JP7457938B2 - Placement support method, program, placement support system and work system - Google Patents

Description

The present disclosure generally relates to a placement assistance method, a program, a placement assistance system, and a work system. More specifically, the present disclosure relates to a placement assistance method, a program, a placement assistance system, and a work system that assists in determining the placement of multiple components at multiple supply units for a component mounting system that mounts multiple components supplied to multiple supply units on a target object.

Patent Document 1 discloses an operation analysis device for maintaining high production efficiency of the entire line by monitoring line mounting tact or line operating rate to prevent a drop in a component mounting line, and analyzing and removing factors causing the decline. is listed.

This operation analyzer reduces tact loss in order to eliminate the reason why the line mounting tact, which is the component mounting machine with the highest mounting tact performance value among the component mounting lines, does not reach the target value. Optimize the arrangement of component supply devices or the order of component mounting. As a result, for example, if the cause is an imbalance in the actual mounting takt values of each component mounter, by correcting the distribution of components to each mounter, the takt loss can be reduced and the line mounting tact can be improved. Can be maintained at target value.

Japanese Patent Application Publication No. 2002-111298

However, even if the allocation of parts to each mounting machine is corrected, Patent Document 1 does not clearly disclose how to allocate parts to each mounting machine, and improvements are required regarding the placement of parts (including allocation).

The present disclosure has been made in view of the above reasons, and aims to provide a placement support method, a program, a placement support system, and a work system that can propose improved component placement.

An arrangement support method according to an aspect of the present disclosure is a method for supporting determination of the arrangement of a plurality of components in a plurality of supply units with respect to a component mounting system, and includes an acquisition step, a proposal step, an identification step, and a re-proposal step. arranging step. The component mounting system is a system that generates a product by mounting the plurality of components supplied to the plurality of supply units on a target object. The acquisition step is a step of acquiring mounting data regarding the plurality of components included in the product. The proposing step is a step of proposing arrangement of the plurality of parts with respect to the plurality of supply units. The specifying step is a step of specifying, as a target supply section, a supply section that satisfies a specific condition among the plurality of supply sections, when the arrangement of the plurality of parts proposed at the proposal step is adopted. The specific condition is a condition regarding the time required to generate the product in the component mounting system. The rearrangement step is a step of proposing the arrangement of the plurality of parts to the target supply unit and a reference supply unit including at least one supply unit other than the target supply unit among the plurality of supply units. It is. In the proposing step, the first trained model generated in association with the characteristics of at least one of the plurality of supply units is used to determine the implementation required for generation of the product in the component mounting system. The arrangement of the plurality of components with respect to the plurality of supply units is proposed from the mounting data so as to shorten the time.

A program according to one aspect of the present disclosure is a program for causing one or more processors to execute the placement support method.

An arrangement support system according to an aspect of the present disclosure is a system that supports determining the arrangement of a plurality of components in a plurality of supply sections regarding a component mounting system, and includes an acquisition section, a proposal section, a specification section, and a re-installation section. A placement section. The component mounting system is a system that generates a product by mounting the plurality of components supplied to the plurality of supply units on a target object. The acquisition unit acquires mounting data regarding the plurality of components included in the product. The proposal unit proposes placement of the plurality of parts with respect to the plurality of supply units. The specifying unit specifies, as a target supply unit, a supply unit that satisfies a specific condition among the plurality of supply units when the arrangement of the plurality of parts proposed by the proposal unit is adopted. The specific condition is a condition regarding the time required to generate the product in the component mounting system. The relocation unit proposes placement of the plurality of parts to the target supply unit and a reference supply unit including at least one supply unit other than the target supply unit among the plurality of supply units. . The proposal unit calculates the mounting time required to generate the product in the component mounting system using a learned model that is generated in association with the characteristics of at least one of the plurality of supply units. Based on the mounting data, the arrangement of the plurality of components with respect to the plurality of supply units is proposed so as to be short.

A work system according to one aspect of the present disclosure includes the placement support system and the component mounting system. The component mounting system is used in the placement of the plurality of components proposed by the placement support system, and generates the product.

According to the present disclosure, there is an advantage that it is possible to provide a placement support method, a program, a placement support system, and a work system that can propose improved component placement.

FIG. 1 is a schematic diagram showing the appearance of a component mounting system to which the placement support method according to the first embodiment is applied. FIG. 2 is a conceptual diagram showing the arrangement of components in the supply section of the component mounting system using the above arrangement support method. FIG. 3 is a block diagram showing an overview of a work system including the placement assistance system according to the first embodiment. FIGS. 4A and 4B are conceptual diagrams illustrating how a plurality of parts are proposed for placement in a supply unit using the placement support method described above. FIG. 5 is a flowchart showing an example of the placement support method as described above. FIG. 6 is an explanatory diagram schematically showing how components are distributed in a multi-stage manner using the placement support method described above. FIG. 7 is an explanatory diagram schematically showing the state of relocation using the above arrangement support method.

(Embodiment 1)
The placement support method, program, placement support system 20 (see FIG. 3), and work system 200 (see FIG. 3) according to the present embodiment will be described below with reference to FIGS. 1 to 7.

1, the placement assistance method according to this embodiment is a placement assistance method that supports the placement of multiple components P1 in multiple supply units 3 in a component mounting system 100. The component mounting system 100 has multiple supply units 3 for supplying the components P1 used in the component mounting system 100, and generates a product P3 by mounting the multiple components P1 supplied to these multiple supply units 3 on a target object P2.

That is, as shown in FIG. 1, the component mounting system 100 includes at least one mounting machine (mounting device) 10 for mounting a component P1 on an object P2. The mounting machine 10 has a capture unit 41 (see FIG. 1) for capturing the component P1. The capture unit 41 is, for example, a suction nozzle, and captures (holds) the component P1 in a state in which it can be released (i.e., released from capture). The mounting machine 10 captures the component P1 supplied to the supply unit 3 with the capture unit 41, moves the capture unit 41 with the component P1 captured, and releases the component P1 above the object P2, thereby mounting the component P1 on the mounting surface of the object P2.

In this embodiment, as an example, the component mounting system 100 is a mounting line configured by connecting a plurality of mounting machines 10 (four in the example of FIG. 1). In other words, the component mounting system 100 includes a plurality of mounting machines 10 that are connected to each other to form a mounting line. In such a component mounting system 100 (mounting line), for example, multiple mounting machines 10 sequentially mount components P1 on one object P2, so that ultimately multiple components P1 are mounted on one object P2. An implemented product P3 is generated.

Each of the plurality of mounting machines 10 has at least one supply section 3 and mounts the component P1 supplied to the supply section 3. That is, each mounting machine 10 mounts one or more components P1 supplied to its own supply unit 3 onto the object P2. In the example of FIG. 1, each of the plurality of mounting machines 10 has a plurality of (here, two) supply units 3. In this embodiment, the component mounting system 100 includes a plurality of mounting machines 10, so even if each of the plurality of mounting machines 10 has one supply section 3, the component mounting system 100 as a whole , a plurality of supply units 3 will exist.

The component mounting system 100 is used, for example, in facilities such as factories, research institutes, offices, and educational facilities to manufacture various products such as electronic devices, automobiles, clothing, foods, pharmaceuticals, and crafts. used.

In such a component mounting system 100, there are many patterns of arrangement of the plurality of components P1 in the plurality of supply units 3 provided in the plurality of mounting machines 10. In other words, since it is possible to select which of the plurality of mounting machines 10 to place each of the plurality of parts P1 in the supply section 3 of the mounting machine 10, if the number of parts P1 is several hundred pieces, for example, The number of layout patterns for the plurality of parts P1 in the plurality of supply units 3 is enormous. The mounting time required to generate the product P3 in the component mounting system 100 varies greatly depending on the arrangement of the plurality of components P1 in the plurality of supply units 3. For example, the mounting time varies greatly depending on how the plurality of components P1 are distributed to the plurality of mounting machines 10. As described above, the arrangement of the plurality of components P1 in the plurality of supply units 3 is an important factor related to the mounting time of the component mounting system 100, but since there are many arrangement patterns, it is difficult to ensure appropriate arrangement. The task of finding out is extremely difficult.

Therefore, the placement support method according to the present embodiment supports the work of determining the placement of the plurality of components P1 in the plurality of supply units 3 in the component mounting system 100 as described above. According to this placement support method, it becomes possible to find a more appropriate placement more easily (in a short time), and for example, it is possible to find a more appropriate placement of a plurality of parts in a plurality of supply units 3 without the help of an expert. It becomes possible to determine the arrangement of P1.

In other words, the placement assistance method according to this embodiment is a method for proposing a placement of multiple components P1 in multiple supply units 3 for the component mounting system 100. The component mounting system 100 generates a product P3 by mounting multiple components P1 supplied to the multiple supply units 3 on a target object P2. Here, the placement assistance method according to this embodiment further employs the following three functions to enable the proposal of an improved placement of components P1.

The first function is an arrangement proposal using the learned model M1 (see FIG. 3). In order to realize the first function, the placement support method includes an acquisition step and a proposal step. The acquisition step is a step of acquiring mounting data D1 (see FIG. 3). The mounting data D1 is data regarding the plurality of parts P1 included in the product P3. The proposal step is a step of proposing the arrangement of the plurality of parts P1 to the plurality of supply units 3 from the mounting data D1 using the learned model M1 so as to shorten the mounting time. The learned model M1 is a model generated in association with the characteristics of at least one of the plurality of supply units 3. The mounting time is the time required for the component mounting system 100 to generate the product P3.

Thus, in the first function, the placement support method proposes the placement of the plurality of parts P1 to the plurality of supply units 3 using the learned model M1 in the proposal step. That is, in the proposal step, instead of proposing a uniquely determined layout, for example, the trained model M1 is used to acquire the skill of "determining" the layout, as would be done by an expert, so that an appropriate layout can be made. , it is possible to find out more easily. In particular, the learned model M1 is a model that is generated in association with the characteristics of at least one of the plurality of supply units 3, so for example, the performance or specifications of the mounting machine 10 are taken into consideration. , the arrangement of the plurality of parts P1 is proposed. Therefore, with this placement support method, it is possible to propose an improved placement of the component P1.

The second function is multi-stage distribution of parts P1. In order to realize the second function, the placement support method includes a primary proposal step and a secondary proposal step. The primary proposal step is a step of proposing the arrangement of the plurality of parts P1 for the plurality of primary groups G11 and G12 (see FIG. 6). The secondary proposal step includes, after the primary proposal step, a plurality of secondary groups G21 to G24 when each of the plurality of primary groups G11 and G12 is classified into a plurality of secondary groups G21 to G24 (see FIG. 6). This is a step of proposing the arrangement of a plurality of parts P1 with respect to G24. Each of the plurality of secondary groups G21 to G24 includes at least one supply section 3 among the plurality of supply sections 3.

Here, the primary proposal step and secondary proposal step in the second function are included in the proposal step in the first function. In other words, the proposal step includes a primary proposal step and a secondary proposal step.

In this way, in the second function, the proposal for the placement of multiple parts P1 is divided into a primary proposal step in which parts P1 are placed in multiple primary groups G11 and G12, and a secondary proposal step in which parts P1 are placed in multiple smaller secondary groups G21 to G24. In short, the placement of multiple parts P1 is achieved not in a single-stage process but in a hierarchically set multi-stage process, so that at each stage, the number of options for deriving an appropriate placement of multiple parts P1 can be kept small. As a result, the process for proposing the placement of multiple parts P1 at each stage can be simplified. Therefore, this placement support method makes it possible to propose improved placements of parts P1.

The third function is relocation. In order to realize the third function, the placement support method includes a proposal step, a specifying step, and a relocation step. The proposal step is a step of proposing the arrangement of the plurality of parts P1 with respect to the plurality of supply units 3. The specifying step is a step of specifying a certain supply section 3 among the plurality of supply sections 3 as a target supply section. The supply unit 3 identified as the target supply unit is a supply unit that satisfies specific conditions regarding the time required to generate the product P3 in the component mounting system 100 when the arrangement of the plurality of components P1 proposed in the proposal step is adopted. This is part 3. The rearrangement step is a step of proposing the arrangement of the plurality of parts P1 to the target supply unit and the reference supply unit. The reference supply unit includes at least one supply unit 3 other than the target supply unit among the plurality of supply units 3 .

In this way, with the third function, even if the arrangement of the plurality of parts P1 proposed in the proposal step is not optimal, a new arrangement of the plurality of parts P1 can be proposed in the relocation step. Moreover, when the supply unit 3 to be rearranged in the rearrangement step is adopted in the arrangement proposed in the proposal step, the product P3 is generated in the component mounting system 100 among the plurality of supply parts 3. A target supply unit that satisfies certain conditions regarding the time required for That is, in the rearrangement step, among the layouts proposed in the proposal step, it is possible to re-propose the layout of the supply unit 3 that satisfies a certain condition regarding the time required to generate the product P3 in the component mounting system 100. . Therefore, with this placement support method, it is possible to propose an improved placement of the component P1.

Further, the placement support method according to the present embodiment is executed by the placement support system 20, as an example. In other words, the placement support system 20 is one aspect for realizing the placement support method described above. In other words, the placement support system 20 supports determining the placement of the plurality of components P1 in the plurality of supply units 3 regarding the component mounting system 100. As described above, the component mounting system 100 is a system that generates a product P3 by mounting a plurality of components P1 supplied to a plurality of supply units 3 onto an object P2, and in this embodiment, as an example. , is the implementation line.

Here, the placement assistance system 20 mainly comprises a computer system having one or more processors and one or more memories. In other words, the placement assistance method according to this embodiment is used on a computer system (placement assistance system 20). In other words, the placement assistance method can also be embodied as a program. The program according to this embodiment is a program for causing one or more processors to execute the placement assistance method according to this embodiment.

Further, the work system 200 according to this embodiment includes an arrangement support system 20 and a component mounting system 100. The component mounting system 100 is a system that is used in the placement of a plurality of components P1 proposed by the placement support system 20, and generates a product P3.

(2) Details The details of the placement support method, program, placement support system 20, and work system 200 according to the present embodiment will be described below.

(2.1) Premise In this embodiment, a case will be described in which the component mounting system 100 is used for manufacturing electronic devices in a factory. A typical electronic device includes various circuit blocks such as a power supply circuit and a control circuit. In manufacturing these circuit blocks, for example, a solder application process, a mounting process, and a soldering process are performed in this order. In the solder application process, creamy solder is applied (or printed) onto a board (including a printed wiring board). In the mounting process, the component P1 (including electronic components) is mounted (mounted) on the board. In the soldering process, for example, the board on which the component P1 is mounted is heated in a reflow oven to melt the creamy solder and perform soldering.

In a mounting process, the component mounting system 100 performs work to mount a plurality of components P1 (electronic components) onto a substrate, which is a target object P2. As a result, the component mounting system 100 generates a product P3 consisting of a substrate (object P2) on which a plurality of components P1 are mounted. In other words, the product P3 includes an object P2 (here, a substrate) and a plurality of components P1 mounted on the object P2.

In this embodiment, as an example, a case will be described in which the component mounting system 100 is used to mount a component (component P1) using surface mount technology (SMT). That is, the component P1 is a surface mount device (SMD), and is mounted by being placed on the surface (mounting surface) of a substrate as the object P2. However, the component mounting system 100 is not limited to this example, and the component mounting system 100 may be used to mount a component (component P1) using insertion mounting technology (IMT). In this case, the component P1 is a component for insertion mounting that has a lead terminal, and by inserting the lead terminal into the hole of the board (object P2), the surface of the board (object P2) ( mounting surface).

In addition, the "supply unit" in this disclosure is a portion (location) of the component mounting system 100 for supplying the components P1 used in the component mounting system 100. The component mounting system 100 has multiple supply units 3, and performs mounting work using the components P1 supplied to each supply unit 3. For example, the supply unit 3 is configured to be able to mount a tape feeder for supplying the components P1. The tape feeder is capable of supplying the multiple components P1 from the supply unit 3 to the component mounting system 100 by attaching a reel of carrier tape containing multiple components P1. This type of supply unit 3 includes multiple slots to which tape feeders can be attached, and multiple tape feeders are attached to these multiple slots to supply multiple components P1 to the component mounting system 100 (mounting machine 10). In this embodiment, as an example, it is assumed that the supply unit 3 is a "table" consisting of a collection of multiple slots. The "table" referred to here is a virtual table and does not have an actual entity.

In the following, as an example, three mutually orthogonal axes, the X-axis, the Y-axis, and the Z-axis, are set, and the axes parallel to the surface of the substrate, which is the object P2, are the "X-axis" and "Y-axis", and the axis parallel to the thickness direction of the substrate is the "Z" axis. In particular, the "X-axis" is an axis along the direction in which the multiple mounting machines 10 in the component mounting system 100 are arranged. Furthermore, the side of the capture unit 41 as seen from the substrate, which is the object P2, is defined as the positive direction of the Z-axis (also referred to as "above"). In addition, the state seen from the positive direction of the Z-axis (above) is also referred to as "planar view" below. The X-axis, Y-axis, and Z-axis are all virtual axes, and the arrows indicating "X", "Y", and "Z" in the drawings are merely indicated for the purpose of explanation, and none of them have any substance. In addition, these directions are not intended to limit the directions when the component mounting system 100 is used.

Further, the proposal for the "arrangement" of the parts P1 in the present disclosure includes proposals for various items regarding the arrangement of the plurality of parts P1 in the plurality of supply units 3, such as the allocation of the parts P1 and the arrangement of the parts P1. Including both suggestions. Sorting the plurality of parts P1 means dividing the plurality of parts P1 into a plurality of parts and assigning one or more parts P1 after the division to one of the plurality of supply units 3 (table in this embodiment). do. That is, in the distribution, when a plurality of parts P1 are allocated within one supply unit 3, the order in which these plurality of parts P1 are arranged is not specified. On the other hand, the proposal for arranging the plurality of parts P1 is to divide the plurality of parts P1 into a plurality of parts and place one or more parts P1 after the division into one of the plurality of supply units 3 (in this embodiment, a table). This means specifying the allocation and even the arrangement order (arrangement) within each supply unit 3. Therefore, as in this embodiment, when the supply section 3 is a "table" consisting of a set of a plurality of slots, the arrangement of the parts P1 is determined by which one of the plurality of slots included in one supply section 3 (table). It is defined which component P1 corresponds to the slot. In other words, in the arrangement proposal, when a plurality of parts P1 are allocated within one supply unit 3, the arrangement order of these plurality of parts P1 is also defined.

In this embodiment, as an example, the proposal for the "placement" of the component P1 performed by the placement support method or the placement support system 20 is only the distribution of the component P1 among the distribution of the component P1 and the proposal of the arrangement of the component P1. Assume that That is, in the placement support method or placement support system 20 according to the present embodiment, a plurality of parts P1 are divided into a plurality of parts, and one or more parts P1 after the division are assigned to one of the plurality of supply units 3. However, the order in which one or more parts P1 are arranged after division is not specified.

Furthermore, the aspect of "proposing" the placement referred to in the present disclosure refers to the aspect of outputting the derivation result of the placement of the component P1 to a person or an external system, and the aspect of actually providing multiple supplies according to the derivation result of the placement of the component P1. This includes both a mode of determining the arrangement of the plurality of parts P1 in the section 3. According to the former aspect, the person or external system that receives the derivation result of the placement of the component P1 from the placement support method or the placement support system 20 only receives a proposal (suggestion) for the placement of the component P1; It is then decided whether or not to adopt this derived result. According to the latter aspect, the result of deriving the placement of the component P1 from the placement support method or the placement support system 20 is directly adopted by the component mounting system 100 without judgment by a person or an external system.

In addition, the "characteristics" of the supply unit 3 in this disclosure include, for example, characteristics of the mounting machine 10 in which the supply unit 3 is provided. The characteristics of the mounting machine 10 include, for example, the type, performance, characteristics, or specifications of the mounting machine 10, such as the speed (maximum mounting speed), the number of capture units 41 (number of nozzles), the number of supply units 3, the type of capture unit 41, the number of slots, the number of mounting heads 4, and the model. The "number of capture units 41" means the maximum number of capture units 41 that can be attached to one mounting head 4. The "type of capture unit 41" includes, for example, a suction nozzle that picks up the component P1 and a mechanical chuck that clamps (picks up) the component P1. The "number of slots" means the number of slots in one supply unit 3 (or one mounting machine 10), or in other words, the maximum number of tape feeders that can be attached to one supply unit 3 (or one mounting machine 10).

Further, the "speed" of the mounting machine 10 in the present disclosure means the maximum mounting speed of the mounting machine 10, that is, the maximum value of the speed of mounting the component P1 on the mounting machine 10. That is, the mounting machine 10 operates to capture the component P1 with the capture section 41, move the capture section 41 in a state of capturing the component P1, and mount the component P1 on the object P2. Therefore, for example, the speed of the mounting machine 10 (maximum mounting speed) differs depending on the speed of capturing and releasing (that is, releasing the capture) of the component P1 in the capturing section 41, the moving speed of the capturing section 41, and the like. However, in this embodiment, speeds are classified into multiple speed ranges, such as multi-function aircraft (low-speed aircraft), medium-speed aircraft, and high-speed aircraft. They will also be considered to be in the same speed range, such as being referred to as "high-speed aircraft."

Furthermore, the “specific conditions” in the present disclosure are specific conditions set regarding the time required for the component mounting system 100 to generate the product P3. As an example, the specific condition may be that the time required to generate the product P3 in the component mounting system 100 (mounting time) is the longest or the shortest among the plurality of supply units 3.

(2.2) Configuration of component mounting system Next, the configuration of the component mounting system 100 in which the placement support method according to the present embodiment is used will be described with reference to FIGS. 1 and 2.

As described above, the component mounting system 100 according to the present embodiment includes a plurality of (here, four) mounting machines 10 that constitute a mounting line. The plurality of mounting machines 10 are arranged in a line along the X axis. When distinguishing these multiple mounting machines 10, each of the multiple mounting machines 10 is divided into a first mounting machine 11, a second mounting machine, and a second mounting machine in order from the negative side of the X axis, as shown in FIG. 12, the third mounting machine 13, and the fourth mounting machine 14.

In the component mounting system 100 according to the present embodiment, the first mounter 11 is at the head, followed by the second mounter 12, the third mounter 13, and then the fourth mounter 14 at the end. , the object P2 moves through a plurality of mounting machines 10. In other words, the object P2 sequentially passes through the plurality of mounting machines 10 while moving in the positive direction of the X-axis. In the component mounting system 100, each mounting machine 10 mounts a plurality of components P1 on the target object P2 while the target object P2 passes through the plurality of mounting machines 10. Thereby, the component mounting system 100 introduces the board, which is the object P2, from the first mounting machine 11 side, and mounts the plurality of components P1 (electronic components) on the object P2 using the plurality of mounting machines 10. After performing this, the product P3 is discharged from the fourth mounting machine 14 side.

Therefore, by sequentially mounting the components P1 using the plurality of mounting machines 10, the component mounting system 100 can finally generate a product P3 on which the plurality of components P1 are mounted. The "mounting time" in the present disclosure is the time required to generate the product P3 in the component mounting system 100, and for example, after one object P2 is introduced into the component mounting system 100, the product P3 This is the time it takes to be ejected from the component mounting system 100. In other words, from the time when one board, which is the object P2, is introduced into the first mounting machine 11, a plurality of components P1 are mounted on this board (object P2), and a fourth mounted part is mounted as the product P3. The time until it is discharged from the machine 14 is the "mounting time."

In this embodiment, each of the plurality of mounting machines 10 has the same basic configuration. Therefore, in the following, unless otherwise specified, the configuration of only the first mounter 11 will be explained, but the configuration of the other mounters (second mounter 12, third mounter 13, and fourth mounter 14) will be explained. ) basically adopts the same configuration.

The mounting machine 10 (first mounting machine 11) includes at least one supply section 3 (table) and at least one mounting head 4. In this embodiment, the mounting machine 10 includes two supply units 3. The two supply units 3 are located at both ends of the mounting machine 10 in the Y-axis direction. Furthermore, the mounting machine 10 includes two mounting heads 4. The two mounting heads 4 are arranged on both sides of the Y-axis direction when viewed from the center line of the mounting machine 10 in the Y-axis direction so as to correspond one-to-one to the two supply units 3, respectively.

In other words, the mounting machine 10 has a structure that is approximately symmetrical in the Y-axis direction, with the mounting heads 4 and supply units 3 arranged on either side of the center line in the Y-axis direction. Therefore, the mounting machine 10 drives the two mounting heads 4 individually, so that the two mounting heads 4 mount the components P1 supplied to the two supply units 3 on the target object P2 introduced between the two supply units 3.

As described above, in this embodiment, one mounting machine 10 has two mounting heads 4, but since two supply sections 3 (tables) are also provided, one mounting head 4 is provided for one supply section 3. The mounting head 4 corresponds to this. That is, each supply section 3 has only one corresponding mounting head 4, and the "number of mounting heads 4" included in the characteristics of the supply section 3 is "1".

The mounting head 4 has one or more capture parts 41. In this embodiment, the mounting head 4 in the first mounting machine 11 has a plurality of (for example, 16) capturing parts 41 (see FIG. 1). With the component P1 (component) captured in the capture section 41, the mounting head 4 moves the capture section 41 close to the object P2 (board), and mounts the component P1 on the mounting surface T21 of the object P2. do.

The supply section 3 is supplied with the component P1 captured by the capture section 41 of the mounting head 4. In this embodiment, as described above, the supply section 3 is a "table" consisting of a set of a plurality of slots to which tape feeders can each be attached. Therefore, a plurality of tape feeders can be attached to the supply unit 3, with the number of slots being the upper limit. The mounting head 4 captures the component P1 (component) from the tape feeder attached to the supply unit 3 using the capture unit 41 .

In addition to the above configuration, the mounting machine 10 may further include a drive device, a transport device, a control device, a communication unit, etc. However, the drive device, transport device, control device, communication unit, etc. are not essential components of the mounting machine 10. In Figures 1 and 2, the illustration of components of the mounting machine 10 other than the supply unit 3 and the mounting head 4 is appropriately omitted.

The drive device is a device that moves the mounting head 4. In this embodiment, the drive device moves the mounting head 4 within the XY plane. The "XY plane" here is a plane that includes the X axis and the Y axis, and is perpendicular to the Z axis. In other words, the drive device moves the mounting head 4 in the X-axis direction and the Y-axis direction.

The transport device is a device that transports the substrate as the object P2. The conveyance device is realized by, for example, a belt conveyor. The transport device transports the object P2 (substrate) along the X-axis. The transport device transports the object P2 to at least the mounting space below the mounting head 4, that is, facing the capturing section 41 in the Z-axis direction. The transport device then stops the object P2 in the mounting space until the mounting head 4 completes mounting the component P1 (component) on the object P2 (board).

The control device controls each part of the component mounting system 100. The control device mainly includes a microcontroller having one or more processors and one or more memories. That is, the functions of the control device are realized by the processor of the microcontroller executing a program recorded in the memory of the microcontroller. The program may be pre-recorded in a memory, provided through a telecommunications line such as the Internet, or provided recorded on a non-temporary recording medium such as a memory card.

The communication unit is configured to communicate with the host system directly or indirectly via a network, a repeater, or the like. This allows the mounting machine 10 to exchange data with the host system.

The mounting machine 10 configured as described above is used with a tape feeder mounted with a reel of carrier tape containing a plurality of components P1 attached to each of a plurality of slots in the supply section 3. As a result, the parts P1 taken out from the carrier tape by the tape feeder are sequentially supplied to each of the plurality of slots in the supply section 3. In this state, the mounting machine 10 captures the component P1 supplied to the supply unit 3 by the tape feeder with the capture unit 41 of the mounting head 4, and performs an operation to mount (place) the component P1 on the target position on the object P2. , executed as a basic operation. The mounting machine 10 repeatedly performs such basic operations.

Here, if the mounting head 4 has multiple (16, for example) capture units 41, the mounting machine 10 can mount multiple components P1 with one basic operation. In other words, the mounting machine 10 can capture multiple components P1 collectively with the multiple capture units 41 in the mounting head 4 in one basic operation, and therefore can mount multiple components P1 collectively. Furthermore, a mounting machine 10 equipped with multiple (two, for example) mounting heads 4 can mount multiple components P1 simultaneously with these multiple mounting heads 4 by driving the multiple mounting heads 4 individually.

By the way, in this embodiment, the plurality of mounting machines 10 included in the component mounting system 100 have partially different characteristics, as described below. Here, the first mounter 11 and the second mounter 12 have the same characteristics, and the third mounter 13 and the fourth mounter 14 respectively have the same characteristics as the first mounter 11 ( Alternatively, the second mounting machine 12) may have different characteristics.

That is, since there are many types, performances, characteristics, or specifications of the mounting machines 10, the plurality of mounting machines 10 forming the component mounting system 100 may have different characteristics from each other. Specifically, the mounting machine 10 determines, for example, the speed (maximum mounting speed), the number of catching sections 41 (number of nozzles), the number of supply sections 3, the type of catching sections 41, the number of slots, and the number of mounting heads 4. And the model etc. may be different.

In this embodiment, the characteristics that differ between the plurality of mounting machines 10 (four in this case) include speed, the number of capturing sections 41, the type and model of the capturing sections 41, and the like. As an example, regarding "speed", the first mounter 11 and the second mounter 12 are "high-speed machines", while the third mounter 13 is a "medium-speed machine", and the fourth The mounting machine 14 is a "multifunctional machine". Regarding the "number of trapping units 41," the first mounter 11 and the second mounter 12 have ``16'', the third mounter 13 has ``8'', and the fourth mounter has ``number''. 14 is "3".

On the other hand, common features among the plurality of mounting machines 10 (here, four mounting machines 10) include the number of supply units 3, the number of slots, the number of mounting heads 4, etc. As an example, the "number of supply units 3" is "2" for all mounting machines 10, as described above. Similarly, as an example, the "number of mounting heads 4" is "2" for all mounting machines 10, as described above. Further, regarding the "number of slots", it is assumed that each mounting machine 10 has "60".

However, since the "number of catching parts 41" represents the number of catching parts 41 in one mounting head 4, if we look at the unit of mounting machine 10 equipped with two mounting heads 4, the number of catching parts 41 is twice as many as above. will have the following. For example, the number of capture units 41 in the entire first mounting machine 11 is "32". Similarly, the "number of slots" represents the number of slots in one supply section 3, so if you look at the unit of 10 mounting machines equipped with two supply sections 3, it will have twice as many slots as above. . For example, the number of slots in the entire first mounting machine 11 is "120". In addition, the characteristics of the mounting machines 10 as described above are such that even if the models of the mounting machines 10 are the same, for example, the detailed specifications of the mounting machines 10 may differ, or the performance may deteriorate due to aging etc. Now, things are different.

As described above, in this embodiment, the component mounting system 100 includes four mounting machines 10, and each mounting machine 10 has two supply units 3, so the component mounting system 100 as a whole has eight supply units. Part 3 exists. When distinguishing these eight supply parts 3, each of the plurality of supply parts 3 is divided into a first supply part 31, a second supply part 32, a third supply part 33, a second supply part 32, a third supply part 33, They are also referred to as a fourth supply section 34, a fifth supply section 35, a sixth supply section 36, a seventh supply section 37, and an eighth supply section 38. The first supply section 31 and the second supply section 32 are provided in the first mounting machine 11, and the third supply section 33 and the fourth supply section 34 are provided in the second mounting machine 12. There is. The fifth supply section 35 and the sixth supply section 36 are provided in the third mounting machine 13, and the seventh supply section 37 and the eighth supply section 38 are provided in the fourth mounting machine 14. There is.

(2.3) Configuration of placement support system Next, the configuration of the placement support system 20 according to this embodiment will be described with reference to FIG. 3.

As described above, the placement support system 20 is a system that supports determining the placement of the plurality of components P1 in the plurality of supply units 3 in the component mounting system 100. In this embodiment, as described above, the component mounting system 100 as a whole includes eight supply sections 3, the first supply section 31 to the eighth supply section 38. Therefore, the arrangement support system 20 according to the present embodiment is used to determine the arrangement of the plurality of parts P1 in these eight supply units 3.

As shown in FIG. 3, the placement support system 20 includes an acquisition section 21, a proposal section 22, a specification section 23, a rearrangement section 24, an output section 25, a simulation section 26, a model storage section 27, It is equipped with In this embodiment, the placement support system 20 mainly includes a computer system having one or more processors and one or more memories, as described above. In the placement support system 20, the functions of at least the acquisition unit 21, the proposal unit 22, the identification unit 23, the relocation unit 24, the output unit 25, and the simulation unit 26 are realized by one or more processors executing programs. Ru.

The acquisition unit 21 acquires the mounting data D1. The mounting data D1 is data regarding the plurality of parts P1 included in the product P3. That is, the mounting data D1 is data regarding all of the plurality of components P1 mounted in the component mounting system 100. As an example, when "200" components P1 are mounted in the component mounting system 100, the mounting data D1 includes data regarding each of these "200" components P1. The mounting data D1 includes at least data for distinguishing between the plurality of components P1, such as the type, product number, specifications, manufacturer, size, number of terminals, terminal arrangement, and circuit constants for each of the plurality of components P1. Contains.

The proposal unit 22 proposes placement of the plurality of parts P1 to the plurality of supply units 3. In this embodiment, the proposal unit 22 uses the learned model M1 to propose placement of the plurality of parts P1 to the plurality of supply units 3 from the mounting data D1 so as to shorten the mounting time. The learned model M1 is a model generated in association with the characteristics of at least one of the plurality of supply units 3. The mounting time is the time required for the component mounting system 100 to generate the product P3. The learned model M1 will be explained in detail in the section "(3.2) Learned model".

Here, the placement support system 20 (placement support method) according to the present embodiment employs a multistage system for allocating the parts P1 (proposing placement). Therefore, in this embodiment, the proposal unit 22 includes a plurality of processing blocks so as to be compatible with multi-stage distribution. Specifically, the proposal section 22 includes a primary proposal section 221 , a secondary proposal section 222 , and a tertiary proposal section 223 .

The primary proposal unit 221 proposes placement of the plurality of parts P1 for the plurality of primary groups G11 and G12. The secondary proposal unit 222 generates a plurality of parts P1 for the plurality of secondary groups G21 to G24 when each of the plurality of primary groups G11 and G12 is classified into a plurality of further subdivided secondary groups G21 to G24. Suggest placement of. Each of the plurality of secondary groups G21 to G24 includes at least one supply section 3 among the plurality of supply sections 3. The tertiary proposal unit 223 generates a plurality of tertiary groups G31 to G38 when each of the plurality of secondary groups G21 to G24 is classified into a plurality of more subdivided tertiary groups G31 to G38 (see FIG. 6). The arrangement of component P1 is proposed. Each of the plurality of tertiary groups G31 to G38 includes at least one supply section 3 among the plurality of supply sections 3. The multi-stage method will be explained in detail in the section “(3.3) Multi-stage method”.

The specifying unit 23 specifies a certain supply unit 3 among the plurality of supply units 3 as a target supply unit when the arrangement of the plurality of parts P1 proposed by the proposal unit 22 is adopted. Here, the supply section 3 specified as the target supply section is a supply section 3 that satisfies a specific condition regarding the time required to generate the product P3 in the component mounting system 100. In other words, the specifying unit 23 specifies the supply unit 3 that satisfies the specific condition regarding the time required to generate the product P3 in the component mounting system 100 as the “target supply unit”. Specification of the target supply section will be described in detail in the "(3.4) Relocation" section.

The rearrangement unit 24 proposes the arrangement of the plurality of parts P1 to the target supply unit and the reference supply unit. Here, the reference supply section includes at least one supply section 3 other than the target supply section among the plurality of supply sections 3. Therefore, the specifying unit 23 substantially extracts the supply unit 3 as the “target supply unit” and the supply unit 3 as the “reference supply unit” from among the plurality of supply units 3. In other words, the specifying unit 23 identifies at least one of the plurality of supply units 3 that does not satisfy the specific condition regarding the time required to generate the product P3 in the component mounting system 100 as a “target supply unit”. Specify as.

Then, the rearrangement section 24 rearranges the plurality of parts P1, targeting the extracted (identified) target supply section and reference supply section among the plurality of supply sections 3. In other words, the relocation unit 24 proposes a new arrangement in place of the arrangement (distribution) of the plurality of parts P1 to the target supply unit and the reference supply unit, which was once proposed by the proposal unit 22. In this embodiment, the relocation unit 24 resets the arrangement of the plurality of parts P1 in the target supply unit and the reference supply unit, and then proposes the arrangement of the plurality of parts P1 anew. Relocation will be explained in detail in the "(3.4) Relocation" section.

The output unit 25 outputs placement data D2 generated by at least one of the proposal unit 22 and the rearrangement unit 24. “Placement data” in the present disclosure is data representing the placement of the plurality of parts P1 with respect to the plurality of supply units 3, proposed by at least one of the proposal unit 22 and the relocation unit 24. That is, the arrangement data D2 is data representing the distribution to one of the supply units 3 with respect to all of the plurality of components P1 mounted in the component mounting system 100. As an example, when "200" parts P1 are mounted in the component mounting system 100, the mounting data D1 is set for each of the "200" parts P1 by a plurality of (eight here) supply units. 3. Contains data specifying which of the 3 locations it is placed in.

Examples of output modes of the placement data D2 by the output unit 25 include output to the simulation unit 26, transmission to the component mounting system 100 or other systems, display, audio output, and recording to a non-temporary recording medium ( writing) and printing (printout), etc. In this embodiment, as an example, the output unit 25 directly or indirectly outputs the placement data D2 to the simulation unit 26. Further, in this embodiment, as an example, the output unit 25 directly or indirectly outputs (transmits) the placement data D2 to the component mounting system 100. Thereby, in the component mounting system 100, it becomes possible to mount a plurality of components P1 using the arrangement of the plurality of components P1 defined by the arrangement data D2. Further, for example, according to aspects such as display or audio output, the output unit 25 can output the arrangement data D2 to a person such as a worker.

The simulation unit 26 simulates the operation of mounting the plurality of components P1 in the component mounting system 100. Here, the simulation unit 26 simulates the operation of the component mounting system 100 when the arrangement of the plurality of components P1 proposed by at least one of the proposal unit 22 and the relocation unit 24 is adopted. In this embodiment, the simulation unit 26 acquires the placement data D2 from the output unit 25 and performs simulation based on this placement data D2. At this time, the simulation unit 26 executes the simulation using device data representing the configuration of the component mounting system 100 in addition to the placement data D2. The "apparatus data" here includes the characteristics of the supply section 3, that is, the characteristics regarding the mounting machine 10 in which the supply section 3 is provided.

The simulation unit 26 determines at least the “mounting time” required for the component mounting system 100 to generate the product P3. Particularly in this embodiment, the simulation unit 26 calculates the mounting time for each of the plurality of supply units 3 included in the component mounting system 100. That is, regarding the component mounting system 100 including a plurality of supply units 3, the simulation unit 26 obtains the mounting time required for mounting the component P1 for each supply unit 3 as a simulation result. The simulation results in the simulation unit 26 are outputted from the output unit 25 in an arbitrary manner, for example. In this embodiment, the simulation result by the simulation unit 26 is outputted to at least the identification unit 23, and is used by the identification unit 23 to identify the target supply unit.

The model storage unit 27 stores the trained model M1. The trained model M1 stored in the model storage unit 27 is used at least for the proposal unit 22 to propose the placement of the component P1. In this embodiment, the trained model M1 stored in the model storage unit 27 is used not only by the proposal unit 22 but also by the relocation unit 24 to propose the placement of the component P1. Although details will be explained in the section "(3.2) Trained Model," the trained model M1 is generated through prior learning. Furthermore, the learned model M1 is a model that is generated in association with the characteristics of at least one of the plurality of supply units 3 in the component mounting system 100. Here, since the component mounting system 100 includes a plurality of supply units 3 having mutually different characteristics, there are also a plurality of types of learned models M1. Therefore, the model storage unit 27 is configured to be able to store a plurality (types) of trained models M1.

In addition to the above configuration, the placement support system 20 may further include a communication unit, a user interface, and the like. However, the communication unit, user interface, etc. are not essential components of the placement support system 20. In FIG. 3, illustration of the configuration of the placement support system 20 other than the acquisition unit 21, proposal unit 22, identification unit 23, relocation unit 24, output unit 25, simulation unit 26, and model storage unit 27 is omitted as appropriate. ing.

The communication unit is configured to communicate with the component mounting system 100 and/or the host system directly or indirectly via a network, a repeater, or the like. This allows the placement support system 20 to exchange data with the component mounting system 100 and/or the host system.

The user interface includes, for example, a touch panel display, and receives user operations and presents (displays) information to the user. The user interface is not limited to a touch panel display, and may include an input device such as a keyboard, pointing device, mechanical switch, or gesture sensor. Further, the user interface may include an audio input/output section instead of or in addition to the touch panel display.

By the way, as described above, the placement support system 20 according to this embodiment constitutes the work system 200 together with the component mounting system 100. That is, the work system 200 according to this embodiment includes an arrangement support system 20 and a component mounting system 100, as shown in FIG. The component mounting system 100 is a system that is used in the placement of a plurality of components P1 proposed by the placement support system 20, and generates a product P3.

(3) Placement Support Method The placement support method according to this embodiment will be described in more detail below. In this embodiment, the placement support method employs three functions, as described above, such as placement proposal using the trained model M1, multi-stage distribution of parts P1, and relocation. Therefore, in the following, the placement support method according to the present embodiment will be explained in four parts: basic aspect, placement proposal using learned model M1, multi-stage distribution of parts P1, and relocation.

Further, in the following description, as an example, it is assumed that 240 parts P1 are distributed to the following eight supply units 3. In other words, in this embodiment, as described above, the component mounting system 100 includes a total of four mounting machines: the first mounting machine 11, the second mounting machine 12, the third mounting machine 13, and the fourth mounting machine 14. A mounting machine 10 is provided. Furthermore, since each of these four mounting machines 10 has two supply sections 3, in terms of the entire component mounting system 100, there are a total of eight supply sections as destinations for distributing a plurality of (here, 240) components P1. 3 exists.

Here, it is assumed that both the first mounting machine 11 and the second mounting machine 12 have a feature that the number of capturing sections 41 is "16". Therefore, the first supply section 31 and the second supply section 32 provided in the first mounting machine 11, and the third supply section 33 and the fourth supply section 34 provided in the second mounting machine 12. Both have the feature that the number of capturing units 41 is "16". On the other hand, it is assumed that the third mounting machine 13 has a characteristic that the number of trapping units 41 is "8". Therefore, the fifth supply section 35 and the sixth supply section 36 provided in the third mounting machine 13 both have the characteristic that the number of capturing sections 41 is "8". Furthermore, it is assumed that the fourth mounting machine 14 has a characteristic that the number of trapping units 41 is "3". Therefore, the seventh supply section 37 and the eighth supply section 38 provided in the fourth mounting machine 14 both have the characteristic that the number of capturing sections 41 is "3".

However, these conditions are merely specific examples to explain the placement support method and are not intended to limit the scope of application of the placement support method.

(3.1) Basic aspects First, the basic aspects of the placement support method according to this embodiment will be described with reference to FIGS. 4A, 4B, and 5. FIGS. 4A and 4B are conceptual diagrams showing how the arrangement of the plurality of parts P1 in the plurality of supply units 3 is proposed by the arrangement support method.

In the component mounting system 100 having multiple (here, eight) supply units 3 as in this embodiment, there are many patterns for arranging the multiple components P1 in the multiple supply units 3. In particular, in this embodiment, as described above, the number of slots in each supply unit 3 is "60", so the component mounting system 100 as a whole has 480 (= 60 x 8) slots. Therefore, the component mounting system 100 can mount up to 480 components P1, and if the number of components P1 actually mounted is several hundred, the number of arrangement patterns for the multiple components P1 in the multiple supply units 3 will be enormous. Moreover, the mounting time required for the component mounting system 100 to generate the product P3 varies greatly depending on the arrangement of the multiple components P1 in the multiple supply units 3.

In other words, even if the configuration of the component mounting system 100 is the same, if the arrangement of the plurality of components P1 in the plurality of supply units 3 is different, which mounting machine 10 will mount each component P1 will be different. The time required for mounting each component P1 varies greatly. Therefore, for example, even if the mounting time required to generate one product P3 is to be shortened, it is extremely difficult to find an appropriate pattern for arranging a plurality of parts P1 from among a huge number of patterns. . Therefore, the placement support method according to the present embodiment supports the task of determining the placement of the plurality of components P1 in the plurality of supply units 3 in the component mounting system 100, thereby achieving more appropriate placement more easily (and in a shorter time). time).

As described above, in the placement assistance method according to this embodiment, the proposal for the "placement" of part P1 is only the allocation of part P1 out of the proposals for the allocation and arrangement of part P1. In other words, in this embodiment, multiple parts P1 are divided into multiple parts, and one or more parts P1 after the division are assigned to one of multiple supply units 3, but the order in which the one or more parts P1 are arranged after the division is not specified.

That is, the basic aspect of the placement support method according to this embodiment is to distribute a plurality of unplaced parts P1 to two or more supply units 3, as shown in FIGS. 4A and 4B. In FIGS. 4A and 4B, an unarranged space Sp0 labeled "unarranged" is a virtual space that schematically represents a state where the space is not distributed to any supply unit 3, that is, an unarranged state. That is, in FIG. 4A, the component P1 existing in the unplaced space Sp0 is not distributed to any of the supply units 3. On the other hand, in FIGS. 4A and 4B, the space labeled "supply section" is a virtual space that schematically represents a state where the supplies are distributed to any of the supply sections 3, that is, an already arranged state. That is, in FIG. 4B, the component P1 existing in the space designated by reference numeral "31" is in a state of being distributed (assigned) to the first supply section 31. Similarly, in FIG. 4B, the component P1 present in the space designated by reference numeral “32” is in a state of being distributed (assigned) to the second supply unit 32.

In the placement support method according to the present embodiment, as shown in FIG. 4A, the initial state is a state in which all of the plurality of components P1 to be mounted in the component mounting system 100 are not placed. In other words, in the placement support method, by first setting all of the plurality of parts P1 in a state where they are not distributed to any of the supply units 3, as shown in FIG. 4A, all of the plurality of parts P1 are placed in the unplaced space Sp0. Realize the initial state that exists in . In the placement support method, once the initial state is achieved, the unplaced parts P1 are selected one by one, and it is determined to which supply unit 3 the selected parts P1 should be distributed (assigned). decide. That is, in the placement support method, by allocating the plurality of parts P1 one by one to one of the supply units 3, the allocation destinations of the plurality of parts P1 are sequentially determined.

Then, all of the plurality of components P1 to be mounted in the component mounting system 100 are distributed (allocated) to one of the supply units 3, that is, there are no unplaced components P1, and according to the basic aspect of the placement support method. Processing completes. In short, according to the basic aspect of the placement support method, as shown in FIG. state) is realized.

Specifically, for example, by associating component identification information for identifying each of the plurality of parts P1 and supply section identification information for identifying each of the plurality of supply sections 3 on a one-to-one basis, The parts P1 are distributed. As an example, for a component P1 that is not distributed to any supply section 3, the supply section identification information is not associated with the component identification information, or the supply section identification information corresponding to the component identification information is null. ). Furthermore, regarding the component P1 distributed to the first supply section 31, the supply section identification information of the first supply section 31 is associated with the component identification information. Then, when the correspondence between the component identification information and the supply section identification information is completed for all of the plurality of parts P1, a state in which all the plurality of parts P1 are distributed to one of the supply sections 3 is realized. . The data representing the correspondence between the component identification information and the supply section identification information in a state where all the plurality of components P1 are sorted becomes the arrangement data D2. In other words, the arrangement data D2 represents the correspondence relationship with the supply unit identification information for all of the plurality of parts P1, and becomes data representing distribution to any one of the supply units 3.

By the way, in the placement support method according to the present embodiment, the trained model M1 is used in proposing the placement of the component P1 according to such a basic aspect. That is, in the basic aspect of the placement support method, the learned model M1 is used to propose placement of the plurality of parts P1 to the plurality of supply units 3. The learned model M1 is a model generated in association with the characteristics of at least one of the plurality of supply units 3. In the placement support method according to the present embodiment, using such a trained model M1, a plurality of components are placed on a plurality of supply units 3 so as to shorten the mounting time required to generate a product P3 in the component mounting system 100. The arrangement of component P1 is proposed. As will be explained in detail in the section “(3.2) Learned Model”, the trained model M1 is generated by reinforcement learning.

Furthermore, as shown in FIG. 5, the placement support method according to the present embodiment includes a processing part S100 for temporary placement and a processing part S200 for relocation. Then, the placement support method proposes distribution of the plurality of parts P1 in both the processing part S100 for temporary placement and the processing part S200 for relocation, according to the basic aspect as described above. That is, in this embodiment, the trained model M1 is used in both the processing part S100 for temporary placement and the processing part S200 for relocation.

That is, in the processing part S100 for temporary placement, the plurality of parts P1 are once distributed to the plurality of supply units 3. However, if at least some of the components P1 are distributed to inappropriate supply units 3, this may lead to problems such as a longer mounting time in the component mounting system 100, for example. Therefore, in the processing part S200 for rearrangement, a more appropriate arrangement (allocation) is proposed by re-allocating the plurality of parts P1 that have been allocated once.

In addition, when distributing the plurality of parts P1 to the plurality of supply units 3 in the processing part S100 for temporary placement, if the number of supply units 3 increases, the search space for performing reinforcement learning of the trained model M1 becomes wider. This makes it difficult to generate the trained model M1. Therefore, in the placement support method according to the present embodiment, a multi-stage distribution of components P1 is adopted in the processing part S100 for temporary placement. In other words, according to the multi-stage distribution of parts P1, even if, for example, multiple parts P1 are simply distributed into two groups at each stage, the multiple parts P1 will ultimately be distributed into four or more groups. Can be done. As a result, it is possible to narrow the search space for performing reinforcement learning of the trained model M1 while using the trained model M1 in the distribution of each stage.

As explained above, according to the placement support method according to the present embodiment, it is possible to determine the placement of the plurality of parts P1 in the plurality of supply units 3, for example, without the help of an expert or the like. , it is possible to propose an improved arrangement of the component P1.

Further, the flowchart shown in FIG. 5 is only an example, and the order of processing may be changed as appropriate, and processing may be added or deleted as appropriate.

(3.2) Learned model Next, in the placement support method according to the present embodiment, a proposal for placement of a plurality of parts P1 using the learned model M1 will be explained with reference to FIGS. 5 and 6. Explain in detail.

The placement support method has an acquisition step and a proposal step. The acquisition step is a step of acquiring mounting data D1, and corresponds to process S101 in the flowchart shown in FIG. 5. The acquisition step is executed by the acquisition unit 21 of the placement support system 20. The mounting data D1 is data on multiple components P1 included in the product P3. The proposal step is a step of proposing, using the trained model M1, the placement of multiple components P1 to multiple supply units 3 from the mounting data D1 so as to shorten the mounting time. The proposal step is executed by the proposal unit 22 of the placement support system 20. In this embodiment, a multi-stage method of allocating components P1 is adopted, so in the flowchart shown in FIG. 5, the processes S102 to S10m of allocation from the "1st stage" to the "Nth stage" correspond to the proposal step.

In this embodiment, the generation (pre-learning) of the learned model M1 is executed by the placement support system 20. Furthermore, as described above, reinforcement learning is used to generate the trained model M1. In other words, the placement support system 20 uses the proposal unit 22 as a learning device for reinforcement learning, for example. “Reinforcement learning” as referred to in this disclosure is a method of machine learning technology that is a framework for automatically acquiring rules from data.

In machine learning technology, apart from "reinforcement learning," ``supervised learning'' is a widely used method. "Supervised learning" is a method of learning based on data with clearly defined numerical values as learning objectives. Therefore, in ``supervised learning,'' a large amount of data (learning data) with a clear goal is required for learning. However, in the technical field of the component mounting system 100, the target values for the arrangement of the plurality of components P1 in the plurality of supply sections 3 are not clear, and it is difficult to collect a large amount of learning data for learning. It is.

In contrast, "reinforcement learning" is a technique in which an "action" is performed in a certain "environment", the "situation" that changes as a result of that "action" is observed, and a high "reward" is given to "actions" that produce good results. Then, "reinforcement learning" learns how to select the optimal "action" that maximizes the "reward" through a series of these "actions". Therefore, with "reinforcement learning", unlike with "supervised learning", it is not necessary to prepare learning data with clearly defined goals, and it is possible to generate a trained model M1 that has learned how to "select" the optimal "action". In other words, with "reinforcement learning", even when the solution space is too large and the actual correct answer is unknown, the method of "action" is learned by repeating trial and error in a given "environment" and evaluating "actions" from the reward sequence observed.

Therefore, reinforcement learning is useful in cases where the correct answer is not clear and optimization is required for a huge number of combinations, such as the trained model M1 for proposing the placement of multiple parts P1 in multiple supply units 3. This is particularly effective in generating the trained model M1.

More specifically, in reinforcement learning, the mounting time when a certain arrangement is adopted for multiple components P1 is calculated, and the "reward" is determined based on how close this mounting time is to the ideal mounting time (the mounting time according to the specifications of the mounting machine 10). In this embodiment, as an example, the mounting time is calculated by the simulation unit 26. In reinforcement learning, the larger the search space becomes, the more times trial and error must be repeated to obtain a good "reward," and the longer it takes to search for the optimal solution. Therefore, in the placement support method according to this embodiment, a multi-stage method of allocating components P1 is adopted to reduce the size of the search space in reinforcement learning, and the multi-stage method will be described in detail in the "(3.3) Multi-stage method" section.

Furthermore, in the component mounting system 100, the characteristics and number of mounting machines 10, the type and number of components P1 to be mounted, etc. differ depending on the specifications of the product P3, for example. However, if reinforcement learning is performed each time to generate the trained model M1 according to the product P3, there is a concern that it will take time to generate the trained model M1 after the specifications of the product P3 are decided. There is. Therefore, in this embodiment, the trained model M1 is generated by "pre-learning" in which learning is performed before the specifications of the product P3 are determined. As a result, in the placement support method according to the present embodiment, once the specifications of the product P3 are determined, it is possible to immediately start proposing the placement of the part P1 using the learned model M1 that has been generated in advance learning. be.

Further, in the present embodiment, the learning device (for example, the proposal unit 22) creates placement data D2 using a reinforcement learning algorithm, and the created placement data D2 is output from the output unit 25 to the simulation unit 26. Thereby, the simulation unit 26 performs simulation based on the placement data D2 and calculates the "mounting time". The learning device (for example, the proposal unit 22) converts the implementation time obtained in this manner into a ratio to the ideal implementation time, and performs reinforcement learning using the obtained ratio as a "reward." Reinforcement learning is then performed by repeating the series of processes described above many times in order to obtain better "rewards." In this embodiment, as an example, in order to perform reinforcement learning, deep reinforcement learning (DQN: Deep Q-Network), etc., which has added feature extraction performance of deep learning, is used.

By the way, in the present embodiment, the learned model M1 is a model generated in association with the characteristics of at least one supply section 3 among the plurality of supply sections 3 in the component mounting system 100. In other words, the learned model M1 reflects the characteristics of the supply unit 3, and the learned model M1 is generated for each characteristic of the supply unit 3. Therefore, if the component mounting system 100 includes a plurality of supply units 3 having mutually different characteristics, a plurality of types of learned models M1 will be generated.

In particular, in this embodiment, the trained model M1 is associated with the characteristics of the supply unit 3 to which the part P1 is to be allocated (assigned) in the proposed placement of the part P1 using the trained model M1. Therefore, for example, even when the part P1 is allocated to two allocation destinations as shown in FIG. 6, various trained models M11 to M17 are used depending on the allocation destination. The trained models M11 to M17 used in FIG. 6 will be explained in the section "(3.3) Multi-stage method". In this disclosure, when there is no particular distinction between these multiple trained models M11 to M17, each of the multiple trained models M11 to M17 will simply be referred to as "trained model M1".

Here, for example, if the two supply units 3 that are the distribution destinations have the same feature (referred to as the "first feature"), the trained model M1 is generated in association with the first feature. That will happen. That is, the learned model M1 includes a model generated in association with the feature (first feature) of one of the plurality of supply units 3. As an example, if the two supply units 3 that are the distribution destinations both have the characteristic that the number of traps 41 is "16", the learned model M1 for distributing the part P1 has the number of traps 41 "16". 16" is reflected.

On the other hand, for example, if the two supply units 3 that are the distribution destinations have different characteristics (referred to as "first characteristics" and "second characteristics"), the trained model M1 has the first characteristics. and the second feature. That is, the learned model M1 includes a model generated in association with the characteristics of two or more of the plurality of supply units 3. As an example, if two supply units 3 to be distributed have the characteristic that the number of traps 41 is "16" or "8", the trained model M1 for distributing the part P1 includes the number of traps 41. Two features are reflected as numbers: "16" and "8".

Further, the learned model M1 includes a model generated in association with one or more feature groups when the features of the plurality of supply units 3 are classified into one or more feature groups. For example, the speed (maximum mounting speed) of the mounting machine 10 can be classified into multiple speed ranges, such as multi-function machines (low-speed machines), medium-speed machines, and high-speed machines, so that small speed differences can be minimized. If so, they can be considered to be in the same speed range, such as being considered "high-speed aircraft." In other words, if the characteristic of the supply unit 3 is the "speed" of the mounting machine 10, the "speed range" such as a multi-function machine (low-speed machine), a medium-speed machine, and a high-speed machine is a feature group that includes multiple features (speeds). becomes. In this way, when setting a feature group that includes a plurality of mutually different features, the learned model M1 also includes a model that is generated in association with the feature group instead of individual features. Since the feature group consists of a set of a plurality of features, the learned model M1 generated in association with the feature group also corresponds to the learned model M1 generated in association with the feature of at least one supply unit 3. .

Furthermore, the placement support method according to the present embodiment further includes an updating step of updating the trained model M1. That is, the learned model M1 generated by machine learning (reinforcement learning in this embodiment) is not fixed, but can be updated as appropriate through an update step. Specifically, the learning device (for example, the proposal unit 22) updates the learned model M1 stored in the model storage unit 27 regularly or irregularly. Updating the learned model M1 may be realized, for example, by transfer learning that uses knowledge acquired in the past for current learning, or by replacing it with a new learned model M1. If it is possible to update the trained model M1, it becomes possible to generate an appropriate trained model M1 according to the user's request during the operation stage of the placement support method (placement support system 20).

Furthermore, in the present embodiment, the learned model M1 includes a model generated in association with information regarding the product P3 generated by the component mounting system 100. The information regarding the product P3 includes, for example, the technical field to which the product P3 belongs, the lot number of the product P3, or the price range of the product P3. The component mounting system 100 is used to generate products P3 in various technical fields, such as the technical field of electronic equipment or the technical field of automobiles. Therefore, due to circumstances unique to each technical field (industry), the optimal arrangement of the parts P1 may differ even for similar products P3. Therefore, in the present embodiment, the learned model M1 is generated in association with information regarding the product P3 so as to reflect not only the characteristics of at least one supply unit 3 but also the circumstances specific to the product P3. Ru.

Furthermore, in the arrangement support method according to the present embodiment, when arranging the plurality of parts P1 to the plurality of supply parts 3, a constraint condition is attached that defines whether or not a particular part P1 can be arranged to a particular supply part 3. There is. That is, depending on the supply section 3, it may not be possible to arrange a specific component P1 due to restrictions on the specifications of the mounting machine 10, restrictions on the size of the component P1, or the like. In preparation for such a case, it is possible to add constraints. By adding a constraint condition, for a specific part P1 that is specified by the constraint condition as being impossible to place in a specific supply section 3, the specific supply section 3 is excluded from the distribution target. Ru. As an example, in the supply unit 3 where a tape feeder cannot be attached and only a tray can be installed, the constraint condition can specify that it is impossible to arrange the component P1 supplied by the tape feeder. It is.

Furthermore, in the present embodiment, the determination of whether or not a specific part P1 can be placed in a specific supply section 3 based on the constraint condition is a proposal for placement of a plurality of parts P1 in a plurality of supply sections 3 using the trained model M1. is done separately. That is, the restriction on the placement of the component P1 based on the constraint condition is performed, for example, before or after the proposal of the placement of the component P1 using the learned model M1. As an example, if the placement of part P1 is constrained by constraint conditions before proposing the placement of part P1 using trained model M1, options for deriving an appropriate placement of multiple parts P1 are selected. can be kept to a minimum.

As explained above, in the placement support method according to the present embodiment, when arranging the plurality of parts P1, the learned model M1 is used and the plurality of supply parts 3 are Propose the arrangement of the plurality of parts P1 for (proposal step). Therefore, in the proposal step, rather than proposing an unambiguously determined layout, for example, by using the trained model M1 to realize the skill of "determining" the layout, as done by an expert, the appropriate layout can be achieved. can be found more easily.

(3.3) Multi-stage method Next, among the placement support methods according to the present embodiment, the multi-stage method of distributing parts P1 will be described in more detail with reference to FIGS. 5 and 6.

The placement support method has a primary proposal step and a secondary proposal step. The primary proposal step is a step of proposing the placement (allocation) of multiple parts P1 to multiple primary groups G11 and G12, and corresponds to process S102 in the flowchart shown in FIG. 5. The primary proposal step is executed by the primary proposal unit 221 of the proposal unit 22 in the placement support system 20. The secondary proposal step is a step of proposing the placement of multiple parts P1 to multiple secondary groups G21 to G24 after the primary proposal step, and corresponds to process S103 in the flowchart shown in FIG. 5. The secondary proposal step is executed by the secondary proposal unit 222 of the proposal unit 22 in the placement support system 20. That is, in the flowchart shown in FIG. 5, the processes S102 to S10m of allocation of the "1st tier" to the "Nth tier", which correspond to the proposal step, include the primary proposal step and the secondary proposal step.

Here, the placement support method according to the present embodiment further includes a tertiary proposal step. The tertiary proposal step includes, after the secondary proposal step, the classification of the plurality of parts P1 for the plurality of tertiary groups G31 to G38 when each of the plurality of secondary groups G21 to G24 is classified into the plurality of tertiary groups G31 to G38. This is the step of proposing placement. Each of the plurality of tertiary groups G31 to G38 includes at least one supply section 3 among the plurality of supply sections 3. In short, according to the tertiary proposal step, each of the plurality of secondary groups G21 to G24 is classified into a plurality of more subdivided tertiary groups G31 to G38, and a plurality of parts P1 for these tertiary groups G31 to G38 are classified. arrangement is proposed.

That is, in this embodiment, as shown in FIG. 5, the arrangement of the plurality of parts P1 is not performed in two stages, but in hierarchically set N stages (here, N is a natural number of "3" or more). This is achieved through the processing of Therefore, even after the second stage of distribution (S103) is performed as a secondary proposal step, the third and subsequent stages of distribution are performed, thereby making it possible to realize more detailed distribution. In particular, in this embodiment, it is assumed that the plurality of parts P1 are distributed into two groups at each stage and finally distributed to eight supply units 3, so the distribution is performed in three stages. . Therefore, the tertiary proposal step corresponds to the final stage of the proposal step, that is, the process S10m (here, m is "4") in the flowchart shown in FIG. The tertiary proposal step is executed by the tertiary proposal unit 223 of the proposal unit 22 in the placement support system 20.

FIG. 6 is an explanatory diagram schematically showing how parts P1 are distributed in a multi-stage system. In this embodiment, the proposal for the arrangement of the plurality of parts P1 includes at least a primary proposal step of arranging the part P1 in a plurality of primary groups G11 and G12, and a further arrangement of the part P1 in a plurality of finer secondary groups G21 to G24. It is divided into a secondary proposal step. In this way, the arrangement of the plurality of parts P1 is realized not by one-step processing but by multi-stage processing set hierarchically, so that the appropriate arrangement of the plurality of parts P1 can be derived at each stage. The number of options can be kept to a minimum.

In FIG. 6, the plurality of primary groups G11 and G12 are divided into groups of two or more groups. This corresponds to the group after classification. Each of the plurality of primary groups G11, G12 includes at least one supply section 3 among the plurality of supply sections 3, respectively.

Specifically, as shown in FIG. 6, the primary group G11 (denoted as "Group 1" in the figure) includes a first supply section 31, a second supply section 32, a third supply section 33, and a fourth supply section 33. A supply section 34 is included. The primary group G12 (denoted as "Group 2" in the figure) includes a fifth supply section 35, a sixth supply section 36, a seventh supply section 37, and an eighth supply section 38.

In the primary proposal step, the plurality of unplaced parts P1 existing in the unplaced space Sp0 are sorted into a plurality of primary groups G11 and G12. As a result, the plurality of parts (240 in this case) P1 are sorted into one of the plurality of primary groups G11 and G12.

Further, in FIG. 6, the plurality of secondary groups G21 to G24 correspond to groups after classification when each of the plurality of primary groups G11 and G12 is further classified into two or more groups. Here, it is assumed that each of the two primary groups G11 and G12 is further classified into two secondary groups to generate a total of four secondary groups G21 to G24. Each of the plurality of secondary groups G21 to G24 includes at least one supply section 3 among the plurality of supply sections 3, respectively.

Specifically, as shown in FIG. 6, the secondary group G21 (denoted as "Group 1_1" in the diagram) and the secondary group G22 (denoted as "Group 1_2" in the diagram) are located under the primary group G11. do. In other words, the primary group G11 is classified into two secondary groups G21 and G22. The secondary group G23 (denoted as "Group 2_1" in the figure) and the secondary group G24 (denoted as "Group 2_2" in the figure) are located under the primary group G12. In other words, the primary group G12 is classified into two secondary groups G23 and G24. The secondary group G21 includes a first supply section 31 and a second supply section 32, and the secondary group G22 includes a third supply section 33 and a fourth supply section 34. Secondary group G23 includes a fifth supply section 35 and a sixth supply section 36, and secondary group G24 includes a seventh supply section 37 and an eighth supply section 38.

In the secondary proposal step, the plurality of parts P1 included in the primary group G11 are distributed to the plurality of secondary groups G21 and G22, and the plurality of parts P1 included in the primary group G12 are divided into the plurality of secondary groups G23 and G24. Sort it out. As a result, the plurality of parts P1 (240 in this case) are sorted into one of the plurality of secondary groups G21 to G24.

In addition, in FIG. 6, the multiple tertiary groups G31 to G38 correspond to the groups after classification when each of the multiple secondary groups G21 to G24 is further classified into two or more groups. Here, it is assumed that each of the four secondary groups G21 to G24 is further classified into two tertiary groups, generating a total of eight tertiary groups G31 to G38. Each of the multiple tertiary groups G31 to G38 includes at least one supply unit 3 out of the multiple supply units 3.

Specifically, as shown in FIG. 6, tertiary group G31 and tertiary group G32 are located under secondary group G21, and tertiary group G33 and tertiary group G34 are located under secondary group G22. In other words, the secondary group G21 is classified into two tertiary groups G31 and G32, and the secondary group G22 is classified into two tertiary groups G33 and G34. Tertiary group G35 and tertiary group G36 are located under secondary group G23, and tertiary group G37 and tertiary group G38 are located under secondary group G24. In other words, the secondary group G23 is classified into two tertiary groups G35 and G36, and the secondary group G24 is classified into two tertiary groups G37 and G38. In the example of FIG. 6, the plurality of tertiary groups G31 to G38 are the final stages of the multi-stage system, so each of the plurality of tertiary groups G31 to G38 includes one supply section 3. That is, in this embodiment, since it is assumed that the parts P1 are ultimately distributed to eight supply units 3, the plurality (here, eight) tertiary groups G31 to G38, which are the final stage, are -8 supply units 31-38 on a one-to-one basis.

In the tertiary proposal step, the multiple parts P1 included in the secondary group G21 are allocated to multiple tertiary groups G31 and G32, and the multiple parts P1 included in the secondary group G22 are allocated to multiple tertiary groups G33 and G34. Furthermore, in the tertiary proposal step, the multiple parts P1 included in the secondary group G23 are allocated to multiple tertiary groups G35 and G36, and the multiple parts P1 included in the secondary group G24 are allocated to multiple tertiary groups G37 and G38. As a result, the multiple parts P1 (240 in this case) are allocated to one of the multiple tertiary groups G31 to G38, that is, the first to eighth supply units 31 to 38.

Here, in the placement support method according to the present embodiment, as shown in FIG. 6, the learned model M1 is used when allocating each stage. That is, in at least one of the primary proposal step and the secondary proposal step, the learned model M1 is used to propose the arrangement of the plurality of parts P1. The trained model M1 is a model generated in association with the characteristics of at least one supply unit 3 among the plurality of supply units 3, as explained in the section “(3.2) Trained model”. . In this embodiment, the trained model M1 is used in each of the primary proposal step, secondary proposal step, and tertiary proposal step.

That is, in the first proposal step of distributing the plurality of parts P1 into the plurality of primary groups G11 and G12, the learned model M11 is used to divide the plurality of primary groups G11 and G12 from the mounting data D1 so as to shorten the mounting time. The arrangement of the plurality of parts P1 is proposed. In the secondary proposal step of distributing the plurality of parts P1 into the plurality of secondary groups G21 to G24, the learned models M12 and M13 are used to divide the plurality of secondary groups G21 from the mounting data D1 so as to shorten the mounting time. - Propose the arrangement of the plurality of parts P1 for G24. In the tertiary proposal step of distributing the plurality of parts P1 into the plurality of tertiary groups G31 to G38, the learned models M14 to M17 are used to create a model for the plurality of tertiary groups G31 to G38 from the mounting data D1 so as to shorten the mounting time. The arrangement of the plurality of parts P1 is proposed.

Here, as is clear from FIG. 6, the trained model M1 to be used differs depending on which stage among the primary proposal step, secondary proposal step, and tertiary proposal step. That is, in this embodiment, as described above, various learned models M11 to M17 are used depending on the destination to which the part P1 is allocated. For example, the trained model M11 used in the primary proposal step is different from the trained models M12 and M13 used in the secondary proposal step. As a result, in this embodiment, the algorithms for proposing the arrangement of the plurality of parts P1 are different between the primary proposal step and the secondary proposal step. In this embodiment, "the algorithms are different" means that the trained models M1 to be used are different. Furthermore, in this embodiment, a different algorithm (trained model M1) from the primary proposal step and the secondary proposal step is employed in the tertiary proposal step as well.

Furthermore, in this embodiment, various learned models M11 to M17 are used in the distribution at each stage depending on the destination to which the part P1 is distributed. For example, in the secondary proposal step, the learned model M12 is used to sort the plurality of parts P1 included in the primary group G11 into the plurality of secondary groups G21 and G22. On the other hand, in the secondary proposal step, the learned model M13 is used to allocate the multiple parts P1 included in the primary group G12 to the multiple secondary groups G23 and G24. Similarly, in the tertiary proposal step, the learned model M14 is used to sort the plurality of parts P1 included in the secondary group G21 to the plurality of tertiary groups G31 and G32. On the other hand, in the tertiary proposal step, the learned model M17 is used to sort the plurality of parts P1 included in the secondary group G24 to the plurality of tertiary groups G37 and G38.

As a result, in the placement support method according to this embodiment, seven trained models M11 to M17 are used, as shown in FIG.

Specifically, the trained model M11 used in the primary proposal step is a model for distributing the plurality of parts P1 to be distributed to the first to eighth supply units 31 to 38 into two primary groups G11 and G12. . Regarding the learned model M11, the distribution destinations include the first to fourth supply units 31 to 34 where the number of capture units 41 is “16”, and the fifth and sixth supply units where the number of capture units 41 is “8”. Supply sections 35 and 36, and seventh and eighth supply sections 37 and 38 in which the number of capturing sections 41 is "3" are included. Therefore, the trained model M11 is a model that is generated in association with the three features "16", "8", and "3" as the number of capture units 41 so as to reflect these three features.

The trained model M12 used in the secondary proposal step is a model for allocating multiple parts P1 to be allocated to the first to fourth supply units 31 to 34 into two secondary groups G21, G22. For the trained model M12, the allocation destinations include the first to fourth supply units 31 to 34, which have 16 capture units 41 in number. Therefore, the trained model M12 is a model generated in association with the feature of 16 as the number of capture units 41, so as to reflect one feature of 16 as the number of capture units 41.

On the other hand, the learned model M13 used in the secondary proposal step is a model for distributing the plurality of parts P1 to be distributed to the fifth to eighth supply units 35 to 38 into two secondary groups G23 and G24. Regarding the learned model M13, the distribution destinations include the fifth and sixth supply units 35 and 36 where the number of capture units 41 is “8”, and the seventh and eighth supply units where the number of capture units 41 is “3”. supply sections 37 and 38 are included. Therefore, the learned model M13 is a model that is generated in association with the two features "8" and "3" as the number of capture units 41 so as to reflect these two features.

The trained model M14 used in the tertiary proposal step is a model for distributing the plurality of parts P1 to be distributed to the first and second supply units 31 and 32 into two tertiary groups G31 and G32. Regarding the learned model M14, the distribution destinations include the first and second supply units 31 and 32 in which the number of capture units 41 is “16”. Therefore, the trained model M14 is a model that is generated in association with the feature "16" as the number of capture units 41 so as to reflect the single feature "16" as the number of capture units 41.

The learned model M15 used in the tertiary proposal step is a model for distributing the plurality of parts P1 to be distributed to the third and fourth supply units 33 and 34 into two tertiary groups G33 and G34. Regarding the learned model M15, the distribution destinations include the third and fourth supply units 33 and 34 in which the number of capture units 41 is “16”. Therefore, the learned model M15 is a model generated in association with the feature "16" as the number of capture units 41 so as to reflect one feature of "16" as the number of capture units 41.

The trained model M16 used in the tertiary proposal step is a model for distributing the plurality of parts P1 to be distributed to the fifth and sixth supply units 35 and 36 into two tertiary groups G35 and G36. Regarding the trained model M16, the distribution destinations include the fifth and sixth supply units 35 and 36 in which the number of capture units 41 is “8”. Therefore, the learned model M16 is a model that is generated in association with the feature of "8" as the number of capture units 41 so as to reflect the single feature of "8" as the number of capture units 41.

The learned model M17 used in the tertiary proposal step is a model for distributing the plurality of parts P1 to be distributed to the seventh and eighth supply units 37 and 38 into two tertiary groups G37 and G38. As for the learned model M17, the distribution destinations include the seventh and eighth supply units 37 and 38 in which the number of capture units 41 is “3”. Therefore, the learned model M17 is a model that is generated in association with the feature that the number of capture units 41 is “3” so as to reflect the single feature that the number of capture units 41 is “3”.

The plurality of trained models M11 to M17 (seven in this case) as described above are generated by individually performing reinforcement learning. That is, reinforcement learning is performed in advance for each of a plurality of hierarchically set stages (here, three stages), and the trained models M11 to M17 as described above are generated. By linking the plurality of learned models M11 to M17 generated in this way, a multi-stage architecture as shown in FIG. 6 is constructed.

As explained above, in the placement support method according to the present embodiment, the placement of the plurality of parts P1 is realized not by one-step processing but by multi-step processing (here, three steps) set hierarchically. Ru. This makes it possible to reduce the number of options for deriving an appropriate arrangement of the plurality of parts P1 at each stage, compared to a multiple selection method in which the plurality of parts P1 are distributed in one stage of processing. As a result, the search space for performing reinforcement learning on the trained model M1 can be narrowed. For example, when distributing 240 parts to the eight supply units 3, it is assumed that the search space is "10 ²⁴⁰ " in the case of a one-stage multiple selection method. On the other hand, in the case of a three-stage multi-stage method, even under the same conditions, the search space for the primary proposal step is 10 ⁸⁰ , the search space for the secondary proposal step is 10 ⁷² , and the search space for the tertiary proposal step is 10 80 . The search space becomes "10 ³⁶ ". As a result, the exploration space for distributing 240 parts to the eight supply units 3 is "10 ⁸⁰ +10 ⁷² +10 ³⁶ ", which is much narrower than "10 ²⁴⁰ " in the multiple selection method. The size of the search space can be reduced to a size that allows actual learning.

Furthermore, the above description is only an example of the placement support method according to the present embodiment, and for example, the placement of the plurality of parts P1 may be realized by two steps or four or more steps of processing instead of three steps of processing. Good too. When the distribution is performed in two stages, the tertiary proposal step is omitted, and the secondary groups G21 to G24 are respectively associated with the plurality of supply units 3 on a one-to-one basis. On the other hand, when the distribution is performed in four stages, a plurality of quaternary groups are generated further below (under) the tertiary groups G31 to G38 to which the plurality of parts P1 are distributed in the tertiary proposal step. When the distribution is performed in five stages, a plurality of quintic groups are generated below (under) the quartic group.

(3.4) Relocation Next, of the placement support method according to the present embodiment, relocation will be described in more detail with reference to FIGS. 5 and 7.

The placement support method includes a proposing step, a specifying step, and a relocation step. The proposal step is a step of proposing the arrangement of the plurality of parts P1 to the plurality of supply units 3, and corresponds to processes S102 to S10m in the flowchart shown in FIG. The proposal step is executed by the proposal unit 22 of the placement support system 20. The specifying step is a step of specifying a certain supply section 3 among the plurality of supply sections 3 as a target supply section, and corresponds to processing S201 in the flowchart shown in FIG. The specifying step is executed by the specifying unit 23 of the placement support system 20. The supply unit 3 specified as the target supply unit is the supply unit 3 that satisfies the specific condition regarding the mounting time when the arrangement of the plurality of components P1 proposed in the proposal step is adopted. The rearrangement step is a step of proposing the arrangement of the plurality of parts P1 to the target supply unit and the reference supply unit, and corresponds to processes S202 to S204 in the flowchart shown in FIG. The relocation step is executed by the relocation unit 24 of the placement support system 20. The reference supply unit includes at least one supply unit 3 other than the target supply unit among the plurality of supply units 3 .

In this embodiment, in the relocation step (S202 to S204), additional distribution (S203) is repeatedly executed a specified number of times for the component P1 placed in the target supply unit. The "additional distribution" here refers to the arrangement (distribution) of the plurality of parts P1 to the plurality of supply parts 3 proposed in the temporary arrangement (S100), for some parts P1, to the plurality of supply parts 3. This is the process of redoing the arrangement (distribution) for the Therefore, the "designated number of times" for repeating additional distribution is the number of times determined according to the number of parts P1 to be subjected to additional distribution.

That is, in the processing part S100 for temporary placement, when distributing a plurality of parts P1 to a plurality of supply units 3, if at least some of the parts P1 are improperly disposed (distributed), the desired arrangement is performed as is. There is a possibility that no results will be obtained. For example, in the temporary placement (S100), if a certain component P1 is assigned to an inappropriate supply section 3, it will take time to mount this component P1, resulting in an inconvenience that the mounting time of the component mounting system 100 as a whole becomes longer. obtain. Therefore, in the placement support method according to the present embodiment, instead of finalizing the placement of the component P1 in the proposal step, the placement proposal in the proposal step is a "temporary placement", and in the subsequent relocation step, multiple It is possible to change (correct) the arrangement of the component P1.

Furthermore, the object to be rearranged in the rearrangement step is the supply unit 3 that satisfies a specific condition regarding the mounting time, that is, the component P1 placed in the target supply unit. Furthermore, what is subject to relocation in the relocation step is not only the target supply section that satisfies the specific conditions, but also includes the part P1 placed in the reference supply section, which is a supply section 3 different from the target supply section. There is. Therefore, it is possible to shuffle the plurality of parts P1 arranged in different supply sections 3 (target supply section and reference supply section) in the temporary arrangement. Therefore, even if a certain component P1 is assigned to an inappropriate supply section 3 during the temporary placement, relocation of the component P1 in the relocation step may cause inconveniences such as a longer mounting time. can be resolved.

In addition, in the placement support method according to the present embodiment, as shown in FIG. Looking for the placement of P1. In this embodiment, "improving the mounting time" means that the mounting time of the component mounting system 100 as a whole is shortened. That is, as shown in FIG. 5, in the placement support method, after the relocation step (S202 to S204), it is determined whether the mounting time has improved (S205). Therefore, the arrangement data D2 created in the relocation step is output from the output section 25 to the simulation section 26. Thereby, the simulation unit 26 performs a simulation based on the placement data D2 and calculates the "mounting time" after the rearrangement. In step S205, it is determined whether the mounting time has improved based on the mounting time obtained in this manner.

Here, in the placement support method, if the mounting time has not improved (S205: No), the placement of the component P1 changed in the relocation step is changed to the state before the relocation step, that is, the "original component placement". (S206). On the other hand, if the mounting time has not improved (S205: Yes), processing S206 is skipped. In other words, if the mounting time does not improve due to rearrangement, returning to the state before rearrangement improves (reduces) the mounting time, only when the part P1 obtained by rearrangement Adopt the following arrangement.

After that, the placement support method determines whether or not the component P1 has been moved from the state before the relocation step (S207). If any component P1 is moved in the relocation step (S207: Yes), the process returns to step S201. On the other hand, if none of the parts P1 is moved in the relocation step (S207: No), the processing part S200 for relocation ends. That is, as long as the arrangement of the part P1 can be changed (corrected) in the relocation step, since any part P1 is moved in the relocation step (S207: Yes), the identification step (S201) and the relocation step ( S202 to S204) are repeatedly executed. In other words, the specifying step (S201) and the rearranging steps (S202 to S204) are repeatedly executed until the pattern of changing (correcting) the arrangement of the component P1 that improves the mounting time in the rearranging step is exhausted.

FIG. 7 is an explanatory diagram schematically showing the state of rearrangement. In FIG. 7, based on the arrangement (distribution) of the plurality of parts P1 to the plurality of supply parts 3 proposed in the tentative arrangement, the fourth supply part 34 and the sixth supply part 34 among the first to eighth supply parts 31 to 38 are This conceptually shows how a plurality of parts P1 arranged in the supply section 36 are rearranged. Here, as an example, a case will be described in which the fourth supply section 34 is a "target supply section" and the sixth supply section 36 is a "reference supply section."

Here, in this embodiment, as an example, the supply unit 3 that becomes a bottleneck regarding the mounting time is set as the target supply unit. In other words, the component mounting system 100 sequentially mounts a plurality of components P1 arranged in a plurality of supply sections 3, and among the plurality of supply sections 3, the supply section 3 that takes the longest time to mount the component P1 is mounted. This creates a bottleneck regarding time. That is, in the present embodiment, the specific condition includes that the time (mounting time) required to generate the product P3 in the component mounting system 100 is the longest among the plurality of supply units 3. In the example of FIG. 7, when the arrangement proposed in the temporary arrangement is adopted for the component mounting system 100, the time required to mount the component P1 placed in the fourth supply section 34 among the plurality of supply sections 3 is the longest. Therefore, the fourth supply unit 34 is extracted as the target supply unit.

In this way, in the identification step, of the multiple supply units 3, a supply unit 3 that satisfies a specific condition regarding mounting time is identified as a target supply unit. Therefore, in this embodiment, the placement data D2 created in the temporary placement is output from the output unit 25 to the simulation unit 26. As a result, the simulation unit 26 performs a simulation based on the placement data D2 and calculates the "mounting time". The identification unit 23 extracts a supply unit 3 that satisfies the specific condition (target supply unit) based on the mounting time obtained in this way.

On the other hand, the reference supply section is an arbitrary supply section 3 different from the target supply section (here, the fourth supply section 34) among the plurality of supply sections 3. In this embodiment, it is assumed that any one supply section 3 other than the target supply section (here, the fourth supply section 34) among the plurality of supply sections 3 is sequentially selected as the reference supply section. do. The example in FIG. 7 shows the state of rearrangement when the sixth supply section 36 among the plurality of supply sections 3 is selected as the reference supply section. For example, once the rearrangement shown in FIG. 7 is completed, the seventh supply section 37 among the plurality of supply sections 3 is selected as the reference supply section, and the rearrangement is executed.

Also, in the rearrangement step, as shown in FIG. 7, the multiple parts P1 arranged in the target supply unit (fourth supply unit 34) and the reference supply unit (sixth supply unit 36) are temporarily moved to the unarranged space Sp0, and then reassigned to the target supply unit and the reference supply unit. In other words, the multiple parts P1 arranged in the target supply unit and the reference supply unit in the tentative arrangement are once returned to a state in which they are not assigned to any supply unit 3, that is, an unarranged state, and then reassigned to the target supply unit and the reference supply unit. In other words, in the rearrangement step, the arrangement of the multiple parts P1 is reset for the target supply unit and the reference supply unit, and then a new arrangement of the multiple parts P1 is proposed.

Furthermore, in the arrangement support method according to the present embodiment, as shown in FIG. 7, the learned model M1 is also used in the arrangement (distribution) of the plurality of parts P1 during relocation. In this embodiment, in at least one of the proposal step and the rearrangement step, the learned model M1 is used to propose the arrangement of the plurality of parts P1. The trained model M1 is a model generated in association with the characteristics of at least one supply unit 3 among the plurality of supply units 3, as explained in the section “(3.2) Trained model”. . In particular, in this embodiment, the trained model M1 is used in both the proposal step and the rearrangement step.

Here, in this embodiment, as described above, various learned models M1 are used depending on the destination to which the part P1 is allocated. Therefore, in relocation where the fourth supply unit 34 as the target supply unit and the sixth supply unit 36 as the reference supply unit are allocated, the trained model M11 used in the temporary placement (proposal step) A trained model M18, which is different from ~M17, is used. As a result, in this embodiment, the proposal step and the relocation step use different algorithms for proposing the placement of the plurality of parts P1.

Specifically, the trained model M18 used in the rearrangement step is a model for distributing the plurality of parts P1 to be distributed to the two supply units 3 to the fourth supply unit 34 and the sixth supply unit 36. be. Regarding the trained model M18, the distribution destinations include the fourth supply unit 34 where the number of capture units 41 is “16” and the sixth supply unit 36 where the number of capture units 41 is “8”. It will be done. Therefore, the trained model M18 is a model that is generated in association with the two features "16" and "8" as the number of capture units 41 so as to reflect these two features.

Also, in the relocation step, similar to the proposal step, the arrangement of the plurality of components P1 with respect to the plurality of supply units 3 is proposed so as to shorten the mounting time. That is, in the rearrangement step, the arrangement of the plurality of components P1 with respect to the target supply section and the reference supply section is proposed so as to shorten the mounting time required to generate the product P3 in the component mounting system 100.

Furthermore, in this embodiment, in the rearrangement step, as in the proposal step, when placing multiple parts P1 on multiple supply units 3, a constraint condition is imposed that specifies whether or not a specific part P1 can be placed on a specific supply unit 3. As explained in detail in the "(3.2) Trained model" section, by imposing a constraint condition, for a specific part P1 that is specified in the constraint condition as being impossible to place on a specific supply unit 3, the specific supply unit 3 is excluded from the targets for rearrangement (allocation).

In the placement support method according to the present embodiment, as described above, the identification step (S201) and the rearrangement steps (S202 to S204) are performed until the change pattern of the placement of the component P1 that improves the mounting time in the rearrangement step is exhausted. ) is executed repeatedly. Therefore, as a result of rearranging the supply unit 3 (target supply unit) that satisfies a specific condition regarding the implementation time (becoming a bottleneck), if another supply unit 3 satisfies the specific condition, another supply The relocation step is repeatedly performed using unit 3 as the target supply unit. On the other hand, as a result of rearranging the supply parts 3 that satisfy the specific conditions regarding the mounting time (becoming a bottleneck), if the same supply parts 3 still satisfy the specific conditions, the change pattern of the placement of the component P1 will be changed. As this is exhausted, the processing part S200 for relocation ends.

As described above, the placement support method according to the present embodiment further includes a relocation step (S202 to S204) in addition to the acquisition step (S101) and the proposal step (S102 to S10m). The rearrangement step is a step of proposing the arrangement of the plurality of parts P1 with respect to the plurality of supply units 3 after the proposal step. In particular, in this embodiment, the trained model M1 generated by reinforcement learning is used also in the rearrangement step, and the part P1 is It is possible to re-propose the placement of

Furthermore, since the placement assistance method according to this embodiment employs a multi-stage method in the proposal step, the rearrangement step is a step of proposing the placement of multiple components P1 after the secondary proposal step. Then, in the rearrangement step, the placement of multiple components P1 is proposed at least for the supply unit 3 that requires the longest time among the multiple supply units 3 to generate the product P3 in the component mounting system.

(4) Modifications Embodiment 1 is just one of various embodiments of the present disclosure. Embodiment 1 can be modified in various ways depending on the design, etc., as long as the objective of the present disclosure can be achieved. Furthermore, all the drawings referred to in this disclosure are schematic drawings, and the ratios of the sizes and thicknesses of each component in the drawings do not necessarily reflect the actual dimensional ratios. . Further, the same functions as the placement support method according to the first embodiment may be realized by the placement support system 20, a (computer) program, a non-temporary recording medium on which the program is recorded, or the like. A program according to one aspect is a program for causing one or more processors to execute the placement support method according to the first embodiment.

Modifications of the first embodiment will be listed below. The modified examples described below can be applied in combination as appropriate.

The placement support system 20 in the present disclosure includes a computer system. A computer system mainly consists of a processor and a memory as hardware. The function of the placement support system 20 in the present disclosure is realized by a processor executing a program recorded in the memory of the computer system. The program may be pre-recorded in the memory of the computer system, may be provided through a telecommunications line, or may be recorded on a non-transitory storage medium readable by the computer system, such as a memory card, optical disc, hard disk drive, etc. may be provided. A processor in a computer system is comprised of one or more electronic circuits including semiconductor integrated circuits (ICs) or large scale integrated circuits (LSIs). The integrated circuits such as IC or LSI referred to herein have different names depending on the degree of integration, and include integrated circuits called system LSI, VLSI (Very Large Scale Integration), or ULSI (Ultra Large Scale Integration). Furthermore, an FPGA (Field-Programmable Gate Array), which is programmed after the LSI is manufactured, or a logic device that can reconfigure the connections inside the LSI or reconfigure the circuit sections inside the LSI, may also be used as a processor. Can be done. The plurality of electronic circuits may be integrated into one chip, or may be provided in a distributed manner over a plurality of chips. A plurality of chips may be integrated into one device, or may be distributed and provided in a plurality of devices. The computer system herein includes a microcontroller having one or more processors and one or more memories. Therefore, the microcontroller is also composed of one or more electronic circuits including semiconductor integrated circuits or large-scale integrated circuits.

Further, it is not an essential configuration of the placement support system 20 that a plurality of functions in the placement support system 20 are integrated into one housing. The components of the placement support system 20 may be distributed and provided in a plurality of housings. Furthermore, at least some of the functions of the placement support system 20 may be realized by a cloud (cloud computing) or the like.

Examples of functions that can be realized by being distributed over two or more systems such as a cloud (or server) and an edge include the following functions.

The first function is to generate a learned model M1. That is, it is possible to generate the trained model M1 in one system and perform the placement support method (proposal step, etc.) using this trained model M1 in another system. As an example, the trained model M1 can be generated in the cloud (or a server), and the placement support method (proposal step, etc.) using this trained model M1 can be performed at the edge. In this case, in one system such as a cloud, a trained model is generated by associating the trained model used in the placement support method with the characteristics of at least one of the plurality of supply units 3. The method will be implemented.

The second function is to allocate the parts P1 in a multi-stage manner. That is, it is possible to perform the primary proposal step in one system, and perform the secondary proposal step and subsequent steps (including the tertiary proposal step, etc.) in another system. As an example, the primary proposal step can be performed in the cloud (or server), and the secondary proposal steps and subsequent steps (including the tertiary proposal step, etc.) can be performed at the edge. In this case, the placement support system 20 is implemented as a system such as Edge, and executes only the secondary proposal step and subsequent steps (including the tertiary proposal step, etc.). In short, the placement support system 20 supports determining the placement of the plurality of components P1 in the plurality of supply units 3 regarding the component mounting system 100. The component mounting system 100 generates a product P3 by mounting a plurality of components P1 supplied to a plurality of supply units 3 onto an object P2. The placement support system 20 does not include a primary proposal unit 221 but includes a secondary proposal unit 222. The secondary proposal unit 222 proposes placement of the plurality of parts P1 in the plurality of secondary groups G21 to G24 when each of the plurality of primary groups G11 and G12 is classified into the plurality of secondary groups G21 to G24. . Each of the plurality of secondary groups G21 to G24 includes at least one supply section 3 among the plurality of supply sections 3. The secondary proposal unit 222 receives the proposal for the arrangement of the plurality of parts P1 for the plurality of primary groups G11 and G12, and proposes the arrangement of the plurality of parts P1 for the plurality of secondary groups G21 to G24. Here, proposals for the placement of the plurality of parts P1 for the plurality of primary groups G11 and G12 are made in a system different from the placement support system 20, and in a separate system (cloud, server, etc.) that includes a primary proposal unit 221. It will be done. That is, the placement support system 20 receives a proposal for placement of a plurality of parts P1 for a plurality of primary groups G11 and G12 from another system, and proposes a placement of a plurality of parts P1 for a plurality of secondary groups G21 to G24. .

The third function is the relocation function. That is, it is possible to perform the proposal step in one system, and perform the identification step and relocation step in another system. As an example, the proposal step can be performed at the edge, and the identification and relocation steps can be performed in the cloud (or server). In this case, the placement support method is implemented in a system such as a cloud (or server), and includes only a specifying step and a relocation step. In short, the placement support method is a method for supporting the determination of the placement of a plurality of components P1 in a plurality of supply units 3 regarding the component mounting system 100. The component mounting system 100 generates a product P3 by mounting a plurality of components P1 supplied to a plurality of supply units 3 onto an object P2. The placement support method does not include a proposal step, but includes a specifying step and a relocation step. The specifying step includes, in the case where the proposed arrangement of the plurality of parts P1 is adopted in response to the proposal of the arrangement of the plurality of parts in the plurality of supply parts, a supply part that satisfies a specific condition among the plurality of supply parts 3; 3 as the target supply unit. The specific conditions are conditions regarding the time required for the component mounting system 100 to generate the product P3. The rearrangement step is a step of proposing the arrangement of the plurality of parts P1 to the target supply section and a reference supply section consisting of at least one supply section 3 other than the target supply section among the plurality of supply sections 3. be.

On the contrary, in the first embodiment, at least some of the functions of the placement support system 20 or the work system 200, which are distributed over a plurality of devices, may be integrated into one housing. For example, some functions distributed between the component mounting system 100 and the placement support system 20 may be integrated into the component mounting system 100.

Further, the application of the component mounting system 100 is not limited to manufacturing electronic devices in a factory. For example, when the component mounting system 100 is used to mount a mechanical component onto a glass plate, the component mounting system 100 performs work to mount the mechanical component, which is the component P1, onto the glass plate, which is the object P2.

The number of capture units 41 provided on the mounting head 4 is not limited to the number described in the first embodiment. For example, the number of capture units 41 may be 17 or more. Of course, the mounting head 4 may be provided with only one capture unit 41. The mounting head 4 may be a rotary head.

Further, at least one mounting machine 10 among the plurality of mounting machines 10 may include only one supply section 3, or three or more supply sections 3. Similarly, at least one of the plurality of mounting machines 10 may include only one mounting head 4, or three or more mounting heads 4.

Further, in the first embodiment, the reference supply section is composed of any supply section 3 other than the target supply section among the plurality of supply sections 3, but the reference supply section is not limited to this example. For example, the supply unit 3 that has the most margin in terms of mounting time may be used as the reference supply unit. That is, the component mounting system 100 sequentially mounts a plurality of components P1 arranged in a plurality of supply sections 3, and among the plurality of supply sections 3, the supply section 3 that takes the shortest time to mount the component P1 It has the most leeway in terms of implementation time. That is, the reference supply section includes the supply section 3 that takes the shortest time among the plurality of supply sections 3 to generate the product P3 in the component mounting system 100. According to this configuration, in rearrangement, it is possible to shuffle the plurality of components P1 between the target supply section that is a bottleneck in terms of mounting time and the reference supply section that has the most margin in terms of mounting time. As a result, it becomes easier to improve the mounting time by rearranging.

In addition, the specific condition for specifying the target supply section may be a condition regarding the mounting time, and the mounting time is the longest among the plurality of supply sections 3 (the supply section 3 becomes a bottleneck). Not exclusively. For example, the specific condition is that the time required to generate the product P3 in the component mounting system 100 (mounting time) is the Mth longest (M is an integer greater than or equal to "2") among the plurality of supply units 3. There may be. On the other hand, the specific condition may be that the time required to generate the product P3 in the component mounting system 100 (mounting time) is the shortest among the plurality of supply units 3, or the like. In this way, depending on specific conditions, for example, it is possible to reduce variations in the time required to generate the product P3 in the component mounting system 100 in the plurality of supply units 3. In this case, for example, concentration of burden on a specific mounting machine 10 can be alleviated.

Further, the target supply section is not limited to one supply section 3 but may be two or more supply sections 3. Similarly, the reference supply section is not limited to one supply section 3, but may be two or more supply sections 3.

Further, the supply unit 3 is not limited to a configuration in which a tape feeder is attached, and for example, a tray on which a plurality of parts P1 are placed may be installed. Furthermore, the entire component mounting system 100 may include, for example, a supply section 3 to which a tape feeder is attached and a supply section 3 to which a tray is installed.

Furthermore, the placement assistance method may only propose the "placement" of parts P1. In this case, the placement assistance method divides multiple parts P1 into multiple parts, assigns one or more parts P1 after the division to one of multiple supply units 3, and even specifies the order (arrangement) of the parts within each supply unit 3. As a result, when multiple parts P1 are assigned to one supply unit 3, even the order of the parts P1 is specified.

Further, the pre-learning of the trained model M1 is not limited to the placement support system 20, and may be performed by another system. In this case, the placement support system 20 uses the learned model M1 generated by another system to have the proposal unit 22 and the relocation unit 24 propose the placement of the component P1.

Furthermore, it is not essential that the proposal for the placement of the component P1 using the learned model M1 be made in both the proposal step and the rearrangement step. For example, between the proposal step and the relocation step, the proposal for the placement of the part P1 using the learned model M1 may be made only in the proposal step, or the proposal for the placement of the part P1 using the learned model M1 only in the relocation step. A proposal for placement of P1 may be made. Furthermore, the trained model M1 may not be used in either the proposal step or the rearrangement step. That is, regarding functions such as multi-stage distribution and rearrangement of parts P1, the same functions as in the first embodiment can be achieved without using the learned model M1.

In addition, in embodiment 1, it is not essential that the placement of component P1 is proposed using the trained model M1 in all of the primary proposal step, secondary proposal step, and tertiary proposal step. For example, the placement of component P1 may be proposed using the trained model M1 in only one or two of the primary proposal step, secondary proposal step, and tertiary proposal step.

Further, the means for generating the trained model M1 is not limited to reinforcement learning, and may be, for example, "supervised learning" or the like.

In addition, the placement support method according to the first embodiment is not limited to a case where all of the processing is performed by one or more processors, and at least some of the processing may involve human intervention. For example, processing such as setting constraint conditions may be performed by a human using a user interface, etc.

Further, the means for determining the implementation time used for generating the learned model M1, etc. is not limited to the simulation performed by the simulation unit 26. For example, instead of simulation, the implementation time may be determined using a classifier generated by deep learning using a multilayer neural network.

(Embodiment 2)
The arrangement support method according to the present embodiment is different from the arrangement support method according to the first embodiment in a processing part S200 for relocation (see FIG. 5). Hereinafter, configurations similar to those in Embodiment 1 will be given the same reference numerals and descriptions will be omitted as appropriate.

That is, in the first embodiment, when rearranging the component P1 in the rearrangement step, the supply unit 3 (target supply unit) that satisfies the specific condition is identified in the specific step, and then the part P1 is placed in the target supply unit. The component P1 that is present is targeted for relocation. Then, as a result of rearranging the supply units 3 (target supply units) that meet the specific conditions, if the same supply unit 3 still satisfies the specific conditions, it is assumed that the pattern for changing the arrangement of the component P1 has been exhausted. , the processing part S200 for relocation ends.

In contrast, in the present embodiment, even if the same supply unit 3 still satisfies the specific condition as a result of rearranging the supply unit 3 that satisfies the specific condition regarding the mounting time, the Processing part S200 continues. In other words, in the placement support method according to the present embodiment, even if the pattern for changing the placement of the component P1 with the supply section 3 that satisfies the specific condition as the target supply section is exhausted, other supply sections 3 are used as the target supply section and the component P1 is rearranged. Repeat steps. Specifically, after the pattern of changing the arrangement of the component P1 using the supply section 3 that satisfies a specific condition as the target supply section is exhausted, any of the supply sections 3 of the plurality of supply sections 3 that satisfy the specific condition is exhausted. Any supply section 3 is sequentially selected as a target supply section.

As a result, according to the arrangement support method according to the present embodiment, it is possible to perform relocation targeting all of the plurality of supply units 3, and even compared to Embodiment 1, it is possible to perform relocation in a more appropriate manner. It becomes possible to find the arrangement.

As a modification of the second embodiment, the placement support method may not include the step of specifying the supply section 3 that satisfies the specific condition as the target supply section. In this case, the placement support method sequentially selects any supply section 3 from among the plurality of supply sections 3 as the target supply section during relocation, regardless of whether or not the specific condition is satisfied.

The configuration described in the second embodiment (including the modified example) can be applied in appropriate combination with the configuration described in the first embodiment (including the modified example).

(summary)
As described above, the placement support method according to the first aspect is a method for supporting the determination of placement of a plurality of components (P1) in a plurality of supply units (3) in a component mounting system (100), and includes a proposal step, a specification step, and a rearrangement step. The component mounting system (100) is a system that generates a product (P3) by mounting a plurality of components (P1) supplied to the plurality of supply units (3) on a target object (P2). The proposal step is a step of proposing the placement of the plurality of components (P1) for the plurality of supply units (3). The specification step is a step of specifying, among the plurality of supply units (3), a supply unit (3) that satisfies a specific condition as a target supply unit when the placement of the plurality of components (P1) proposed in the proposal step is adopted. The specific condition is a condition regarding the time required for the component mounting system (100) to generate the product (P3). The rearrangement step is a step of proposing an arrangement of multiple parts (P1) to a target supply unit and a reference supply unit consisting of at least one supply unit (3) other than the target supply unit among the multiple supply units (3).

According to this aspect, even if the arrangement of the plurality of parts (P1) proposed in the proposal step is not optimal, a new arrangement of the plurality of parts (P1) can be proposed in the relocation step. Furthermore, if the arrangement proposed in the proposal step is adopted, the supply section (3) to be relocated in the relocation step is the component mounting system (100) among the plurality of supply sections (3). This is a target supply unit that satisfies a specific condition regarding the time required to produce the product (P3). In other words, in the rearrangement step, out of the layouts proposed in the proposal step, the supply section (3) is arranged such that it satisfies a certain condition regarding the time required to generate the product (P3) in the component mounting system (100). You can re-propose the placement. Therefore, with this placement support method, it is possible to propose an improved placement of the component (P1).

In the placement support method according to the second aspect, in the first aspect, the specific condition is that the time required to generate the product (P3) in the component mounting system (100) is Including being the longest in the world.

According to this aspect, the relocation step targets the component (P1) placed in the supply section (3), which is a bottleneck regarding the time required to generate the product (P3) in the component mounting system (100). Accordingly, a new arrangement of the plurality of parts (P1) can be proposed.

In the placement support method according to the third aspect, in the first or second aspect, the reference supply unit is configured such that the time required to generate the product (P3) in the component mounting system (100) is ), which is the shortest in the supply section (3).

According to this aspect, in the relocation step, the component (P1) placed in the supply section (3) is targeted for a particularly short time required to generate the product (P3) in the component mounting system (100). It is possible to propose a new arrangement of multiple parts (P1).

In the arrangement support method according to the fourth aspect, in any one of the first to third aspects, when arranging the plurality of parts (P1) to the plurality of supply parts (3), the A constraint condition is attached that defines whether or not the part (P1) can be placed.

According to this aspect, for a specific part (P1) that is specified as being impossible to place in a specific supply section (3) due to the constraint conditions, the specific part (P1) is not allocated to the specific supply section (3). can be excluded, making it easier to simplify the placement proposal.

In the placement support method according to the fifth aspect, in any one of the first to fourth aspects, in at least one of the proposal step and the rearrangement step, the trained model (M1) is used to arrange a plurality of parts (P1). Suggest placement. The learned model (M1) is a model generated in association with the characteristics of at least one supply unit (3) among the plurality of supply units (3).

According to this aspect, instead of proposing a uniquely determined layout, for example, the trained model (M1) realizes the skill of "determining" the layout, as would be done by an expert. placement can be found more easily. In particular, the learned model (M1) is a model generated in association with the characteristics of at least one of the plurality of supply units (3), so for example, the learned model (M1) The arrangement of the plurality of parts (P1) is proposed in consideration of performance, specifications, etc.

In the placement support method according to the sixth aspect, in the fifth aspect, the trained model (M1) is generated using reinforcement learning.

According to this aspect, it becomes easy to generate a trained model (M1) in a case where the correct answer is not clear and optimization for a huge number of combinations is required.

The placement support method according to the seventh aspect further includes an update step of updating the trained model (M1) in the fifth or sixth aspect.

According to this aspect, it is possible to generate an appropriate trained model (M1) according to a user's request at the operation stage of the placement support method.

In the placement support method according to the eighth aspect, in any one of the first to seventh aspects, in the relocation step, the placement of the plurality of parts (P1) is reset for the target supply unit and the reference supply unit. Based on this, the arrangement of the plurality of parts (P1) is proposed again.

According to this aspect, it is possible to propose a highly flexible arrangement of the supply unit (3) to be rearranged in the relocation step, regardless of the arrangement in the proposal step.

In the placement support method according to the ninth aspect, in any of the first to eighth aspects, in the relocation step, the mounting time required to generate the product (P3) in the component mounting system (100) is shortened. Next, the arrangement of the plurality of parts (P1) with respect to the target supply section and the reference supply section is proposed.

According to this aspect, it is possible to improve the mounting time required to generate the product (P3) in the component mounting system (100).

The arrangement support method according to the tenth aspect is a method for supporting the determination of the arrangement of a plurality of components (P1) in a plurality of supply units (3) regarding a component mounting system (100), and includes a specifying step and a re-ordering step. arranging step. The component mounting system (100) is a system that generates a product (P3) by mounting a plurality of components (P1) supplied to a plurality of supply units (3) on a target object (P2). In the identifying step, when the proposed arrangement of the plurality of parts (P1) with respect to the plurality of supply parts (3) is adopted, the arrangement of the plurality of parts (P1) with respect to the plurality of supply parts (3) is adopted. This is a step of identifying the supply section (3) that satisfies the specific conditions as the target supply section. The specific conditions are conditions regarding the time required to generate the product (P3) in the component mounting system (100). The rearrangement step includes relocating the plurality of parts (P1) with respect to the target supply section and a reference supply section consisting of at least one supply section (3) other than the target supply section among the plurality of supply sections (3). This is the step of proposing placement.

According to this aspect, it is possible to propose an improved placement of the component (P1).

The program according to the eleventh aspect is a program for causing one or more processors to execute the placement support method according to any one of the first to tenth aspects.

According to this aspect, it is possible to propose an improved placement of the component (P1).

An arrangement support system (20) according to a twelfth aspect is a system that supports determining the arrangement of a plurality of components (P1) in a plurality of supply sections (3) with respect to a component mounting system (100), and includes a proposal section. (22), a specifying section (23), and a relocation section (24). The component mounting system (100) is a system that generates a product (P3) by mounting a plurality of components (P1) supplied to a plurality of supply units (3) on a target object (P2). The proposal unit (22) proposes placement of the plurality of parts (P1) with respect to the plurality of supply units (3). When the arrangement of the plurality of parts (P1) proposed by the proposing section (22) is adopted, the specifying section (23) selects a supply section (3) that satisfies a specific condition from among the plurality of supply sections (3). Specify as the target supply department. The specific conditions are conditions regarding the time required to generate the product (P3) in the component mounting system (100). The relocation unit (24) arranges a plurality of parts ( We propose the arrangement of P1).

According to this aspect, it is possible to propose an improved placement of the component (P1).

The work system according to the thirteenth aspect includes the placement support system (20) according to the twelfth aspect and a component mounting system (100). The component mounting system (100) is used to place a plurality of parts (P1) proposed by the placement support system (20), and generates a product (P3).

This aspect makes it possible to propose an improved arrangement of part (P1).

Not limited to the above aspects, various aspects (including modified examples) of the placement assistance method according to embodiment 1 and embodiment 2 can be embodied in a placement assistance system (20), an operation system (200), a program, and a non-transitory recording medium on which the program is recorded.

The configurations according to the second to ninth aspects are not essential to the placement support method and can be omitted as appropriate.

3 Supply section 20 Placement support system 22 Proposal section 23 Specification section 24 Relocation section 100 Component mounting system 200 Work system M1 Learned model P1 Part P2 Target object P3 Product

Claims (12)

1. A placement assistance method for a component mounting system that generates a product by mounting a plurality of components supplied to a plurality of supply units on a target object, the method comprising the steps of:
acquiring mounting data relating to the plurality of components included in the product;
a proposing step of proposing an arrangement of the plurality of components for the plurality of supply units;
a step of identifying, as a target supply unit, a supply unit among the plurality of supply units that satisfies a specific condition regarding a time required for generating the product in the component mounting system when the arrangement of the plurality of components proposed in the suggestion step is adopted;
a rearrangement step of proposing an arrangement of the plurality of components to the target supply unit and a reference supply unit including at least one supply unit other than the target supply unit among the plurality of supply units,
The proposing step uses a first trained model generated in association with a feature of at least one of the plurality of supply units to propose an arrangement of the plurality of components with respect to the plurality of supply units from the mounting data so as to shorten a mounting time required for generating the product in the component mounting system.
Placement assistance methods. The specific condition includes that the time required to generate the product in the component mounting system is the longest among the plurality of supply units,
The arrangement support method according to claim 1. The reference supply unit includes a supply unit whose time required for generating the product in the component mounting system is the shortest among the plurality of supply units.
The arrangement support method according to claim 1 or 2. When arranging the plurality of parts with respect to the plurality of supply parts, a constraint condition is attached that defines whether or not a particular part can be arranged with respect to a particular supply part,
The placement support method according to any one of claims 1 to 3. In the rearrangement step, a second trained model generated in association with the characteristics of at least one of the plurality of supply units is used to propose the arrangement of the plurality of parts.
The placement support method according to any one of claims 1 to 4. The first trained model is generated using reinforcement learning.
The placement assistance method according to any one of claims 1 to 5. Further comprising an updating step of updating the first trained model.
The placement assistance method according to any one of claims 1 to 6. In the rearranging step, for the target supply unit and the reference supply unit, the arrangement of the plurality of parts is reset, and then the arrangement of the plurality of parts is proposed anew.
The arrangement support method according to any one of claims 1 to 7. After performing the acquisition step, the proposal step, the identification step, and the relocation step, the arrangement of the plurality of parts proposed in the proposal step and the arrangement of the plurality of parts proposed in the relocation step. If different, the identifying step and the rearranging step are performed again.
The arrangement support method according to any one of claims 1 to 8. A program for causing one or more processors to execute the placement support method according to any one of claims 1 to 9. 1. A component mounting system that generates a product by mounting a plurality of components supplied to a plurality of supply units on an object, the component placement assistance system providing assistance in determining a placement of the plurality of components in the plurality of supply units, the system comprising:
an acquisition unit that acquires mounting data regarding the plurality of components included in the product;
a proposal unit that proposes placement of the plurality of parts with respect to the plurality of supply units;
When the arrangement of the plurality of components proposed by the proposal section is adopted, among the plurality of supply sections, a supply section that satisfies a specific condition regarding the time required to generate the product in the component mounting system is targeted. a specific department identified as a supply department;
a relocation unit that proposes placement of the plurality of parts to the target supply unit and a reference supply unit consisting of at least one supply unit other than the target supply unit among the plurality of supply units; Prepare,
The proposal unit calculates the mounting time required to generate the product in the component mounting system using a learned model that is generated in association with the characteristics of at least one of the plurality of supply units. proposing placement of the plurality of components with respect to the plurality of supply units from the mounting data so as to shorten the time;
Placement support system. A placement support system according to claim 11;
the component mounting system that is used in the placement of the plurality of components proposed by the placement support system and generates the product;
Working system.

Images