State estimation device, implementation system, and state estimation method

Abstract

To provide a state estimation device that can improve accuracy of detecting a head requiring maintenance.SOLUTION: A state estimation device 100 is a device that includes a head having a head main body part to which a nozzle configured to hold an object is attached, and manages a state of the head in equipment that holds the object with the head to perform predetermined operations, and the state estimation device comprises: a threshold creation unit 110 that acquires an equipment log of the head to which the nozzle is attached, and creates a first threshold on the basis of a dataset consisting of a plurality of characteristic values of the head included in the equipment log; and a state estimation unit 120 that acquires the characteristic values of the head to which the nozzle is attached and is in an operating state, and estimates whether the head is in a condition related to disorder on the basis of the acquired characteristic values of the head and the first threshold. The dataset consists of a plurality of characteristic values of the head exceeding a reference value.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a state estimation device, an implementation system, and a state estimation method. [Background technology]

[0002] Conventionally, equipment such as component mounting systems may deteriorate with use or over time, and therefore require maintenance. For example, Patent Document 1 discloses a technique for measuring the vacuum pressure of a vacuum pump in a head with a sensor, and determining that the vacuum pump requires maintenance when the measured vacuum pressure reaches a threshold value at which the vacuum pump requires maintenance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2012-033522 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the threshold value for when it is considered that head maintenance is necessary is often determined empirically, and depending on the environment in which the equipment equipped with the head is installed, the threshold value may not be an accurate value for the sensor measurement value. For this reason, even if the sensor measurement value reaches the threshold value, there are cases in which no malfunction is actually observed in the head, and there are also cases in which a malfunction is actually observed in the head even if the sensor measurement value does not reach the threshold value, resulting in a problem of insufficient accuracy in detecting heads requiring maintenance.

[0005] Therefore, the present disclosure provides a state estimation device etc. that can improve the accuracy of detecting a head requiring maintenance. [Means for solving the problem]

[0006] A state estimation device according to one embodiment of the present disclosure is a state estimation device that manages the state of a head in equipment that holds an object using the head to perform a specified task, and that includes a threshold generation unit that acquires an equipment log of the head to which the nozzle is attached and generates a first threshold based on a data set consisting of multiple characteristic values ​​of the head included in the equipment log, and a state estimation unit that acquires characteristic values ​​of the head to which the nozzle is attached and in an operating state and estimates whether the head is in a state related to a malfunction based on the acquired characteristic value of the head and the first threshold, and the data set consists of multiple characteristic values ​​of the head that exceed a reference value.

[0007] These comprehensive or specific aspects may be realized by a system, an apparatus, a method, a recording medium, or a computer program, or may be realized by any combination of a system, an apparatus, a method, a recording medium, and a computer program. Effect of the Invention

[0008] According to the state estimation device and the like according to the present disclosure, it is possible to improve the accuracy of detecting heads requiring maintenance. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a configuration diagram illustrating an example of a state estimation device according to an embodiment. [Figure 2A] FIG. 1 is a configuration diagram illustrating an example of a mounting system according to an embodiment. [Figure 2B] 1 is a configuration diagram showing an example of a component mounting apparatus according to an embodiment; [Figure 3A] 5A and 5B are schematic diagrams showing the configuration of the head main body during vacuuming according to the embodiment. [Figure 3B] 5A and 5B are schematic diagrams showing the configuration of the head main body during blowing in the embodiment. [Figure 4] 4 is a diagram for explaining the operation of the state estimating device according to the embodiment; FIG. [Diagram 5] 11 is a diagram for explaining a method of generating an online flow rate reduction determination threshold value. FIG. [Figure 6] 11 is a diagram for explaining a method of generating an offline flow rate reduction determination threshold value. FIG. [Figure 7] 11A and 11B are diagrams for explaining a method of estimating the cause of a malfunction of a head. [Figure 8] 11 is a graph showing an example of waveform data of a flow rate in an air path. [Figure 9] FIG. 4 is a sequence diagram showing an example of the operation of the facility maintenance system and the maintenance technician according to the embodiment. [Figure 10] 13 is a flowchart illustrating an example of a state estimation method according to another embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] The state estimation device disclosed herein is a state estimation device that manages the state of a head in equipment that is equipped with a head having a head main body to which a nozzle configured to hold an object is attached and that holds the object with the head to perform a specified task, and is equipped with a threshold generation unit that acquires an equipment log of the head to which the nozzle is attached and generates a first threshold based on a data set consisting of multiple characteristic values ​​of the head included in the equipment log, and a state estimation unit that acquires characteristic values ​​of the head to which the nozzle is attached and in an operating state and estimates whether the head is in a state related to a malfunction based on the acquired characteristic value of the head and the first threshold, and the data set consists of multiple characteristic values ​​of the head that exceed a reference value.

[0011] For example, equipment logs of the head when the equipment performs a predetermined operation (e.g., production) using a head with a nozzle attached thereto are accumulated in the equipment, and a first threshold for estimating whether the head is in a state related to malfunction is generated based on a data set consisting of multiple characteristic values ​​(e.g., a large number of characteristic values) of the head included in such equipment logs. Then, the characteristic values ​​of the head in the equipment that is currently performing the predetermined operation and in operation are acquired, and the acquired characteristic values ​​are compared with the first threshold to estimate whether the head is currently in a state related to malfunction. In the present disclosure, the threshold for estimating whether the head is in a state related to malfunction is not empirically obtained, but is objectively generated based on the equipment logs, so that the accuracy of detection of a head that requires maintenance can be improved. In addition, the multiple characteristic values ​​of the head included in the equipment logs are data that can be acquired without making mechanical modifications to the equipment, etc. Therefore, the accuracy of detection of a head that requires maintenance can be improved without making mechanical modifications to the equipment, etc.

[0012] In addition, the threshold generation unit may allocate an amount of change in the state of the head calculated by comparing multiple characteristic values ​​of the head included in the equipment log with the reference value as learning data to multiple clusters, and generate the first threshold based on the characteristic value of the head in one of the multiple clusters having the smallest amount of change in the state.

[0013] For example, if the head is not holding the object correctly, the amount of state change tends to be large, and if the head is in a state related to a malfunction, the amount of state change tends to be small. In other words, the characteristic value of the head in a cluster with a large amount of state change is likely to be the characteristic value when the head is not in a malfunction, and the characteristic value of the head in a cluster with a small amount of state change is likely to be the characteristic value when the head is in a state related to a malfunction. Therefore, by generating the first threshold based on the characteristic value of the head in the cluster with the smallest amount of state change, it is possible to further improve the accuracy of detecting a head requiring maintenance.

[0014] The threshold generation unit may further acquire an inspection log of the head main body part to which the nozzle is not attached, and generate a second threshold value based on a plurality of characteristic values ​​of the head main body part included in the inspection log, and when the state estimation unit estimates that the head is in a state related to a malfunction, it may acquire an inspection result of the head main body part to which the nozzle is not attached, and estimate whether the nozzle is in a malfunction state or the head main body part is in a malfunction state based on the inspection result and the second threshold value. For example, the plurality of characteristic values ​​of the head main body part are data measured by removing the nozzle from the head in which the characteristic value of the head to which the nozzle is attached exceeds the reference value, and the threshold generation unit may generate the second threshold value based on the first threshold value by linear regression using the plurality of characteristic values ​​of the head to which the nozzle is attached and the plurality of characteristic values ​​of the head main body part corresponding to the plurality of characteristic values ​​as learning data.

[0015] For example, the head body inspection log of the head body when the nozzle is removed from the head is stored in the equipment, and when the head is estimated to be in a malfunction, a second threshold for estimating whether the nozzle is in a malfunction or the head body is in a malfunction is generated based on multiple characteristic values ​​(e.g., a large number of characteristic values) of the head body contained in such an inspection log. Then, the inspection result of the head body when the nozzle is removed from the head estimated to be in a malfunction-related state (specifically, the latest characteristic value of the head body) is obtained, and the obtained inspection result is compared with the second threshold to estimate whether the nozzle is in a malfunction or the head body is in a malfunction. In this way, the cause of the malfunction of the head requiring maintenance can be estimated.

[0016] Furthermore, the state estimation unit may estimate that the head main body is in a malfunction when the inspection result of the head main body exceeds the second threshold value. Furthermore, the state estimation unit may estimate that the nozzle is in a malfunction when the inspection result of the head main body does not exceed the second threshold value.

[0017] In this way, if the inspection result of the head main body exceeds the second threshold value, it can be assumed that the head main body is in a malfunctioning state, and if the inspection result of the head main body does not exceed the second threshold value, it can be assumed that the nozzle is in a malfunctioning state.

[0018] In addition, if the condition estimation unit estimates that the head main body is in a malfunction, it may use a malfunction factor estimation table generated by correlation analysis using the factor estimation value calculated from the inspection log and the malfunction factors of the head main body as learning data to estimate the malfunction factor of the head main body based on the factor estimation value calculated from the inspection results of the head main body.

[0019] For example, a factor estimation value is calculated for each of a plurality of characteristic values ​​of the head main body included in the inspection log, and a malfunction factor estimation table is generated in which a malfunction factor is associated with each calculated factor characteristic value. Then, a factor estimation value is calculated from the latest inspection result of the head main body in which the nozzle is removed from the head estimated to be in a malfunction-related state, and the factor estimation value is collated with the malfunction factor estimation table, thereby making it possible to estimate the malfunction factor of the head main body.

[0020] Furthermore, the factor estimate value calculated from the inspection result of the head main body may be calculated based on a statistical value of the inspection log in which the head main body is determined to be in a normal state.

[0021] In this way, based on the statistical values ​​of the inspection log in which the head body is judged to be in a normal state, a factor estimate can be calculated for the latest inspection result of the head body in which the nozzle is removed from the head that is estimated to be in a state related to the malfunction. For example, a unit space indicating the range of the normal state can be generated from the inspection log in which the head body is judged to be in a normal state, and the Mahalanobis distance can be used as the factor estimate.

[0022] The characteristic value may be a measurement result of a flow rate or pressure in an air path of the head main body when air is supplied from an air source of the head main body at a positive pressure or a negative pressure.

[0023] With this, by using the measurement results of the flow rate or pressure in the air path of the head main body, it is possible to estimate whether or not the head is in a state related to a malfunction, whether or not the head is in a malfunctioning state, the cause of the malfunction in the head, or the cause of the malfunction in the head main body.

[0024] The vehicle may further include an output unit that outputs information based on the estimation result of the state estimation unit.

[0025] This makes it possible to take action in accordance with the estimation result of the state estimation unit.

[0026] The information may also include information indicating that the head is in a malfunction-related state or that the head is in a malfunction state.

[0027] This allows the equipment maintenance personnel or the like to recognize that the head is in a malfunction-related state or that the head is in a malfunctioning state.

[0028] The information may also include details of maintenance for the head that is presumed to be in a malfunction.

[0029] This makes it possible to carry out maintenance according to the maintenance content for the head that is estimated to be in a malfunction.

[0030] The information may also be output to an equipment maintenance planning unit that manages a maintenance plan for maintaining the equipment.

[0031] This allows the equipment maintenance planning unit to manage the equipment maintenance plan in accordance with the output information.

[0032] The mounting system of the present disclosure comprises a head having a head main body to which a nozzle configured to hold an object is attached, a measurement unit that measures characteristic values ​​of the head, and the above-mentioned state estimation device that manages the state of the head.

[0033] This makes it possible to provide a mounting system that can improve the accuracy of detecting heads that require maintenance.

[0034] The state estimation method disclosed herein is a state estimation method for managing the state of a head in equipment that is equipped with a head having a head main body to which a nozzle configured to hold an object is attached, and that holds the object with the head to perform a specified task, and includes a threshold generation step of acquiring an equipment log of the head to which the nozzle is attached and generating a first threshold based on a data set consisting of multiple characteristic values ​​of the head included in the equipment log, and a state estimation step of acquiring characteristic values ​​of the head to which the nozzle is attached and in an operating state, and estimating whether the head is in a state related to a malfunction based on the characteristic values ​​of the head and the first threshold, wherein the data set consists of multiple characteristic values ​​of the head that exceed a reference value.

[0035] This makes it possible to provide a state estimation method that can improve the accuracy of detecting heads that require maintenance.

[0036] The embodiments described below are all comprehensive or specific examples. The numerical values, shapes, materials, components, the arrangement and connection of the components, steps, and the order of steps shown in the following embodiments are merely examples and are not intended to limit the present disclosure.

[0037] (Embodiment) Hereinafter, the embodiment will be described with reference to FIG. 1 to FIG.

[0038] First, a state estimating device 100 according to an embodiment will be described.

[0039] FIG. 1 is a diagram illustrating an example of a configuration of a state estimating device 100 according to an embodiment.

[0040] The state estimation device 100 is a device that manages the state of a head in a facility. The facility is equipped with a head configured to hold an object (specifically, a head having a head main body configured to hold an object), and holds the object with the head to perform a predetermined operation, for example, a component mounting device. For example, a nozzle is attached to the head (head main body), and the nozzle holds the object. The component mounting device holds a component as the object, and performs mounting work of the held component on a board or the like as a predetermined operation (i.e., production of a mounting board or the like). For example, the state estimation device 100 is a computer (server, etc.) provided in a facility separate from the facility in which the facility is installed, but may be provided in the facility in which the facility is installed. In addition, the state estimation device 100 may be a computer provided in one housing, or may be divided into two or more housings and realized by two or more computers.

[0041] The state estimation device 100 includes a threshold generation unit 110, a state estimation unit 120, and an output unit 130. The state estimation device 100 is realized by a computer including a processor, a memory, etc. The threshold generation unit 110, the state estimation unit 120, and the output unit 130 are realized by the processor operating in accordance with a program stored in the memory.

[0042] The threshold value generating unit 110 acquires an equipment log of the head to which the nozzle is attached, and generates a first threshold value based on a data set consisting of multiple characteristic values ​​of the head included in the equipment log. The data set consists of multiple characteristic values ​​of the head that exceed a reference value. The reference value will be described later. In other words, the equipment log of the head to which the nozzle is attached is data that records the operation results (errors or events, etc.) of the head when the equipment holds an object with the head and performs a predetermined operation (specifically, a mounting operation in which a component held by a nozzle attached to the head is mounted on a board, etc.). The characteristic value of the head is a measurement result of the flow rate or pressure in the air path of the head. Specifically, the characteristic value of the head is a measurement result of the flow rate or pressure in the air path of the nozzle and the head main body when air is supplied from the air source with positive or negative pressure. The air source is provided in the component mounting device or outside the component mounting device. Here, the characteristic value of the head will be described as a flow rate value. The equipment performing a predetermined operation, that is, during mounting work, can be called "online," so the characteristic value of the head included in the equipment log is called the online flow rate value. The threshold value generating unit 110 acquires chronologically older online flow rate values ​​from the equipment log, and therefore the head characteristic values ​​input to the threshold value generating unit 110 are referred to as past online flow rate values.

[0043] Moreover, the threshold generating unit 110 acquires an inspection log of the head main body part to which the nozzle is not attached, and generates a second threshold based on the multiple characteristic values ​​of the head main body part included in the inspection log. The multiple characteristic values ​​of the head main body part are data measured by removing the nozzle from the head to which the nozzle is attached and the characteristic value of the head exceeds the reference value. The characteristic value exceeds the reference value when the characteristic value exceeds the lower limit or upper limit of the normal range. When the reference value is the lower limit, the characteristic value exceeds the reference value when the characteristic value falls below the reference value. When the reference value is the upper limit, the characteristic value exceeds the reference value when the characteristic value exceeds the reference value. In other words, the inspection log of the head main body part to which the nozzle is not attached is a log of data of the head main body part when the equipment is not holding an object by the head and is not performing a specified operation (specifically, not performing mounting work). Here, the data is the inspection result when an inspection is performed on the head main body part. Since the equipment is not performing a specified operation, that is, not performing mounting work, can be called "offline", the characteristic value of the head main body part included in the inspection log is called an offline flow rate value. Since the threshold value generating unit 110 obtains chronologically older offline flow rate values ​​from the inspection log, the characteristic values ​​of the head main body input to the threshold value generating unit 110 are called past offline flow rate values.

[0044] Furthermore, the threshold generating unit 110 generates a malfunction cause estimation table in which the cause estimation value calculated from the inspection log and the malfunction cause based on the maintenance record of the head main body are associated with each other.

[0045] The details of the threshold generating unit 110 will be described later.

[0046] The state estimation unit 120 has a first estimation unit 121, a second estimation unit 122, and a factor estimation unit 123, and the first estimation unit 121, the second estimation unit 122, and the factor estimation unit 123 estimate the state of the head.

[0047] The first estimation unit 121 acquires characteristic values ​​of a head in operation with a nozzle attached, and estimates whether the head is in a state related to malfunction based on the acquired characteristic values ​​of the head and the first threshold generated by the threshold generation unit 110. A state related to malfunction is a state in which there may be a sign of malfunction before an abnormal state that causes production by the equipment to be stopped is reached. The first estimation unit 121 acquires characteristic values ​​of a head to which a nozzle newly output from the equipment performing a predetermined operation is attached. The characteristic value of the head acquired by the first estimation unit 121 is called the latest online flow rate value in contrast to the past online flow rate value. Details of the first estimation unit 121 will be described later.

[0048] When it is estimated that the head is in a state related to a malfunction, the second estimation unit 122 acquires the inspection result of the head main body unit to which the nozzle is not attached, and estimates whether the nozzle is in a malfunction state or the head main body unit is in a malfunction state based on the inspection result and the second threshold value. After it is estimated that the head is in a state related to a malfunction, the second estimation unit 122 acquires the inspection result of the flow rate of the air path of the head main body unit when the production of the equipment is stopped, the nozzle is removed from the head main body unit, and the equipment is not performing a predetermined operation. The inspection result of the head main body unit acquired by the second estimation unit 122 is called the latest offline flow rate value in contrast to the past offline flow rate value. The second estimation unit 122 will be described in detail later.

[0049] The cause estimation unit 123 estimates the cause of the malfunction of the head main body based on a cause estimation value calculated from the inspection result of the head main body and a malfunction cause estimation table. The cause estimation unit 123 will be described in detail later.

[0050] The output unit 130 outputs information based on the estimation result of the state estimation unit 120.

[0051] The output unit 130 outputs information to a maintenance person, for example, and the information output from the output unit 130 includes maintenance instructions to the maintenance person.

[0052] The information output from the output unit 130 also includes maintenance details for the head estimated to be in a malfunctioning state. The information including the maintenance details output from the output unit 130 is output, for example, to an equipment maintenance planning unit that manages equipment maintenance plans. For example, the information may be output to a maintenance device that maintains the equipment. For example, the maintenance details for the head include the serial number of the head to be maintained, the installation location of the head to be maintained, the details of the maintenance work, the person in charge, or the maintenance deadline, etc.

[0053] The information output from the output unit 130 may include information indicating that the head is in a state related to malfunction or that the head is in a malfunction state. The information including these pieces of information output from the output unit 130 is displayed, for example, in a form recognizable by a maintenance personnel in the equipment connected to the state estimation device 100 or in the state estimation device 100. For example, based on the estimation result by the first estimation unit 121, characters such as "The head may be malfunctioning" or "Inspection of the head is required" are displayed on a display or the like, output from a speaker or the like, or a buzzer that is previously recognized to indicate these contents is sounded or a lamp is turned on. Also, for example, based on the estimation result by the second estimation unit 122, characters such as "The head main body is malfunctioning" or "The nozzle is malfunctioning" are displayed on a display or the like, output from a speaker or the like, or a buzzer that is previously recognized to indicate these contents is sounded or a lamp is turned on. Also, for example, based on the result of estimation by the cause estimation unit 123, text such as "A filter clog has occurred in the head main body" or "An air hose has broken in the head main body" may be displayed on a display or output from a speaker, or a buzzer or lamp that is known in advance to indicate such content may sound or light up. These displays, speakers, buzzers, etc. may be provided in the facility where the equipment is installed, and these alerts may be notified directly to the maintenance personnel of the facility.

[0054] By outputting information based on the estimation result of the state estimation unit 120, it is possible to take action according to the estimation result of the state estimation unit. For example, it is possible to make a maintenance person of the equipment recognize that the head is in a state related to a malfunction or that the head is in a malfunctioning state, and it is possible to carry out maintenance according to the maintenance content for the head that is estimated to be in a malfunctioning state or a state related to a malfunction.

[0055] For example, the information output from the output unit 130 may include information on the head that is the subject of inspection based on the estimation result of the first estimation unit 121. The output unit 130 may output a maintenance instruction to instruct inspection of the head that is the subject of inspection based on a maintenance plan assigned to a time outside the time when the equipment performs a predetermined operation. The state estimation device 100 can notify the maintenance personnel that the head needs to be inspected. The time outside the time when the equipment performs a predetermined operation is, for example, a time when the equipment is not producing. Since the head inspection needs to be performed with the nozzle removed, the head inspection is performed during the time when the equipment is not producing. Note that the time when the equipment is not producing may be the timing of switching the type of product to be produced. This allows the head that is the subject of inspection to be inspected outside the time when the equipment performs a predetermined operation (for example, production). Furthermore, the head inspection may be performed outside the equipment. In this case, the head that is the subject of inspection can be inspected during the time when the equipment is producing.

[0056] As described above, the facility may be a component mounting device, and the state estimation device 100 may configure a mounting system together with the component mounting device. Here, a mounting system 2 according to an embodiment will be described.

[0057] FIG. 2A is a configuration diagram showing an example of a mounting system 2 according to an embodiment.

[0058] The mounting system 2 is a system for mounting components on a board or the like, and includes a component mounting apparatus 300 having a head 310 and a control unit 330, and a state estimation apparatus 100.

[0059] The head 310 has a head main body 311 and a sensor 320, and the nozzle 312 can be attached to the head main body 311. The sensor 320 is an example of a measuring unit that measures a characteristic value of the head 310 (head main body 311). The sensor 320 is a flow sensor that measures a flow rate in an air path of the head main body 311. The sensor 320 measures an online flow rate when the component mounting device 300 is performing a predetermined operation with the head 310 to which the nozzle 312 is attached holding an object, and an offline flow rate when the component mounting device 300 is not performing a predetermined operation without the nozzle 312 attached to the head 310. The head 310 may also have a vacuum sensor 340 that measures a vacuum pressure in the air path of the head main body 311 (see FIG. 2B).

[0060] The control unit 330 controls the head 310. Details of the control of the head 310 will be described later. The control unit 330 also acquires an online flow rate value and an offline flow rate value measured by the sensor 320. The control unit 330 outputs the online flow rate value and the offline flow rate value to the state estimation device 100 when the state estimation device 100 generates a first threshold value, a second threshold value, and a malfunction factor estimation table. The control unit 330 also outputs the latest online flow rate value and the latest offline flow rate value to the state estimation device 100 when the state estimation device 100 estimates the state of the head 310.

[0061] Here, a specific example of the component mounting apparatus 300 will be described with reference to FIG. 2B.

[0062] Fig. 2B is a configuration diagram showing an example of a component mounting apparatus 300 according to an embodiment. In Fig. 2B, the X direction (the direction perpendicular to the paper surface in Fig. 2B) of the board transport direction and the Y direction (the left-right direction in Fig. 2B) perpendicular to the board transport direction are shown as two axial directions perpendicular to each other in a horizontal plane. In addition, the Z direction (the up-down direction in Fig. 2B) is shown as a height direction perpendicular to the horizontal plane.

[0063] The component mounting apparatus 300 has a function of mounting a component D on a board B. A board transport mechanism 12 provided on the upper surface of a base 11 transports the board B in the X direction and positions and holds it. A head moving mechanism 13 moves a head 310 mounted via a plate 13a in the X and Y directions. A nozzle 312 is mounted on the lower end of the head 310.

[0064] A plurality of tape feeders 16 are attached to the top of a carriage 17 coupled to the base 11 on the side of the board transport mechanism 12, lined up in the X direction. A carrier tape 18 storing components D to be supplied to the component mounting device 300 is wound and stored on a reel 19 and held on the carriage 17. The carrier tape 18 inserted into the tape feeder 16 is pitch-fed at regular intervals by a tape feed mechanism 16a built into the tape feeder 16. As a result, the components D stored on the carrier tape 18 are sequentially supplied to a component supply port 16b provided on the top of the tape feeder 16.

[0065] 2B, component mounting apparatus 300 includes a control unit 330 that controls board conveying mechanism 12, head moving mechanism 13, head 310, and tape feeder 16 to execute a component mounting operation. In the component mounting operation, control unit 330 controls head moving mechanism 13 to move head 310 to above tape feeder 16, and vacuum-adsorbs and picks up component D supplied by tape feeder 16 to component supply port 16b with nozzle 312 (arrow a). Next, control unit 330 controls head moving mechanism 13 to move head 310 holding component D to above board B held by board conveying mechanism 12, and mounts component D at a predetermined component mounting position Ba on board B (arrow b).

[0066] 2B, head 310 includes vacuum sensor 340 that measures the degree of vacuum when nozzle 312 vacuum-sucks component D. The presence or absence of a vacuum error such as a suction failure (suction error) or a malfunction of head 310 can be detected from the result of measurement of the degree of vacuum of nozzle 312 by vacuum sensor 340 during component holding operation. For example, when nozzle 312 normally picks up component D, the degree of vacuum becomes smaller than a predetermined value, and when nozzle 312 cannot hold component D or picks up component D in an abnormal position, the degree of vacuum does not decrease to the predetermined value. Therefore, control unit 330 can detect a vacuum error by determining whether the degree of vacuum measured by vacuum sensor 340 exceeds a predetermined value.

[0067] 2B, a board recognition camera 20 with its optical axis oriented downward is attached to plate 13a. Board recognition camera 20 moves in the X and Y directions together with head 310 by head moving mechanism 13. Board recognition camera 20 moves above tape feeder 16 and captures an image of component D supplied to the supply position of component supply port 16b.

[0068] The control unit 330 performs image recognition on the imaging results and calculates the amount of deviation of the actually supplied component D from the expected regular supply position. Furthermore, the control unit 330 corrects the suction position (stop position of the head 310) when the nozzle 312 picks up the component D, or the supply position of the component D on the tape feeder 16, based on the calculated amount of deviation of the supply position. Furthermore, the control unit 330 performs image recognition on the imaging results and detects a supply error in which the component D cannot be recognized because the component D is not supplied to the component supply port 16b.

[0069] 2B, a component recognition camera 21 with its optical axis oriented upward is attached to the upper surface of the base 11 between the board transport mechanism 12 and the tape feeder 16. The component recognition camera 21 captures an image of the underside of the component D held by the nozzle 312 (or the nozzle 312 that was unable to hold the component D) when the nozzle 312 that picked up the component D passes above.

[0070] The control unit 330 performs image recognition on the imaging results to determine whether the posture of the component D held by the nozzle 312 is abnormal, or whether a recognition error has occurred that prevents the component D that should be held by the nozzle 312 from being recognized. The control unit 330 also performs image recognition on the imaging results to calculate the pickup position deviation amount of the component D actually picked up by the nozzle 312 that has shifted from the expected regular pickup position. When mounting the component D at the component mounting position Ba on the board B, the control unit 330 executes mounting position correction and mounting posture correction based on the pickup position deviation amount.

[0071] In this manner, the component mounting apparatus 300 includes the tape feeder 16, the head 310, and the nozzle 312. The control unit 330 transmits the detected pickup error, supply error, and recognition error occurrence status, the calculated supply position deviation amount, the correction amount of the pickup position of the component D by the nozzle 312, the pickup position deviation amount, the mounting position correction amount, and the mounting attitude correction amount, to a management computer or the like in association with the device status (normal, abnormal, etc.). The control unit 330 also transmits the measurement results of various sensors provided in each mechanism of the component mounting apparatus 300, such as the degree of vacuum by the vacuum sensor 340, to the state estimation apparatus 100 in association with, for example, the device status (normal, abnormal, etc.).

[0072] Here, the configuration of head main body 311 will be described with reference to FIGS. 3A and 3B.

[0073] FIG. 3A is a schematic diagram showing the configuration of head main body 311 according to the embodiment during vacuuming.

[0074] FIG. 3B is a schematic diagram showing the configuration of head main body 311 according to the embodiment during blowing.

[0075] 3A and 3B, in addition to the head main body 311, a nozzle 312 attached to the head main body 311, and an air source 319 that supplies air to the head main body 311 are also shown.

[0076] The head main body 311 includes a nozzle holder 313 , a blow valve 314 , a vacuum valve 315 , a common air path 316 , a blow air path 317 , and a vacuum air path 318 .

[0077] A nozzle 312 is attached to the nozzle holder 313, and a component is picked up through the nozzle 312.

[0078] The air source 319 is a device that supplies air under positive or negative pressure.

[0079] The blow valve 314 is a valve that controls the supply of air to the nozzle holder 313 when the air source 319 is supplying air at positive pressure (that is, during blowing).

[0080] The vacuum valve 315 is a valve that controls the suction of air from the nozzle holder 313 when the air source 319 supplies air at negative pressure (that is, during vacuum).

[0081] Common air path 316 is an air path through which air from air source 319 passes when air source 319 supplies air at positive pressure, and through which air from nozzle holder 313 passes when air source 319 supplies air at negative pressure. In other words, common air path 316 is a path through which air passes commonly during blowing and vacuuming.

[0082] The blow air path 317 is an air path through which air from the air source 319 passes when the air source 319 supplies air at positive pressure.

[0083] The vacuum air path 318 is an air path through which air from the nozzle holder 313 passes when the air source 319 supplies air at negative pressure.

[0084] The blow valve 314 and the vacuum valve 315 have a switching mechanism for switching the air path between blowing and vacuuming. For example, as shown in Fig. 3A, during vacuuming, the switching mechanisms in the blow valve 314 and the vacuum valve 315 are controlled so that the vacuum air source is connected to the nozzle holder 313 via the vacuum air path 318 and the common air path 316. For example, as shown in Fig. 3B, during blowing, the switching mechanisms in the blow valve 314 and the vacuum valve 315 are controlled so that the blow air source is connected to the nozzle holder 313 via the blow air path 317 and the common air path 316.

[0085] When a component is to be picked up by the nozzle 312 attached to the nozzle holder 313, the vacuum valve 315 is controlled to suck air from the nozzle 312 to the air source 319 via the common air path 316 and the vacuum air path 318. When the suction of the component by the nozzle 312 attached to the nozzle holder 313 is to be released, the vacuum valve 315 is controlled to close the path from the air source 319 to the vacuum air path 318, and the suction of the component by the nozzle 312 is released. Even if the nozzle 312 is not attached to the nozzle holder 313 and the component cannot be picked up, air is sucked in order to obtain the inspection results of the head main body 311 (i.e., the offline flow rate).

[0086] When air is to be supplied, the blow valve 314 is controlled to supply air from the air source 319 to the nozzle 312 via the blow air path 317 and the common air path 316. Even when the nozzle 312 is not attached to the head main body 311, air is supplied to obtain the inspection results of the head main body 311 (i.e., the offline flow rate).

[0087] The sensor 320 is a flow rate sensor, which measures the flow rate in the air paths (specifically, the common air path 316 and the blow air path 317) when air is supplied from the air source 319 to the nozzle holder 313, and measures the flow rate in the air paths (specifically, the common air path 316 and the vacuum air path 318) when air is sucked from the nozzle holder 313 to the air source 319. In addition, by controlling the air source 319, the blow valve 314, and the vacuum valve 315, the common air path 316, the blow air path 317, and the vacuum air path 318 can be put into a vacuum state.

[0088] Next, the operation of the state estimating device 100 will be described.

[0089] 4 is a diagram for explaining the operation of the state estimation device 100 according to the embodiment. The phases in which the state estimation device 100 operates include the operation of the threshold generation unit 110 in the learning phase and the operation of the state estimation unit 120 in the estimation phase. The operation contents of the state estimation device 100 include an online flow rate change detection block in which the threshold generation unit 110 generates a first threshold and the first estimation unit 121 performs estimation using the generated first threshold, a flow rate change factor unit estimation block in which the threshold generation unit 110 generates a second threshold and the second estimation unit 122 performs estimation using the generated second threshold, and a head malfunction factor location estimation block in which the threshold generation unit 110 generates a malfunction factor estimation table and the factor estimation unit 123 performs estimation using the generated malfunction factor estimation table.

[0090] First, the online flow rate change detection block will be described.

[0091] In the online flow rate change detection block in the learning phase, the threshold value generation unit 110 acquires an equipment log from the component mounting device 300. The equipment log includes past online flow rate values. The past online flow rate values ​​acquired in the online flow rate change detection block are online flow rate values ​​when the vacuum sensor 340 detects a vacuum error in the air path. The vacuum error threshold value for determining whether the vacuum sensor 340 detects a vacuum error is, for example, an empirically determined value, and depending on the environment in which the component mounting device 300 is installed, the vacuum error threshold value may not be an accurate value for the measurement value of the vacuum sensor 340. For this reason, even if the measurement value of the vacuum sensor 340 reaches the vacuum error threshold value, there are cases in which the head 310 is not actually malfunctioning, and there are cases in which the measurement value of the vacuum sensor 340 does not reach the vacuum error threshold value but the head 310 is actually malfunctioning, resulting in a problem that the detection accuracy of the head 310 requiring maintenance is insufficient.

[0092] Therefore, the threshold value generating unit 110 uses the vacuum error threshold value to generate an online flow rate reduction determination threshold value that can estimate the malfunction of the head 310 more accurately than the vacuum error threshold value. Note that the online flow rate reduction determination threshold value is an example of a first threshold value, and the vacuum error threshold value is an example of a reference value to be compared with the online flow rate value.

[0093] For example, the threshold generating unit 110 allocates the difference between the online flow rate value of the head 310, calculated by comparing the past online flow rate value with the vacuum error threshold, to multiple clusters as learning data, and generates an online flow rate reduction judgment threshold based on the online flow rate value in one cluster among the multiple clusters with the smallest difference. The difference between the online flow rate value and the vacuum error threshold is an example of a state change amount. Here, a method for generating the online flow rate reduction judgment threshold will be described with reference to FIG. 5.

[0094] Fig. 5 is a diagram for explaining a method for generating the online flow rate reduction determination threshold value. Fig. 5 plots the online flow rate values ​​included in the equipment log, with the horizontal axis representing the online flow rate value and the vertical axis representing the difference between the online flow rate value and the vacuum error threshold value.

[0095] The threshold value generating unit 110 classifies the acquired past online flow rate value. For example, the threshold value generating unit 110 classifies the difference between the online flow rate value and the vacuum error threshold value when a vacuum error is detected into two classes by applying the k-means method. For example, as shown in FIG. 5, the classes are classified into class A in which the difference between the online flow rate value and the vacuum error threshold value is large, and class B in which the difference between the online flow rate value and the vacuum error threshold value is small. When the head 310 does not properly pick up a component, the air path (specifically, the common air path 316 and the vacuum air path 318) communicates with the outside, so a large amount of air is sucked in, and the above difference tends to be large. Therefore, class A is a class in which it is highly likely that the head 310 does not properly pick up a component, in other words, a class in which it is highly likely that the head 310 itself is not malfunctioning. On the other hand, when the head 310 properly picks up a component, the amount of sucked air is small, and the above difference tends to be small. Therefore, class B is a class in which it is highly likely that the head 310 is malfunctioning. Therefore, the threshold generator 110 generates an online flow rate reduction judgment threshold based on the online flow rate value in class B where the difference is the smallest. Specifically, the threshold generator 110 subtracts 1 from the minimum online flow rate value in class B (point P: -70 in FIG. 5) to set the online flow rate reduction judgment threshold (dashed line th: -71 in FIG. 5). When generating the online flow rate reduction judgment threshold, the value to be subtracted from the minimum online flow rate value in the class where the difference is the smallest is not limited to 1 and may be selected as appropriate.

[0096] In the online flow rate change detection block in the estimation phase, the first estimation unit 121 acquires the latest online flow rate value of the head 310 to which the nozzle 312 is attached, and estimates whether or not the head 310 is in a state related to a malfunction based on the acquired online flow rate value and an online flow rate reduction judgment threshold.

[0097] If the latest acquired online flow rate value exceeds the online flow rate reduction determination threshold (specifically, if the absolute value of the online flow rate value is smaller than the absolute value of the online flow rate reduction determination threshold), the first estimation unit 121 estimates that the head 310 is in a state related to a malfunction, and the output unit 130 outputs that fact. For example, a maintenance person or the like is notified that the head 310 is estimated to be in a state related to a malfunction and determines whether to inspect the head 310.

[0098] The online flow rate reduction determination threshold is an estimated value derived by classifying past online flow rate values ​​as learning data, for indirectly determining whether or not there is an abnormality such as a blockage in the flow system. In the online flow rate change detection block, such an online flow rate reduction determination threshold is used to estimate whether or not the head 310 is in a state related to a malfunction, so that it is possible to improve the accuracy of detecting the head 310 requiring maintenance compared to when a vacuum error threshold is used to estimate whether or not the head 310 is in a state related to a malfunction.

[0099] Then, upon receiving the information about the malfunction of the head output from the output unit 130, the maintenance person inspects the head 310. For example, when the component mounting apparatus 300 is not performing a predetermined operation (that is, for example, when production is stopped), the nozzle 312 is removed from the head main body 311, and the head main body 311 without the nozzle 312 attached is inspected. Specifically, the latest offline flow rate of the head main body 311 is measured. The latest measured offline flow rate value is used for estimation by the second estimator 122 in the flow rate change factor unit estimation block.

[0100] Next, the flow rate change factor unit estimation block will be described.

[0101] In the flow rate change factor unit estimation block in the learning phase, the threshold value generation unit 110 acquires an inspection log from the component mounting device 300. The inspection log includes past offline flow rate values. The inspection log acquired in the flow rate change factor unit estimation block includes past offline flow rate values ​​when the vacuum sensor 340 detected a vacuum error in the air path.

[0102] For example, the threshold generating unit 110 acquires an inspection log of the head main body 311 to which the nozzle 312 is not attached, and generates an offline flow rate reduction determination threshold based on a past offline flow rate value of the head main body 311 included in the inspection log. The offline flow rate reduction determination threshold is an example of a second threshold. Here, a method for generating the offline flow rate reduction determination threshold will be described with reference to FIG. 6.

[0103] Fig. 6 is a diagram for explaining a method for generating an offline flow rate reduction determination threshold value. Fig. 6 plots combinations of online flow rate values ​​and offline flow rate values ​​when a vacuum error is detected, which are included in the equipment log, with the horizontal axis representing the online flow rate value and the vertical axis representing the offline flow rate value.

[0104] The threshold value generating unit 110 calculates a regression line from each plotted point as shown in FIG. 6. Since there is a correlation between the online flow rate value acquired when a vacuum error occurs and the offline flow rate value acquired when the nozzle 312 is removed from the head 310 and the head main body 311 is inspected at that time, there is also a correlation between the online flow rate reduction judgment threshold and the offline flow rate reduction judgment threshold. Therefore, the threshold value generating unit 110 sets the offline flow rate value corresponding to the online flow rate reduction judgment threshold as the offline flow rate reduction judgment threshold based on the calculated regression line. Specifically, the threshold value generating unit 110 generates the offline flow rate value -90.5 on the vertical axis corresponding to the online flow rate value -71 (i.e., the online flow rate reduction judgment threshold) on the horizontal axis on the regression line as the offline flow rate reduction judgment threshold as shown in FIG. 6.

[0105] In this way, the threshold generation unit 110 generates an offline flow rate reduction judgment threshold based on the online flow rate reduction judgment threshold by linear regression using multiple online flow rate values ​​of the head 310 to which the nozzle 312 is attached and multiple offline flow rate values ​​of the head main body unit 311 corresponding to the multiple online flow rate values ​​as learning data.

[0106] In the flow rate change factor unit estimation block in the estimation phase, when the first estimation unit 121 estimates that the head 310 is in a state related to a malfunction, the second estimation unit 122 acquires the inspection results (i.e., the latest offline flow rate value) of the head main body unit 311 to which the nozzle 312 is not attached, and estimates whether the nozzle 312 is in a malfunctioning state or whether the head main body unit 311 is in a malfunctioning state based on the acquired inspection results and the offline flow rate reduction judgment threshold.

[0107] The second estimation unit 122 estimates that the head main body 311 is in a malfunction state when the inspection result of the head main body 311 exceeds the offline flow rate reduction judgment threshold (specifically, the absolute value of the offline flow rate value is smaller than the absolute value of the offline flow rate reduction judgment threshold). This is because it can be estimated that the head main body 311 side is in a malfunction state, not the nozzle 312 side, because the inspection result of the head main body 311 exceeds the offline flow rate reduction judgment threshold even when the nozzle 312 is removed. For example, when air leakage or air clogging occurs in the air path of the head main body 311, the inspection result of the head main body 311 exceeds the offline flow rate reduction judgment threshold even when the nozzle 312 is removed, and it can be estimated that the head main body 311 side is in a malfunction state. On the other hand, the second estimation unit 122 estimates that the nozzle 312 is in a malfunction state when the inspection result of the head main body 311 does not exceed the offline flow rate reduction judgment threshold. This is because by removing the nozzle 312, it can be presumed that the inspection result of the head main body 311 does not exceed the offline flow rate reduction judgment threshold, and it can be presumed that the malfunction is not on the head main body 311 side, but on the nozzle 312 side. For example, the output unit 130 outputs that the nozzle 312 is in a malfunction, and a maintenance person for the equipment or the like can perform maintenance on the nozzle 312.

[0108] The offline flow rate reduction judgment threshold is an estimated value derived by linear regression using past offline flow rate values ​​as learning data, for indirectly judging the presence or absence of an abnormality such as a clog in the flow system. The flow rate change factor unit estimation block uses such an offline flow rate reduction judgment threshold to estimate whether the nozzle 312 or the head main body 311 is in a malfunction, and therefore the accuracy of the estimation can be improved.

[0109] Next, the head malfunction cause location estimation block will be described.

[0110] In the head malfunction factor location estimation block in the learning phase, the threshold generation unit 110 acquires an inspection log from the component mounting device 300. The inspection log includes waveform data of past offline flow rates. For example, the waveform data of past offline flow rates acquired in the head malfunction factor location estimation block includes waveform data of offline flow rates when the vacuum sensor 340 detects a vacuum error in the air path, as well as waveform data of offline flow rates in normal times when the vacuum sensor 340 does not detect a vacuum error in the air path. The threshold generation unit 110 generates a malfunction factor estimation table by correlation analysis using the factor estimation value calculated from the inspection log and the malfunction factor of the head main body 311 as learning data. The factor estimation value calculated from the inspection log and the malfunction factor estimation table will be described later.

[0111] In the head malfunction cause location estimation block in the estimation phase, when the second estimation unit 122 estimates that the head main body 311 is in a malfunction state, the cause estimation unit 123 uses a malfunction cause estimation table to estimate the malfunction cause of the head main body 311 based on a cause estimation value calculated from the inspection result of the head main body 311. Here, a method of estimating the malfunction cause of the head 310 will be described with reference to FIG.

[0112] Fig. 7 is a diagram for explaining a method for estimating a malfunction factor of the head 310. The upper side of Fig. 7 shows a method for generating an average vector for calculating a factor estimate value and a covariance matrix for calculating a factor estimate value from an inspection log in the threshold generating unit 110, and the lower side of Fig. 7 shows a method for estimating a malfunction factor of the head main body 311 using a factor estimate value calculated based on the average vector for calculating a factor estimate value and the covariance matrix for calculating a factor estimate value in the factor estimating unit 123.

[0113] 7, the threshold generator 110 acquires from the inspection log a waveform data set of past offline flow rates under normal conditions when the vacuum sensor 340 does not detect a vacuum error in the air path. A specific example of the waveform data will now be described with reference to FIG.

[0114] FIG. 8 is a graph showing an example of waveform data of the flow rate in the air path. FIG. 8 shows time series data of flow rate values ​​sampled at, for example, 256 points, with the horizontal axis representing time and the vertical axis representing flow rate. FIG. 8 shows, as an example, waveform data of the flow rate in the air path when the vacuum valve 315 is repeatedly turned on and off during vacuuming. Note that similar waveform data is obtained during blowing. In this embodiment, when waveform data of past offline flow rates is obtained, it is obtained as a waveform data set defined by an array as shown in the upper part of FIG. 7.

[0115] The waveform data of the flow measured by the sensor 320 has a waveform shape as shown in Fig. 8, making it difficult to compare the waveform data with each other. Therefore, as shown in the upper part of Fig. 7, the threshold generation unit 110 converts each of the waveform data sets of the past offline flow rates into a principal component vector by principal component analysis so as to make it possible to compare the characteristics of each of the waveform data of the multiple past offline flow rates with the characteristics of the waveform data of the latest offline flow rate. Then, the threshold generation unit 110 generates a factor estimate value calculation average vector and a factor estimate value calculation covariance matrix from the converted principal component vector.

[0116] The threshold generator 110 also calculates the Mahalanobis distance of each of the principal component vectors converted from the waveform data set of the past offline flow rate as a factor estimation value. For example, it is possible to know from the maintenance record that each of the principal component vectors, in other words, each of the waveform data sets, was obtained when the head main body 311 was experiencing a malfunction factor. Therefore, it is possible to associate the malfunction factor based on the maintenance record with the factor estimation value of the principal component vector corresponding to each of the waveform data sets of the past offline flow rate. In this way, the threshold generator 110 generates a malfunction factor estimation table in which the factor estimation value calculated from the inspection log is associated with the malfunction factor based on the maintenance record of the head main body 311.

[0117] As shown in the lower part of FIG. 7, the factor estimation unit 123 acquires waveform data of the latest offline flow rate and converts it into a principal component vector by principal component analysis. Then, the factor estimation unit 123 calculates the Mahalanobis distance of the converted principal component vector. The factor estimation unit 123 uses the calculated Mahalanobis distance as a factor estimation value and an index for estimating the malfunction factor of the head main body unit 311. In this way, the factor estimation value calculated from the inspection result of the head main body unit 311 is calculated based on the statistical value of the inspection log in which the head main body unit 311 is determined to be in a normal state (specifically, the average vector and the variance matrix generated from the statistical value of the inspection log). The factor estimation unit 123 estimates the malfunction factor of the head main body unit 311 by collating the factor estimation value corresponding to the calculated waveform data of the latest offline flow rate with the malfunction factor estimation table. For example, when a factor estimation value equivalent to the calculated factor estimation value is present in the malfunction factor estimation table, the factor estimation unit 123 estimates that the malfunction factor associated with the factor estimation value in the malfunction factor estimation table is the malfunction factor of the head main body unit 311. For example, the output unit 130 outputs the cause of the malfunction of the head main body 311, and a maintenance person for the equipment can carry out maintenance according to the cause of the malfunction of the head main body 311.

[0118] When the calculated factor estimation value is within the unit space (range of non-defective products), the head main body 311 may not be in a malfunctioning state, but the first estimation unit 121 estimates that the head 310 is in a malfunctioning state, and the second estimation unit 122 estimates that the head main body 311 is in a malfunctioning state, so that the head main body 311 may be in a malfunctioning state. Therefore, the factor estimation unit 123 may estimate that the head main body 311 may be in a malfunctioning state when the calculated factor estimation value is within the unit space. For example, the output unit 130 outputs that the head main body 311 may be in a malfunctioning state, and a maintenance person for the facility or the like can perform maintenance of the head main body 311.

[0119] The malfunction factor table is a correlation table generated by a correlation analysis between the factor estimation value obtained from the inspection log and the malfunction factor recorded in the maintenance record. The head malfunction factor location estimation block estimates the malfunction factor of the head main body 311 using this malfunction factor estimation table, so that the accuracy of the estimation can be improved.

[0120] Next, the operation between the state estimating device 100 and the maintenance staff of the facility will be described with reference to FIG.

[0121] FIG. 9 is a sequence diagram showing an example of the operation of state estimating device 100 and a maintenance technician according to the embodiment.

[0122] First, the state estimation device 100 performs learning in advance using past data (step S101). That is, the state estimation device 100 generates in advance an online flow rate reduction determination threshold, an offline flow rate reduction determination threshold, and a malfunction cause estimation table.

[0123] The state estimating device 100 periodically receives the latest online flow rate value from the component mounting device 300 (step S102), and performs processing in the online flow rate change detection block shown in FIG. 4 (step S103).

[0124] If there is no abnormality in the most recent online flow rate value received (i.e., if the most recent online flow rate value received does not exceed the online flow rate reduction determination threshold), the state estimation device 100 continues the processing in steps S102 and S103.

[0125] If the latest received online flow rate value is abnormal (i.e., if the latest received online flow rate value exceeds the online flow rate decrease determination threshold), the state estimation device 100 issues a flow rate change detection alert (step S104). For example, in this case, the state estimation device 100 outputs information for inspecting the head 310, specifically, an instruction to inspect the head 310. The timing of transmitting the instruction to inspect the head 310 can be appropriately determined.

[0126] The maintenance technician receives an instruction to inspect the head 310 (step S105) and inspects the head 310 (step S106). For example, the maintenance technician removes the nozzle 312 from the head main body 311 and inspects the head main body 311 (measures the latest offline flow rate).

[0127] The state estimating device 100 receives the latest offline flow rate value from the component mounting device 300 (step S107), and performs processing in the flow rate change factor unit estimating block shown in FIG. 4 (step S108).

[0128] If there is no abnormality in the latest received offline flow rate value (i.e., if the latest received online flow rate value does not exceed the offline flow rate reduction judgment threshold), the state estimation device 100 estimates that the nozzle 312 is in a malfunction, and notifies nozzle maintenance instruction information, which is information for instructing maintenance of the nozzle 312 (step S109).

[0129] The maintenance person receives the maintenance instruction for the nozzle 312 (step S110) and performs maintenance (step S111) for the nozzle 312. After completing the maintenance for the nozzle 312, the maintenance person registers the completion of the maintenance for the nozzle 312 (step S112).

[0130] On the other hand, if the latest received offline flow rate value is abnormal (i.e., if the latest received online flow rate value exceeds the offline flow rate decrease judgment threshold), the state estimation device 100 estimates that the head main body 311 is in a malfunction state, and performs processing in the head malfunction cause location estimation block shown in Fig. 4 (step S113). The state estimation device 100 estimates the malfunction cause of the head main body 311, and notifies head maintenance instruction information, which is information for instructing maintenance of the head main body 311 (step S114). For example, the head maintenance instruction information includes an instruction to maintain the head main body 311, specifically the malfunction cause of the head main body 311.

[0131] The maintenance technician receives the maintenance instruction for the head main body 311 (step S115) and performs maintenance on the head main body 311 (step S116). The maintenance instruction for the head main body 311 includes the cause of the malfunction of the head main body 311, so the maintenance technician can efficiently perform maintenance on the head main body 311 by focusing on the location causing the malfunction. After completing the maintenance of the head main body 311, the maintenance technician registers the completion of the maintenance of the head main body 311 (step S117).

[0132] As described above, for example, the equipment log of the head 310 when the component mounting device 300 performs a predetermined operation (for example, production) using the head 310 to which the nozzle 312 is attached is accumulated in the component mounting device 300, and an online flow rate reduction judgment threshold for estimating whether the head 310 is in a state related to a malfunction is generated based on the online flow rate value (for example, a large amount of online flow rate value) included in such equipment log. Then, the online flow rate value of the component mounting device 300 that is currently performing a predetermined operation and in an operating state is acquired, and the acquired online flow rate value is compared with the online flow rate reduction judgment threshold to estimate whether the head 310 is currently in a state related to a malfunction. In the present disclosure, the threshold for estimating whether the head 310 is in a state related to a malfunction is not empirically obtained but is objectively generated based on the equipment log, so that the detection accuracy of the head 310 that requires maintenance can be improved. In addition, the online flow rate value included in the equipment log is data that can be acquired without making mechanical modifications to the component mounting device 300 or the like. Therefore, the detection accuracy of the head 310 that requires maintenance can be improved without making mechanical modifications to the component mounting device 300 or the like.

[0133] Furthermore, for example, an inspection log of the head main body 311 when inspecting the head main body 311 with the nozzle 312 removed from the head 310 is accumulated in the component mounting device 300, and when it is estimated that the head 310 is in a malfunction, an offline flow rate reduction judgment threshold for estimating whether the nozzle 312 is in a malfunction or the head main body 311 is in a malfunction is generated based on the offline flow rate value (e.g., a large amount of offline flow rate value) included in such an inspection log. Then, an inspection result (specifically, the latest offline flow rate value) of the head main body 311 with the nozzle 312 removed from the head 310 estimated to be in a malfunction-related state is obtained, and the obtained inspection result is compared with the offline flow rate reduction judgment threshold to estimate whether the nozzle 312 is in a malfunction or the head main body 311 is in a malfunction. In this way, the cause of the malfunction of the head 310 requiring maintenance can be estimated.

[0134] Furthermore, for example, a factor estimation value is calculated for each offline flow rate waveform data included in the inspection log, and a malfunction factor estimation table is generated in which a malfunction factor is associated with each calculated factor characteristic value. Then, a factor estimation value is calculated from the latest offline flow rate waveform data of the head main body 311 from which the nozzle 312 has been removed from the head 310 estimated to be in a malfunction-related state, and the factor estimation value is collated with the malfunction factor estimation table, thereby making it possible to estimate the malfunction factor of the head main body 311.

[0135] (Other embodiments) Although the state estimation device 100 and the implementation system 2 of the present disclosure have been described based on the embodiments, the present disclosure is not limited to the above-mentioned embodiments. As long as they do not deviate from the spirit of the present disclosure, various modifications conceivable by a person skilled in the art to the present embodiments and forms constructed by combining components of different embodiments are also included within the scope of the present disclosure.

[0136] For example, in the above embodiment, the online flow rate value and the offline flow rate value are described as the measurement values ​​of the sensor 320 when the vacuum sensor 340 detects a vacuum error, but this is not limited to the above. For example, the sensor 320 may detect an error using a value that is set regardless of the equipment environment, and the online flow rate value and the offline flow rate value may be the measurement values ​​of the sensor 320 when the sensor 320 detects such an error.

[0137] For example, in the above embodiment, an example has been described in which the state estimation unit 120 includes the factor estimation unit 123, but the state estimation unit 120 may not include the factor estimation unit 123. In this case, the output unit 130 does not need to output information corresponding to the estimation result of the factor estimation unit 123, and may output only information corresponding to the estimation result of the first estimation unit 121 or the second estimation unit 122.

[0138] For example, in the above embodiment, an example has been described in which the state estimation unit 120 includes the second estimation unit 122, but the state estimation unit 120 may not include the second estimation unit 122. In this case, the output unit 130 does not need to output information according to the estimation result of the second estimation unit 122, and may output only information according to the estimation result of the first estimation unit 121.

[0139] For example, in the above embodiment, the output unit 130 outputs information to a maintenance person, but the output unit 130 does not have to output information to a maintenance person. For example, the output unit 130 may output information only to equipment connected to the state estimation device 100 or to a device in the state estimation device 100 that can be recognized by a maintenance person.

[0140] For example, inspection of head 310 may be performed on component mounting apparatus 300, or head 310 may be removed from component mounting apparatus 300 and inspected on an inspection device for head 310 (e.g., an apparatus capable of supplying power and air to head 310).

[0141] For example, the present disclosure can be realized not only as state estimation device 100 but also as a state estimation method including steps (processing) performed by each component of state estimation device 100.

[0142] FIG. 10 is a flowchart showing an example of a state estimation method according to another embodiment.

[0143] The state estimation method is a state estimation method for managing the state of a head in equipment that is equipped with a head having a head main body to which a nozzle configured to hold an object is attached, and that holds an object with the head to perform a specified task, and includes a threshold generation step (step S11) of acquiring an equipment log of the head having a nozzle attached to the head main body and generating a first threshold based on a data set consisting of multiple characteristic values ​​of the head included in the equipment log, as shown in Figure 10, and a state estimation step (step S12) of acquiring characteristic values ​​of the head that is in operation with a nozzle attached to the head main body, and estimating whether or not the head is in a state related to a malfunction based on the characteristic values ​​of the head and the first threshold, wherein the data set consists of multiple characteristic values ​​of the head that exceed a reference value.

[0144] For example, the steps in the state estimation method may be executed by a computer (computer system). The present disclosure can be realized as a program for causing a computer to execute the steps included in the state estimation method. Furthermore, the present disclosure can be realized as a non-transitory computer-readable recording medium, such as a CD-ROM, on which the program is recorded.

[0145] For example, when the present disclosure is realized by a program (software), each step is executed by executing the program using hardware resources such as a computer's CPU, memory, input / output circuitry, etc. In other words, each step is executed by the CPU acquiring data from memory or input / output circuitry, etc., performing calculations, and outputting the calculation results to memory or input / output circuitry, etc.

[0146] Furthermore, each of the components included in the state estimating device 100 of the above embodiment may be realized as a dedicated or general-purpose circuit.

[0147] Furthermore, each of the components included in the state estimation device 100 of the above embodiment may be realized as an LSI (Large Scale Integration) which is an integrated circuit (IC: Integrated Circuit).

[0148] Furthermore, the integrated circuit is not limited to an LSI, and may be realized by a dedicated circuit or a general-purpose processor. A programmable FPGA (Field Programmable Gate Array) or a reconfigurable processor in which the connections and settings of circuit cells within an LSI can be reconfigured may also be used.

[0149] Furthermore, if an integrated circuit technology that can replace LSI emerges due to advances in semiconductor technology or a different derivative technology, the components included in the state estimation device 100 may naturally be integrated into integrated circuits using that technology.

[0150] In addition, the present disclosure also includes forms obtained by applying various modifications to the embodiments that a person skilled in the art may conceive, and forms realized by arbitrarily combining the components and functions of each embodiment within the scope that does not deviate from the spirit of the present disclosure. [Industrial Applicability]

[0151] The present disclosure can be used, for example, in managing equipment that holds an object with a head and performs a specified task. [Explanation of symbols]

[0152] 1. Facility maintenance system 2. Mounting system 11 Foundation 12 Substrate transport mechanism 13 Head movement mechanism 13a Plate 16 Tape Feeder 16a Tape feed mechanism 16b Parts supply port 17 Trolley 18 Carrier Tape 19 Reels 20 Circuit Board Recognition Camera 21 Parts Recognition Camera 100 State Estimation Device 110 Threshold generation unit 120 State Estimation Unit 121 1st estimation part 122 Second estimation part 123 Factor Estimation Department 130 Output section 300 Component Mounting Equipment 310 Head 311 Head body 312 Nozzle 313 Nozzle holder 314 Blow valve 315 Vacuum valve 316 Common Air Route 317 Blow air path 318 Vacuum Air Route 319 Air Source 320 Sensors 330 Control Unit 340 Vacuum Sensor

Claims

1. A state estimation device for managing a state of a head in equipment that holds an object with the head and performs a predetermined operation, the head having a head main body to which a nozzle configured to hold the object is attached, The state estimation device includes: a threshold generation unit that acquires an equipment log of the head to which the nozzle is attached, the equipment log including a plurality of characteristic values ​​of the head when a vacuum error is detected by a vacuum sensor that measures a vacuum degree in an air path formed in the head, and generates a first threshold based on a data set consisting of the plurality of characteristic values ​​of the head; a state estimation unit that acquires a characteristic value of the head to which the nozzle is attached and in an operating state, and estimates whether or not the head is in a state related to a malfunction based on the acquired characteristic value of the head and the first threshold value, the threshold value generation unit allocates, as learning data, to a plurality of clusters an amount of change in state of the head calculated by comparing each of a plurality of characteristic values ​​of the head included in the equipment log with a reference value, and generates the first threshold value based on the characteristic value of the head in one cluster among the plurality of clusters having the smallest amount of change in state. State estimator.

2. A state estimation device for managing a state of a head in equipment for holding an object with the head and performing a predetermined operation, the head having a head main body portion to which a nozzle configured to hold the object is attached, The state estimation device includes: a threshold generation unit that acquires an equipment log of the head to which the nozzle is attached, the equipment log including a plurality of characteristic values ​​of the head when a vacuum error is detected by a vacuum sensor that measures a vacuum degree in an air path formed in the head, and generates a first threshold based on a data set consisting of the plurality of characteristic values ​​of the head; a state estimation unit that acquires a characteristic value of the head to which the nozzle is attached and in an operating state, and estimates whether or not the head is in a state related to a malfunction based on the acquired characteristic value of the head and the first threshold value, The threshold value generation unit further acquires an inspection log of the head main body unit to which the nozzle is not attached, and generates a second threshold value based on a plurality of characteristic values ​​of the head main body unit included in the inspection log; when it is estimated that the head is in a state related to a malfunction, the state estimation unit acquires inspection results of the head main body unit to which the nozzle is not attached, and estimates whether the nozzle is in a malfunction state or whether the head main body unit is in a malfunction state based on the inspection results and the second threshold value, and when it is estimated that the head main body unit is in a malfunction state, it estimates the malfunction cause of the head main body unit based on the factor estimation value calculated from the inspection results of the head main body unit using a malfunction cause estimation table generated by correlation analysis using the factor estimation value calculated from the inspection log and the malfunction cause of the head main body unit as learning data. State estimator.

3. the plurality of characteristic values ​​of the head main body are data measured by removing the nozzle from the head in which the characteristic value of the head to which the nozzle is attached exceeds a reference value, the threshold value generation unit generates the second threshold value based on the first threshold value by linear regression using a plurality of characteristic values ​​of the head to which the nozzle is attached and a plurality of characteristic values ​​of the head main body portion corresponding to the plurality of characteristic values ​​as learning data. The state estimation device according to claim 2 .

4. the state estimation unit estimates that the head main body is in a malfunction when the inspection result of the head main body exceeds the second threshold value. The state estimation device according to claim 3 .

5. the state estimation unit estimates that the nozzle is in a malfunction when the inspection result of the head main body does not exceed the second threshold value. The state estimation device according to claim 3 or 4.

6. the factor estimation value calculated from the inspection result of the head main body is calculated based on a statistical value of the inspection log in which the head main body is determined to be in a normal state; The state estimation device according to claim 2 .

7. the characteristic value is a measurement result of a flow rate or a pressure in an air path of the head main body when air is supplied from an air source of the head main body at a positive pressure or a negative pressure; The state estimation device according to claim 1 .

8. An output unit that outputs information based on the estimation result of the state estimation unit. The state estimation device according to claim 1 .

9. the information includes information indicating that the head is in a malfunction-related state or that the head is in a malfunction state; The state estimation device according to claim 8.

10. The information includes maintenance details for the head that is estimated to be in a malfunction. The state estimation device according to claim 8 or 9.

11. The information is output to an equipment maintenance planning unit that manages a maintenance plan for maintaining the equipment. The state estimation device according to any one of claims 8 to 10.

12. a head having a head body to which a nozzle configured to hold an object is attached; A measurement unit that measures a characteristic value of the head; and a state estimation device according to any one of claims 1 to 11, which manages the state of the head. Implementation system.

13. A state estimation method for managing a state of a head in equipment that holds an object with the head and performs a predetermined operation, the head having a head main body to which a nozzle configured to hold the object is attached, The state estimation method includes: a threshold value generating step of acquiring an equipment log of the head having the nozzle attached to the head main body, the equipment log including a plurality of characteristic values ​​of the head when a vacuum error is detected by a vacuum sensor that measures a vacuum degree in an air path formed in the head, and generating a first threshold value based on a data set consisting of the plurality of characteristic values ​​of the head; a state estimation step of acquiring a characteristic value of the head in which the nozzle is attached to the head main body and in an operating state, and estimating whether or not the head is in a state related to a malfunction based on the characteristic value of the head and the first threshold value, In the threshold value generation step, a state change amount of the head, which is calculated by comparing each of a plurality of characteristic values ​​of the head included in the equipment log with a reference value, is allocated to a plurality of clusters as learning data, and the first threshold value is generated based on the characteristic value of the head in one of the plurality of clusters having the smallest state change amount. State estimation methods.

14. A state estimation method for managing a state of a head in equipment for holding an object with the head to perform a predetermined operation, the head having a head main body portion to which a nozzle configured to hold the object is attached, The state estimation method includes: a threshold value generating step of acquiring an equipment log of the head having the nozzle attached to the head main body, the equipment log including a plurality of characteristic values ​​of the head when a vacuum error is detected by a vacuum sensor that measures a vacuum degree in an air path formed in the head, and generating a first threshold value based on a data set consisting of the plurality of characteristic values ​​of the head; a state estimation step of acquiring a characteristic value of the head in which the nozzle is attached to the head main body and in an operating state, and estimating whether or not the head is in a state related to a malfunction based on the characteristic value of the head and the first threshold value, The threshold value generating step further includes acquiring an inspection log of the head main body portion to which the nozzle is not attached, and generating a second threshold value based on a plurality of characteristic values ​​of the head main body portion included in the inspection log; the state estimation step, when it is estimated that the head is in a state related to a malfunction, acquires an inspection result of the head main body part to which the nozzle is not attached, and estimates whether the nozzle is in a malfunction state or whether the head main body part is in a malfunction state based on the inspection result and the second threshold value, and, when it is estimated that the head main body part is in a malfunction state, estimates the malfunction cause of the head main body part based on a factor estimation value calculated from the inspection result of the head main body part using a malfunction cause estimation table generated by correlation analysis using a factor estimation value calculated from the inspection log and the malfunction cause of the head main body part as learning data. State estimation methods.

Images