CN114585982A - Configuration assistance method, generation method of learned model, program, configuration assistance system, and operating system - Google Patents

Abstract

The subject of this disclosure is to be able to propose an improved arrangement of components. The configuration assistance method according to the present disclosure has an acquisition step and a proposal step. A 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) to an object (P2). The acquiring step is a step of acquiring mounting data (D1) related to a plurality of components (P1) included in the product (P3). The proposal step is to propose the arrangement of the plurality of parts (P1) for the plurality of supply units (3) based on the installation data (D1) using the learned model so as to shorten the production of the product (P3) in the parts installation system (100). Steps for the required installation time. The learned model is a model generated in association with the characteristics of at least one supply unit (3) among the plurality of supply units (3).

Description

Configuration assistance method, generation method of learned model, program, configuration assistance system, and operating system

technical field

The present disclosure generally relates to a configuration assistance method, a generation method of a learned model, a program, a configuration assistance system, and an operation system. More specifically, it relates to an arrangement assistance method for assisting the determination of arrangement of a plurality of components in a plurality of supply units in a component mounting system for mounting a plurality of components supplied to a plurality of supply units on an object, and a method for generating a learned model , programs, configuration assistance systems, and operating systems.

Background technique

Patent Document 1 describes an operation analyzer for monitoring in a component mounting line so that the line mounting tact or the line operation rate does not decrease, analyzes the cause of the decrease and removes it, thereby maintaining the entire line. of high production efficiency.

In this operation analysis device, the bottleneck component mounting machine, which is the component mounting machine with the largest actual mounting tact value in the component mounting line, is used to eliminate the reason why the actual mounting takt value of the bottleneck component mounting machine, that is, the production line mounting takt does not reach the target value. , and optimize the arrangement of component supply devices or component mounting order to reduce takt loss. Accordingly, if the cause is, for example, an imbalance in the actual mounting takt value of each component mounting machine, the takt loss can be reduced by correcting the allocation of components to each mounting machine, and the line mounting takt can be maintained at the target value.

prior art literature

Patent Literature

Patent Document 1: JP Patent Publication No. 2002-111298

SUMMARY OF THE INVENTION

However, in Patent Document 1, even if the allocation of components to each mounting machine is corrected, how to allocate components to each mounting machine is not clearly disclosed, and improvement is sought regarding the arrangement (including allocation) of components.

The present disclosure has been made in view of the above-mentioned circumstances, and an object of the present disclosure is to provide an arrangement assistance method, a learning model generation method, a program, an arrangement assistance system, and an operation system capable of providing a proposal for improved component arrangement.

An arrangement assistance method according to an aspect of the present disclosure is a method for assisting the determination of arrangement of a plurality of components in a plurality of supply units for a component mounting system, and includes an acquisition step and a proposal 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 to an object. The obtaining step is a step of obtaining mounting data related to the plurality of components included in the product. The proposal step is to propose, based on the mounting data, an arrangement of the plurality of components for the plurality of supply units using the learned model so as to shorten the generation of the product in the component mounting system. Install time steps. The learned model is a model generated in association with a feature of at least one supply unit among the plurality of supply units.

A learned model generation method according to an aspect of the present disclosure generates a learned model used in the arrangement assistance method in association with a feature of at least one supply unit among the plurality of supply units.

A program according to an aspect of the present disclosure is a program for causing one or more processors to execute the placement assistance method or the generation method of the learned model.

An arrangement assistance system according to one aspect of the present disclosure is a system for assisting the determination of arrangement of a plurality of components in a plurality of supply units for a component mounting system, and includes an acquisition unit and a proposal unit. The component mounting system is a system that generates a product by mounting the plurality of components supplied to the plurality of supply units to an object. The acquisition unit acquires mounting data related to the plurality of components included in the product. The proposal unit proposes, based on the mounting data, an arrangement of the plurality of components for the plurality of supply units using the learned model so as to shorten the time required for producing the product in the component mounting system. installation time. The learned model is a model associated with the characteristics of at least one supply unit among the plurality of supply units.

A work system according to an aspect of the present disclosure includes the arrangement assistance system and the component mounting system. The component mounting system is used for the arrangement of the plurality of components proposed in the arrangement assistance system, and generates the product.

Description of drawings

FIG. 1 is a schematic diagram showing the appearance of a component mounting system to which the arrangement assistance method according to Embodiment 1 is applied.

FIG. 2 is a conceptual diagram showing the arrangement of components in the supply unit of the component mounting system according to the arrangement assistance method described above.

3 is a block diagram showing an outline of a work system including the placement assistance system according to Embodiment 1. FIG.

FIG. 4A and FIG. 4B are conceptual diagrams showing the state of the proposal of the arrangement of the plurality of components in the supply unit of the arrangement assistance method as described above.

FIG. 5 is a flowchart showing an example of the same arrangement assistance method.

FIG. 6 is an explanatory diagram schematically showing a state of allocation of components in a multi-stage method according to the same arrangement assistance method.

FIG. 7 is an explanatory diagram schematically showing a state of relocation of the above-mentioned arrangement assistance method.

Detailed ways

(Embodiment 1)

The configuration assistance method, program, configuration assistance system 20 (refer to FIG. 3 ), and operating system 200 (refer to FIG. 3 ) according to the present embodiment will be described below with reference to FIGS. 1 to 7 .

(1) Outline

As shown in FIG. 1 , the arrangement assisting method according to the present embodiment is an arrangement assisting method for assisting the arrangement of the plurality of components P1 in the plurality of supply units 3 with respect to the component mounting system 100 . The component mounting system 100 includes a plurality of supply units 3 for supplying the components P1 used in the component mounting system 100, and generates a product P3 by mounting the plurality of components P1 supplied to the plurality of supply units 3 to the object P2 .

That is, as shown in FIG. 1 , the component mounting system 100 includes at least one mounting machine (mounting apparatus) 10 for mounting the components P1 to the object P2. The mounting machine 10 has the capture|acquisition part 41 (refer FIG. 1) for catching the component P1. The capturing part 41 is constituted by a suction nozzle as an example, and captures (holds) the member P1 in a state in which it can be released (that is, the capture is released). The mounting machine 10 captures the component P1 supplied to the supply unit 3 with the capture unit 41, moves the capture unit 41 in a state of capturing the component P1, and releases the component P1 from the object P2, thereby mounting the component P1 on the object The mounting surface of Object P2.

In the present embodiment, as an example, the component mounting system 100 is a mounting line configured by connecting a plurality of (for example, four in the example of FIG. 1 ) mounting machines 10 . In other words, the component mounting system 100 includes a plurality of mounting machines 10 that are connected to each other to configure a mounting line. In such a component mounting system 100 (mounting line), for example, a plurality of mounting machines 10 sequentially mount components P1 to one object P2 to finally generate a product P3 in which a plurality of components P1 are mounted.

Each of the plurality of mounting machines 10 has at least one supply unit 3 , and mounts the components P1 supplied to the supply unit 3 . That is, each mounting machine 10 mounts one or more components P1 supplied to its own supply unit 3 on 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 the present embodiment, since the component mounting system 100 includes a plurality of mounting machines 10 , it is assumed that each of the plurality of mounting machines 10 has one supply unit 3 , and the component mounting system 100 as a whole also has a plurality of supply units 3 . .

The component mounting system 100 is used for production of various products such as electronic equipment, automobiles, clothing, food, medicine, and handicrafts in facilities such as factories, research institutes, office buildings, and educational facilities, for example.

In such a component mounting system 100 , there are many patterns of arrangement of the plurality of components P1 provided in the plurality of supply units 3 of the plurality of mounting machines 10 . That is, since it is possible to select the supply unit 3 of which mounting machine 10 among the plurality of mounting machines 10 to arrange each of the plurality of components P1, when the number of the components P1 becomes, for example, several hundreds, the plurality of supply units 3 The pattern of the arrangement of the plurality of components P1 becomes large. Furthermore, due to the arrangement of the plurality of components P1 in the plurality of supply units 3, the mounting time required for the generation of the product P3 in the component mounting system 100 greatly varies. For example, depending on how the plurality of components P1 are distributed to the plurality of mounting machines 10, the mounting time greatly varies. In this way, the arrangement of the plurality of components P1 in the plurality of supply units 3 is an important factor concerning the installation time of the component mounting system 100, and since there are many patterns of arrangement, it is very difficult to find a suitable arrangement.

Therefore, the arrangement assistance method according to the present embodiment assists the work of determining the arrangement 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 arrangement assistance method, a more suitable arrangement can be found more easily (in a short time), for example, the arrangement of the plurality of components P1 in the plurality of supply units 3 can be determined without the assistance of a skilled person or the like.

That is, the arrangement assistance method according to the present embodiment is a method of proposing arrangement of the plurality of components P1 in the plurality of supply units 3 with respect to the component mounting system 100 . The component mounting system 100 generates the product P3 by mounting the plurality of components P1 supplied to the plurality of supply units 3 to the object P2. Here, the arrangement assistance method according to the present embodiment can propose an improved arrangement of the component P1 by further employing the following three functions.

The first function is a proposal using the configuration of the learned model M1 (refer to FIG. 3 ). In order to realize the first function, the configuration assistance method has an acquisition step and a proposal step. The obtaining step is a step of obtaining the installation data D1 (refer to FIG. 3 ). The mounting data D1 is data related to the plurality of components P1 included in the product P3. The proposal step proposes the arrangement of the plurality of parts P1 with respect to the plurality of supply units 3 based on the installation data D1 using the learned model M1 so as to shorten the installation time. 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 . The installation time is the time required for generation of the product P3 in the component installation system 100 .

In this way, in the first function, the arrangement assisting method proposes the arrangement of the plurality of components P1 with respect to the plurality of supply units 3 using the learned model M1 in the proposal step. That is, in the proposal step, it is not the arrangement that is uniquely determined by the proposal, but an appropriate arrangement can be found more easily by, for example, the technique of "determination method" of the arrangement performed by the skilled person after learning the model M1. . In particular, since 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 , for example, a plurality of components are proposed in consideration of the performance and specifications of the mounting machine 10 . Configuration of P1. Therefore, in this arrangement assistance method, it is possible to propose an improved arrangement of the components P1.

The second function is the allocation of the part P1 in the multi-stage method. To implement the second function, the configuration helper method has a one-time proposal step and a second-order proposal step. The primary proposal step is a step of proposing the arrangement of the plurality of components P1 for the plurality of primary groups G11 and G12 (refer to FIG. 6 ). The secondary proposal step is to propose a plurality of secondary groups G21 to G24 (refer to FIG. 6 ) when each of the plurality of primary groups G11 and G12 is classified into a plurality of secondary groups G21 to G24 (refer to FIG. 6 ) after the primary proposal step Steps for the configuration of multiple parts P1 of G24. Each of the plurality of secondary groups G21 to G24 includes at least one supply unit 3 among the plurality of supply units 3 .

Here, the primary proposal step and the secondary proposal step in the 2nd function are included in the proposal step in the 1st function. In other words, a proposal step consists of a one-time proposal step and a secondary proposal step.

In this way, in the second function, the proposal for the arrangement of the plurality of components P1 is divided into a primary proposal procedure for arranging the component P1 in the plurality of primary groups G11 and G12, and a plurality of more detailed secondary groups G21 to G24. Configure the secondary proposal step for part P1. In a word, since the arrangement of the plurality of parts P1 is realized not by a single-stage process but by a multi-stage process that is set hierarchically, in each stage, an appropriate method for deriving the plurality of parts P1 can be obtained. Configured options are less suppressed. As a result, the process for proposing the arrangement of the plurality of components P1 in each stage can be simplified. Therefore, in this arrangement assistance method, it is possible to propose an improved arrangement of the components P1.

The third function is reconfiguration. In order to realize the third function, the configuration assistance method has a proposal step, a determination step, and a reconfiguration step. The proposal step is a step of proposing the arrangement of the plurality of components P1 with respect to the plurality of supply units 3 . The identifying step is a step of identifying a certain supply unit 3 among the plurality of supply units 3 as a target supply unit. The supply unit 3 specified as the target supply unit is the supply unit 3 that satisfies the specified condition regarding the time required for the generation of 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. . The rearrangement step is a step of proposing the arrangement of the plurality of components P1 to the target supply unit and the reference supply unit. The reference supply unit is composed of at least one supply unit 3 other than the target supply unit among the plurality of supply units 3 .

In this way, in the third function, even when the arrangement of the plurality of parts P1 proposed in the proposal step is not optimal, it is possible to propose a new arrangement of the plurality of parts P1 in the relocation step. Furthermore, the supply unit 3 to be rearranged in the rearrangement step is the time required for the generation of the product P3 in the component mounting system 100 among the plurality of supply units 3 when the arrangement proposed in the proposal step is adopted. The target supply unit that satisfies the specified conditions. That is, in the re-arrangement step, among the arrangements proposed in the proposal step, in particular, the arrangement 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 can be re-proposed. Therefore, in this arrangement assistance method, it is possible to propose an improved arrangement of the components P1.

In addition, as an example, the arrangement assistance method according to the present embodiment is executed in the arrangement assistance system 20 . In other words, the placement assistance system 20 is one form for embodying the aforementioned placement assistance method. That is, the arrangement assistance system 20 assists the determination of the arrangement of the plurality of components P1 in the plurality of supply units 3 with respect to 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 to the object P2, and in the present embodiment, is a mounting line as an example.

Here, the configuration assistance system 20 is mainly constituted by a computer system having one or more processors and one or more memories. In other words, the arrangement assistance method according to the present embodiment is used in the computer system (the arrangement assistance system 20 ). That is, the configuration assistance method can also be embodied by a program. The program according to the present embodiment is a program for causing one or more processors to execute the arrangement assistance method according to the present embodiment.

Furthermore, the work system 200 according to the present embodiment includes the placement assistance system 20 and the component mounting system 100 . The component mounting system 100 is a system that uses the arrangement of the plurality of components P1 proposed in the arrangement assistance system 20 to generate a product P3.

(2) Details

The details of the configuration assistance method, program, configuration assistance system 20, and operating system 200 according to the present embodiment will be described below.

(2.1) Premise

In the present embodiment, a case where the component mounting system 100 is used in the manufacture of electronic equipment in a factory will be described. A general electronic device has, for example, various circuit blocks such as a power supply circuit and a control circuit. In the manufacture of these circuit blocks, as an example, these steps are performed in the order of a solder coating step, a mounting step, and a soldering step. In the solder coating step, paste-like solder is coated (or printed) on a substrate (including a printed wiring board). In the mounting step, the components P1 (including electronic components) are mounted (mounted) on the substrate. In the soldering step, for example, the substrate in the state where the component P1 is mounted is heated in a reflow oven to melt the solder paste to perform soldering.

The component mounting system 100 performs an operation of mounting a plurality of components P1 (electronic components) on a substrate that is an object P2 in a mounting process. Thereby, in the component mounting system 100, the product P3 which consists of the board|substrate (object P2) on which the some component P1 is mounted is produced|generated. In other words, the product P3 includes the object P2 (here, a substrate) and a plurality of components P1 mounted on the object P2.

In the present embodiment, as an example, a case where the component mounting system 100 is used for mounting of a component (component P1 ) based on a surface mount technology (SMT: Surface Mount Technology) will be described. That is, the component as the component P1 is a component for surface mounting (SMD: Surface Mount Device), and is mounted by being mounted on the surface (mounting surface) of the substrate as the object P2. However, it is not limited to this example, and the component mounting system 100 may be used for mounting of a component (component P1 ) based on InsertionMount Technology (IMT: InsertionMount Technology). In this case, the component as the component P1 is a component for insertion and mounting having lead terminals, and the lead terminals are inserted into the holes of the substrate as the object P2 to be mounted on the surface (mounting surface) of the substrate (object P2 ). superior.

In addition, the "supply part" as used in the present disclosure is a part (position) for supplying the components P1 used in the component mounting system 100 in the component mounting system 100 . The component mounting system 100 includes a plurality of supply units 3 , and performs mounting work using the components P1 supplied to the respective supply units 3 . For example, the supply part 3 is comprised so that the tape feeder for supplying the component P1 can be equipped. The tape feeder can supply the plurality of components P1 to the component mounting system 100 from the supply unit 3 by attaching a reel of the carrier tape that accommodates the plurality of components P1. Such a supply unit 3 includes a plurality of slots into which tape feeders can be mounted, and supplies a plurality of components to the component mounting system 100 (mounting machine 10 ) by mounting a plurality of tape feeders in the plurality of slots. P1. In the present embodiment, as an example, it is assumed that the supply unit 3 is a “table” composed of a set of a plurality of slots. The "unloading table" mentioned here is an imaginary unloading table, and does not accompany the entity.

Hereinafter, as an example, three axes of the X axis, the Y axis, and the Z axis that are orthogonal to each other are set, the axes parallel to the surface of the substrate as the object P2 are referred to as the "X axis" and the "Y axis", and the The axis parallel to the thickness direction of the substrate is referred to as the "Z" axis. In particular, the "X-axis" is an axis along the direction in which the plurality of mounting machines 10 in the component mounting system 100 are arranged. Furthermore, the side of the capturing portion 41 viewed from the substrate as the object P2 is defined as the positive direction of the Z axis (also referred to as "upward"). In addition, the state seen from the positive direction (upward) of the Z axis is also referred to as a "plan view" below. The X-axis, the Y-axis, and the Z-axis are all imaginary axes, and the arrows representing "X", "Y", and "Z" in the drawings are only for illustration, and are not accompanied by entities. In addition, these directions are not intended to limit the directions in use of the component mounting system 100 .

In addition, the proposal of the "arrangement" of the components P1 in the present disclosure includes proposals for various items related to the arrangement of the components P1 in the plurality of supply units 3, such as the allocation of the components P1 and the arrangement of the components P1. both sides of the proposal. The assignment of the plurality of parts P1 refers to dividing the plurality of parts P1 into a plurality of parts, and assigning one or more divided parts P1 to any of the plurality of supply units 3 (discharge tables in this embodiment) . That is, in the allocation, when a plurality of parts P1 are allocated to one supply unit 3, the order of the plurality of parts P1 is not defined. On the other hand, the proposal of arranging the plurality of parts P1 means dividing the plurality of parts P1 into a plurality of parts, and assigning one or more divided parts P1 to the plurality of supply parts 3 (in this embodiment, discharging Table), and the order (arrangement) in each supply unit 3 is defined. Therefore, as in the present embodiment, when the supply unit 3 is a “discharge table” constituted by a collection of a plurality of slots, as the arrangement of the components P1, which component P1 and one supply unit 3 (discharge table) are specified. Which slot of the multiple slots included in the feed table) corresponds. That is, in the proposal of an arrangement, when a plurality of parts P1 are allocated to one supply unit 3, the order of the plurality of parts P1 is defined.

In the present embodiment, as an example, it is assumed that the proposal for “arrangement” of the components P1 by the arrangement assisting method or the arrangement assisting system 20 is only the allocation of the components P1 among the proposals for the allocation of the components P1 and the arrangement of the components P1. That is, in the arrangement assistance method or arrangement assistance system 20 according to the present embodiment, the plurality of components P1 are divided into multiple parts, and one or more divided components P1 are assigned to any one of the plurality of supply units 3 , and does not prescribe the ordering to one or more parts P1 after division.

In addition, the “proposal” method of arrangement referred to in the present disclosure includes a method of outputting the result of derivation of the arrangement of the components P1 to a person or an external system, and actually determining a plurality of supply units 3 according to the result of derivation of the arrangement of the component P1 Both of the ways in which the multiple components P1 are arranged. According to the former method, the person or external system that receives the result of the derivation of the arrangement of the component P1 from the arrangement assistance method or the arrangement assistance system 20 receives only the proposal (information) of the arrangement of the component P1, and judges whether or not to adopt the derivation result. According to the latter method, the result of derivation of the arrangement of the component P1 is directly used in the component mounting system 100 from the arrangement assistance method or the arrangement assistance system 20 without judgment by a person or an external system.

In addition, the "feature" of the supply unit 3 referred to in the present disclosure includes, for example, features and the like related to the mounting machine 10 in which the supply unit 3 is provided. Features related to the mounting machine 10 are, for example, speed (maximum mounting speed), the number of catching parts 41 (number of suction nozzles), the number of supply parts 3, the type of catching parts 41, the number of slots, the number of mounting heads 4, and The type, performance, characteristics, or specifications of the mounting machine 10 are included such as the model or the like. The “number of catches 41 ” means the maximum number of catches 41 that can be attached to one mounting head 4 . The "type of the capture part 41" includes, for example, a suction nozzle for suctioning the member P1, a mechanical chuck for sandwiching the member P1 (pinching), and the like. The "number of slots" refers to the number of slots in one supply unit 3 (or one mounting machine 10 ), in other words, the tapes that can be equipped in one supply unit 3 (or one mounting machine 10 ). Maximum number of feeders.

In addition, the “speed” of the mounting machine 10 referred to in the present disclosure refers to the highest mounting speed in the mounting machine 10 , that is, the maximum value of the speed involved in the mounting of the component P1 in the mounting machine 10 . That is, the mounting machine 10 operates so that the component P1 is caught by the catching part 41, and the catching part 41 in the state which caught the component P1 is moved, and the component P1 is mounted on the object P2. Therefore, for example, the speed (maximum mounting speed) of the mounting machine 10 varies depending on the speed of capturing and releasing (ie, releasing the capturing) of the component P1 in the capturing unit 41 , the moving speed of the capturing unit 41 , and the like. However, in the present embodiment, the speed is classified into a plurality of speed ranges such as a multi-function machine (low-speed machine), a medium-speed machine, and a high-speed machine. ”, etc., regarded as the same speed domain.

In addition, the "determination condition" referred to in the present disclosure is a specific condition set regarding the time required to generate the product P3 in the component mounting system 100 . As an example, the time required for the production of the product P3 in the component mounting system 100 (installation time) may be the longest or the shortest among the plurality of supply units 3 as a determination condition.

(2.2) Structure of the component mounting system

Next, the configuration of the component mounting system 100 using the arrangement assistance method according to the present embodiment 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 constituting a mounting line. The plurality of mounting machines 10 are arranged in a row along the X-axis. When distinguishing the plurality of mounting machines 10, each of the plurality of mounting machines 10 will be referred to as a first mounting machine 11, a second mounting machine 12, a first mounting machine 11, a second mounting machine 12, and a first mounting machine 10 in this order from the negative side of the X axis as shown in FIG. 3 mounting machine 13, fourth mounting machine 14.

In the component mounting system 100 according to the present embodiment, the first mounter 11 is at the head of the line, and the object is placed in the order of the second mounter 12 , the third mounter 13 , and then the last fourth mounter 14 . P2 moves through the plurality of mounting machines 10 . That is, the object P2 sequentially passes through the plurality of mounting machines 10 while moving in the positive direction of the X-axis. The component mounting system 100 mounts the plurality of components P1 to the object P2 by each of the mounting machines 10 while the object P2 passes through the plurality of mounting machines 10 . In this way, the component mounting system 100 introduces the substrate as the object P2 from the side of the first mounting machine 11 , and mounts the plurality of components P1 (electronic components) on the object P2 by the plurality of mounting machines 10 . The product P3 is discharged from the fourth mounting machine 14 side.

Therefore, the component mounting system 100 can finally generate the product P3 in which the plurality of components P1 are mounted by sequentially mounting the components P1 using the plurality of mounting machines 10 . The “installation time” referred to in the present disclosure refers to the time required for the generation of the product P3 in the component mounting system 100 , and is, for example, from the time when one object P2 is introduced into the component mounting system 100 until the product P3 is removed from the component mounting system. 100 time until discharge. That is, from the time when the object P2, that is, one board, is introduced into the first mounting machine 11 until the time when the plurality of components P1 are mounted on the board (object P2) and discharged from the fourth mounting machine 14 as the product P3 The time until the point is called "installation time".

In the present embodiment, the basic configuration of each of the plurality of mounting machines 10 is common to each other. Therefore, unless otherwise specified, only the configuration of the first mounter 11 will be described below, but the other mounters (the second mounter 12 , the third mounter 13 , and the fourth mounter 14 ) have basically the same configuration.

The mounting machine 10 (the first mounting machine 11 ) includes at least one supply unit 3 (discharge table) and at least one mounting head 4 . In the present 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. Further, the mounting machine 10 includes two mounting heads 4 . The two mounting heads 4 are spaced apart from the center line in the Y-axis direction of the mounting machine 10 to both sides in the Y-axis direction, and are arranged so as to be connected to the two supply units 3 , respectively. One-to-one correspondence.

That is, the mounting machine 10 has a substantially symmetrical structure with respect to the Y-axis direction, and the mounting head 4 and the supply unit 3 are arranged on both sides of the center line in the Y-axis direction, respectively. Therefore, the mounting machine 10 mounts the components P1 supplied to the two supply units 3 with the two mounting heads 4 to the object P2 introduced between the two supply units 3 by individually driving the two mounting heads 4 .

In this way, in the present embodiment, although there are two mounting heads 4 in one mounting machine 10, since two supply units 3 (discharge tables) are also provided, one mounting head 4 and one supply are Part 3 corresponds. That is, in each supply unit 3 , there is only one corresponding mounting head 4 , and the “number of mounting heads 4 ” included in the characteristics of the supply unit 3 is “1”.

The mounting head 4 has one or more catch parts 41 . In the present embodiment, the mounting head 4 in the first mounting machine 11 has a plurality of (16 as an example) capturing sections 41 (refer to FIG. 1 ). The mounting head 4 moves the capturing portion 41 close to the object P2 (substrate) while capturing the component P1 (component) by the capturing portion 41, and mounts the component P1 on the mounting surface T21 of the object P2.

The component P1 captured by the capturing unit 41 of the mounting head 4 is supplied to the supply unit 3 . In the present embodiment, as described above, each of the supply units 3 is a “discharge table” constituted by a collection of a plurality of slots into which the tape feeder can be mounted. Therefore, in the supply part 3, a plurality of tape feeders can be mounted with the number of slots as the upper limit. The mounting head 4 captures the components P1 (components) from the tape feeder capture section 41 attached to the supply section 3 .

In addition to the above-described configuration, the mounting machine 10 may include a driving device, a conveying device, a control device, a communication unit, and the like. However, the driving device, the conveying device, the control device, the communication unit, and the like are not essential components of the mounting machine 10 . In FIGS. 1 and 2 , as the configuration of the mounting machine 10 , the illustration of the configuration other than the supply unit 3 and the mounting head 4 is suitably omitted.

The drive device is a device that moves the mounting head 4 . In the present embodiment, the drive device moves the mounting head 4 in the X-Y plane. The "X-Y plane" referred to here is a plane including the X axis and the Y axis, and is a plane orthogonal 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 conveying device is a device that conveys the substrate as the object P2. The conveying device is realized, for example, by a belt conveyor or the like. The conveying device conveys the object P2 (substrate) along the X axis. The conveying device conveys the object P2 at least in the mounting space facing the capturing portion 41 in the Z-axis direction below the mounting head 4 . Then, the conveying device stops the object P2 in the mounting space until the mounting of the component P1 (component) on the object P2 (substrate) by the mounting head 4 is completed.

The control device controls each part of the component mounting system 100 . The main structure of the control device is 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 the program recorded in the memory of the microcontroller. The program may be recorded in a memory in advance, may be provided via an electric communication line such as the Internet, or may be provided by being recorded on a non-transitory recording medium such as a memory card.

The communication unit is configured to communicate with a higher-level system directly or indirectly via a network, a repeater, or the like. Thereby, the mounting machine 10 can exchange data with the upper system.

The mounting machine 10 configured as described above is used in a state in which a tape feeder equipped with a reel for accommodating a carrier tape of the plurality of components P1 is mounted in each of the plurality of slots in the supply unit 3 . Thereby, the components P1 taken out from the carrier tape by the tape feeder are sequentially supplied to each of the plurality of slots in the supply unit 3 . In this state, the mounting machine 10 performs the following operation as a basic operation: the component P1 supplied by the supply unit 3 by the tape feeder is captured by the capturing unit 41 of the mounting head 4, and the component P1 is captured by the capturing unit 41 of the mounting head 4 to the target position on the object P2 Install (configure). The mounting machine 10 repeatedly performs such basic operations.

Here, if the mounting head 4 has a plurality of (16 as an example) catching parts 41, the mounting machine 10 can mount a plurality of components P1 by one basic operation. That is, since the mounting machine 10 can catch the plurality of components P1 collectively by the plurality of catching parts 41 in the mounting head 4 in one basic operation, the plurality of components P1 can be collectively mounted. Furthermore, the mounting machine 10 provided with a plurality of (two, as an example) mounting heads 4 can simultaneously mount a plurality of components P1 using the plurality of mounting heads 4 by individually driving the plurality of mounting heads 4 .

In addition, in the present embodiment, as described below, the plurality of mounting machines 10 included in the component mounting system 100 have partially different characteristics. Here, the first mounter 11 and the second mounter 12 have the same features, and the third mounter 13 and the fourth mounter 14 have different features from the first mounter 11 (or the second mounter 12 ).

That is, since there are many types, performances, characteristics, or specifications of the mounting machines 10, the plurality of mounting machines 10 constituting the component mounting system 100 may have mutually different characteristics. Specifically, depending on the mounting machine 10 , there are, for example, a speed (maximum mounting speed), the number of catching parts 41 (number of suction nozzles), the number of supply parts 3 , the type of catching parts 41 , the number of slots, and the number of mounting heads 4 . and different models, etc.

In the present embodiment, there are the speed, the number of capturing units 41 , the types and models of capturing units 41 , and the like as features that differ among a plurality of (here, four) mounting machines 10 . As an example, regarding the "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 mounter 14 is a "multi-function machine" machine". Regarding the "number of catches 41", the first mounter 11 and the second mounter 12 are "16", whereas the third mounter 13 is "8" and the fourth mounter 14 is "3".

On the other hand, the number of supply units 3 , the number of slots, the number of mounting heads 4 , and the like exist as features common to a plurality of (here, four) mounting machines 10 . As an example, with regard to the "number of supply units 3", as described above, any of the mounting machines 10 is "2". Similarly, as an example, "the number of mounting heads 4" is also "2" in any of the mounting machines 10 as described above. In addition, regarding the "number of slots", it is assumed that all of the mounting machines 10 are "60".

However, since “the number of capturing parts 41 ” represents the number of capturing parts 41 in one mounting head 4 , if the mounting machine 10 having two mounting heads 4 is viewed as a unit, there are twice as many capturing parts as described above. Section 41. For example, the number of the capture|acquisition part 41 in the whole 1st mounting machine 11 is "32". Similarly, since “the number of slots” represents the number of slots in one supply unit 3 , if the mounting machine 10 having two supply units 3 is viewed as a unit, there are twice as many slots as described above. . For example, the number of slots in the entire first mounting machine 11 is "120". In addition, even if the features of the mounting machine 10 described above are the same, for example, when the detailed specifications of the mounting machine 10 are different, or when the performance of the mounting machine 10 is degraded due to deterioration over time, etc. different.

As described above, in the present embodiment, the component mounting system 100 includes four mounting machines 10 , and each mounting machine 10 includes two supply units 3 . Therefore, the entire component mounting system 100 has eight supply units 3 . When distinguishing these eight supply units 3, each of the plurality of supply units 3 is referred to as a first supply unit 31, a second supply unit 32, a third supply unit 33, and a fourth supply unit as shown in FIG. 2 . 34. A fifth supply part 35, a sixth supply part 36, a seventh supply part 37, and an eighth supply part 38. The first supply part 31 and the second supply part 32 are provided in the first mounting machine 11 , and the third supply part 33 and the fourth supply part 34 are provided in the second mounting machine 12 . The fifth supply part 35 and the sixth supply part 36 are provided in the third mounting machine 13 , and the seventh supply part 37 and the eighth supply part 38 are provided in the fourth mounting machine 14 .

(2.3) The structure of the configuration auxiliary system

Next, the configuration of the arrangement assistance system 20 according to the present embodiment will be described with reference to FIG. 3 .

The arrangement assisting system 20 is a system that assists the determination of the arrangement of the plurality of components P1 in the plurality of supply units 3 with respect to the component mounting system 100 as described above. In the present embodiment, as described above, as the entire component mounting system 100 , there are eight supply units 3 of the first supply unit 31 to the eighth supply unit 38 . Therefore, the arrangement assistance system 20 according to the present embodiment is used to determine the arrangement of the plurality of components P1 in the eight supply units 3 .

As shown in FIG. 3 , the placement assistance system 20 includes an acquisition unit 21 , a proposal unit 22 , a determination unit 23 , a rearrangement unit 24 , an output unit 25 , a simulation unit 26 , and a model storage unit 27 . In the present embodiment, the configuration assistance system 20 has, as described above, a computer system having one or more processors and one or more memories as its main configuration. The functions of at least the acquisition unit 21 , the proposal unit 22 , the determination unit 23 , the rearrangement unit 24 , the output unit 25 , and the simulation unit 26 in the placement assistance system 20 are embodied by one or more processors executing programs.

The acquisition unit 21 acquires the installation data D1. The mounting data D1 is data related to the plurality of components P1 included in the product P3. That is, the mounting data D1 is data related to 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 related to each of these "200" components P1. The mounting data D1 includes at least data for distinguishing the plurality of components P1, such as quality, product number, specification, manufacturer, size, number of terminals, terminal arrangement, and circuit constants of the plurality of components P1, for example.

The proposal unit 22 proposes the arrangement of the plurality of components P1 with respect to the plurality of supply units 3 . In the present embodiment, the proposal unit 22 proposes the arrangement of the plurality of components P1 for the plurality of supply units 3 based on the installation data D1 using the learned model M1 so as to shorten the installation time. 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 . The installation time is the time required for generation of the product P3 in the component installation system 100 . The details of the learned model M1 are described in the column of "(3.2) The learned model".

Here, in the arrangement assistance system 20 (arrangement assistance method) according to the present embodiment, the allocation of the components P1 (proposed arrangement) of the multi-stage method is adopted. Therefore, in the present embodiment, the proposal unit 22 includes a plurality of processing blocks so as to be able to cope with the assignment of the multi-level method. Specifically, the proposal unit 22 includes a primary proposal unit 221 , a secondary proposal unit 222 and a tertiary proposal unit 223 .

The primary proposal unit 221 proposes the arrangement of the plurality of parts P1 for the plurality of primary groups G11 and G12. The secondary proposal unit 222 proposes a plurality of components 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 subdivided secondary groups G21 to G24 Configuration of P1. Each of the plurality of secondary groups G21 to G24 includes at least one supply unit 3 among the plurality of supply units 3 . The tertiary proposal unit 223 proposes a proposal for the plurality of tertiary groups G31 to G38 when each of the plurality of secondary groups G21 to G24 is classified into a plurality of tertiary groups G31 to G38 (refer to FIG. 6 ) that are further subdivided. Configuration of multiple components P1. Each of the plurality of tertiary groups G31 to G38 includes at least one supply unit 3 among the plurality of supply units 3 . The details of the multi-stage method are described in the column of "(3.3) Multi-stage method".

When the arrangement of the plurality of components P1 proposed by the proposal unit 22 is adopted, the specifying unit 23 specifies a certain supply unit 3 among the plurality of supply units 3 as a target supply unit. Here, the supply unit 3 specified as the target supply unit is the supply unit 3 that satisfies the specified condition regarding the time required for the generation of the product P3 in the component mounting system 100 . That is, the determination part 23 determines the supply part 3 which satisfies a determination condition with respect to the time required for generation|occurence|production of the product P3 in the component mounting system 100 as a "target supply part". The details of the determination of the target supply unit are described in the column of "(3.4) Relocation".

The rearrangement unit 24 proposes the arrangement of the plurality of components P1 to the target supply unit and the reference supply unit. Here, the reference supply unit is constituted by at least one supply unit 3 other than the target supply unit among the plurality of supply units 3 . Therefore, in the specifying unit 23 , the supply unit 3 serving as the “target supply unit” and the supply unit 3 serving as the “reference supply unit” are substantially extracted from the plurality of supply units 3 . That is, the specifying unit 23 specifies at least one of the supplying units 3 among the plurality of supplying units 3 that does not satisfy the specified condition regarding the time required for the generation of the product P3 in the component mounting system 100 as the “target supplying unit”.

Then, the rearrangement unit 24 performs the rearrangement of the plurality of components P1 by targeting the extracted (determined) target supply unit and the reference supply unit among the plurality of supply units 3 . That is, the relocation unit 24 proposes a new arrangement in place of the arrangement (assignment) of the plurality of components P1 for the target supply unit and the reference supply unit proposed once in the proposal unit 22 . In the present embodiment, the rearrangement unit 24 re-proposes the arrangement of the plurality of components P1 after resetting the arrangement of the plurality of components P1 to the target supply unit and the reference supply unit. Regarding the relocation, the details are explained in the column of "(3.4) Relocation".

The output unit 25 outputs the arrangement data D2 generated by at least one of the proposal unit 22 and the rearrangement unit 24 . The “arrangement data” referred to in the present disclosure is data representing the arrangement of the plurality of components P1 in the plurality of supply units 3 proposed by at least one of the proposal unit 22 and the rearrangement unit 24 . That is, the arrangement data D2 is data representing allocation to any one of the supply units 3 about 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 which of the plurality of (here, eight) supply units 3 is specified for each of these "200" components P1. one's data.

Examples of the output form of the configuration data D2 in the output unit 25 include output to the analog unit 26, transmission to the component mounting system 100 or other systems, display, sound output, and recording (writing to a non-transitory recording medium) ) and printing (printing out), etc. In the present embodiment, as an example, the output unit 25 directly or indirectly outputs the configuration data D2 to the simulation unit 26 . Furthermore, in the present embodiment, as an example, the output unit 25 directly or indirectly outputs (transmits) the arrangement data D2 to the component mounting system 100 . As a result, in the component mounting system 100, the mounting of the plurality of components P1 using the arrangement of the plurality of components P1 specified in the arrangement data D2 can be performed. In addition, the output unit 25 can output the configuration data D2 to a person such as an operator, for example, by means of display or sound output.

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 rearrangement unit 24 is adopted. In the present embodiment, the simulation unit 26 acquires the configuration data D2 from the output unit 25, and performs simulation based on the configuration data D2. At this time, the simulation unit 26 performs simulation using, in addition to the configuration data D2 , device data and the like that characterize the configuration of the component mounting system 100 . The "device data" referred to here includes the characteristics of the supply unit 3 , that is, the characteristics related to the mounting machine 10 provided with the supply unit 3 , and the like.

The simulation unit 26 obtains at least the “installation time” required to generate the product P3 in the component mounting system 100 . In the present embodiment, in particular, the simulation unit 26 obtains the mounting time for each of the plurality of supply units 3 included in the component mounting system 100 . That is, the simulation unit 26 obtains, as a simulation result, the installation time required for the installation of the component P1 for each supply unit 3 with respect to the component mounting system 100 including the plurality of supply units 3 . The simulation result in the simulation unit 26 is output from the output unit 25 in an arbitrary manner, for example. In the present embodiment, the simulation result in the simulation unit 26 is output to at least the determination unit 23 and used for determination of the object supply unit in the determination unit 23 .

The model storage unit 27 stores the learned model M1. The learned model M1 stored in the model storage unit 27 is used at least in the proposal of the arrangement of the components P1 in the proposal unit 22 . In the present embodiment, the learned model M1 stored in the model storage unit 27 is used not only in the proposal unit 22 but also in the proposal of the arrangement of the components P1 in the rearrangement unit 24 . Details are described in the column of "(3.2) Learning completed model", and the learning completed model M1 is generated in the pre-learning. Furthermore, 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 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 the learned models M1. Therefore, the model storage unit 27 is configured to store a plurality of (types) of the learned models M1.

In addition to the above-described configuration, the arrangement assistance system 20 may further include a communication unit, a user interface, and the like. However, the communication unit, the user interface, and the like are not required for the configuration support system 20 . In FIG. 3 , as the configuration of the placement assistance system 20 , the illustration of configurations other than the acquisition unit 21 , the proposal unit 22 , the determination unit 23 , the rearrangement unit 24 , the output unit 25 , the simulation unit 26 , and the model storage unit 27 is appropriately omitted. .

The communication unit is configured to communicate with the component mounting system 100 and/or a higher-level system directly or indirectly via a network, a repeater, or the like. Thereby, the arrangement assistance system 20 can exchange data with the component mounting system 100 and/or a higher-level system.

The user interface includes, for example, a touch panel display, and performs reception of user operations and presentation (display) of information to the user. The user interface is not limited to a touch panel display, but may have input devices such as a keyboard, a pointing device, a mechanical switch, or a gesture sensor, for example. In addition, the user interface may have an audio input/output unit instead of the touch panel display or together with the touch panel display.

In addition, the arrangement assistance system 20 according to the present embodiment constitutes the work system 200 together with the component mounting system 100 as described above. That is, as shown in FIG. 3 , the work system 200 according to the present embodiment includes the placement assistance system 20 and the component mounting system 100 . The component mounting system 100 is used for the arrangement of the plurality of components P1 proposed in the arrangement assistance system 20, and is a system that generates a product P3.

(3) Configuration assistance method

The arrangement assistance method according to the present embodiment will be described in more detail below. In the present embodiment, as described above, the arrangement assistance method employs the three functions of the proposal of arrangement using the learned model M1 , the allocation of the components P1 in the multi-level method, and the rearrangement. Therefore, the arrangement assistance method according to the present embodiment is divided into four parts: the basic method, the proposal of arrangement using the learned model M1, and the allocation and rearrangement of the components P1 in the multi-level method.

In addition, in the following, as an example, a case where 240 parts P1 are allocated to the following eight supply units 3 will be described. That is, in the present embodiment, as described above, the component mounting system 100 includes a total of four mounting machines 10 , the first mounting machine 11 , the second mounting machine 12 , the third mounting machine 13 , and the fourth mounting machine 14 . Furthermore, since each of the four mounting machines 10 has two supply units 3, in the entire component mounting system 100, there are a total of eight supply units as distribution destinations of a plurality of (here, 240) components P1 3.

Here, it is assumed that both the first mounting machine 11 and the second mounting machine 12 have a feature that the number of the capturing parts 41 is “16”. Therefore, the first supply part 31 and the second supply part 32 provided in the first mounting machine 11 and the third supply part 33 and the fourth supply part 34 provided in the second mounting machine 12 all have the number of the capturing parts 41 . For such characteristics as "16". On the other hand, it is assumed that the third mounting machine 13 has a feature that the number of the catch sections 41 is "8". Therefore, both the fifth supply part 35 and the sixth supply part 36 provided in the third mounting machine 13 have a feature that the number of the capturing parts 41 is "8". Furthermore, it is assumed that the fourth mounting machine 14 has a feature that the number of the catch sections 41 is "3". Therefore, both the seventh supply part 37 and the eighth supply part 38 provided in the fourth mounting machine 14 have the feature that the number of the capturing parts 41 is "3".

However, these conditions are only a specific example for explaining the configuration assistance method, and are not intended to limit the scope of application of the configuration assistance method.

(3.1) Basic method

First, the basic form of the arrangement assistance method according to the present embodiment will be described with reference to FIG. 4A , FIG. 4B , and FIG. 5 . FIG. 4A and FIG. 4B are conceptual diagrams showing how the arrangement of the plurality of components P1 in the plurality of supply units 3 is proposed based on the arrangement assistance method.

As in the present embodiment, in the component mounting system 100 having a plurality of (here, eight) supply units 3 , there are many patterns of arrangement of the plurality of components P1 in the plurality of supply units 3 . In particular, in the present embodiment, since the number of slots in each supply unit 3 is "60" as described above, there are 480 (=60×8) slots as the entire component mounting system 100 . Therefore, the component mounting system 100 can mount a maximum of 480 components P1, and if the number of components P1 actually mounted becomes several hundreds, the pattern of arrangement of the components P1 in the plurality of supply units 3 becomes large. Furthermore, depending on the arrangement of the plurality of components P1 in the plurality of supply units 3, the mounting time required for the production of the product P3 in the component mounting system 100 greatly varies.

That is, 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 is used to mount each component P1 differs, and the time required for the mounting of each component P1 is significantly different. change. Therefore, even if the installation time required for the production of one product P3 is shortened, it is very difficult to find an appropriate pattern for the arrangement of the plurality of components P1 from among a large number of patterns. Therefore, the arrangement assisting method according to the present embodiment assists the work of determining the arrangement of the plurality of components P1 in the plurality of supply units 3 in the component mounting system 100, thereby making it possible to find a suitable arrangement more easily (in a short period of time). Configuration.

Here, in the arrangement assistance method according to the present embodiment, as described above, the proposal of "arrangement" of the components P1 is only the allocation of the components P1 among the proposals for the allocation of the components P1 and the arrangement of the components P1. That is, in the present embodiment, the plurality of parts P1 are divided into multiple parts, and one or more divided parts P1 are assigned to any one of the plurality of supply units 3, and are not limited to one or more divided parts The sorting of parts P1.

That is, as shown in FIG. 4A and FIG. 4B , the arrangement assisting method according to the present embodiment is based on the basic scheme of allocating a plurality of components P1 that are not arranged to two or more supply units 3 . In FIG. 4A and FIG. 4B , the unallocated space Sp0 denoted as “unallocated” is a virtual space schematically representing a state in which no allocation is made to any supply unit 3 , that is, an unallocated state. That is, in A of FIG. 4 , the components P1 existing in the non-arrangement space Sp0 are not allocated to any supply unit 3 . On the other hand, in FIG. 4A and FIG. 4B , the space denoted as “supply unit” is an imaginary space schematically representing a state of being allocated to an arbitrary supply unit 3 , that is, a state of being arranged. That is, in B of FIG. 4 , the part P1 existing in the space marked with the reference numeral “ 31 ” is in a state of being allocated (assigned) to the first supply unit 31 . Similarly, in B of FIG. 4 , the component P1 existing in the space denoted by the reference numeral “ 32 ” is in a state of being allocated (assigned) to the second supply unit 32 .

As shown in FIG. 4A , the arrangement assistance method according to the present embodiment sets a state in which all of the plurality of components P1 mounted in the component mounting system 100 are not arranged as an initial state. That is, in the arrangement assisting method, first, by setting all of the plurality of components P1 in a state in which none of the supply units 3 is allocated, as shown in A of FIG. The initial state of Sp0. In the placement assistance method, when the initial state is realized, the components P1 in the unplaced state are selected one by one, and the selected component P1 is determined to which supply unit 3 is assigned (assigned). That is, in the arrangement assistance method, by assigning the plurality of components P1 to an arbitrary supply unit 3 one by one, the assignment destinations of the plurality of components P1 are sequentially determined.

Then, all of the plurality of components P1 mounted in the component mounting system 100 are allocated (distributed) to any supply unit 3 , ie, the component P1 that is not in an unplaced state, and the process based on the basic method of the placement assist method is completed. In a word, according to the basic form of the arrangement assistance method, as shown in FIG. 4B , there is no part P1 existing in the non-arrangement space Sp0 , and a state in which a plurality of parts P1 are all allocated (assigned) to an arbitrary supply unit 3 is realized. .

Specifically, for example, by associating one-to-one correspondence between the respective part identification information for identifying the plurality of parts P1 and the respective supply part identification information for identifying the plurality of supply parts 3, the plurality of parts P1 are processed. distribute. As an example, for the part P1 to which none of the supply parts 3 is assigned, the supply part identification information does not correspond to the part identification information, or the supply part identification information corresponding to the part identification information is null. In addition, regarding the part P1 allocated to the 1st supply part 31, the supply part identification information of the 1st supply part 31 is associated with the part identification information. Then, when the association between the component identification information and the supply unit identification information is completed for all of the plurality of components P1, a state in which all the plurality of components P1 are assigned to any supply unit 3 is realized. The data representing the correspondence between the component identification information and the supply unit identification information in a state in which all the plurality of components P1 are allocated is the arrangement data D2. That is, the arrangement data D2 becomes data representing distribution to an arbitrary supply unit 3 by the correspondence between all the representations of the plurality of components P1 and the supply unit identification information.

In the arrangement assistance method according to the present embodiment, the learned model M1 is used in the proposal of arrangement of the components P1 according to the basic form. That is, in the basic form of the arrangement assistance method, the arrangement of the plurality of components P1 with respect to the plurality of supply units 3 is proposed using the learned model M1. 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 . In the arrangement assistance method according to the present embodiment, the arrangement of the plurality of components P1 with respect to the plurality of supply units 3 is proposed using the learned model M1 so as to be necessary for the production of the product P3 in the component mounting system 100 installation time is shortened. The details are explained in the column of "(3.2) Learning completed model", and the learning completed model M1 is generated by reinforcement learning.

In addition, as shown in FIG. 5 , the arrangement assistance method according to the present embodiment is roughly divided into a processing section S100 for temporary arrangement and a processing section S200 for relocation. Furthermore, in the arrangement assistance method, in either the processing section S100 for provisional arrangement and the processing section S200 for relocation, the allocation of the plurality of components P1 is proposed by the above-described basic method. That is, in the present embodiment, the learned model M1 is used in both the processing section S100 for provisional placement and the processing section S200 for relocation.

That is, in the processing section S100 for provisional arrangement, the plurality of parts P1 are provisionally allocated to the plurality of supply parts 3 . However, when at least a part of the components P1 are allocated to the unsuitable supply unit 3 , there is a possibility of causing troubles such as a longer mounting time in the component mounting system 100 , for example. Therefore, in the processing section S200 for relocation, a more suitable arrangement (allocation) is proposed by redistributing the plurality of components P1 that were temporarily allocated.

In addition, in the processing section S100 for provisional arrangement, when allocating the plurality of components P1 to the plurality of supply units 3, if the number of the supply units 3 increases, the search space for performing the reinforcement learning of the learned model M1 changes. If it is large, it becomes difficult to generate the learned model M1. Therefore, the arrangement assisting method according to the present embodiment adopts the allocation of the components P1 of the multi-stage method in the processing section S100 for provisional arrangement. That is, according to the assignment of the parts P1 in the multi-stage method, even if the multiple parts P1 are assigned to two groups at each stage, the multiple parts P1 can be finally assigned to four or more groups. As a result, in the assignment of each stage, the search space for performing the reinforcement learning of the learned model M1 can be narrowed while using the learned model M1.

As described above, according to the arrangement assisting method according to the present embodiment, the arrangement of the plurality of components P1 in the plurality of supply units 3 can be determined without the assistance of, for example, a skilled person, and improved components can be provided. Proposal for the configuration of P1.

In addition, the flowchart shown in FIG. 5 is only an example, and the order of processing can be suitably changed, and processing can be added or deleted as appropriate.

(3.2) Model after learning

Next, a proposal for the arrangement of the plurality of parts P1 using the learned model M1 in the arrangement assistance method according to the present embodiment will be described in more detail with reference to FIGS. 5 and 6 .

The configuration helper method has a get step and a proposal step. The acquisition step is a step of acquiring the installation data D1, and corresponds to the process S101 of the flowchart shown in FIG. 5 . The acquisition step is performed by the acquisition unit 21 of the placement assistance system 20 . The mounting data D1 is data related to the plurality of components P1 included in the product P3. The proposal step is a step of proposing the arrangement of the plurality of parts P1 for the plurality of supply units 3 based on the installation data D1 using the learned model M1 so as to shorten the installation time. The proposal step is performed by the proposal unit 22 of the placement assistance system 20 . In the present embodiment, since the allocation of the components P1 in the multi-stage method is adopted, in the flowchart shown in FIG. 5 , the processes S102 to S10m of the allocation of the “first stage” to the “Nth stage” correspond to the proposal steps. .

In the present embodiment, the generation of the learned model M1 (pre-learning) is performed in the placement assistance system 20 . In addition, as described above, reinforcement learning is used to generate the learned model M1. That is, the placement assistance system 20 uses, for example, the proposal unit 22 as a learner of reinforcement learning. The "reinforcement learning" referred to in the present disclosure is a framework for automatically obtaining rules from data, that is, a method of machine learning technology.

In machine learning technology, there is "learning with a teacher" as a technique widely used differently from "reinforcement learning". "Learning with a teacher" is a method of learning based on data whose numerical values are clearly defined as learning objectives. Therefore, in "learning with a teacher", a large amount of data (learning data) for which a clear target is defined is required at the time of learning. However, in the technical field of the component mounting system 100, regarding the arrangement of the plurality of components P1 in the plurality of supply units 3, the target numerical value is not clear, and it is difficult to collect a large amount of learning data for learning.

On the other hand, "reinforcement learning" is a method of performing an "action" in a certain "environment", observing the "situation" that changes as a result of the "action", and assigning a high value to the "action" that can give a good result. "remuneration". Furthermore, in the "reinforcement learning", a method of selecting an optimal "action" that maximizes the "reward" through the series of "actions" is learned. Therefore, in "reinforcement learning", it is not necessary to prepare learning data with clear objectives as in "learning with a teacher", and a learned model M1 that learns the "selection method" of the optimal "action" can be generated. . That is, even if the solution space is too large and the actual correct solution is unclear, "reinforcement learning" can learn while evaluating "action" based on the reward series observed by repeating trial and error on a given "environment". way of "action".

Therefore, reinforcement learning is performed on the learned model M1 in the case where the correct solution is not clear and the optimization of a large number of combinations is required, such as the learned model M1 for proposing the arrangement of the plurality of components P1 in the plurality of supply units 3 . is particularly effective in the generation of .

In more detail, in reinforcement learning, the installation time when a certain arrangement is adopted for a plurality of parts P1 is obtained, and how close the installation time is to the ideal installation time (installation time according to the specifications of the installation machine 10 ) is set as the “reward”. ". In the present embodiment, as an example, the installation time at this time is obtained by the simulation unit 26 . In reinforcement learning, the larger the search space, the greater the number of repeated trial and error in order to obtain a good "reward", and the more time-consuming the search for the best solution. Therefore, in the arrangement assistance method according to the present embodiment, in order to reduce the size of the search space in reinforcement learning, the allocation of the components P1 in the multi-level method is adopted, and the details of the multi-level method are described in "(3.3) Multi-level method ” column to explain.

In addition, in the component mounting system 100 , the characteristics and the number of the mounting machines 10 , the type and number of the mounted components P1 , and the like differ, for example, depending on the specifications of the product P3 . However, if reinforcement learning is performed every time to generate the learned model M1 in combination with the product P3, it may take time from the time when the specifications of the product P3 are determined until the learned model M1 is generated. Therefore, in the present embodiment, the learned model M1 is generated by "pre-learning" in which learning is performed before the specification of the product P3 is determined. Accordingly, in the arrangement assistance method according to the present embodiment, when the specification of the product P3 is determined, it is possible to immediately start the arrangement of the components P1 using the learned model M1 generated in the prior learning.

Further, in the present embodiment, the learner (eg, the proposal unit 22 ) creates the configuration data D2 in the reinforcement learning algorithm, and outputs the created configuration data D2 from the output unit 25 to the simulation unit 26 . Thereby, the simulation part 26 performs a simulation based on the arrangement data D2, and calculates "installation time". The learner (eg, the proposal unit 22 ) converts the thus obtained installation time into a ratio with respect to the ideal installation time, and performs reinforcement learning using the obtained ratio as a "reward". Then, reinforcement learning is performed by repeating the above-described series of processes many times in order to obtain a better "reward". In the present embodiment, as an example, in order to perform reinforcement learning, deep reinforcement learning (DQN: DeepQ-NetWork), which incorporates the performance of feature extraction of deep learning, or the like is used.

In addition, in the present embodiment, 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 in the component mounting system 100 . That is, the characteristics of the supply unit 3 are reflected in the learned model M1 , and the learned model M1 is generated for each characteristic of the supply unit 3 . Therefore, when the component mounting system 100 includes a plurality of supply units 3 having mutually different characteristics, a plurality of types of learned models M1 are also generated.

In particular, in the present embodiment, the learned model M1 is associated with the characteristics of the supply unit 3 to which the parts P1 are allocated (distributed) through the proposal of the arrangement of the parts P1 using the learned model M1. Therefore, for example, as shown in FIG. 6 , even when the part P1 is assigned to two assignment (assignment) destinations, various learned models M11 to M17 can be used depending on the assignment destination. In FIG. 6 , what kind of learned models M11 to M17 are used is described in the column of “(3.3) Multi-level method”. In the present disclosure, each of the plurality of learned models M11 to M17 is simply referred to as a "learned model M1" unless the plurality of learned models M11 to M17 are particularly distinguished.

Here, for example, when the two supply units 3 serving as distribution destinations have the same feature (referred to as "first feature"), the learned model M1 is generated in association with the first feature. That is, the learned model M1 includes a model generated in association with the feature (first feature) of one supply unit 3 among the plurality of supply units 3 . As an example, when the two supply units 3 serving as distribution destinations have the feature that the number of capturing units 41 is “16”, the learned model M1 for the distribution part P1 reflects the number of capturing units 41 . The number of such features as "16".

On the other hand, for example, when two supply units 3 serving as distribution destinations have mutually different characteristics (referred to as “first characteristics” and “second characteristics”), the first characteristics and the second characteristics The two sides of the characteristics of , establish a correspondence to generate the learned model M1. That is, the learned model M1 includes models generated in association with the characteristics of two or more supply units 3 among the plurality of supply units 3 . As an example, when the two supply units 3 serving as distribution destinations each have a feature that the number of capturing units 41 is "16" or "8", the learned model M1 for the distribution part P1 reflects The number of capturing parts 41 is two features, "16" and "8".

Further, when the features of the plurality of supply units 3 are classified into one or more feature groups, the learned model M1 includes models generated in association with one or more feature groups. For example, the speed (maximum mounting speed) of the mounting machine 10 is classified into a plurality of speed ranges such as a multi-function machine (low-speed machine), a medium-speed machine, and a high-speed machine. "High-speed machines" etc. can be regarded as the same speed range. That is, if the feature of the supply unit 3 is the "speed" of the mounting machine 10, the "speed range" such as the multifunction machine (low-speed machine), the medium-speed machine, and the high-speed machine becomes a feature group including a plurality of features (speeds). In this way, when a feature group including a plurality of features that are different from each other is set, the learned model M1 also includes a model generated in association not with each feature but with the feature group. Since the feature group is composed of a plurality of feature sets, 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 .

In addition, the arrangement assistance method according to the present embodiment further includes an update step of updating the learned model M1. That is, the learned model M1 generated by machine learning (reinforcement learning in this embodiment) is not fixed and can be appropriately updated by an update procedure. Specifically, the learner (for example, the proposal unit 22 ) regularly or irregularly updates the learned model M1 stored in the model storage unit 27 . Updating of the learned model M1 can be realized by, for example, transfer learning in which knowledge acquired in the past is used in current learning, or can be realized by replacement with a new learned model M1. If the learning completed model M1 can be updated, it is also possible to generate an appropriate learning completed model M1 according to the user's request in the operation stage of the placement assistance method (the placement assistance system 20 ).

In addition, in the present embodiment, the learned model M1 includes a model generated in association with information on the product P3 generated by the component mounting system 100 . The information related to the product P3 includes, for example, the technical field to which the product P3 belongs, the number of batches of the product P3, the price range of the product P3, and the like. The component mounting system 100 is used to generate the product P3 in various technical fields such as the technical field of electronic equipment and the technical field of automobiles, for example. Therefore, even if it is the same product P3, the optimal arrangement|positioning of the component P1 may differ according to the matter specific to each technical field (industry). Therefore, in the present embodiment, the learned model M1 is also generated in association with the information related to the product P3 so as to reflect not only the characteristics of the at least one supply unit 3 but also the matters specific to the product P3 .

In addition, in the arrangement assistance method according to the present embodiment, when arranging the plurality of components P1 in the plurality of supply units 3 , a constraint that defines whether or not the arrangement of the specific component P1 in the specific supply unit 3 is possible is added. . That is, according to the supply part 3, there exists a case where the arrangement|positioning of the specific component P1 cannot be performed due to restrictions on the specifications of the mounting machine 10, restrictions on the size of the components P1, and the like. In order to cope with such a situation, restrictive conditions can be attached. By attaching the constraints, the specific parts P1 specified in the constraints as being incapable of being arranged in the specific supply parts 3 are excluded from the allocation target of the specific supply parts 3 . As an example, the arrangement of the components P1 that cannot be supplied by the tape feeder can be specified in the restriction conditions in the supply portion where the tape feeder cannot be attached but only the tray can be installed.

Furthermore, in the present embodiment, the determination of the availability of the arrangement of the specific components P1 for the specific supply unit 3 according to the constraint conditions and the arrangement of the plurality of components P1 for the plurality of supply units 3 using the learned model M1 proposals are carried out separately. That is, the restriction of the arrangement of the components P1 according to the constraint conditions is performed, for example, before or after the proposal of the arrangement of the components P1 using the learned model M1. As an example, by restricting the arrangement of the parts P1 according to the constraint conditions before the proposal of the arrangement of the parts P1 using the learned model M1, the options for deriving the appropriate arrangement of the plurality of parts P1 can be suppressed relatively. few.

As described above, in the arrangement assistance method according to the present embodiment, at the time of arranging the plurality of components P1, the learned model MI is used to propose the arrangement of the plurality of components P1 for the plurality of supply units 3 based on the mounting data D1. Configured so that installation time is shortened (proposal step). Therefore, in the proposal step, instead of proposing a uniquely determined arrangement, it is possible to find an appropriate arrangement more easily by, for example, using the learned model M1 to implement the technique of "determination method" in which a skilled person performs such arrangement.

(3.3) Multi-level method

Next, allocation of the components P1 of the multi-stage method in the arrangement assistance method according to the present embodiment will be described in more detail with reference to FIGS. 5 and 6 .

The configuration helper method has a one-time proposal step and a second-order proposal step. The primary proposal step is a step of proposing the arrangement (allocation) of the plurality of components P1 for the plurality of primary groups G11 and G12, and corresponds to the process S102 of 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 assistance system 20 . The secondary proposal step is a step of proposing the arrangement of the plurality of components P1 for the plurality of secondary groups G21 to G24 after the primary proposal step, and corresponds to the process S103 of the flowchart shown in FIG. 5 . The secondary proposal step is performed by the secondary proposal unit 222 of the proposal unit 22 in the placement assistance system 20 . That is, in the flowchart shown in FIG. 5 , the processes S102 to S10m corresponding to the assignment of the “first stage” to the “Nth stage” of the proposal steps include a primary proposal step and a secondary proposal step.

Here, the arrangement assistance method according to the present embodiment further includes three proposal steps. The tertiary proposal step is to propose a plurality of parts P1 for the plurality of tertiary groups G31 to G38 when the plurality of secondary groups G21 to G24 are each classified into the plurality of tertiary groups G31 to G38 after the secondary proposal step configuration steps. Each of the plurality of tertiary groups G31 to G38 includes at least one supply unit 3 among the plurality of supply units 3 . To sum up, according to the tertiary proposal step, each of the plurality of secondary groups G21 to G24 is classified into a plurality of tertiary groups G31 to G38 that are further subdivided, and the plurality of parts P1 for the plurality of tertiary groups G31 to G38 are proposed. Configuration.

That is, in the present embodiment, as shown in FIG. 5 , the arrangement of the plurality of components P1 is not performed in two stages, but in N stages (here, N is “3” or more) set in layers. processing of natural numbers). Therefore, after the second-level allocation ( S103 ) is performed as the secondary proposal step, it is also possible to achieve a more subdivided allocation by performing the third-level and later allocations. In particular, in the present embodiment, since it is assumed that the plurality of components P1 are allocated to two groups at each stage, and finally the eight supply units 3 are allocated, the allocation is performed in three stages. Therefore, the three-time proposal step corresponds to the final stage in the proposal step, that is, the process S10m of the flowchart shown in FIG. 5 (here, m is "4"). The tertiary proposal step is executed by the tertiary proposal unit 223 of the proposal unit 22 in the arrangement assistance system 20 .

FIG. 6 is an explanatory diagram schematically showing a state of allocation of components P1 in a multi-stage system. In the present embodiment, the proposal for the arrangement of the plurality of parts P1 is at least divided into a primary proposal procedure of arranging the part P1 for the plurality of primary groups G11 and G12 and the arrangement of the part P1 for the more detailed plurality of secondary groups G21 to G24 the second proposal step. In this way, since the arrangement of the plurality of parts P1 is realized not by one-stage processing but by a multi-stage process set hierarchically, it is possible to derive a suitable method for deriving the plurality of parts P1 in each stage. Configured options are less suppressed.

In FIG. 6 , the plurality of primary groups G11 and G12 correspond to a state in which none of the supply units 3 is allocated, that is, a non-arranged space Sp0 in which a plurality of components P1 in a non-arranged state exists, is first classified into two or more groups The classified group in the case of a group. Each of the plurality of primary groups G11 and G12 includes at least one supply unit 3 among the plurality of supply units 3 .

Specifically, as shown in FIG. 6 , the primary group G11 (indicated as “group 1 ” in the figure) includes a first supply unit 31 , a second supply unit 32 , a third supply unit 33 , and a fourth supply unit 34 . The primary group G12 (indicated as "group 2" in the figure) includes a fifth supply part 35 , a sixth supply part 36 , a seventh supply part 37 , and an eighth supply part 38 .

In the primary proposal step, the plurality of components P1 existing in the non-arranged state of the non-arrangement space Sp0 are allocated to the plurality of primary groups G11 and G12. Thereby, a plurality of (here, 240) parts P1 are assigned to any one of the plurality of primary groups G11 and G12.

In addition, in FIG. 6 , the plurality of secondary groups G21 to G24 correspond to the classified groups 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, and a total of four secondary groups G21 to G24 are generated. Each of the plurality of secondary groups G21 to G24 includes at least one supply unit 3 among the plurality of supply units 3 .

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

The secondary proposal step assigns the plurality of parts P1 included in the primary group G11 to the plurality of secondary groups G21 and G22, and assigns the plurality of parts P1 included in the primary group G12 to the plurality of secondary groups G23, G24. Thereby, a plurality of (here, 240) parts P1 are assigned to any one of the plurality of secondary groups G21 to G24.

In addition, in FIG. 6 , the plurality of tertiary groups G31 to G38 correspond to the classified groups when each of the plurality of 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, and a total of eight tertiary groups G31 to G38 are generated. Each of the plurality of tertiary groups G31 to G38 includes at least one supply unit 3 among the plurality of supply units 3 .

Specifically, as shown in FIG. 6 , the tertiary group G31 and the tertiary group G32 are located under the secondary group G21 , and the tertiary group G33 and the tertiary group G34 are located under the 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. The tertiary group G35 and the tertiary group G36 are located under the secondary group G23 , and the tertiary group G37 and the tertiary group G38 are located under the 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. Furthermore, in the example of FIG. 6 , since the plurality of tertiary groups G31 to G38 are the final stages of the multi-stage method, each of the plurality of tertiary groups G31 to G38 includes one supply unit 3 . That is, in the present embodiment, since the final assignment to the components P1 of the eight supply units 3 is assumed, the plurality of (here, eight) tertiary groups G31 to G38 serving as the final stage are supplied to the first to eighth groups, respectively. The parts 31 to 38 are in one-to-one correspondence.

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

Here, in the arrangement assistance method according to the present embodiment, as shown in FIG. 6 , the learned model M1 is used in the assignment of 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 components P1. 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 , as also explained in the column of “(3.2) Learning completed model”. In the present embodiment, the learned model M1 is used in all of the primary proposal step, the secondary proposal step, and the tertiary proposal step, respectively.

That is, in the primary proposal step of allocating the plurality of parts P1 to the plurality of primary groups G11 and G12, the learned model M11 is used to propose proposals for the plurality of parts P1 of the plurality of primary groups G11 and G12 based on the mounting data D1. configuration so that installation time is shortened. In the secondary proposal step of allocating the plurality of components P1 to the plurality of secondary groups G21 to G24, the learned models M12 and M13 are used to propose a plurality of the plurality of secondary groups G21 to G24 based on the mounting data D1 Component P1 is configured so that the installation time is shortened. In the tertiary proposal step of assigning the plurality of parts P1 to the plurality of tertiary groups G31 to G38, the learned models M14 to M17 are used to propose proposals for the plurality of parts P1 of the plurality of tertiary groups G31 to G38 based on the mounting data D1 Configured to make install time.

Here, as is clear from FIG. 6 , the learned model M1 used differs depending on which stage of the primary proposal step, secondary proposal step, and tertiary proposal step is used. That is, in the present embodiment, as described above, various learned models M11 to M17 are used according to the assignment destination of the component P1. For example, the learned model M11 used in the first proposal step and the learned models M12 and M13 used in the second proposal step are different. As a result, in the present embodiment, the algorithm for proposing the arrangement of the plurality of components P1 is different in the primary proposal step and the secondary proposal step. Here, the "algorithms are different" means that the learned models M1 used are different in the present embodiment. Furthermore, in the present embodiment, an algorithm (learned model M1 ) different from the primary proposal step and the secondary proposal step is also used in the tertiary proposal step.

In addition, in the present embodiment, in the assignment of each stage, various learned models M11 to M17 are used according to the assignment destination of the component P1. For example, in the secondary proposal step, the learned model M12 is used for the assignment of the plurality of components P1 included in the primary group G11 to the plurality of secondary groups G21 and G22. On the other hand, in the secondary proposal step, the learned model M13 is used for the assignment of the plurality of components P1 included in the primary group G12 to the plurality of secondary groups G23 and G24. Similarly, in the tertiary proposal step, the learned model M14 is used for the assignment of the plurality of components 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 for the assignment of 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 arrangement assistance method according to the present embodiment, seven learned models M11 to M17 are used as shown in FIG. 6 .

Specifically, the learned model M11 used in the primary proposal step is a model for assigning the plurality of parts P1 to be assigned to the first to eighth supply units 31 to 38 to the two primary groups G11 and G12. The learned model M11 includes the first to fourth supply units 31 to 34 whose number of capturing units 41 is “16” and the fifth and sixth supply units 35 and 36 whose number of capturing units 41 is “8” in the distribution destination. and the seventh and eighth supply parts 37 and 38 whose number of the capturing parts 41 is "3". Therefore, the learned model M11 is a model generated in order to reflect the three features "16", "8", and "3" as the number of capturing units 41 and to correspond to these three features.

The learned model M12 used in the secondary proposal step is a model for allocating the plurality of parts P1 to be allocated to the first to fourth supply units 31 to 34 to the two secondary groups G21 and G22. The learned model M12 includes the first to fourth supply units 31 to 34 whose number of capturing units 41 is "16" in the distribution destination. Therefore, the learned model M12 is a model generated in order to reflect one feature that the number of capturing units 41 is “16” and that the number of capturing units 41 is “16”.

On the other hand, the learned model M13 used in the secondary proposal step is a model for allocating the plurality of parts P1 to be allocated to the fifth to eighth supply units 35 to 38 to the two secondary groups G23 and G24. The learned model M13 includes the fifth and sixth supply units 35 and 36 whose number of capturing units 41 is “8” and the seventh and eighth supply units 37 and 38 whose number of capturing units 41 is “3” in the distribution destination. . Therefore, the learned model M13 is a model that is generated in order to reflect the two features that are "8" and "3" as the number of capturing units 41, and to correspond to these two features.

The learned model M14 used in the tertiary proposal step is a model for assigning a plurality of parts P1 to be allocated to the first and second supply units 31 and 32 to two tertiary groups G31 and G32. The learned model M14 includes the first and second supply units 31 and 32 whose number of capturing units 41 is "16" in the distribution destination. Therefore, the learned model M14 is a model generated in order to reflect one feature that the number of capturing units 41 is “16” and that the number of capturing units 41 is “16”.

The learned model M15 used in the tertiary proposal step is a model for assigning a plurality of parts P1 to be allocated to the third and fourth supply units 33 and 34 to two tertiary groups G33 and G34. The learned model M15 includes the third and fourth supply units 33 and 34 whose number of capturing units 41 is "16" in the distribution destination. Therefore, the learned model M15 is a model generated in order to reflect one feature that the number of capturing units 41 is “16” and to correspond to the feature that the number of capturing units 41 is “16”.

The learned model M16 used in the tertiary proposal step is a model for assigning a plurality of parts P1 to be allocated to the fifth and sixth supply units 35 and 36 to two tertiary groups G35 and G36. The learned model M16 includes the fifth and sixth supply units 35 and 36 whose number of capturing units 41 is "8" in the distribution destination. Therefore, the learned model M16 is a model generated in order to reflect one feature that the number of capture units 41 is "8" and to correspond to the feature that the number of capture units 41 is "8".

The learned model M17 used in the tertiary proposal step is a model for assigning the plurality of parts P1 to be allocated to the seventh and eighth supply units 37 and 38 to the two tertiary groups G37 and G38. The learned model M17 includes the seventh and eighth supply units 37 and 38 whose number of capturing units 41 is "3" in the distribution destination. Therefore, the learned model M17 is a model generated in order to reflect one feature that the number of capturing units 41 is "3" and to correspond to the feature that the number of capturing units 41 is "3".

Then, the above-mentioned plural (here, seven) learned models M11 to M17 are generated by individually performing reinforcement learning. That is, reinforcement learning is performed in advance for each stage of a plurality of stages (here, three stages) set hierarchically, and the learned models M11 to M17 as described above are generated. By cooperating the plurality of learned models M11 to M17 thus generated, a multi-level architecture as shown in FIG. 6 is constructed.

As described above, in the arrangement assistance method according to the present embodiment, the arrangement of the plurality of components P1 is not performed by one-stage processing, but by multi-stage (here, three-stage) processing that is set hierarchically realized. As a result, compared with the multi-selection method in which the plurality of components P1 are allocated in one stage of processing, options for deriving an appropriate arrangement of the plurality of components P1 can be reduced in each stage. As a result, the search space for performing reinforcement learning of the learned model M1 can be narrowed. For example, when 240 parts are allocated to the above-mentioned eight supply units 3, it is assumed that the search space is "10240" in the case of the one-stage multi-selection method. In contrast, in the case of the three-stage multi-stage method, even under the same conditions, the search space involved in the first proposal step is "1080", the search space involved in the second proposal step is "1072", and the search space involved in the third proposal step is "1072". The search space involved becomes "1036". As a result, the search space for allocating 240 parts to the eight supply units 3 is "1080+1072+1036", which is significantly narrower than "10240" in the multi-selection method, and the size of the search space can be reduced to A size that enables actual learning.

Note that the above description is merely an example of the arrangement assistance method according to the present embodiment. For example, the arrangement of the plurality of components P1 may be realized not by three stages of processing but by two or more stages of processing. When the allocation is performed in two stages, the three-time 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 assignment is performed in four stages, the further subordinates (subordinates) of the tertiary groups G31 to G38 to which the plurality of components P1 are assigned in the tertiary proposal step generate a plurality of quaternary groups. When the assignment is carried out in five stages, a plurality of quintile groups are generated in the further subordinates (subordinates) of the quaternary group.

(3.4) Reconfiguration

Next, the rearrangement in the arrangement assistance method according to the present embodiment will be described in more detail with reference to FIGS. 5 and 7 .

The configuration assist method has a proposal step, a determination step, and a reconfiguration step. The proposal step is a step of proposing the arrangement of the plurality of components P1 with respect to the plurality of supply units 3 , and corresponds to the processes S102 to S10m of the flowchart shown in FIG. 5 . The proposal step is performed by the proposal unit 22 of the placement assistance system 20 . The identifying step is a step of identifying a certain supply unit 3 among the plurality of supply units 3 as a target supply unit, and corresponds to the process S201 of the flowchart shown in FIG. 5 . The determination step is performed by the determination section 23 of the configuration assistance system 20 . The supply unit 3 specified as the target supply unit is the supply unit 3 that satisfies the specified condition regarding the installation 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 components P1 with respect to the target supply unit and the reference supply unit, and corresponds to the processes S202 to S204 of the flowchart shown in FIG. 5 . The relocation step is performed by the relocation unit 24 of the arrangement assistance system 20 . The reference supply unit is composed of at least one supply unit 3 other than the target supply unit among the plurality of supply units 3 .

In the present embodiment, in the rearrangement steps ( S202 to S204 ), the additional allocation ( S203 ) is repeatedly performed for a predetermined number of times by targeting the component P1 arranged in the target supply unit. The "additional assignment" referred to here is based on the arrangement (assignment) of the plurality of components P1 to the plurality of supply units 3 proposed in the provisional arrangement ( S100 ), and re-arranges some of the components P1 to the plurality of supply units 3 ( allocation) processing. Therefore, the "designated number of times" that the additional assignment is repeatedly performed is the number of times determined according to the number of components P1 to be additionally assigned, and the like.

That is, in the processing section S100 for provisional arrangement, when distributing the plurality of components P1 to the plurality of supply units 3, when at least some of the components P1 are inappropriately arranged (distributed), the process is performed as such. There is a possibility that the desired result may not be obtained. For example, when a certain component P1 is allocated to an inappropriate supply unit 3 in the temporary arrangement ( S100 ), the installation of the component P1 takes time, and the installation time of the component mounting system 100 as a whole may increase. Therefore, in the arrangement assistance method according to the present embodiment, the arrangement of the components P1 is not determined by the proposal step, but the proposal of the arrangement in the proposal step is regarded as a "temporary arrangement", and multiple relocation steps can be performed afterward. A change (correction) of the arrangement of the individual components P1.

In addition, the object to be rearranged in the rearrangement step is the supply unit 3 that satisfies the specified condition regarding the mounting time, that is, the component P1 arranged in the target supply unit. Furthermore, the object to be rearranged in the rearrangement step includes not only the object supply part satisfying the specified condition but also the component P1 arranged in the reference supply part of the supply part 3 different from the object supply part. Therefore, the plurality of components P1 arranged in the different supply units 3 (target supply unit and reference supply unit) in the temporary arrangement can be shuffled. Therefore, even when a certain component P1 is allocated to an inappropriate supply unit 3 in the temporary arrangement, the relocation of the component P1 in the rearrangement step can eliminate such problems as increased installation time.

In addition, in the arrangement assistance method according to the present embodiment, as shown in FIG. 5 , by repeatedly executing the determination step ( S201 ) and the rearrangement steps ( S202 to S204 ), it is possible to search for the improvement of the installation time of the component P1 . configuration. In the present embodiment, "improvement of the installation time" refers to shortening of the installation time of the component mounting system 100 as a whole. That is, as shown in FIG. 5 , in the arrangement assistance method, it is determined whether or not the installation time has been improved ( S205 ) after the rearrangement steps ( S202 to S204 ). Therefore, the arrangement data D2 created in the rearrangement step is output from the output unit 25 to the simulation unit 26 . Thereby, the simulation part 26 performs a simulation based on the arrangement data D2, and calculates the "installation time" after relocation. In process S205, it is determined whether or not the installation time has been improved based on the installation time thus obtained.

Here, in the arrangement assistance method, if the installation time is not improved (No in S205), the arrangement of the component P1 changed in the relocation step is returned to the state before the relocation step, that is, the "original component arrangement" ( S206). On the other hand, if the installation time is improved (YES in S205), the process S206 is skipped. That is, if the installation time is not improved by the relocation, the state before the relocation is returned, and only when the installation time is improved (shortened), the arrangement of the components P1 obtained by the relocation is adopted.

After that, the arrangement assisting method determines whether or not there is movement of the part P1 from the state before the relocation step (S207). If there is any movement of the part P1 in the rearrangement step (S207: YES), the process returns to process S201. On the other hand, if none of the components P1 has moved in the rearrangement step (NO in S207), the processing section S200 for rearrangement ends. That is, as long as the arrangement of the parts P1 can be changed (corrected) in the rearrangement step, there is any movement of the part P1 in the rearrangement step (YES in S207), so the determination step (S201) and the rearrangement step ( S202～S204). In other words, the determination step ( S201 ) and the rearrangement steps ( S202 to S204 ) are repeatedly executed until the change (correction) mode of the arrangement of the component P1 whose installation time is improved in the rearrangement step is exhausted.

FIG. 7 is an explanatory diagram schematically showing a state of rearrangement. In FIG. 7 , based on the arrangement (allocation) of the plurality of components P1 to the plurality of supply units 3 proposed in the provisional arrangement, the fourth supply that is arranged among the first to eight supply units 31 to 38 is conceptually represented. The part 34 and the plurality of parts P1 of the sixth supply part 36 are rearranged. Here, as an example, a case where the fourth supply unit 34 is the “target supply unit” and the sixth supply unit 36 is the “reference supply unit” is taken as an example.

Here, in the present embodiment, as an example, the supply unit 3 that becomes a bottleneck regarding the installation time is set as the target supply unit. That is, as the component mounting system 100 sequentially mounts the plurality of components P1 arranged in the plurality of supply units 3, the supply unit 3 that takes the most time to mount the component P1 among the plurality of supply units 3 becomes a bottleneck in terms of mounting time. That is, in the present embodiment, it is determined that the time (installation time) required for the generation of 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 by the temporary arrangement is adopted in the component mounting system 100 , the time required for the mounting of the component P1 arranged in the fourth supply unit 34 among the plurality of supply units 3 is the longest. , so the fourth supply unit 34 is extracted as a target supply unit.

In this way, in the determination step, the supply unit 3 that satisfies the determination condition with respect to the installation time among the plurality of supply units 3 is determined as the target supply unit. Therefore, in the present embodiment, the arrangement data D2 created under the temporary arrangement is output from the output unit 25 to the simulation unit 26 . Thereby, the simulation part 26 performs a simulation based on the arrangement data D2, and calculates "installation time". The specifying unit 23 extracts the supplying unit 3 (target supplying unit) that satisfies the specified condition based on the mounting time thus obtained.

On the other hand, the reference supply unit is constituted by an arbitrary supply unit 3 that is different from the target supply unit (here, the fourth supply unit 34 ) among the plurality of supply units 3 . In the present embodiment, it is assumed that any one supply unit 3 other than the target supply unit (here, the fourth supply unit 34 ) among the plurality of supply units 3 is sequentially selected as the reference supply unit. In the example of FIG. 7 , the state of the rearrangement in the case where the sixth supply unit 36 among the plurality of supply units 3 is selected as the reference supply unit is represented. For example, when the relocation shown in FIG. 7 is completed, next, the seventh supply part 37 among the plurality of supply parts 3 is selected as the reference supply part, and the relocation is executed.

In addition, in the rearrangement step, as shown in FIG. 7 , the plurality of components 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 non-arrangement space After Sp0, it is reassigned to the target supply unit and the reference supply unit. That is, the plurality of components P1 arranged in the target supply unit and the reference supply unit in the provisional arrangement are reassigned to the target supply unit and the reference supply unit after returning to a state where none of the supply units 3 is assigned, ie, the undistributed state. That is, in the rearrangement step, the arrangement of the plurality of components P1 is newly proposed for the target supply unit and the reference supply unit after the arrangement of the plurality of components P1 is reset.

Furthermore, in the arrangement assistance method according to the present embodiment, as shown in FIG. 7 , the learned model M1 is also used for arrangement (assignment) of the plurality of components P1 being rearranged. In the present 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 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 , as also explained in the column of “(3.2) Learning completed model”. In particular, in the present embodiment, the learned model M1 is used in both the proposal step and the rearrangement step, respectively.

Here, in the present embodiment, as described above, various learned models M1 are used according to the assignment destination of the component P1. Therefore, in the rearrangement in which the fourth supply unit 34 serving as the target supply unit and the sixth supply unit 36 serving as the reference supply unit are assigned as distribution destinations, the learned models M11 to M11 used in the provisional arrangement (proposing step) are used. M17 different learning completed model M18. As a result, in the present embodiment, the algorithm for proposing the arrangement of the plurality of components P1 is different in the proposal step and the rearrangement step.

Specifically, the learned model M18 used in the rearrangement step is a model for assigning the plurality of components P1 to be assigned to the two supply units 3 to the fourth supply unit 34 and the sixth supply unit 36 . The learned model M18 includes the fourth supply unit 34 whose number of capturing units 41 is "16" and the sixth supply unit 36 whose number of capturing units 41 is "8" in the distribution destination. Therefore, the learned model M18 is a model that is generated in order to reflect the two features that are “16” and “8” as the number of capturing units 41 and to correspond to these two features.

In addition, also in the rearrangement step, similarly to the proposal step, the arrangement of the plurality of components P1 for the plurality of supply units 3 is proposed so as to shorten the installation time. That is, in the rearrangement step, the arrangement of the plurality of components P1 for the target supply unit and the reference supply unit is proposed so as to shorten the mounting time required for the generation of the product P3 in the component mounting system 100 .

Furthermore, in the present embodiment, also in the rearrangement step, similarly to the proposal step, when arranging the plurality of components P1 for the plurality of supply units 3, a specific component P1 for a specific supply unit 3 is additionally defined. Constraints on the availability of the configuration. The details are as explained in the column of "(3.2) Learning Completion Model", by attaching constraints, with regard to the specific component P1 specified in the constraints that cannot be placed in the specific supply unit 3, from the rearrangement (assignment) to the specific component P1. The object excludes the specific supply unit 3 .

In the arrangement assistance method according to the present embodiment, as described above, the determination step ( S201 ) and the relocation step ( S202 ) are repeatedly executed until the pattern of changing the arrangement of the component P1 whose installation time is improved in the relocation step is exhausted. ~S204). Therefore, if the supply unit 3 (target supply unit) that satisfies the specified condition (becomes a bottleneck) with respect to the installation time is relocated and the result is that the other supply unit 3 meets the specified condition, the other supply unit 3 is set as the target supply unit, and the process is repeated. Reconfigure steps. On the other hand, if the same supply unit 3 that satisfies the specified condition (becomes a bottleneck) with respect to the installation time is relocated and the same supply unit 3 satisfies the specified condition and remains unchanged, it is considered that the change pattern of the arrangement of the components P1 is exhausted, and the function is terminated. In the reconfiguration processing part S200.

As described above, the arrangement assistance method according to the present embodiment includes relocation steps ( S202 to S204 ) in addition to the acquisition step ( S101 ) and the proposal steps ( S102 to S10m ). The rearrangement step is a step of proposing the arrangement of the plurality of components P1 with respect to the plurality of supply units 3 after the proposal step. In particular, in the present embodiment, the learned model M1 generated in the reinforcement learning is also used in the rearrangement step, and the arrangement of the components P1 can be re-proposed to shorten the installation time compared with the arrangement proposed in the proposal step.

Furthermore, since the arrangement assistance method according to the present embodiment adopts a multi-stage method in the proposal step, the rearrangement step is a step of proposing the arrangement of the plurality of components P1 after the second proposal step. Furthermore, in the rearrangement step, the arrangement of the plurality of components P1 is proposed for at least the supply unit 3 whose time required for the generation of the product P3 in the component mounting system is the longest among the plurality of supply units 3 .

(4) Modifications

Embodiment 1 is only one of various embodiments of the present disclosure. Embodiment 1 can be variously changed in accordance with the design and the like as long as the object of the present disclosure can be achieved. In addition, the drawings referred to in the present disclosure are all schematic drawings, and the respective ratios of the sizes and thicknesses of the respective constituent elements in the drawings do not necessarily reflect the actual dimensional ratios. In addition, the same function as the arrangement assistance method according to Embodiment 1 can be embodied by the arrangement assistance system 20, a (computer) program, or a non-transitory recording medium in which the program is recorded. The program according to one aspect is a program for causing one or more processors to execute the arrangement assistance method according to the first embodiment.

Modifications of Embodiment 1 are listed below. The modifications described below can be combined and used as appropriate.

The configuration assistance system 20 in this disclosure includes a computer system. A computer system is mainly composed of a processor and a memory as hardware. The function as the configuration assistance system 20 in the present disclosure is realized by the processor executing the program recorded in the memory of the computer system. The program may be pre-recorded in the memory of the computer system, or provided via an electrical communication line, or may be provided by being recorded in a non-transitory recording medium such as a memory card, an optical disk, and a hard disk drive readable by the computer system. The processor of a computer system is composed of one or more electronic circuits including a semiconductor integrated circuit (IC) or a large-scale integrated circuit (LSI). The integrated circuits such as IC or LSI mentioned here are called differently according to the degree of integration, including those called system LSI, VLSI (Very Large Scale Integration, very large scale integration) or ULSI (Ultra Large Scale Integration, very large scale integration) of integrated circuits. Furthermore, an FPGA (Field-Programmable Gate Array) programmed after the LSI is manufactured, or a logic device capable of reconfiguring the bonding relationship within the LSI or reconfiguring the circuit division within the LSI, is also applicable. Can be used as a processor. A plurality of electronic circuits may be integrated into one chip, or may be distributed over a plurality of chips. A plurality of chips may be integrated into one device, or may be distributed in a plurality of devices. The computer system referred to here includes a microcontroller having one or more processors and one or more memories. Therefore, the microcontroller is also constituted by one or a plurality of electronic circuits including a semiconductor integrated circuit or a large-scale integrated circuit.

In addition, it is not an essential structure for the arrangement assistance system 20 to integrate a plurality of functions in the arrangement assistance system 20 into one housing. The structural elements of the arrangement assistance system 20 may be distributed in a plurality of housings. Furthermore, at least a part of the functions of the configuration assistance system 20 may be realized by cloud (cloud computing) or the like.

As functions that can be implemented in two or more systems such as the cloud (or server) and the cloud edge (edge), for example, there are the following functions.

As the first function, there is a function of generating the learned model M1. That is, the generation of the learned model M1 can be performed in one system, and the arrangement assistance method (proposal step, etc.) using the learned model M1 can be performed in another system. As an example, the generation of the learned model M1 may be performed in the cloud (or server), and the configuration assistance method (proposal step, etc.) using the learned model M1 may be performed in the cloud edge. In this case, in a system such as a cloud, a method for generating a learned model that is generated by associating the learned model used in the placement assistance method with the characteristics of at least one supply unit 3 among the plurality of supply units 3 specific.

As the second function, there is a function of distributing the components P1 in the multi-level system. That is, the first proposal step can be performed in one system, and the steps after the second proposal step (including the third proposal step, etc.) can be performed in another system. As an example, the first proposal step can be performed in the cloud (or server), and the steps after the second proposal step (including the third proposal step, etc.) can be performed in the cloud edge. In this case, the placement assistance system 20 is embodied in a system such as a cloud edge, and executes only the steps after the second proposal step (including the third proposal step and the like). In short, the arrangement assisting system 20 assists the decision of the arrangement of the plurality of components P1 in the plurality of supply units 3 with respect to the component mounting system 100 . The component mounting system 100 generates the product P3 by mounting the plurality of components P1 supplied to the plurality of supply units 3 to the object P2. The arrangement assistance system 20 is not provided with the primary proposal unit 221 but is provided with the secondary proposal unit 222 . The secondary proposal unit 222 proposes the arrangement of the 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 the plurality of secondary groups G21 to G24. Each of the plurality of secondary groups G21 to G24 includes at least one supply unit 3 among the plurality of supply units 3 . The secondary proposal unit 222 receives proposals 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, the proposal for the arrangement of the plurality of components P1 of the plurality of primary groups G11 and G12 is performed by a system different from the arrangement support system 20 by another system (cloud, server, etc.) including the primary proposal unit 221 . That is, the arrangement assistance system 20 receives proposals for arrangement of the plurality of parts P1 for the plurality of primary groups G11 and G12 from other systems, and proposes the arrangement of the plurality of parts P1 for the plurality of secondary groups G21 to G24.

As the third function, there is a function of relocation. That is, the proposal step can be performed in one system, and the determination step and the relocation step can be performed in the other system. As an example, the proposal step may be performed in the cloud edge, and the determination step and the reconfiguration step may be performed in the cloud (or server). In this case, the configuration assistance method is embodied in a system such as a cloud (or server), and includes only a determination step and a reconfiguration step. In short, the arrangement assisting method is a method for assisting the determination of the arrangement of the plurality of components P1 in the plurality of supply units 3 with respect to the component mounting system 100 . The component mounting system 100 generates the product P3 by mounting the plurality of components P1 supplied to the plurality of supply units 3 to the object P2. The configuration assist method does not have a proposal step, but has a determination step and a reconfiguration step. The determination step is a step of accepting a proposal for the arrangement of the plurality of components in the plurality of supply units, and in the case of adopting the proposed arrangement of the plurality of components P1, among the plurality of supply units 3 satisfying the determination condition The supply part 3 of the target supply part is determined. The determination condition is a condition regarding the time required for generation of the product P3 in the component mounting system 100 . The rearrangement step is a step of proposing the arrangement of the plurality of components P1 with respect to the target supply unit and the reference supply unit composed of at least one supply unit 3 other than the target supply unit among the plurality of supply units 3 .

Conversely, in Embodiment 1, at least a part of the functions of the configuration assistance system 20 or the operating system 200 dispersed in a plurality of apparatuses can be integrated into one casing. For example, part of the functions dispersed in the component mounting system 100 and the arrangement support system 20 may be integrated into the component mounting system 100 .

Furthermore, the use of the component mounting system 100 is not limited to the manufacture of electronic equipment in a factory. For example, when the component mounting system 100 is used for attachment of a mechanical component to a glass plate, the component mounting system 100 performs the work of mounting the mechanical component as the component P1 to the glass plate as the object P2.

In addition, the number etc. of the capture|acquisition part 41 provided in the mounting head 4 are not limited to the number demonstrated in Embodiment 1. FIG. For example, the number of capturing parts 41 may be 17 or more. Of course, the mounting head 4 may include only one capturing portion 41 . The mounting head 4 may be a rotary head.

In addition, at least one mounting machine 10 among the plurality of mounting machines 10 may include only one supply unit 3 or may include three or more supply units 3 . Similarly, at least one mounting machine 10 among the plurality of mounting machines 10 may be provided with only one mounting head 4 , or may be provided with three or more mounting heads 4 .

In addition, in Embodiment 1, although the reference supply part was comprised by the arbitrary supply part 3 other than the object supply part among the several supply parts 3, it is not limited to this example. For example, the supply unit 3 having the most allowance for the installation time may be set as the reference supply unit. That is, as a result of the component mounting system 100 sequentially mounting the plurality of components P1 arranged in the plurality of supply units 3, the supply unit 3 that takes the shortest time to mount the component P1 among the plurality of supply units 3 has the longest mounting time. surplus. That is, the reference supply part includes the supply part 3 whose time required to generate the product P3 in the component mounting system 100 is the shortest among the plurality of supply parts 3 . According to this configuration, in the rearrangement, the plurality of components P1 can be shuffled between the target supply unit that becomes the bottleneck regarding the mounting time and the reference supply unit that has the most margin regarding the mounting time. As a result, it is easy to improve the installation time by relocation.

In addition, the determination condition for specifying the target supply unit may be a condition related to the installation time, and the installation time is not limited to be the longest among the plurality of supply units 3 (the supply unit 3 becomes the bottleneck). For example, the determination condition may be that the time (installation time) required to generate the product P3 in the component mounting system 100 is the Mth (M is an integer of "2" or more) long among the plurality of supply units 3 . Conversely, the determination condition may be that the time (installation time) required for the generation of the product P3 in the component mounting system 100 is the shortest among the plurality of supply units 3 or the like. In this way, depending on the specific conditions, for example, in the plurality of supply units 3, it is possible to reduce the variation in the time required for the generation of the product P3 in the component mounting system 100. In this case, for example, the concentration of the load on a specific mounting machine 10 can be alleviated.

In addition, the target supply unit is not limited to one supply unit 3 , and may be two or more supply units 3 . Likewise, the reference supply unit is not limited to one supply unit 3 , and may be two or more supply units 3 .

In addition, it is not limited to the structure which attaches a tape feeder to the supply part 3, For example, it is possible to provide a tray on which a plurality of components P1 are loaded. Furthermore, as the entire component mounting system 100, for example, the supply unit 3 to which the tape feeder is attached and the supply unit 3 to which the tray is installed may coexist.

In addition, the proposal of "arrangement" of the components P1 by the arrangement assistance method may be up to the proposal of the arrangement of the components P1. In this case, in the arrangement assistance method, the plurality of components P1 are divided into multiple parts, and one or more divided components P1 are allocated to any one of the plurality of supply units 3 , and are specified to each of the supply units 3 . Sorting (arranging) within. As a result, when a plurality of parts P1 are allocated to one supply unit 3, the order of the plurality of parts P1 is defined.

In addition, the pre-learning of the learned model M1 is not limited to the placement assistance system 20, and may be performed in other systems. In this case, the arrangement assistance system 20 uses the learned model M1 generated in the other system to execute proposal of arrangement of the components P1 in the proposal unit 22 and the rearrangement unit 24 .

In addition, in both the proposal step and the rearrangement step, it is not necessary to propose the arrangement of the components P1 using the learned model M1. For example, only in the proposal step among the proposal step and the rearrangement step, the proposal of the arrangement of the parts P1 using the learned model M1 may be performed, or only in the rearrangement step, the proposal of the arrangement of the parts P1 using the learned model M1 may be performed. Configured proposals. Furthermore, the learned model M1 may not be used in either the proposal step or the rearrangement step. That is, the functions similar to those of the first embodiment can be realized without using the learned model M1 for functions such as assignment and rearrangement of the components P1 in the multi-stage method.

In addition, in Embodiment 1, it is not absolutely necessary to propose the arrangement of the components P1 using the learned model M1 in all of the primary proposal step, the secondary proposal step, and the tertiary proposal step. For example, the proposal of the arrangement of the components P1 using the learned model M1 may be performed only in any one or two steps of the primary proposal step, the secondary proposal step, and the tertiary proposal step.

In addition, the generation means of the learned model M1 is not limited to reinforcement learning, and may be, for example, "learning with a teacher" or the like.

In addition, the arrangement assistance method according to Embodiment 1 is not limited to a method in which one or more processors execute all the processing, and at least a part of the processing may be intervened by a human. For example, processing such as setting of constraints may be performed by a human using a user interface or the like.

In addition, the means for obtaining the installation time used for generation of the learned model M1 or the like is not limited to the simulation in the simulation unit 26 . For example, instead of the simulation, a classifier or the like generated by deep learning using a multilayer neural network may be used to obtain the installation time.

(Embodiment 2)

The arrangement assisting method according to this embodiment is different from the arrangement assisting method according to Embodiment 1 in the processing section S200 (refer to FIG. 5 ) for relocation. Hereinafter, the same reference numerals are assigned to the same structures as those in Embodiment 1, and descriptions thereof will be omitted as appropriate.

That is, in Embodiment 1, when the component P1 is rearranged in the rearrangement step, after the supply unit 3 (target supply unit) that satisfies the determination condition is determined in the determination step, the Part P1 is set as the object of relocation. Then, if the same supply unit 3 that satisfies the specified condition is relocated as a result of relocating the supply unit 3 (target supply unit) that satisfies the specified condition, the pattern for changing the arrangement of the component P1 is considered to be exhausted, and the relocation is terminated. The processing part S200.

In contrast, in the present embodiment, even if the same supply unit 3 that satisfies the determination condition is relocated as a result of relocating the supply unit 3 satisfying the determination condition with respect to the installation time, the processing section S200 for relocation is continued. That is, in the arrangement assistance method according to the present embodiment, even if the pattern of changing the arrangement of the components P1 for which the supply unit 3 that satisfies the specified condition is set as the target supply unit is exhausted, the other supply units 3 are repeated as the target supply unit. Reconfigure steps. Specifically, after the supply unit 3 that satisfies the specified condition is used as the target supply unit for changing the pattern of the arrangement of the components P1, any one of the plurality of supply units 3 is sequentially selected regardless of whether or not the specified condition is satisfied. Object Supply Department.

As a result, according to the arrangement assisting method according to the present embodiment, all of the plurality of supply units 3 can be relocated as objects, and a more suitable arrangement can be found even as compared with the first embodiment.

As a modification example of the second embodiment, the arrangement assistance method may not have a determination step of determining the supply unit 3 that satisfies the determination condition as the target supply unit. In this case, the arrangement assisting method sequentially selects any supply unit 3 among the plurality of supply units 3 as the target supply unit regardless of whether or not the determination condition is satisfied at the time of rearrangement.

The configuration described in Embodiment 2 (including modifications) can be used in combination with the configuration described in Embodiment 1 (including modifications).

(summary)

As described above, the arrangement assistance method according to the first aspect is a method for assisting the determination of arrangement of the plurality of components (P1) in the plurality of supply units (3) for the component mounting system (100), and includes an acquisition step and a Proposal steps. A 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) to an object (P2). The acquiring step is a step of acquiring mounting data (D1) related to a plurality of components (P1) included in the product (P3). The proposal step is to propose the arrangement of the plurality of parts (P1) for the plurality of supply units (3) based on the installation data (D1) using the learned model (M1) so that the product (P3) in the parts installation system (100) can be shortened ) to generate the required installation time steps. 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 method, in the proposal step, it is not only possible to propose an arrangement that is uniquely determined, but, for example, by using the learned model (M1) to realize the technique of "determination method" in which a skilled person performs such arrangement, it is possible to find a suitable arrangement more easily. configuration. In particular, since 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 ), for example, the performance of the mounting machine ( 10 ) or the According to specifications, etc., the arrangement of multiple parts (P1) is proposed. Therefore, in this arrangement assistance method, it is possible to propose an improved arrangement of the parts (P1).

In the arrangement assistance method according to the second aspect, in addition to the first aspect, the learned model ( M1 ) includes correspondence with characteristics of two or more supply units ( 3 ) among the plurality of supply units ( 3 ). and the generated model.

According to this aspect, for example, even when a plurality of parts ( P1 ) are allocated to two or more supply parts ( 3 ) in the proposal step, it is easy to use the one suitable for the two or more supply parts ( 3 ) to be the distribution destinations. The learned model (M1) proposes a suitable configuration.

In the arrangement assistance method according to the third aspect, in addition to the first or second aspect, when the features of the plurality of supply units (3) are classified into one or more feature groups, the learned model (M1) is Contains models generated in association with one or more feature groups.

According to this aspect, for example, by setting the same feature as one feature group, even in the case of the supply unit (3) having various features, it is easy to use the learned model (M1) suitable for the supply unit (3). to propose a suitable configuration.

In the arrangement assistance method according to the fourth aspect, in addition to any one of the first to third aspects, the learned model ( M1 ) is generated using reinforcement learning.

According to this aspect, the generation of the learned model (M1) in the case where the correct solution is unclear and optimization for a large combination is required is facilitated.

The arrangement assistance method according to the fifth aspect further includes an update step of updating the learned model ( M1 ) in addition to any one of the first to fourth aspects.

According to this aspect, it is possible to generate an appropriate learned model (M1) in accordance with the user's request in the operation stage of the placement assistance method.

In the arrangement assistance method according to the sixth aspect, in addition to any one of the first to fifth aspects, the learned model (M1) includes the information related to the product (P3) generated by the component mounting system (100). information to establish a corresponding model.

According to this aspect, since the learned model (M1) reflecting not only the characteristics of the supply unit (3) but also the matters specific to the product (P3) is used, it is easy to propose an appropriate arrangement.

In the arrangement assistance method according to the seventh aspect, in addition to any one of the first to sixth aspects, the proposal step includes a primary proposal step and a secondary proposal step. The primary proposal step is a step of proposing the arrangement of a plurality of parts (P1) for a plurality of primary groups (G11, G12). The secondary proposal step is a proposal for a plurality of secondary groups ( G21 ) when each of the plurality of primary groups ( G1 1 , G12 ) is classified into a plurality of secondary groups ( G21 to G24 ) after the primary proposal step. ~G24) of the arrangement of the multiple parts (P1). Each of the plurality of secondary groups ( G21 to G24 ) includes at least one supply unit ( 3 ) among the plurality of supply units ( 3 ).

According to this method, the proposal for the arrangement of the plurality of parts (P1) is divided into the primary proposal procedure of arranging the parts (P1) for the plurality of primary groups (G11, G12) and the more detailed plurality of secondary groups (G21 to G12) G24) The secondary proposal step of the configuration part (P1). In a word, since the arrangement of the plurality of parts (P1) is realized not by the processing of stages but by the multi-stage processing set hierarchically, it is possible to derive an appropriate arrangement of the plurality of parts (P1) at each stage. options are less suppressed. As a result, the process for proposing the arrangement of the plurality of components (P1) in each stage can be simplified. Therefore, in this arrangement assistance method, it is possible to propose an improved arrangement of the parts (P1).

In the arrangement assistance method according to the eighth aspect, in addition to the seventh aspect, the learned model ( M1 ) is different in the primary proposal step and the secondary proposal step.

According to this aspect, the arrangement of the plurality of parts ( P1 ) can be proposed using an appropriate learned model ( M1 ) in each of the primary proposal step and the secondary proposal step.

In the arrangement assistance method according to the ninth aspect, in addition to the seventh or eighth aspect, in at least one of the primary proposal step and the secondary proposal step, the learned model (M1) is used to propose a plurality of parts ( P1) configuration.

According to this aspect, it is not possible to propose a uniquely determined arrangement, but to find a suitable arrangement more easily by, for example, using the learned model (M1) to realize the technique of "determination method" of arrangement such as that performed by a skilled person.

In the arrangement assistance method according to the tenth aspect, in addition to any one of the seventh to ninth aspects, there are further three proposal steps. The tertiary proposal step is to propose 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 tertiary groups (G31 to G38) after the secondary proposal step. ) of the configuration steps of the multiple parts (P1). Each of the plurality of tertiary groups ( G31 to G38 ) includes at least one supply unit ( 3 ) among the plurality of supply units ( 3 ).

According to this method, in addition to the primary proposal step and the primary proposal step, the proposal for the arrangement of the plurality of parts ( P1 ) is divided into the tertiary proposal step of arranging the parts ( P1 ) for a plurality of more detailed tertiary groups ( G31 to G38 ) to fulfill. As a result, the process for proposing the arrangement of the plurality of components ( P1 ) in each stage can be further simplified.

In addition to any one of the first to tenth aspects, the arrangement assistance method according to the eleventh aspect further includes a rearrangement step of proposing a plurality of components (P1) for the plurality of supply units (3) after the proposal step. Configuration.

According to this aspect, even when the arrangement of the plurality of parts ( P1 ) proposed in the proposal step is not optimal, it is possible to propose a new arrangement of the plurality of parts ( P1 ) in the relocation step.

In the wiring assistance method according to the twelfth aspect, in addition to the eleventh aspect, in the rearrangement step, at least the time required to generate the product (P3) in the component mounting system (100) is a plurality of times. The longest supply part ( 3 ) among the supply parts ( 3 ) proposes the arrangement of a plurality of parts ( P1 ).

According to this aspect, the component (P1) placed in the supply unit (3) whose time required for the generation of the product (P3) in the component mounting system (100) becomes a bottleneck can be targeted and proposed in the rearrangement step Configuration of new multiple parts (P1).

In the arrangement assisting method according to the thirteenth aspect, in addition to any one of the first to twelfth aspects, when disposing the plurality of components (P1) of the plurality of supply units (3), there is additionally stipulated that specific Constraints on the availability or disposition of specific components (P1) in the supply unit (3).

According to this aspect, it is possible to exclude the specific supply part (3) from the allocation target of the specific component (P1) that cannot be placed in the specific supply part (3) under the restriction conditions, and it is easy to obtain a proposal for placement. simplify.

In the arrangement assisting method according to the 14th aspect, in addition to the thirteenth aspect, the judgment of the availability of the arrangement of the specific component (P1) with respect to the specific supply unit (3) according to the constraint conditions and the use of the learned completion Proposals for the arrangement of the plurality of parts (P1) of the plurality of supply units (3) of the model (M1) are performed separately.

According to this aspect, options for deriving an appropriate arrangement of the plurality of parts ( P1 ) can be suppressed to a small number.

The learning completed model generation method according to the fifteenth aspect is associated with the feature of at least one supply unit ( 3 ) among the plurality of supply units ( 3 ) to generate learning used in the arrangement assistance method of any one of the first to fourteenth aspects. Finished model.

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

The program according to the sixteenth aspect is a program for causing one or more processors to execute the arrangement assistance method according to any one of the first to fourteenth aspects or the generation method of the learned model according to the fifteenth aspect.

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

An arrangement assistance system (20) according to the seventeenth aspect is a system for assisting the determination of arrangement of a plurality of components (P1) in a plurality of supply units (3) for a component mounting system (100), and includes an acquisition unit (21) and Proposal Section (22). A 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) to an object (P2). An acquisition unit (21) acquires mounting data (D1) related to a plurality of components (P1) included in the product (P3). The proposal part (22) proposes the arrangement of the plurality of parts (P1) for the plurality of supply parts (3) based on the installation data (D1) using the learned model (M1) so as to shorten the generation in the parts installation system (100). The installation time required for the generation of the object (P3). The learned model ( M1 ) is a model associated with the characteristics of at least one supply unit ( 3 ) among the plurality of supply units ( 3 ).

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

In the arrangement assistance system (20) according to the eighteenth aspect, in addition to the seventeenth aspect, the proposal unit (22) includes a primary proposal unit (221) and a secondary proposal unit (222). The primary proposal unit (221) proposes the arrangement of the plurality of components (P1) for the plurality of primary groups (G11, G12). The secondary proposal unit ( 222 ) proposes for a plurality of secondary groups ( G21 to G24 ) when each of the plurality of primary groups ( G1 1 , G1 2 ) is classified into a plurality of secondary groups ( G21 to G24 ) ) configuration of multiple parts (P1). Each of the plurality of secondary groups ( G21 to G24 ) includes at least one supply unit ( 3 ) among the plurality of supply units ( 3 ).

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

In the arrangement assistance system (20) according to the nineteenth aspect, in addition to the seventeenth aspect, the proposal unit (22) includes a secondary proposal unit (222). The secondary proposal unit (222) proposes a proposal for a plurality of secondary groups (G21 to G24) when each of the plurality of primary groups (G11, G12) is classified into a plurality of secondary groups (G21 to G24). Configuration of multiple parts (P1). Each of the plurality of secondary groups ( G21 to G24 ) includes at least one supply unit ( 3 ) among the plurality of supply units ( 3 ). The secondary proposal unit (222) receives proposals for the arrangement of a plurality of parts (P1) for a plurality of primary groups (G11, G12), and proposes a plurality of parts (P1) for a plurality of secondary groups (G21 to G24). P1) configuration.

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

The work system (200) according to the twentieth aspect includes the arrangement assistance system (20) and the component mounting system (100) according to any one of the seventeenth to nineteenth aspects. The component mounting system (100) is used under the arrangement of a plurality of components (P1) proposed in the arrangement assistance system (20) to generate a product (P3).

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

The present invention is not limited to the above-mentioned embodiments, and various forms (including modified examples) of the arrangement assistance method according to the first and second embodiments can be implemented by the arrangement assistance system ( 20 ), the operating system ( 200 ), the program, and the recording program. Temporary recording medium materialized.

The configurations according to the second to fourteenth aspects are not necessary for the arrangement assistance method, and can be omitted as appropriate.

The configuration according to the 17th or 18th is not necessary for the arrangement assistance system (20), and can be omitted as appropriate.

Explanation of reference numerals

3 Supply Department

20 Configuring the auxiliary system

21 Acquisition Department

22 Proposal Department

100 Component Mounting System

200 Operating Systems

221 Primary Proposal Department

222 Second Proposal Department

D1 installation data

M1 learned model

G11, G12 primary group

G21～G24 Secondary group

G31～G38 tertiary group

P1 part

P2 Object

P3 product.

Claims (20)

1. An arrangement assistance method for assisting the arrangement of a plurality of components in a plurality of supply units with respect to a component mounting system for generating a product by mounting a plurality of components supplied to a plurality of supply units to an object decision, The configuration assistance method has: an obtaining step of obtaining installation data related to the plurality of components contained in the product; and a proposal step of proposing, based on the mounting data, an arrangement of the plurality of components for the plurality of supply units using a learned model generated in association with a feature of at least one supply unit among the plurality of supply units , so that the installation time required for the generation of the product in the component mounting system is shortened. 2. The configuration assistance method according to claim 1, wherein, The learned model includes a model generated in association with the characteristics of two or more supply units among the plurality of supply units. 3. The configuration assistance method according to claim 1 or 2, wherein, When the features of the plurality of supply units are classified into one or more feature groups, the learned model includes a model generated in association with the one or more feature groups. 4. The configuration assistance method according to any one of claims 1 to 3, wherein, The learned model is generated using reinforcement learning. 5. The configuration assistance method according to any one of claims 1 to 4, wherein, The configuration assistance method also has: The update step is to update the learned model. 6. The configuration assistance method according to any one of claims 1 to 5, wherein, The learned model includes a model generated in association with information on the product generated by the component mounting system. 7. The configuration assistance method according to any one of claims 1 to 6, wherein, The proposed steps include: a proposal step, proposing configurations of the plurality of components for a plurality of primary groups; and In the secondary proposal step, after the primary proposal step, the case where each of the plurality of primary groups is classified into a plurality of secondary groups including at least one supply unit among the plurality of supply units is proposed Configurations of the plurality of components for the plurality of secondary groups below. 8. The configuration assistance method of claim 7, wherein, In the primary proposal step and the secondary proposal step, the learned models are different. 9. The configuration assistance method according to claim 7 or 8, wherein, In at least one of the primary proposal step and the secondary proposal step, the learned model is used to propose the arrangement of the plurality of components. 10. The configuration assistance method according to any one of claims 7 to 9, wherein, The configuration assistance method also has: The tertiary proposal step, after the secondary proposal step, proposes a case where each of the plurality of secondary groups is classified into a plurality of tertiary groups including at least one supply unit among the plurality of supply units Configurations of the plurality of components for the plurality of tertiary groups below. 11. The configuration assistance method according to any one of claims 1 to 10, wherein, The configuration assistance method also has: In the rearrangement step, after the proposal step, the arrangement of the plurality of components with respect to the plurality of supply units is proposed. 12. The configuration assistance method of claim 11, wherein, In the rearrangement step, the arrangement of the plurality of components is proposed at least for the supply unit whose time required for the generation of the product in the component mounting system is the longest among the plurality of supply units. 13. The configuration assistance method according to any one of claims 1 to 12, wherein, In the arrangement of the plurality of components with respect to the plurality of supply units, constraints that define whether or not the arrangement of a specific component with respect to a specific supply unit is possible are attached. 14. The configuration assistance method of claim 13, wherein, Judgment of the availability of the arrangement of the specific components for the specific supply unit based on the constraint conditions and the arrangement of the components for the plurality of supply units using the learned model Proposals are made separately. 15. A method for generating a learned model, wherein learning used in the arrangement assistance method according to any one of claims 1 to 14 is generated in association with a feature of at least one supply unit among the plurality of supply units Finished model. 16 . A program for causing one or more processors to execute the arrangement assistance method according to any one of claims 1 to 14 or the method for generating a learned model according to claim 15 . 17 . 17. An arrangement assistance system for assisting the arrangement of a plurality of components in a plurality of supply units for a component mounting system for generating a product by mounting a plurality of components supplied to a plurality of supply units to an object decision, The configuration assistance system includes: an acquisition unit that acquires installation data related to the plurality of components included in the product; and a proposal unit that proposes, based on the mounting data, an arrangement of the plurality of components for the plurality of supply units by using a learned model associated with a feature of at least one supply unit among the plurality of supply units, As a result, the installation time required for the generation of the product in the component mounting system is shortened. 18. The configuration assistance system of claim 17, wherein: The proposal section includes: a primary proposal section that proposes configurations of the plurality of components for a plurality of primary groups; and A secondary proposal unit that proposes, when each of the plurality of primary groups is classified into a plurality of secondary groups including at least one supply unit among the plurality of supply units, for the plurality of secondary groups a configuration of the plurality of components of the group. 19. The configuration assistance system of claim 17, wherein: The proposal section includes: a secondary proposal unit that accepts proposals for the arrangement of the plurality of components in the plurality of primary groups, and proposes to classify the plurality of primary groups into each of the plurality of supply units including at least one supply unit among the plurality of supply units The configuration of the plurality of components for the plurality of secondary groups in the case of a plurality of secondary groups of . 20. An operating system, comprising: The configuration assistance system of any one of claims 17-19; and The component mounting system is used for the arrangement of the plurality of components proposed in the arrangement assistance system, and generates the product.

Images