Display system, display method, and display program

Abstract

The display system according to the present invention is arranged in a production equipment for producing products, and the production equipment has at least one driving unit for driving the production equipment and at least one monitoring unit for monitoring the production as components, and each component has a controllable characteristic quantity. The display system has a control unit, a display unit and a storage unit. The storage unit stores the relationship between two or more of the multiple components as a causal relationship model for abnormalities that may occur in the production equipment. The control unit is configured to: display a model diagram on the display unit according to the causal relationship model, and the model diagram has nodes corresponding to the each component and edges connecting the nodes. When an abnormality occurs in the production equipment, the display mode of at least one of the nodes corresponding to the component associated with the abnormality and the edges connected to the node is changed.

Description

Technical Field

[0001] The present invention relates to a display system, a display method and a display program. Background Art

[0002] Patent Document 1 proposes a method for monitoring equipment status: event signals are segmented into operating state patterns, a normal model is created for each pattern, and abnormality determination is performed based on the created normal model. This method checks the sufficiency of the learning data used to create the normal model and sets the threshold used for abnormality determination based on the sufficiency of the learning data, thereby preventing false positives where normal conditions are misidentified as abnormal.

[0003] Patent Document 2 also proposes a method for detecting abnormalities in products produced by production equipment. Specifically, Patent Document 2 proposes the following method: data collected from a production system is classified into normal product conditions and abnormal product conditions, and feature quantities that significantly differ between normal and abnormal conditions are determined. Based on the determined feature quantities, the method then diagnoses whether the product is normal.

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: Japanese Patent Application Laid-Open No. 2015-172945

[0007] Patent Document 2: Japanese Patent Application Laid-Open No. 2010-277199 Summary of the Invention

[0008] Technical problem to be solved by the invention

[0009] However, when an abnormality occurs in production equipment, it must be resolved immediately. However, users typically consult manuals, etc., for the cause of the abnormality and then proceed to resolve it. However, consulting the manual each time an abnormality occurs takes time, sometimes delaying resolution. The present invention was developed to address this issue and aims to provide a display system, display method, and display program that easily identify components associated with abnormalities that may occur in production equipment.

[0010] Technical solutions to solve problems

[0011] The display system according to the present invention is arranged in a production equipment for producing products, and the production equipment has at least one driving unit for driving the production equipment and at least one monitoring unit for monitoring the production as components, and each component has a controllable characteristic quantity. The display system has a control unit, a display unit and a storage unit. The storage unit stores the relationship between two or more of the multiple components as a causal relationship model for abnormalities that may occur in the production equipment. The control unit is configured to: display a model diagram on the display unit according to the causal relationship model, and the model diagram has nodes corresponding to the each component and edges connecting the nodes. When an abnormality occurs in the production equipment, the display mode of at least one of the nodes corresponding to the component associated with the abnormality and the edges connected to the node is changed.

[0012] This configuration allows the relationship between two or more components of a production facility to be stored as a causal relationship model, and a model diagram based on this causal relationship model, comprising nodes corresponding to each component and edges connecting these nodes, can be displayed on the display unit. Furthermore, when an anomaly occurs in the production facility, the display method of at least one of the node corresponding to the component associated with the anomaly and the edges connecting these nodes is changed. This allows the user to easily visually identify the component associated with the anomaly.

[0013] In the above-mentioned display system, the control unit may be configured to change the display mode when a sign of the abnormality is detected.

[0014] By doing so, the display method of the nodes corresponding to the components associated with the abnormality is changed not only when an abnormality occurs but also when a sign of an abnormality is detected. This allows for easy visual confirmation that the components corresponding to the nodes are associated with the sign of an abnormality. This allows for countermeasures to be taken before an abnormality occurs.

[0015] In the above-mentioned display system, the control unit can regard the abnormality as a sign of occurrence when the characteristic quantity meets the first reference value and set the display mode to the first display mode; when the characteristic quantity meets the second reference value, it can regard the abnormality as occurring and set the display mode to the second display mode.

[0016] In the display system, the storage unit may store temporal changes in feature quantities of the constituent elements included in the causal relationship model, and the control unit may be configured to display the temporal changes in feature quantities on the display unit.

[0017] With this configuration, when an anomaly occurs, the user can visually confirm the temporal changes in the characteristic values of the associated components. This allows, for example, to later confirm how the characteristic values changed to indicate an anomaly. Alternatively, by visually confirming changes in characteristic values, it is possible to detect signs of an anomaly.

[0018] In the above-mentioned display system, the control unit can be configured to: generate the causal relationship model under predetermined conditions over time and store it in the storage unit, display the list of the causal relationship models stored in the storage unit on the display unit, and display the causal relationship model selected from the list according to a request from the user on the display unit.

[0019] This allows for the temporal verification of changes in the causal relationship model. Predetermined conditions can include, for example, when the causal relationship model changes, when an anomaly occurs that changes the display format of the aforementioned nodes, or when production equipment starts or stops. Causal relationship models stored under these conditions can be retroactively visually verified. This allows, for example, the temporal changes in the causal relationship model and the verification of component elements at the time of an anomaly.

[0020] The display method of the present invention is used to display the causal relationship between components related to abnormalities that may occur in production equipment on a display unit, wherein the production equipment produces products and has at least one driving unit for driving the production equipment and at least one monitoring unit for monitoring the production, which serve as the components respectively, and each component has a controllable characteristic quantity. The display method comprises the following steps: storing the relationship between two or more of the multiple components as a causal relationship model for abnormalities that may occur in the production equipment; displaying a model diagram on the display unit according to the causal relationship model, the model diagram having nodes corresponding to the components and edges connecting the nodes; and changing the display mode of at least one of the nodes corresponding to the components associated with the abnormality and the edges connected to the nodes when an abnormality occurs in the production equipment.

[0021] The display program of the present invention is used to display the causal relationship between components related to abnormalities that may occur in production equipment on a display unit, wherein the production equipment produces products and has at least one driving unit for driving the production equipment and at least one monitoring unit for monitoring the production, which serve as the components respectively, and each component has a controllable characteristic quantity. The display program enables the computer to execute the following steps: storing the relationship between two or more of the multiple components as a causal relationship model for abnormalities that may occur in the production equipment; displaying a model diagram on the display unit according to the causal relationship model, wherein the model diagram has nodes corresponding to each component and edges connecting the nodes; and when an abnormality occurs in the production equipment, changing the display mode of at least one of the nodes corresponding to the component associated with the abnormality and the edges connected to the nodes.

[0022] Effects of the Invention

[0023] According to the present invention, it is possible to easily identify components associated with an abnormality that may occur in a production facility. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 An example of a scenario in which the present invention is applied is schematically illustrated.

[0025] Figure 2 This is a block diagram showing the hardware configuration of an analysis device according to one embodiment of the present invention.

[0026] Figure 3 This is a schematic diagram of a production facility according to one embodiment of the present invention.

[0027] Figure 4 This is a block diagram showing the functional configuration of the analysis device.

[0028] Figure 5 This is a flowchart showing an example of constructing a causal relationship model.

[0029] Figure 6 This is an example of the relationship between control signals and takt time.

[0030] Figure 7A is an example of a causal model.

[0031] Figure 7B is an example of a causal model.

[0032] Figure 7C is an example of a causal model.

[0033] Figure 8 This is a graph where the nodes of the causal model overlap with the diagram of the packaging machine.

[0034] Figure 9A This is an example of a screen of a display device.

[0035] Figure 9B This is an example of a screen of a display device.

[0036] Figure 9C This is an example of a screen of a display device.

[0037] Figure 10 This is an example of the screen displayed when an abnormality occurs.

[0038] Figure 11 This is an example of a screen displayed when a sign of abnormality is detected.

[0039] Figure 12A This is an example of a screen of a display device that displays a list of stored causal relationship models.

[0040] Figure 12B This is an example of a screen of a display device that displays a list of stored causal relationship models.

[0041] Figure 12C This is an example of a screen of a display device that displays a list of stored causal relationship models.

[0042] Figure 13 This is another example of a screen of a display device. DETAILED DESCRIPTION

[0043] Hereinafter, an embodiment of one aspect of the present invention (hereinafter also referred to as "this embodiment") is described with reference to the accompanying drawings. However, the present embodiment described below is merely an illustration of the present invention in all respects. Of course, various improvements and modifications can be made without departing from the scope of the present invention. That is to say, when implementing the present invention, a specific configuration that conforms to the embodiment may also be appropriately adopted. It should be noted that, in this embodiment, natural language is used to describe the data that appears, but, more specifically, it is specified using a computer-recognizable analog language, instructions, parameters, machine language, etc.

[0044] <1. Application Examples>

[0045] First, use Figure 1 An example of a scenario in which the present invention is applied will be described. Figure 1An example application scenario of the production system according to this embodiment is schematically illustrated. The production system according to this embodiment includes a packaging machine 3, an example of production equipment, an analysis device 1, and a display device 2. The analysis device 1 is a computer configured to derive and display causal relationships between servo motors (drive units) and various sensors (monitoring units) installed in the packaging machine 3. Hereinafter, drive units such as servo motors and monitoring units such as various sensors are referred to as components.

[0046] The analysis device 1 generates a cause-effect relationship model between components for possible abnormalities that may occur in the packaging machine 3, and displays it on the screen 21 of the display device 2. Figure 1 In the example of FIG. 1 , the film roll 30 (see FIG. 1 ) described later is shown as abnormal. Figure 3 ) is a causal relationship model when the brake belt of the packaging machine is worn. That is, servos 1, 3, and 4 among the multiple servo motors installed in the packaging machine 3 are displayed as nodes, and they are connected by edges. Moreover, the direction of the edge represents the causal relationship. In other words, when the belt is worn, servo 1 affects servo 3, and then servo 3 affects servo 4, resulting in the belt being worn. Therefore, the operator of the packaging machine 3 only needs to confirm the cause of the abnormality in the order of servo 4, 3, and 1. However, each servo motor has multiple controllable characteristic quantities such as torque and position. Any one of the characteristic quantities of the servo motor constructs the above-mentioned causal relationship, which will be described in detail later.

[0047] In addition, if Figure 1 As shown in the example, a schematic diagram of the packaging machine 3 is displayed on the screen 21 of the display device 2, and a causal relationship model (hereinafter sometimes referred to as a model diagram) is superimposed on the schematic diagram. In this example, the outer edge of the node representing the servo 3 is colored, and the display form is different from that of other nodes. This is to make it easy to visually confirm the nodes corresponding to the components associated with the abnormality that has occurred. For example, when an abnormality occurs after at least one of the characteristic quantities of the servo 3 deviates from a predetermined reference value, the components associated with the abnormality can be easily visually confirmed by changing the display form of the node representing the servo 3. Therefore, abnormality response can be carried out quickly. In addition, in Figure 1 In the example shown, a simplified diagram of the packaging machine is shown, but this is not essential, as long as at least a model diagram is shown.

[0048] In addition, in the above description, a packaging machine 3 is shown as an example of production equipment, but as long as it can produce certain items, its type is not particularly limited. The type of each component is also not particularly limited and can be appropriately selected according to the embodiment. Each component can be, for example, a conveyor, a robotic arm, a servo motor, a cylinder (molding machine, etc.), an adsorption pad, a cutting device, a sealing device, etc. In addition, in addition to the above-mentioned packaging machine 3, the production equipment can also be a composite device such as a printing machine, an installation machine, a reflow oven, a substrate inspection device, etc. Furthermore, in addition to the devices accompanied by certain physical actions as described above, the production equipment can also include devices that perform internal processing, such as devices that detect certain information through various sensors, devices that obtain data from various sensors, devices that detect certain information from the obtained data, devices that perform information processing on the obtained data, etc. A production equipment can be composed of one or more devices, or it can be composed of a part of a device. In addition, when the same device performs multiple processes, they can also be regarded as different components. For example, when the same device performs a first process and a second process, the device that performs the first process can be regarded as the first component, and the device that performs the second process can be regarded as the second component.

[0049] <2. Configuration Example>

[0050] <2-1. Hardware Configuration>

[0051] Next, an example of the hardware configuration of the production system according to this embodiment will be described. Figure 2 is a block diagram showing an example of the hardware configuration of the analysis device 1 according to this embodiment. Figure 3 This is a diagram showing the schematic configuration of a packaging machine.

[0052] <2-1-1.Analysis device>

[0053] First, use Figure 2 An example of the hardware configuration of the analysis device 1 according to this embodiment will be described. Figure 2 As shown, the analysis device 1 is a computer electrically connected to a control unit 11 , a storage unit 12 , a communication interface 13 , an external interface 14 , an input device 15 , and a drive 16 .

[0054] The control unit 11 includes a CPU (Central Processing Unit), RAM (Random Access Memory), and ROM (Read Only Memory), and controls various components based on information processing. The storage unit 12, which is an auxiliary storage device such as a hard disk drive or solid-state drive, stores programs 121 executed by the control unit 11, schematic data 122, causal relationship model data 123, and operational status data 124.

[0055] Program 121 is a program for generating a causal relationship model between abnormalities occurring in the packaging machine 3 and its components, and for displaying the model on the display device 2 or the like. Schematic data 122 is data representing a schematic diagram of the target production equipment. In this embodiment, the schematic diagram represents the packaging machine 3. The schematic diagram only needs to be a schematic diagram of the entire packaging machine, at least showing the positions of the components represented by the causal relationship model. A detailed diagram is not required. Alternatively, an enlarged view showing only a portion of the packaging machine 3 is acceptable.

[0056] The causal relationship model data 123 represents a causal relationship model for abnormality occurrence, constructed from the feature values of each component extracted from the packaging machine 3. Specifically, it represents the causal relationship between the components when an abnormality occurs. As described below, the analysis device 1 generates the causal relationship model data based on the feature values extracted from the packaging machine 3. However, pre-generated causal relationship model data may also be stored in an external device.

[0057] The operating state data 124 is data indicating the operating state of the packaging machine 3. For example, it may include data that may be generated during the operation of the aforementioned components, such as measurement data of torque, speed, acceleration, temperature, and pressure, as described in detail below. Furthermore, if the component is a sensor, it may include detection data indicating the presence or absence of the contents WA, for example, as indicated by "on" or "off," as a result of detection.

[0058] The communication interface 13 is an interface for wired or wireless communication, such as a wired LAN (Local Area Network) module or a wireless LAN module. Specifically, the communication interface 13 is an example of a communication unit configured to communicate with other devices. The analyzer 1 of this embodiment is connected to the packaging machine 3 via the communication interface 13.

[0059] The external interface 14 is an interface for connecting to an external device and is configured appropriately according to the external device to be connected. In this embodiment, the external interface 14 is connected to the display device 2. In addition, the display device 2 can use a well-known liquid crystal display, touch panel display, etc.

[0060] The input device 15 is a device for inputting, such as a mouse and a keyboard.

[0061] The drive 16 is, for example, a CD (Compact Disk) drive or a DVD (Digital Versatile Disk) drive, and is a drive device for reading a program stored in the storage medium 17. The type of the drive 16 can be appropriately selected according to the type of the storage medium 17. Furthermore, at least a portion of the various data 122 to 124 including the program 121 stored in the storage unit may also be stored in the storage medium 17.

[0062] The storage medium 17 is a medium that stores information such as programs by electrical, magnetic, optical, mechanical or chemical means so that computers, other devices, machines, etc. can read the recorded information such as programs. Figure 2 In the embodiment of the present invention, a disk-type storage medium such as a CD or DVD is shown as an example of the storage medium 17. However, the type of the storage medium 17 is not limited to a disk-type storage medium and may be a type other than a disk-type storage medium. Examples of a storage medium other than a disk-type storage medium include semiconductor memories such as flash memory.

[0063] Furthermore, the specific hardware configuration of the analysis device 1 can be omitted, replaced, or supplemented as appropriate depending on the implementation. For example, the control unit 11 may include multiple processors. The analysis device 1 may also be composed of multiple information processing devices. Furthermore, in addition to being designed as an information processing device dedicated to the service provided, the analysis device 1 may also utilize a general-purpose server device.

[0064] <2-1-2. Packaging Machine>

[0065] Next, use Figure 3 An example of the hardware configuration of the packaging machine 3 according to this embodiment will be described. Figure 3 An example of the hardware configuration of the packaging machine 3 according to this embodiment is schematically illustrated. The packaging machine 3 is a so-called horizontal pillow packaging machine, and is used to package contents WA, such as food (dried noodles, etc.) and stationery (erasers, etc.). However, the type of contents WA can be appropriately selected depending on the embodiment and is not particularly limited. The packaging machine 3 primarily comprises three devices: a film conveying unit 31 that conveys a film roll 30 wound from a wrapping film, a contents conveying unit 32 that conveys the contents WA, and a bag-making unit 33 that packages the contents WA with the wrapping film.

[0066] The wrapping film may be a resin film such as a polyethylene film, for example. The film roll 30 includes a core around which the wrapping film is wound. The core is supported so as to be rotatable about an axis, so that the film roll 30 can deliver the wrapping film while rotating.

[0067] The film conveyor 31 includes a drive roller driven by a servo motor (Servo 1) 311, a driven roller 312 that receives rotational force from the drive roller, and a plurality of pulleys 313 that guide the packaging film while applying tension to it. Thus, the film conveyor 31 is configured to deliver the packaging film from the film roll 30 and convey it to the bag-making unit 33 without slack.

[0068] The content conveying section 32 includes a conveyor 321 for conveying the content WA to be packaged and a servo motor (Servo 2) 322 for driving the conveyor 321. Figure 3 As shown, the content conveying section 32 is connected to the bag-making section 33 via the bottom of the film conveying section 31. Thus, the content WA conveyed by the content conveying section 32 is supplied to the bag-making section 33 and packaged using the packaging film supplied from the film conveying section 31. Furthermore, an optical fiber sensor (sensor 1) 324 is installed above and downstream of the conveyor 321 to detect the position of the content WA. Furthermore, an optical fiber sensor (sensor 2) 325 is installed below the conveyor 321 to detect the rise of the content WA. These sensors 1 and 2 detect whether the content WA is conveyed at the correct position, ensuring accurate packaging of the content WA.

[0069] The bag making unit 33 includes a conveyor 331, a servo motor (Servo 3) 332 that drives the conveyor 331, a center seal unit 333 that seals the packaging film in the conveying direction, and end seal units 334 that cut the packaging film at both ends in the conveying direction and seal each end.

[0070] The conveyor 331 transports the contents WA delivered from the contents conveying section 32 and the packaging film supplied from the film conveying section 31. The packaging film supplied from the film conveying section 31 is appropriately bent so that its widthwise end edges overlap and is then fed to the center seal section 333. The center seal section 333 is comprised of, for example, a pair of left and right heating rollers (heaters 1 and 2). Heat is applied to seal the bent end edges of the packaging film along the conveying direction. This forms the packaging film into a cylindrical shape. The contents WA are placed into this cylindrical packaging film. Furthermore, an optical fiber sensor (sensor 3) 336 is provided above the conveyor 331, upstream of the end seal section 334, to detect the position of the contents WA.

[0071] Meanwhile, the end seal unit 334 comprises, for example, a roller driven by a servo motor 335, a pair of cutters that open and close as the rollers rotate, and heaters (heaters 3) positioned on either side of each cutter. Thus, the end seal unit 334 is configured to cut the tubular packaging film perpendicular to the conveyance direction and seal the cut portion by heating. When passing through the end seal unit 334, the leading end of the tubular packaging film is sealed on both sides in the conveyance direction and separated from the downstream portion, forming a package WB containing the contents WA.

[0072] <2-1-3. Packaging process>

[0073] The packaging machine 3 described above can package the contents WA through the following process. Specifically, the film conveying unit 31 unwinds the packaging film from the film roll 30. Furthermore, the contents WA to be packaged are conveyed by the contents conveying unit 32. The unwinding packaging film is then formed into a cylindrical shape by the center seal unit 333 of the bag-making unit 33. After the contents WA are added to the formed cylindrical packaging film, the end seal units 334 cut the cylindrical packaging film in a direction perpendicular to the conveying direction. The cut sections are then sealed on both sides of the conveying direction by heating. This forms a horizontal pillow-shaped package WB containing the contents WA. This completes the packaging of the contents WA.

[0074] Furthermore, the driving control of the packaging machine 3 may be performed by a PLC or the like provided separately from the packaging machine 3. In this case, the operation status data 124 can be obtained from the PLC. In addition, in the packaging machine 3 configured as described above, as an example, 10 components are set to establish a cause-effect relationship of an abnormality (e.g., see Figure 8 That is, the servos 1 to 4, heaters 1 to 3, and sensors 1 to 3 are set as components, and the causal relationship between these components when an abnormality occurs is constructed as a causal relationship model. Details will be described later.

[0075] <2-2. Functional structure>

[0076] Next, the functional configuration (software configuration) of the analysis device 1 will be described. Figure 4 This is an example of the functional configuration of the analysis device 1 involved in this embodiment. The control unit 11 of the analysis device 1 loads the program 121 stored in the storage unit 12 into the RAM. Furthermore, the control unit 11 interprets and executes the program 121 loaded into the RAM through the CPU, thereby controlling each component. Figure 4 As shown, the analysis device 1 according to the present embodiment functions as a computer including a feature quantity acquisition unit 111 , a model construction unit 112 , and a display control unit 113 .

[0077] The feature acquisition unit 111 acquires the values of various feature quantities calculated from the operational state data 124 representing the operational state of the packaging machine 3, both for normal times (when the packaging machine 3 forms packages WB normally) and for abnormal times (when an abnormality occurs in the formed packages WB). The model construction unit 112 selects, from the acquired feature quantities, those effective for predicting abnormalities, based on a predetermined algorithm that derives the correlation between the abnormality occurring in the formed packages WB and the various feature quantities from the acquired feature quantity values for both normal and abnormal times. Furthermore, the causal relationship model 123 is constructed using the selected feature quantities to represent the causal relationships between the components when the abnormality occurs.

[0078] The display control unit 113 has a function of displaying the schematic diagram of the packaging machine 3, the causal relationship model, various feature quantities, etc. on the screen 21 of the display device 2. In addition, the display control unit 113 controls the screen 21 of the display device 2 to display various information.

[0079] The various functions of the analysis device 1 will be described in detail in the operational examples described below. Furthermore, in this embodiment, the above functions are described as being implemented using a general-purpose CPU. However, some or all of the above functions may also be implemented using one or more dedicated processors. Furthermore, the functional configuration of the analysis device 1 may be appropriately omitted, replaced, or added depending on the embodiment.

[0080] <3. Action Example>

[0081] Next, an operation example of the production system configured as described above will be described.

[0082] <3-1. Creation of a Causal Relationship Model>

[0083] First, use Figure 5 The processing sequence when the analysis device creates a causal relationship model is described. Figure 5 An example of the processing procedure of the analysis device when creating a causal relationship model is described.

[0084] (Step S101)

[0085] In the initial step S101, the control unit 11 of the analysis device 1 functions as a feature quantity acquisition unit 111, and obtains the values of multiple feature quantities calculated from the action state data 124 representing the action state of the packaging machine 3, respectively, when the packaging machine 3 normally forms the packaging body WB and when the formed packaging body WB has an abnormality.

[0086] Specifically, the control unit 11 first categorizes the state of the packaging machine 3 into normal and abnormal conditions and collects operating status data 124. The type of operating status data 124 collected is not particularly limited as long as it represents the state of the packaging machine 3. However, in this embodiment, the data may be data generated during the operation of the aforementioned components, such as measurement data on torque, speed, acceleration, temperature, and pressure.

[0087] When the component is a sensor, measurement data such as ON time, OFF time, turn-on time, and turn-off time can be used as the operation state data 124. Figure 6 As shown, the on-time and off-time are the total time that the control signal is on or off within the target frame, while the open-time and close-time are the time until the control signal is first turned on or off within the target frame. Furthermore, the control unit 11 can acquire detection results from various sensors, such as detection data indicating the presence of content WA as "on" or "off," as operational status data 124. The collected operational status data 124 can be stored in the storage unit 12 or in an external storage device.

[0088] Next, the control unit 11 divides the collected operational status data 124 into frames to define a processing range for calculating the feature value. For example, the control unit 11 may divide the operational status data 124 into frames of a certain length. However, the packaging machine 3 does not necessarily operate at fixed time intervals. Therefore, dividing the operational status data 124 into frames of a certain length may cause variations in the operation of the packaging machine 3 reflected in each frame.

[0089] Therefore, in this embodiment, the control unit 11 divides the operation status data 124 into frames based on takt time. Takt time is the time required to produce a predetermined number of products, that is, to form a predetermined number of packages WB. This takt time can be determined based on signals controlling the packaging machine 3, such as control signals controlling the operation of the packaging machine 3's servo motors.

[0090] use Figure 6 The relationship between control signals and takt time is explained. Figure 6 The relationship between the control signal and the takt time is schematically illustrated. Figure 6 As shown, the control signal for production equipment such as the packaging machine 3 that repeatedly produces products is a pulse signal that periodically turns on and off according to the production of a predetermined number of products.

[0091] For example, in Figure 6In the control signal shown, "on" and "off" appear once each during the formation of one package WB. Therefore, the control unit 11 can obtain the control signal from the packaging machine 3 and set the time from the rising edge ("on") of the obtained control signal to the next rising edge ("on") as the takt time. Figure 6 As shown, the control unit 11 can divide the motion state data 124 into frames according to the takt time.

[0092] Furthermore, the type of control signal is not particularly limited as long as it can be used to control the packaging machine 3. For example, if the packaging machine 3 includes a sensor for detecting a mark attached to the packaging film, and the output signal of the sensor is used to adjust the feeding amount of the packaging film, the output signal of the sensor can be used as the control signal.

[0093] Next, the control unit 11 calculates the value of the feature quantity from each frame of the operation state data 124. The type of the feature quantity is not particularly limited as long as it is a type that indicates the characteristics of the production equipment.

[0094] For example, the operation state data 124 is quantitative data such as the above-mentioned measurement data ( Figure 6 In the case of physical quantity data), the control unit 11 can also calculate the amplitude, maximum value, minimum value, average value, variance value, standard deviation, autocorrelation coefficient, maximum value, skewness, kurtosis, etc. of the power spectrum obtained by Fourier transform within the frame as feature quantities.

[0095] In addition, for example, the operation state data 124 is qualitative data such as the above-mentioned detection data ( Figure 6 In the case of pulse data), the control unit 11 may calculate the "on" time, "off" time, duty ratio, "on" times, "off" times, etc. in each frame as feature quantities.

[0096] Furthermore, the feature quantity can be derived not only from a single piece of motion state data 124 but also from multiple pieces of motion state data 124. For example, the control unit 11 can calculate a correlation coefficient, a ratio, a difference, a synchronization offset, a distance, etc. between corresponding frames of two pieces of motion state data 124 as the feature quantity.

[0097] The control unit 11 calculates the aforementioned multiple feature quantities from the operational state data 124. This allows the control unit 11 to obtain the values of the multiple feature quantities calculated from the operational state data 124 for both normal and abnormal conditions. Furthermore, the processing from collecting the operational state data 124 to calculating the feature quantity values can be performed by the analyzer 1 or the packaging machine 3 or various devices that control it. Furthermore, the control unit 11 can discretize the values of the various feature quantities, for example, by setting a value above a threshold to "1" or "high" and a value below a threshold to "0" or "low."

[0098] (Step S102)

[0099] In the next step S102, the control unit 11 functions as a model building unit 112, and selects a feature value that is effective for predicting an abnormality from the multiple feature values obtained according to a predetermined algorithm. The predetermined algorithm refers to an algorithm that determines the correlation between the abnormality occurring in the formed packaging body WB and the various feature values from the values of the various feature values obtained in normal and abnormal times in step S101.

[0100] The predetermined algorithm may be constructed using, for example, a Bayesian network, which is a type of graphical modeling that represents the causal relationship between multiple random variables using a directed acyclic graph structure and represents the causal relationship between each random variable using conditional probabilities.

[0101] The control unit 11 treats the acquired feature quantities and the state of the package WB as random variables. Specifically, by setting the acquired feature quantities and the state of the package WB as nodes, a Bayesian network is constructed, thereby deriving the causal relationship between each feature quantity and the state of the package WB. A Bayesian network can be constructed using known methods. For example, a structured learning algorithm such as the Greedy Search algorithm, the Stingy Search algorithm, or the full search method can be used to construct the Bayesian network. Furthermore, evaluation criteria for the constructed Bayesian network can include AIC (Akaike's Information Criterion), C4.5, CHM (Cooper Herskovits Measure), MDL (Minimum Description Length), ML (Maximum Likelihood), and the like. Furthermore, methods for handling missing values in the learning data (action state data 124) used to construct the Bayesian network can include a pairing method, a list method, and the like.

[0102] For example, Figure 7AThe following causal relationship model is shown when belt wear is an abnormal event. Specifically, the following causal relationship model is constructed: the torque mean value and position standard deviation, which are characteristic quantities of servo 1, affect the speed minimum value and torque maximum value, which are characteristic quantities of servo 3. These factors, in turn, affect the torque mean value of servo 4.

[0103] Figure 7B This figure shows a causal relationship model for the abnormal event of chain slack in conveyor 321 of content conveying section 32. Specifically, a causal relationship model is constructed in which the on-time, a characteristic quantity of sensor 2, affects the off-time, a characteristic quantity of sensor 3, which in turn affects the average torque value of servo 4.

[0104] Figure 7C This figure shows a causal relationship model when a sealing failure of the packaging film is an abnormal event. For this abnormal event, a causal relationship model is constructed in which only the average torque value of the servo 4 is the cause. The causal relationship model constructed in this way is stored in the storage unit 12 as causal relationship model data 123.

[0105] Furthermore, the method for treating each acquired feature value and the state of the package WB as a random variable can be appropriately determined depending on the implementation. For example, a normal package WB can be assigned a probability of "0" and an abnormal package WB can be assigned a probability of "1," thereby treating the state of the package WB as a random variable. Alternatively, for example, a feature value below a threshold value can be assigned a probability of "0," while a feature value exceeding the threshold value can be assigned a probability of "1," thereby treating the state of each feature value as a random variable. However, the number of states set for each feature value is not limited to two and can be three or more.

[0106] <3-2. Display of the Causal Relationship Model>

[0107] Next, the display of the causal relationship model constructed as described above will be described. In this case, the control unit 11 of the analysis device 1 functions as the display control unit 113. The display control unit 113 controls the display of the following screen 21. First, the display control unit 113 displays the schematic 122 read from the storage unit 12 and the causal relationship model 123 on the screen 21 of the display device 2, superimposing them. Figure 8This diagram overlays the components that may cause abnormal events in this embodiment with a schematic diagram. As described above, the servos 1-4, heaters 1-3, and sensors 1-3, which serve as nodes of the causal relationship model, are positioned in the schematic diagram at their respective locations. Furthermore, on the screen 21 of the display device 2 described below, components that form the causal relationship model are selected from these components as nodes based on the abnormal event selected by the user, and edges with arrows indicating causal relationships are displayed along with the nodes.

[0108] Figure 9A This is an example of a screen 21 of the display device 2 showing a causal relationship model. This screen 21 can be operated using the aforementioned input device 15. In the upper left corner of this screen 21, a selection box 211 for selecting an abnormal event is displayed, and an abnormal event can be selected using a pull-down menu. In this example, belt wear, chain slack, and seal failure are displayed as abnormal events, and belt wear is selected from these.

[0109] Below the selection box 211, a model diagram 212 is displayed in which a schematic diagram of a packaging machine and a causal relationship model are superimposed. Figure 9A In the example, a model diagram is displayed when the abnormal event is belt wear. In addition, a list 213 representing the components and their characteristic quantities is displayed in the lower left corner of the model diagram 212 according to the selected abnormal event. The user can select any component and characteristic quantity from the list 213. When any one is selected, the corresponding component in the model diagram 212 is highlighted. In this example, (Servo 1 - Torque Average) is selected from the list 213, and thus Servo 1 in the model diagram 212 is highlighted. The highlighting can be various methods, as long as it is displayed in a manner that can be distinguished from other nodes, such as coloring, flashing, etc.

[0110] Furthermore, on the right side of the list 213, temporal changes of the selected feature amount are displayed by a graph 214. In this example, since (Servo 1 - Torque Average) is selected, a line graph 214 showing its temporal changes is displayed.

[0111] Figure 9B An example is shown in which chain slack is displayed as an abnormal event in frame 211. Consequently, the components and characteristic quantities that cause the chain slack are displayed in list 213. Since (Servo 4 - Torque Average) is selected, Servo 4 is highlighted in model graph 212, and a line graph 214 showing the temporal changes of (Servo 4 - Torque Average) is displayed.

[0112] Figure 9CAn example is shown in which a sealing failure is displayed as an abnormal event in frame 211. Consequently, the components and characteristic quantities that contribute to the sealing failure are displayed in list 213. Since (Servo 4 - Torque Average) is selected, Servo 4 is highlighted in model graph 212, and a line graph 214 showing the temporal changes of (Servo 4 - Torque Average) is displayed.

[0113] The operation of the above-mentioned screen 21 is summarized as follows. First, the user selects the abnormal event to be confirmed from the selection box 211 through the input device 15. As a result, the display control unit 113 displays the model diagram 212 and the list 213 corresponding to the selected abnormal event on the screen. Moreover, when any feature quantity is selected from the list 213, the node of the corresponding model diagram 212 is highlighted, and a graph 214 showing the time change of the selected feature quantity is displayed. Therefore, the user can visually confirm the causal relationship involved in the abnormal event while observing the screen 21. In addition, the period of the time change of the feature quantity displayed on the graph 214 can be appropriately set by the user.

[0114] <3-3. Display when an abnormality occurs>

[0115] Next, refer to Figure 10 The following describes the screen display when an abnormality occurs. Figure 10 is with Figure 9A The corresponding figure shows the model diagram 212 when the abnormal event is the wear of the belt, and an abnormality related to the wear of the belt actually occurs. At this time, the outer edge of the node of Servo 1 in the model diagram 212 is colored and highlighted. This indicates that the abnormality may be caused by Servo 1. In this example, as shown in the line graph 214, the average torque value of Servo 1 has increased since a certain period and exceeded a predetermined value (for example, 0.8). Therefore, it can be considered that the average torque value of Servo 1 exceeding the predetermined value is the cause of the abnormality. In this way, when an abnormality occurs, the display control unit 113 will specifically highlight the node corresponding to the component whose characteristic value exceeds the predetermined value.

[0116] Furthermore, as mentioned above, not only can the node considered as the cause be highlighted when an abnormality occurs, but also when a sign of abnormality is detected. A sign of abnormality means that the packaging machine can continue to operate, but it indicates that an abnormality may occur in the future. For example, Figure 11 As shown in FIG. 1 , when the torque average value of the servo 1 exceeds a reference value (e.g., 0.6) that indicates an abnormality, the outer edges of the nodes of the servo 1 are colored lighter than when an abnormality occurs, thereby allowing the user to visually confirm the abnormality. Then, when an abnormality occurs, the user can Figure 10The outer edges of the nodes are colored as shown. This allows the occurrence of an anomaly to be displayed in stages, starting from the time a sign is detected. Furthermore, the criteria for determining an anomaly or a sign of an anomaly can be modified as appropriate, with various settings possible, such as when a feature value exceeds a predetermined threshold as described above, when the threshold is exceeded for a predetermined period of time, or when the threshold is exceeded for a predetermined period of time.

[0117] <3-4. Temporal Storage of Causal Relationship Models>

[0118] The cause-effect relationship model is stored in the storage unit 12 over time, and can be displayed retroactively. 12A to 12C is with Figures 9A to 9C Different screens 21 can be switched to, for example, by selecting a tab (not shown). 12A to 12C Screen 21 shows an example of storing causal relationship models over time under predetermined conditions. On the left side of the screen, a list 215 containing labels 215a to 215d of causal relationship models stored in time series is displayed. In this example, causal relationship models are stored under predetermined conditions. For example, causal relationship models are stored under various conditions, such as when a new causal relationship model is generated, when a causal relationship model is updated, when an abnormality occurs, when production equipment starts or stops operating, when the settings of production equipment or components are changed, when the characteristic values of each component set in advance by the user reach a predetermined value, when a time arbitrarily set by the user is reached, or when a caption is added by the user during real-time monitoring.

[0119] Furthermore, in the list 215, a label indicating the latest causal relationship model is displayed at the top, and a new label is displayed at the top of the list 215 each time a causal relationship model is stored. Figure 12A In the example of , it is shown that when the causal relationship model is updated, the causal relationship model stored is the latest causal relationship model. Figure 12B In the storage Figure 12A The causal relationship model of the predetermined time set by the user after the predetermined time has passed since the state of , the label 215c representing the causal relationship model is displayed at the top of the list 215. Figure 12C In the storage Figure 12B When a predetermined time has passed since the state of , and an abnormality has occurred, a label 215d indicating the causal relationship model is displayed at the top of the list 215. Figure 12C In the example, since an abnormality has occurred, the node corresponding to the component associated with the abnormality (for example, servo 1) is highlighted. Figure 12A and Figure 12B In the example, no exception occurs. In addition, 12A to 12C , the causal model itself has not changed.

[0120] By setting up such a list 215, the causal relationship model can be confirmed retroactively. Figure 12C In the example of FIG. 2 , when the user selects any one of the tags 215 a to 215 d in the list 215 , the causal relationship model at that time may be displayed in the form of a model diagram 212 .

[0121] <4. Features>

[0122] (1) According to this embodiment, a causal relationship model related to possible abnormalities that may occur in the packaging machine 3 is displayed. When an abnormality occurs in the packaging machine 3, the node corresponding to the component associated with the abnormality is highlighted. This allows the user to easily visually confirm the component associated with the abnormality and quickly proceed with the abnormality response. Furthermore, when a sign of an abnormality is detected, the node corresponding to the component associated with the abnormality can be highlighted in a different display mode than when the abnormality has occurred. This allows visual confirmation of the sign of an abnormality and facilitates preparations to prevent the occurrence of the abnormality, such as the preparation of components.

[0123] (2) Since the temporal changes in the characteristic quantities of each component are displayed in a graph, when an abnormality occurs, the user can visually confirm the temporal changes in the characteristic quantities of the related components. This allows, for example, to later confirm how the characteristic quantities changed and how the abnormality occurred. Alternatively, by visually confirming the changes in the characteristic quantities, it is possible to detect signs of abnormality.

[0124] (3) 12A to 12C As shown, the causal relationship model is stored over time under predetermined conditions and tabulated, allowing users to easily review and visually check the causal relationship model. This allows, for example, to retrospectively check changes in the causal relationship model over time or to identify the components that caused an anomaly.

[0125] <5. Modifications>

[0126] The embodiments of the present invention have been described in detail above, but the above description is merely illustrative of the present invention in all aspects. Of course, various improvements and modifications can be made without departing from the scope of the present invention. For example, the following changes can be made. In addition, the same reference numerals are used below for the same components as the above embodiment, and the description of the same points as the above embodiment is appropriately omitted. The following modifications can be appropriately combined.

[0127] <5-1>

[0128] In the above embodiment, the screen 21 displays the selection box 211, the model diagram 212, the list 213, and the chart 214 for abnormal events, but this is not limited to the above, as long as at least the model diagram 212 is displayed. For example, depending on the production equipment used as the object, there may be a case where there is only one abnormal event. Therefore, in this case, the selection box 211 is not required. In addition, it is not necessary to display all the elements 211 to 214 on the screen 21. They can also be displayed on multiple screens, and the user can switch between these screens. In addition, 12A to 12C The picture is with Figures 9A to 9C Different picture, but also can be Figures 9A to 9C The display list 215 can be appropriately changed in the screen configuration.

[0129] <5-2>

[0130] There is no particular limitation on the display mode of the node when an abnormality occurs or a sign of an abnormality is detected, as long as the display mode is different from the node corresponding to the component that is not associated with the abnormality, or the node corresponding to the component in which no abnormality has occurred. For example, various display modes such as color, shape, and animation can be used. The display mode can be changed over time. For example, by changing the display mode just after the abnormality occurs and when a predetermined time has passed, the user can visually confirm the approximate time elapsed since the abnormality occurred. In addition, not only the node, but also the display mode of the edge connected to the node can be changed. That is, as long as the display mode of at least one of the nodes or edges associated with the abnormality is changed. Furthermore, in addition to the change in the display mode of the node or edge, the abnormality can be notified to the relevant personnel by emitting a warning sound or by means such as email.

[0131] <5-3>

[0132] exist 12A to 12C In the screen, since the causal relationship model is stored over time, the stored model diagrams 212 can be displayed sequentially. Figure 13In the example, a display control box 216 for displaying the model diagram 212 in time series is displayed. Display control box 216 displays a timeline 216a, labels 216b representing stored causal relationship models, a time indicator 216c, and display control buttons 216d. For example, when displaying the causal relationship model in time series, the time indicator 216c moves rightward at a predetermined speed on the timeline 216a. When it reaches the position where each label 216b is created, the corresponding model diagram 212 is displayed in sequence. Furthermore, the time indicator 216c on the timeline 216a can be moved as needed using display control buttons 216d. Specifically, the time indicator 216c can be moved to the earliest or latest time, moved forward or backward by a predetermined time, or stopped. Furthermore, by selecting a predetermined time on the timeline 216a (e.g., the range of symbol 216e), the time indicator 216c can be repeatedly moved within that time. This allows visual confirmation of changes in the causal relationship model over that time. In this example, a case where the model graph is displayed in time series is described, but the form of the display control frame is not particularly limited.

[0133] <5-4>

[0134] The construction of the causal relationship model shown in the above embodiment is an example, and other methods may be used. In addition, the schematic data 122 or the causal relationship model data 123 constructed by other devices may be sequentially stored in the storage unit 12.

[0135] <5-5>

[0136] This method can also be applied to production equipment other than packaging machines 3. In this case, the components used to construct the causal relationship model can be appropriately selected based on the production equipment. Alternatively, schematic data for multiple production equipment can be pre-stored in the storage unit 12 and displayed on the display device 2 for each corresponding production equipment. However, schematic diagrams of the production equipment are not essential; it is also possible to display only the causal relationship model.

[0137] <5-6>

[0138] The display system according to the present invention can be composed of the analyzer 1 and display device 2 in the above-described production system. Therefore, the display device 2 in the above-described embodiment corresponds to the display unit of the present invention, and the control unit 11 and storage unit 12 of the analyzer 1 correspond to the control unit and storage unit of the present invention. For example, the control unit, storage unit, and display unit according to the present invention can also be composed of a tablet PC or the like.

[0139] Description of Reference Numerals

[0140] 1…Analysis device,

[0141] 11…Control Unit

[0142] 12…Storage unit,

[0143] 2…Display device (display unit)

[0144] 3…Packaging machine (production equipment).

Claims

1. A display system provided in a production facility that produces a product, the production facility including at least one drive unit for driving the production facility and at least one monitoring unit for monitoring the production, each of the components having a controllable characteristic quantity, the display system comprising: Control Department; a display unit; and Storage Department, The storage unit stores the relationship between two or more of the plurality of components as a causal relationship model for possible abnormalities that may occur in the production equipment. The control unit is configured as follows: A model diagram is displayed on the display unit based on the causal relationship model, the model diagram having nodes corresponding to the respective components and edges connecting the nodes. The model diagram is displayed superimposed on the diagram showing the production equipment in such a manner that the nodes overlap with the positions where the components are provided. When an abnormality occurs in the production equipment, the display mode of at least one of the node corresponding to the component associated with the abnormality and the edge connected to the node is changed, and generating or updating the causal relationship model under predetermined conditions over time, and storing the generated or updated causal relationship model in the storage unit together with a label indicating a time series of generation or update, causing the stored list of the labels of the causal relationship model to be displayed on the display unit, The causal relationship model corresponding to the label selected from the list is displayed on the display unit in response to a request from a user.

2. The display system according to claim 1, wherein: The control unit is configured to change the display mode when a sign of the abnormality is detected.

3. The display system according to claim 1, wherein: When the characteristic quantity satisfies a first reference value, the control unit regards that a sign of the abnormality has occurred and sets the display mode to a first display mode. When the feature value satisfies a second reference value, the control unit determines that the abnormality has occurred and sets the display mode to a second display mode.

4. The display system according to any one of claims 1 to 3, wherein: The storage unit stores temporal changes in feature quantities of the constituent elements included in the causal relationship model. The control unit is configured to display a temporal change in the feature value on the display unit.

5. A display method for displaying on a display unit a causal relationship between components related to an abnormality that may occur in production equipment, wherein the production equipment produces products and includes at least one drive unit for driving the production equipment and at least one monitoring unit for monitoring the production, each of which serves as the component, each component having a controllable characteristic quantity, the display method comprising the following steps: storing, as a causal relationship model, relationships between two or more of the plurality of components for possible abnormalities that may occur in the production equipment; displaying a model graph on the display unit based on the causal relationship model, the model graph having nodes corresponding to the respective components and edges connecting the nodes; as well as When an abnormality occurs in the production equipment, the display mode of at least one of the node corresponding to the component associated with the abnormality and the edge connected to the node is changed; The storing step includes: generating or updating the causal relationship model under predetermined conditions over time, and storing the generated or updated causal relationship model together with a label indicating a time series of generation or update, The step of displaying the model diagram on the display unit includes: displaying a diagram showing the production equipment on the display unit; overlapping the model diagram on the diagram showing the production equipment in a manner such that the nodes overlap with the positions where the components are set; and displaying a list of the labels of the stored causal relationship model on the display unit, The display method further includes the step of displaying the causal relationship model corresponding to the label selected from the list on the display unit in response to a request from a user.

6. A program product comprising a display program configured to display on a display unit a causal relationship between components related to an abnormality that may occur in production equipment, wherein the production equipment produces products and has at least one drive unit for driving the production equipment and at least one monitoring unit for monitoring the production, each of which serves as the component, each of which has a controllable characteristic quantity. The display program causes the computer to execute the following steps: storing, as a causal relationship model, relationships between two or more of the plurality of components for possible abnormalities that may occur in the production equipment; displaying a model graph on the display unit based on the causal relationship model, the model graph having nodes corresponding to the respective components and edges connecting the nodes; as well as When an abnormality occurs in the production equipment, the display mode of at least one of the node corresponding to the component associated with the abnormality and the edge connected to the node is changed; The storing step includes: generating or updating the causal relationship model under predetermined conditions over time, and storing the generated or updated causal relationship model together with a label indicating a time series of generation or update, The step of displaying the model diagram on the display unit includes: displaying a diagram showing the production equipment on the display unit; overlapping the model diagram on the diagram showing the production equipment in a manner such that the nodes overlap with the positions where the components are set; and displaying a list of the labels of the stored causal relationship model on the display unit, The display program further causes the computer to execute the step of displaying the causal relationship model corresponding to the label selected from the list on the display unit in response to a request from a user.

Images