abnormality prediction information. The failure prediction system according to claim 1.

3. The image forming apparatus further includes an ink or toner cartridge having a memory, the memory stores the sensor information and the operation information of the image forming apparatus, and the first acquisition unit acquires the sensor information and the operation information stored in the memory. The failure prediction system according to claim 1.

4. The server further includes an output unit that stores the abnormality prediction information calculated by the first calculation unit in a memory provided in an ink or toner cartridge, and the image forming apparatus further includes a second acquisition unit that acquires the abnormality prediction information stored in the memory when the cartridge is mounted. The failure prediction system according to claim 1.

5. The abnormality prediction information represents the degree of a sign of an abnormality for each abnormality occurring in the image forming apparatus as a continuous score. The failure prediction system according to any one of claims 1 to 4.

6. The server, a second storage unit that stores the sensor information and the operation information acquired by the first acquisition unit, a learning unit that constructs a learning model for outputting information related to the abnormality prediction information based on the sensor information and the operation information stored in the second storage unit, and is further provided with, The failure prediction system according to any one of claims 1 to 4, wherein the first calculation unit gives the sensor information and the operation information acquired by the first acquisition unit as an input to the learning model, and calculates the abnormal sign information based on the information output from the learning model.

7. The server further includes a second calculation unit that calculates a threshold value for determining whether there is an abnormality corresponding to the abnormal sign information in accordance with the abnormal sign information calculated by the first calculation unit. The image forming apparatus further includes a determination unit that determines whether there is an abnormality corresponding to the threshold value by using the threshold value calculated by the second calculation unit, according to any one of claims 1 to 4. The failure prediction system described.

8. The server determines whether the abnormal sign information calculated by the first calculation unit is equal to or less than a predetermined value, and when it is equal to or less than the predetermined value, notifies the image forming apparatus that the abnormal sign information has decreased. The failure prediction system according to any one of claims 1 to 4, further comprising a notification unit.

9. The sensor information includes at least any one of temperature data of a fixing device mounted on the image forming apparatus, rotational torque of the fixing device, environmental temperature data, environmental humidity data, and power supply voltage data, according to any one of claims 1 to 4. The failure prediction system described.

Images