JP2018077822A - Production support system and production support method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To appropriately produce a product produced by a plurality of processes. SOLUTION: A process knowledge information storage unit 112 storing process knowledge information which is a relationship between a product and an execution time of each process performed for the production of the product, and information on a product to be produced. Based on the order information acquisition unit 141 to be acquired, the product information, and the process knowledge information, the execution process information generation unit 205 that generates the execution process information regarding the execution time of each process to be performed for the production of the product, and each process A constraint condition acquisition unit 302 that acquires constraint condition information, which is information on the conditions of the product, and an executable process that generates executable process information related to the execution timing of each process in the manufacture of a product that satisfies the constraint condition based on the constraint condition information An information generation unit 303, a learning unit 203 that updates process knowledge information based on the feasible execution process information, and an output unit 1 that outputs the feasible process information as product production process information. 32. [Selection] Figure 1

Description

  The present invention relates to a production support system, a production support method, and a production support program.

  Patent Document 1 discloses a planning method for reducing in-process inventory as a technique related to production planning in the manufacturing industry. That is, Patent Document 1 states that “the conventional production plan creation method and the apparatus thereof do not take into account the information on the alignment in the subsequent process, so that the in-process inventory is generated at the end of the process. Therefore, there is described a planning method that makes it possible to supply a plurality of substrates required by a unit in a post-process at the same time immediately before production in the post-process with a minimum in-process inventory.

  Patent Document 2 describes a method for creating a production plan using an operator's rule-of-thumb database. That is, Patent Document 2 states that “a production lot that is an allocation candidate is evaluated based on an empirical rule database that is constructed based on past allocation candidate selection results for each evaluation item of the production condition information of the production lot. An evaluation value and a production lot that is a candidate for allocation were obtained from a second evaluation value that is a prediction result of a production result obtained by executing a production plan simulation in each production line in order from the highest first evaluation value. , Based on the third evaluation value, which is the evaluation result of the allocation candidate production lot and the allocation candidate production line, ranks and outputs the allocation candidate production lots, and among the allocation candidates output with the ranking Assigning a specific production lot to the production line, learning based on the specific production lot, and updating the heuristic database Planning method "is disclosed.

JP 2004-145436 A JP 2012-194712 A

  However, in many manufacturing industries, an empirical element such as considering the restart cost of a machine (equipment) is also necessary when making a production plan. In other words, it takes considerable cost and time to start the machine used in each process, but since these elements are known by the operator's experience the optimal starting conditions (starting frequency and starting time). It is. However, since it is difficult to describe such elements with clear rules, the method of Patent Document 1 cannot consider these elements.

  On the other hand, in Patent Document 2, a plan is created using an operator's rule-of-thumb database. However, when there are a plurality of production processes, each process has a constraint condition. Everything must be satisfied. However, since the planning method of Patent Document 2 does not consider the constraint conditions, it cannot be applied to a production plan composed of a plurality of processes.

  The present invention has been made based on such a background, and is to provide a production support system, a production support method, and a production support program for appropriately producing a product produced by a plurality of processes. .

  One aspect of the present invention for solving the above problems is a production support system that supports the production of a product that includes a processor and a memory and that is produced by performing a plurality of processes. A process knowledge information storage unit that stores process knowledge information that is a relationship between the execution times of each process performed for the purpose, an order information acquisition unit that acquires information on products to be produced, and the acquired Based on the product information and the process knowledge information, an execution process information generation unit that generates execution process information that is information related to the execution timing of each process to be performed for the production of the acquired product, and setting for each of the processes For the manufacture of the acquired product that satisfies the set condition based on the acquired constraint condition information and the constraint condition acquisition unit that acquires the constraint condition information that is the information of the condition that has been set An executable process information generation unit that generates executable process information that is information regarding the execution timing of each process, a learning unit that updates the process knowledge information based on the generated executable execution process information, and the generated And an output unit that outputs executable process information as information on the acquired production process of the product.

  Problems, configurations, and effects other than those described above will be clarified by the following description of embodiments.

  ADVANTAGE OF THE INVENTION According to this invention, the production of the product produced by a some process can be performed appropriately.

FIG. 1 is a diagram illustrating an example of a configuration of a production support system according to the present embodiment. FIG. 2 is a diagram for explaining an example of the hardware configuration of each information processing apparatus constituting the production support system 1. FIG. 3 is a diagram for explaining an example of functions provided in the final / first process ideal plan creation apparatus 104. FIG. 4 is a diagram illustrating an example of functions provided in the ideal plan planning apparatus 105. FIG. 5 is a diagram for explaining an example of functions provided in the plan candidate planning apparatus 106. FIG. 6 is a diagram for explaining an example of functions provided in the plan candidate selection apparatus 110. FIG. 7 is a diagram for explaining an example of functions provided in the worker terminal 109. FIG. 8 is a diagram illustrating an example of the order information DB 101. FIG. 9 is a diagram illustrating an example of the constraint condition DB 102. FIG. 10 is a diagram illustrating an example of the ideal plan DB 107. FIG. 11 is a diagram illustrating an example of the plan candidate DB 108. FIG. 12 is a diagram illustrating an example of the execution plan DB 111. FIG. 13 is a flowchart for explaining the production support process. FIG. 14 is a diagram illustrating an example of an ideal plan generation support screen. FIG. 15 is a diagram illustrating an example of an execution plan generation support screen. FIG. 16 is a flowchart illustrating details of the calculation start process information generation process. FIG. 17 is a flowchart for explaining the details of the ideal plan creation process. FIG. 18 is a flowchart for explaining the details of the plan candidate creation process. FIG. 19 is a flowchart for explaining the details of the learning process.

Embodiments for carrying out the present invention will be described below with reference to the drawings.
(System configuration)
First, the system configuration will be described.

  FIG. 1 is a diagram illustrating an example of a configuration of a production support system according to the present embodiment. As shown in the figure, the production support system 1 is an information processing system that supports production of products produced by performing a plurality of processes, and includes an operator terminal 109 and an automatic planning system 103. It is configured. In the following, the process performed first in the production of the product (the most upstream process) is referred to as the first process, and the process performed last in the production of the product (the most downstream process) is referred to as the final process.

  The automatic planning system 103 includes information processing devices (computers) such as a final / first process ideal plan creation device 104, an ideal plan planning device 105, a plan candidate planning device 106, and a plan candidate selection device 110. The automatic planning system 103 includes each database of a process knowledge DB 112, an ideal plan DB 107, a plan candidate DB 108, and an execution plan DB 111 (DB: database; the same applies hereinafter).

  The final / first process ideal plan creation device 104 and the ideal plan creation device 105 provide information on the execution timing of each process to be performed for product production (for example, the order in which the order lot is introduced into the equipment of each process, etc. Information (hereinafter, such information is referred to as an ideal plan).

  For example, when an order for production of a plurality of products (lots) is received, the ideal plan stipulates which lots are to be introduced and operated in each equipment used for each process. The product production plan.

  Specifically, the final / first process ideal plan creation device 104 identifies the process (hereinafter referred to as the final / first process or the calculation start process) for which the execution time is calculated first, and the identified final / first process and , Based on information about product orders (hereinafter referred to as order information; details will be described later) obtained from the operator terminal 109, information on the execution timing of the final / first process (hereinafter referred to as the final / first process ideal plan, Alternatively, it is referred to as calculation start process information (details are described later). Then, the ideal plan planning apparatus 105 generates an ideal plan based on the final / first process ideal plan generated by the final / first process ideal plan creation apparatus 104.

  The plan candidate planning device 106 generates a plurality of pieces of information (hereinafter referred to as plan candidates; details will be described later) regarding the execution timing of each process that satisfies the specified condition (condition specified by constraint condition information described later). .

  For example, in the above example, the candidate for the plan is operated by introducing which lot into each equipment in which order (time zone) after satisfying the operational and technical constraints of each equipment used in each process. It is a practical production plan for products that defines whether or not

  The plan candidate selection device 110 identifies a predetermined number (for example, one) of plan candidates among the plurality of generated plan candidates. In the following, the identified plan candidate is referred to as an execution plan.

  The process knowledge DB 112 (hereinafter also referred to as a process knowledge information storage unit) is a knowledge database for creating an ideal plan. Specifically, the execution time of each process executed for production of the product and the product. Process knowledge information, which is a relationship between As will be described later, the process knowledge information is updated by machine learning or the like.

  The order information DB 101 stores order information necessary for calculating the ideal plan. The order information includes, for example, an order for a product to be produced and a past order history of the product. The order information includes, for example, information such as the type, quantity, and delivery date of the product requested by the customer.

  The constraint condition DB 102 stores constraint condition information that is information on conditions set for each of the steps. The constraint condition information includes, for example, information such as a manufacturing capability of a product in each process, a specification of a product to be produced, a difference between a specification of the product in each process and a specification in a process before and after the process. Further, the constraint condition information includes, for example, information related to the delivery date of the product or the quantity of the product.

  The ideal plan DB 107 stores an ideal plan for each process. The plan candidate DB 108 stores plan candidates for each process. The execution plan DB 111 stores an execution plan.

  In the present embodiment, each DB is configured by an information processing device such as a general PC (PC: Personal Computer) or general database software. These provide a search function and an update function.

(Hardware configuration)
Next, the hardware configuration of each information processing apparatus constituting the production support system 1 will be described.

  FIG. 2 is a diagram for explaining an example of the hardware configuration of each information processing apparatus constituting the production support system 1. As shown in the figure, each information processing apparatus includes a CPU 401, a memory 402, an interface 403, a network interface 404, a keyboard 405, an output device 406, a mouse 407, and a storage device 408.

  The CPU 401 is, for example, a central processing unit, and is a processor that can execute a program recorded in the memory 402 or transferred from the storage device 408 to the memory 402 in advance. The program may be introduced by a removable storage medium as necessary. In this case, a device for reading the storage medium is connected to the interface 403. As an apparatus for reading such a storage medium, for example, an optical disk (CD, DVD, Blu-ray disk, etc.) or a flash memory can be used. Further, the program may be introduced into each information processing apparatus by the network interface 404 via a communication medium (for example, a communication line or a carrier wave on the communication line) as necessary.

  The memory 402 temporarily records programs and data. The interface 403 is a device for connecting a storage medium or the like. The network interface 404 is a device for communicating with other information processing devices.

  The keyboard 405 receives input of information. The output device 406 is a monitor or the like and outputs various types of information. The mouse 407 changes the position of the pointer output to the output device 406, and receives an input to a button provided on the mouse 407, thereby specifying the position on the screen and instructing the CPU 401 to perform a predetermined process. Tell. The mouse 407 can be replaced by a touch panel, for example. In this case, the function related to the pointer may be omitted.

  The storage device 408 stores a program or data. The storage device 408 is configured by, for example, a magnetic disk, a nonvolatile memory (for example, a hard disk, SSD ()), or the like. In this case, the program or data stored in the storage device 408 is retained even when, for example, the storage device 408 is turned on after the power is turned off. Note that an operating system (OS) may be installed in the storage device 408 in advance. By doing so, it becomes possible to specify a program using a file name. Here, the OS refers to basic software of the computer, and a generally well-known OS can be used. In this embodiment, it is assumed that an OS is installed.

(function)
Next, functions provided in each information processing apparatus will be described.

  FIG. 3 is a diagram for explaining an example of functions provided in the final / first process ideal plan creation apparatus 104. As shown in the figure, the final / first process ideal plan creation device 104 includes an order information acquisition unit 141 and a final / first process ideal plan creation unit 142. The order information acquisition unit 141 acquires information on products to be produced (order information). The final / first process ideal plan creation unit 142 generates a final / first process ideal plan (calculation start process information).

  FIG. 4 is a diagram illustrating an example of functions provided in the ideal plan planning apparatus 105. As shown in the figure, the ideal plan planning apparatus 105 includes an ideal plan generation unit 205, a learning method selection unit 201, a learning input processing unit 202, a learning unit 203, and a learning output processing unit 204.

  The ideal plan generation unit 205 (hereinafter also referred to as an implementation process information generation unit) is configured to store the product information acquired by the order information acquisition unit 141 based on the product information acquired by the order information acquisition unit 141 and the process knowledge information. Implementation process information (ideal plan), which is information relating to the implementation timing of each process implemented for production, is generated.

  Specifically, for example, the execution process information generation unit generates the information specifying the execution time of the process before the predetermined process based on the information related to the predetermined process, thereby obtaining the execution process information. Generate. Hereinafter, a method for generating information regarding such a process is referred to as a forward method.

  In addition, for example, the execution process information generation unit generates information for specifying an execution time of a process performed after the predetermined process based on information on the predetermined process. Hereinafter, a method for generating information regarding such a process is referred to as a backward method.

  Furthermore, the implementation process information calculation unit acquires an index for generating the implementation process information, and generates the implementation process information according to the acquired index. The index is, for example, information on the quantity of the product or the production completion time (for example, delivery date) of the product.

  The learning unit 203 updates (learns) the process knowledge information based on the executable process information generated by the executable process information generation unit described later. The learning unit 203 includes a learning model constructed using a machine learning technique such as a neural network.

  The learning unit 203 is a learning device that outputs information related to a production process of a product similar to a conventionally performed pattern when input of information related to the product and its implementation process is received. In the present embodiment, the learning unit 203 includes two types of learning devices. The first learning device (hereinafter referred to as a reverse learning device) is a backward learning device having a post-process as an input and a pre-process as an output. On the other hand, the second learning device (hereinafter, referred to as a forward learning device) is a learning device of the forward method in which the previous process is an input and the subsequent process is an output.

  Specifically, the learning unit updates the process knowledge information by generating information for specifying an execution time of a process before the predetermined process based on information on the predetermined process, or The process knowledge information is updated by generating information for specifying an execution time of a process performed after the predetermined process based on information on the predetermined process.

  The learning method selection unit 201 accepts selection of a forward learning device or a backward learning device. That is, the learning method selection unit 201 is a processing unit that selects whether to learn a product production process retroactively from the final process or to learn a product production process from the first process to the subsequent process.

  The learning input processing unit 202 inputs information to the learning unit 203. The learning output processing unit 204 outputs the information learned (updated) by the learning unit 203.

  FIG. 5 is a diagram for explaining an example of functions provided in the plan candidate planning apparatus 106. As shown in the figure, the plan candidate planning apparatus 106 includes a search input processing unit 301, a constraint condition input processing unit 302, a search unit 303, and a plan candidate output unit 304.

  The search input processing unit 301 is a processing unit that reads an execution plan from the execution plan DB 111.

  A constraint condition input processing unit 302 (hereinafter also referred to as a constraint condition acquisition unit) acquires constraint condition information, which is information on conditions set for each of the steps, from the constraint condition DB 102. For example, the constraint condition acquisition unit acquires information including information on a use condition of equipment used in the process as the constraint condition information.

  The search unit 303 (hereinafter also referred to as an executable process information generation unit) is a product of the product acquired by the order information acquisition unit 141 that satisfies the set condition based on the constraint condition information acquired by the constraint condition acquisition unit. The feasible process information (plan candidate), which is information related to the execution time of each process in manufacturing, is generated. That is, the search unit 303 is a processing unit that plans candidates based on the constraint conditions of each process. The search unit 303 is configured to include a planning model constructed using a mathematical programming technique such as constraint programming. The plan model can search for a plurality of plan candidates that satisfy the constraint conditions.

  For example, the feasible process information generation unit generates a plurality of feasible process information that satisfies a usage condition of the facility as the feasible process information.

  Further, the executable process information generation unit generates a plurality of the executable process information, calculates similarity between each of the generated executable process information and the generated execution process information, and calculates Based on the similarity, the feasible process information most similar to the implementation process information is specified.

  The plan candidate output unit 304 outputs the executable process information (plan candidate) generated by the search unit 303 to the plan candidate DB 108.

  FIG. 6 is a diagram for explaining an example of functions provided in the plan candidate selection apparatus 110. As shown in the figure, the plan candidate selection device 110 includes a plan candidate selection unit 111. The plan candidate selection unit 111 identifies a predetermined number (for example, one) of plan candidates among the plurality of plan candidates created by the search unit 303.

  FIG. 7 is a diagram for explaining an example of functions provided in the worker terminal 109. The operator terminal 109 is an information processing apparatus (computer) operated by a user (for example, an administrator of the production support system 1 or a person involved in product production, the same applies hereinafter). As shown in the figure, the worker terminal 109 includes a user input unit 131 and a result output unit 132. The user input unit 131 receives input of various information such as order information.

  The result output unit 132 (hereinafter also referred to as an output unit) outputs the executable process information generated by the executable process information generation unit as information on the production process of the product acquired by the order information acquisition unit 141. Specifically, the output unit outputs the executable process information specified by the executable process information generation unit as information on the production process of the product acquired by the order information acquisition unit 141.

(Database)
Next, a database provided in the production support system 1 will be described.

  FIG. 8 is a diagram illustrating an example of the order information DB 101. As shown in the figure, the order information DB 101 includes at least one record including items of an order number 501, a delivery date 502, a quantity 503, and a product type 504. The order number 501 stores information for identifying an order from a customer or the like (hereinafter referred to as an order number). The delivery date 502 stores a time when the product is delivered (for example, delivery deadline; hereinafter referred to as delivery date) for the order with the order number 501. For example, the delivery date 502 stores the number of days until shipment. The quantity 503 stores the number of products designated by the order with the order number 501 (hereinafter referred to as order quantity). The product type 504 stores information (hereinafter referred to as product type) for specifying the type of product designated by the order with the order number 501. The order information DB 101 may include other items necessary for product production in addition to the above items.

  FIG. 9 is a diagram illustrating an example of the constraint condition DB 102. As shown in the drawing, the constraint condition DB 102 has at least one record including items of a process number 601, a decision variable 602, and a constraint condition 603. The process number 601 stores a number for identifying each process (hereinafter referred to as a process number). The decision variable 602 stores information (hereinafter referred to as a decision variable) of elements that determine the conditions or constraints imposed on the process of the process number 601, for example, product delivery date, product order quantity, or Information indicating the product type is stored. The constraint condition 603 stores a condition based on the element of the decision variable 602 or the content of the constraint (hereinafter referred to as a constraint condition). For example, a condition related to the deadline of each process or a condition related to equipment used in each process (machine or the like) Information on the start-up cost and start-up time of the equipment. Note that the decision variable 602 and the constraint condition 603 may include information on the weather that affects the production of the product.

  FIG. 10 is a diagram illustrating an example of the ideal plan DB 107. As shown in the figure, the ideal plan DB 107 has at least one or more records including items of a process number 702, a manufacturing order 701, an order number 703, a delivery date 704, a quantity 705, and a product type 706. Among these, the process number 702, the order number 703, the delivery date 704, the quantity 705, and the product type 706 are the process number 601 in the constraint condition DB 102, the order number 501 in the order information DB 101, the delivery date 502 in the order information DB 101, and the order information DB 101, respectively. This corresponds to the quantity 503 and the type 504 of the order information DB 101. The manufacturing order 701 stores information (hereinafter referred to as a manufacturing order number) that specifies the order of manufacturing the products performed in the process of the process number 702 (the manufacturing order of each product with respect to the order). The manufacturing order number is a value indicating the priority of manufacturing.

  FIG. 11 is a diagram illustrating an example of the plan candidate DB 108. As shown in the figure, the plan candidate DB 108 includes at least one record including items of process number 802, plan candidate number 801, manufacturing order 803, order number 804, delivery date 805, quantity 806, and product type 807. Have Among these, the process number 802, the production order 803, the order number 804, the delivery date 805, the quantity 806, and the product type 807 are the process number 601 in the constraint DB 102, the production order 701 in the ideal plan DB 107, and the order number 703 in the ideal plan DB 107, respectively. This corresponds to the delivery date 704 of the ideal plan DB 107, the quantity 705 of the ideal plan DB 107, and the product type 706 of the ideal plan DB 107.

  The plan candidate number 801 stores information for identifying a plan candidate (hereinafter referred to as a plan candidate number).

  FIG. 12 is a diagram illustrating an example of the execution plan DB 111. The execution plan DB 111 includes at least one item including items of process number 903, adopted plan candidate number 901, distance to ideal plan 902, manufacturing order 904, order number 905, delivery date 906, quantity 907, and product type 908. It has the above records. Among these, the process number 903, the production order 904, the order number 905, the delivery date 906, the quantity 907, and the product type 908 are the process number 601 in the ideal plan DB 107, the production order 701 in the ideal plan DB 107, and the order number 501 in the order information DB 101, respectively. This corresponds to the delivery date 502 of the order information DB 101, the quantity 503 of the order information DB 101, and the product type 504 of the order information DB 101.

  The adopted plan candidate number 901 stores information for identifying the adopted plan candidate (that is, the execution plan) (hereinafter referred to as the adopted plan candidate number). Information indicating the similarity between the adopted plan candidate and the ideal plan is stored in the distance 902 from the ideal plan. In the present embodiment, information indicating the distance between the two is stored. A method for calculating this distance will be described later.

  The functions of each information processing apparatus described above are executed by the hardware of each information processing apparatus or by the CPU 401 (processor) of each information processing apparatus reading out a program stored in the memory 402 or the storage device 408. It is realized by doing.

(processing)
Next, processing performed in the production support system 1 will be described.

  FIG. 13 is a flowchart for explaining a process (hereinafter referred to as a production support process) for generating an execution plan for a process performed for production of a product and learning the plan. The production support process is started, for example, when a predetermined input is made to the worker terminal 109.

  As shown in the figure, first, the final / first process ideal plan creation apparatus 104 acquires order information input from the worker terminal 109 by communicating with the order information DB 101 (S1201). For example, the final / first process ideal plan creation apparatus 104 acquires order information of an order placed in a predetermined period (for example, an order for one week having a close delivery date).

  Then, the worker terminal 109 acquires the order information acquired in S1201 from the final / first process ideal plan creation apparatus 104, and outputs the acquired order information (S1202). This allows the user to confirm the contents of the order information.

  Note that the above communication is performed by general communication, RPC (Remote Procedure Call), or the like. In the following, it is assumed that communication between each information processing apparatus and each DB is performed by such a method.

  Next, the final / first process ideal plan creation apparatus 104 generates a final / first process ideal plan based on the order information acquired in S1201 (S1203). Details of this process (hereinafter referred to as “calculation start process information generation process”) will be described later.

  Then, the ideal plan planning apparatus 105 generates an ideal plan for each process based on the final / first process ideal plan calculated in S1203 (S1204). Details of this processing (hereinafter referred to as ideal plan creation processing) will be described later (FIG. 14). Further, the ideal plan planning apparatus 105 registers the ideal plan generated in S1204 in the ideal plan DB 107 (S1205).

  Further, the plan candidate planning apparatus 106 acquires constraint condition information from the constraint condition DB 102 (S1206). Then, the plan candidate planning apparatus 106 generates at least one or more plan candidates based on the constraint condition information acquired in S1206 (S1207). Details of this processing (hereinafter referred to as plan candidate planning processing) will be described later.

に基づいて行われる。ここで、ＫＮ_i、及びＬＮ_iはそれぞれ、計画候補及び理想計画における製造順序ｉの注文の納期であり、ＫＳ_i、及びＬＳ_iはそれぞれ、計画候補及び理想計画における製造順序ｉの注文の数量であり、ＫＨ_i、及びＬＨ_iはそれぞれ、計画候補及び理想計画における製造順序ｉの注文の品種である。また、ＫＨ_iとＬＨ_iが同じ品種の場合はＫＨ_iとＬＨ_iとの差が０であり、ＫＨ_iとＬＨ_iが異なる品種の場合はＫＨ_iとＬＨ_iとの差が１であるとする。また、計画候補と理想計画との距離Ｄは、計画候補や理想計画における製造順序ｉの注文の距離Ｄ_iの総和である。なお、計画候補と理想計画との距離の算出に際しては、上記の各パラメータの代わりに、各パラメータに対して所定の重み付けの値を乗算した値（重み付けされた各パラメータ）を用いてもよい。 Next, the plan candidate selection apparatus 110 calculates the similarity between each of the plan candidates created in S1207 and the ideal plan (S1208). In the present embodiment, the distance is calculated for calculating the similarity. The calculation of this distance is, for example,

Based on. Here, KN _i and LN _i are the delivery times of orders of the production order i in the plan candidate and the ideal plan, respectively, and KS _i and LS _i are the quantities of the orders of the production order i in the plan candidate and the ideal plan, respectively. KH _i and LH _i are varieties of orders of the production order i in the plan candidate and the ideal plan, respectively. Also, if KH _i and LH _i are the same breed is 0 the difference between KH _i and LH _i, when the case of KH _i and LH _i are different varieties difference between KH _i and LH _i is 1 To do. The distance D between the plan candidate and the ideal plan is the sum of the distances D _i of the orders of the production order i in the plan candidate and the ideal plan. In calculating the distance between the plan candidate and the ideal plan, a value obtained by multiplying each parameter by a predetermined weight value (each weighted parameter) may be used instead of each parameter described above.

  The worker terminal 109 accepts, from the user, selection of a plan candidate to be adopted among the plan candidates created in S1207 (S1209). Instead of the user selecting a plan candidate, the plan candidate selecting device 110 or the like automatically selects the plan candidate having the shortest distance from the ideal plan (the plan candidate having the highest similarity to the ideal plan). May be.

  The plan candidate selection apparatus 110 registers the plan candidate selected in S1209 in the execution plan DB 111 as an execution plan (S1210). In addition, the plan candidate selection apparatus 110 outputs information related to the execution plan selected in S1209 (S1211).

Subsequently, the ideal plan planning apparatus 105 learns an execution plan for each process based on the execution plan selected in S1209 (S1212). Details of this processing (hereinafter referred to as learning processing) will be described later. Thus, the production support process ends (S1213).
Here, an example of a screen displayed in the production support process will be described.

  FIG. 14 is a diagram illustrating an example of a screen (hereinafter referred to as an ideal plan generation support screen) displayed when calculating an ideal plan among screens output to the worker terminal 109. The ideal plan generation support screen is displayed, for example, when the production support process is started.

  As shown in the figure, the ideal plan generation support screen 1000 includes an operator number input box 1001, an order information display box 1002, a final / first process ideal plan selection box 1003, a final / first process ideal plan selection button 1004, an ideal plan. Each column includes a creation index selection box 1005, an ideal plan creation index selection button 1006, a final / first process ideal plan creation button 1007, a final / first process ideal plan display box 1008, and a save button 1009.

  The worker number input box 1001 receives an input of a personal number such as an employee number from the user. In the order information display box 1002, the order information acquired in S1201 is output.

  The final / first process ideal plan selection box 1003 and the final / first process ideal plan selection button 1004 accept input of whether the final process or the first process is selected as the calculation start process. An ideal plan creation index selection box 1005 and an ideal plan creation index selection button 1006 accept selection of an index when generating an ideal plan. For example, it is an index of whether an ideal plan is created so that the delivery date of a product is accelerated or an ideal plan is created so that the quantity of products to be produced is increased.

  The final / first process ideal plan creation button 1007 receives the start of creation of an ideal plan based on the selected calculation start process. The final / first process ideal plan display box 1008 outputs the contents of the created ideal plan. A save button 1009 accepts saving of the created ideal plan.

  FIG. 15 is a diagram illustrating an example of a screen (hereinafter referred to as an execution plan generation support screen) displayed when creating an execution plan among the screens displayed on the worker terminal 109. The execution plan generation support screen is displayed, for example, when creation of an ideal plan is started.

  As shown in the figure, the execution plan generation support screen 1100 includes a plan status display box 1101, an ideal plan display box 1102, a plan candidate display box 1103, a plan candidate selection box 1104, a plan candidate selection button 1105, and an execution plan display box 1106. , And each column of a save button 1107.

  In the plan status display box 1101, information indicating a process for which an ideal plan has been created, a process for which an ideal plan is currently being created, and a process for which an ideal plan has not yet been created is output. In the ideal plan display box 1102, information on a process that is currently creating an ideal plan is output. In the plan candidate display box 1103, information on the plan candidates of the process currently being created is output. A plan candidate selection box 1104 and a plan candidate selection button 1105 display plan candidates and accept the selection of plan candidates. In the execution plan display box 1106, information on the plan candidate selected by the plan candidate selection box 1104 (that is, the execution plan) is output. A save button 1107 accepts saving of information on the execution plan selected by the execution plan display box 1106. When saving is accepted, the execution plan is stored in the execution plan DB 111.

Next, details of each process in the production support process will be described.
<Calculation start process information generation process S1203>

  FIG. 16 is a flowchart illustrating details of the calculation start process information generation process. As shown in the figure, first, the worker terminal 109 selects a reference (whether the first process is the calculation start process or the final process is the calculation start process) when calculating the calculation start process information. Is received by the final / first process ideal plan selection box 1003, and the final / first process ideal plan creation apparatus 104 acquires the contents of the received selection.

  Further, the final / first process ideal plan creation apparatus 104 determines an index for creating an ideal plan (S1302). Specifically, the operator terminal 109 receives a selection from the user for the ideal plan creation index selection box 1005, and the final / first process ideal plan creation device 104 acquires the contents of the accepted selection. In the present embodiment, the index is an index for creating an ideal plan with an early delivery date or an index for creating an ideal plan with a large production volume. It may be used.

  The final / first process ideal plan creation apparatus 104 generates calculation start process information based on the calculation start process acquired in S1301 and the index acquired in S1302 (S1303). Specifically, for example, when the index is a delivery date and the calculation start process is the final process, the final / first process ideal plan creation device 104 is based on an information processing program having a general calculation function and a sort function. At least one or more calculation start process information is generated so that the delivery date of is faster. Further, when the index is the production amount and the calculation start process is the first process, the final / first process ideal plan creation device 104 is based on an information processing program having a general calculation function and sort function, So that at least one calculation start process information is generated.

  Then, the final / first process ideal plan creation apparatus 104 outputs the calculation start process information generated in S1304 (S1304). Thus, the calculation start process information generation process ends (S1305).

<Ideal plan creation process S1204>
Next, the ideal plan creation process will be described in detail.

  FIG. 17 is a flowchart for explaining the details of the ideal plan creation process. As shown in the figure, the ideal planning apparatus 105 selects a learning device by the learning method selection unit 201 (S1401). That is, the ideal plan making apparatus 105 selects a learning device in the reverse direction when the final process is selected as the calculation start process by the calculation start process information generation process. Also, the ideal plan planning apparatus 105 selects a forward learning device when the first process is selected as the calculation start process by the calculation start process information generation process.

  The ideal plan planning apparatus 105 inputs an ideal plan (S1402). For example, when the final process is selected as the calculation start process by the calculation start process information generation process, the ideal plan planning apparatus 105 inputs the final process ideal plan. Also, the ideal plan planning apparatus 105 inputs the initial process ideal plan when the first process is selected as the calculation start process by the calculation start process information generation process.

  The ideal plan planning apparatus 105 creates an ideal plan for the next process based on the ideal plan input in S1402 (S1403). For example, when the final process is selected as the calculation start process by the calculation start process information generation process, the ideal plan planning apparatus 105 creates an ideal plan for the process before the final process. In addition, when the first process is selected as the calculation start process by the calculation start process information generation process, the ideal plan planning apparatus 105 creates an ideal plan after the final process.

  Then, the ideal plan planning device 105 outputs the ideal plan created in S1403 (S1404). The processes of S1402 and S1403 are repeated until an ideal plan is created for all processes.

  For creating the ideal plan, for example, a neural network learner and an error back propagation method are used. For details on neural network learners and error backpropagation, see, for example, `` Car-following behavior with instantaneous driver-vehicle reaction delay: A neural-network-based methodology, Transportation Research Part C 36 (2013) 339-351, Zheng et al Can be used.

  The input made to the learning input processing unit 202 is, for example, information on the delivery date, quantity, and type of each product, and the information output by the learning output processing unit 203 is, for example, the production order of each product (in the equipment of each process) The order in which the order lot is introduced). For the manufacturing order which is a discrete value, the probability that each production order is selected is calculated, and the order is determined in descending order of the calculated probability. The number of layers of the neural network learner is, for example, 3 layers, and the number of neurons in each layer is, for example, 3 in the first layer, 10 in the second layer, and 1 in the third layer. For example, a sigmoid function is used as an activation function between layers.

  In addition, generally available machine learning software can also be used for these calculations. In the above description, specific numerical values, item names, and function names are given as input / output information. However, other numerical values, item names, function names, and the like may be used.

  The ideal plan planning apparatus 105 outputs the ideal plan related to each process generated in S1402 and S1403 to the ideal plan DB 107 (S1404). Thus, the ideal plan creation process ends (S1405).

<Plan candidate creation process S1207>
Next, the plan candidate creation process will be described in detail.

  FIG. 18 is a flowchart for explaining the details of the plan candidate creation process. As shown in the figure, the plan candidate planning apparatus 106 reads an execution plan for each process from the execution plan DB 111 by using the search input processing unit 301 (S1501).

  Specifically, when an ideal plan is created by a backward learning device in the ideal plan creation process, the plan candidate planning device 106 uses the search input processing unit 301 to execute an execution plan for each process in the reverse direction from the first process. get. On the other hand, when an ideal plan is created by a forward learning device in the ideal plan creation process, the plan candidate planning apparatus 106 acquires an execution plan for each process in the reverse direction from the final process by the search input processing unit 301.

  Further, the plan candidate planning apparatus 106 reads the constraint condition information of each process from the constraint condition DB 102 by the constraint condition input processing unit 302 (S1502).

  The plan candidate planning apparatus 106 creates (searches) a plan candidate for each process by the search unit 303 (S1503).

  This search method is performed based on, for example, constraint programming. In this case, the information input by the constraint condition input processing unit 302 includes, for example, the delivery date, quantity, or product type of the product order, the product production order, and the constraint conditions in each process. The output information is, for example, the manufacturing order of products in each process that satisfies the constraint conditions in each process. As the search algorithm, for example, a search method called backtracking is adopted. Note that backtracking is one of general solution search algorithms. When a solution is obtained, a procedure that can find the solution is tried, and the solution is finally obtained by the tried procedure. If it is found that the solution cannot be obtained by the tried procedure, it returns to the previous state when it is found and tries another procedure. It is a technique. In the backtracking search method, a plurality of solutions can be searched. This search is, for example,

This is done by calculating the distance between solutions using. Then, a solution maintaining a certain distance is adopted as a plan candidate. For example, when searching for “solution 2” after searching for “solution 1”, if the distance between “solution 2” and “solution 1” is larger than a preset distance X, “solution 2” is adopted as a plan candidate. .

  For the above calculation, generally available mathematical programming software may be used. In this embodiment, specific numerical values, item names, and constraint conditions are given as input / output information, but other numerical values, item names, constraint conditions, and the like may be used.

  Next, the plan candidate planning apparatus 106 outputs plan candidates for each process by the plan candidate output unit 304 (S1504). Thus, the plan candidate creation process ends (S1505).

<Learning process S1212>
Next, the learning process will be described in detail.

  FIG. 19 is a flowchart for explaining the details of the learning process. As shown in the figure, the ideal planning apparatus 105 first selects a learning device by the learning method selection unit 201 (S1601).

  Specifically, the ideal plan planning apparatus 105 selects a learning device in the reverse direction when the calculation start process is the final process in the calculation start process information generation process. Also, the ideal planning apparatus 105 selects a forward learning device when the calculation start process is the first process in the calculation start process information generation process.

  The ideal plan planning apparatus 105 reads the execution plan from the execution plan DB 111 by the learning input processing unit 202 and inputs each process in the read execution plan to the learning device (S1602). Specifically, the ideal plan planning apparatus 105 inputs the calculation start process selected by the calculation start process information generation process to the learning device.

  The ideal plan planning apparatus 105 outputs an execution plan of the next process (forward process or reverse process) based on the execution plan process input to the learning device by the learning output processing unit 204. (S1603). This process is sequentially repeated.

  The ideal plan planning apparatus 105 updates the process knowledge DB 112 based on the execution plans generated in S1602 and S1063 (execution plans that specify the execution times of all processes). That is, the ideal plan planning apparatus 105 learns the execution plan by the learning unit 203.

  For example, in the case of using a neural network learning device, the input / output in this learning is input of the product delivery date, quantity, and product type in the calculation start process in the input layer, and in the output layer the product manufacturing order in the other processes is output. Is done. The learning method updates the parameters of the neural network by using, for example, an error back propagation method.

  In addition, when learning the first learning device, the user previously inputs predetermined information (execution plan history) regarding each process and the execution timing of each process, which has been performed in the past, to the input layer and the output layer, Based on this information, the parameters of the neural network may be updated using the error back propagation method.

  This completes the learning process (S1605).

  As described above, according to the production plan support system 1 of the present embodiment, based on the process knowledge information, the execution process information, which is the information related to the execution timing of each process, of the ordered product is generated. Generates feasible process information, which is information about the execution timing of each process that satisfies the constraint conditions, and updates the process knowledge information based on the feasible process information, and uses the feasible process information as a product production plan. Therefore, a user such as an operator can appropriately produce a product produced by performing a plurality of steps. That is, according to the production plan support system 1 of the present embodiment, since the process knowledge information is updated based on the executable process information, the machine learning is performed. Production can be performed based on the production plan. This allows the user to perform production that takes into account factors that require skilled experience and knowledge regarding product production, such as the restart cost of the equipment used in each process, so that the product can be produced efficiently and at low cost. Can be produced in In addition, even if there are constraints on each process such as the manufacturing capacity and quantity of the product, the user can perform appropriate production that satisfies these constraints.

  For example, according to the production plan support system 1 of the present embodiment, a plurality of executable process information satisfying the usage conditions of the facility is generated as the executable process information. The product can be produced based on an appropriate production plan corresponding to the equipment conditions.

  In addition, according to the production plan support system 1 of the present embodiment, the similarity between each of the generated plurality of executable process information and the implementation process information is calculated, and the most implementation process among the calculated similarities. The feasible process information similar to the information is identified, and the identified feasible process information is output as the production process information of the product, so that the user can produce the most appropriate product among the production plans of the feasible product Production can be performed based on a production plan that can be performed.

  Further, according to the production plan support system 1 of the present embodiment, the execution process information is generated according to the index when generating the execution process information, so that the user can produce a product according to a predetermined target. .

  For example, according to the production plan support system 1 of the present embodiment, information on the product quantity or product production completion time is acquired as an index for generating execution process information, and the execution process information is obtained according to the acquired index. Therefore, the user can reliably produce the product based on the production plan for producing a predetermined quantity of the product or the production plan for completing the production of the product on the predetermined delivery date.

  Further, according to the production plan support system 1 of the present embodiment, the process knowledge information is updated by generating information specifying the execution time of the previous process based on the information on a certain process, or a certain process Based on the information on the process, learning is performed by updating the process knowledge information by generating information specifying the execution time of the process to be performed later, so the user has the largest number of products at the start of product production Product that reduces the final in-process inventory.

  As described above, as an embodiment of the present invention, the example applied to support for product production planning has been described. In addition, this invention is not limited to above-described embodiment, Various modifications are included. For example, the above-described embodiment has been described in detail for easy understanding of the present invention, and is not necessarily limited to one having all the configurations described. Further, a part of the configuration of an embodiment can be replaced with the configuration of another embodiment, and the configuration of another embodiment can be added to the configuration of an embodiment. In addition, it is possible to add, delete, and replace other configurations for a part of the configuration of each embodiment.

  For example, the present invention is not limited to a business for manufacturing a product (manufacturing industry), but also various other types of business (for example, a decision-making business performed through a plurality of processes) in which a business is performed by a plurality of processes. It can be applied to various business.

  Each of the above-described configurations, functions, processing units, processing means, and the like may be realized by hardware by designing a part or all of them with, for example, an integrated circuit. Each of the above-described configurations, functions, and the like may be realized by software by interpreting and executing a program that realizes each function by the processor. Information such as programs, tables, and files for realizing each function can be stored in a recording device such as a memory, a hard disk, an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

  Further, the control lines and information lines indicate what is considered necessary for the explanation, and not all the control lines and information lines on the product are necessarily shown. Actually, it may be considered that almost all the components are connected to each other.

DESCRIPTION OF SYMBOLS 1 Production support system, 109 Worker terminal, 132 Result output part, 112 Process knowledge DB, 141 Order information acquisition part, 203 Learning part, 205 Ideal plan production | generation part, 302 Restriction condition input process part, 303 Search part

Claims (15)

A production support system that includes a processor and a memory and supports production of a product produced by performing a plurality of processes,
A process knowledge information storage unit that stores process knowledge information that is a relationship between a product and an execution time of each process performed for production of the product;
An order information acquisition unit for acquiring information on products to be produced;
Based on the acquired product information and the process knowledge information, an execution process information generating unit that generates execution process information that is information regarding the execution timing of each process to be performed for production of the acquired product;
A constraint condition acquisition unit that acquires constraint condition information that is information of conditions set for each of the steps;
Based on the acquired constraint condition information, an executable process information generating unit that generates executable process information that is information on an execution timing of each process in manufacturing the acquired product that satisfies the set condition;
A learning unit that updates the process knowledge information based on the generated executable execution process information;
An output unit that outputs the generated feasible process information as information on a production process of the acquired product;
Production support system equipped with. The executable process information generation unit
Generating a plurality of executable process information,
The similarity between each of the generated executable process information and the generated implementation process information is calculated, and the executable process information similar to the implementation process information is specified based on the calculated similarity. ,
The output unit outputs the specified executable process information as information on a production process of the acquired product.
The production support system according to claim 1. The implementation process information calculation unit acquires an index when generating the implementation process information, and generates the implementation process information according to the acquired index.
The production support system according to claim 1. The learning unit updates the process knowledge information by generating information for specifying an execution time of a process before the predetermined process based on information on the predetermined process, or relates to the predetermined process Updating the process knowledge information by generating information identifying an execution time of a process performed after the predetermined process based on the information;
The production support system according to claim 1. The execution process information calculation unit acquires information on the quantity of products or production completion time of the product as an index when generating the execution process information, and generates the execution process information according to the acquired index,
The constraint condition acquisition unit acquires information including information on a use condition of equipment used in the process as the constraint condition information,
The executable process information generation unit
As the feasible process information, generating a plurality of the feasible process information that satisfies the use conditions of the equipment,
The similarity between each of the generated executable process information and the generated execution process information is calculated, and the executable process information most similar to the executed process information is identified based on the calculated similarity. And
The learning unit updates the process knowledge information by generating information for specifying an execution time of a process before the predetermined process based on information on the predetermined process, or relates to the predetermined process Based on the information, update the process knowledge information by generating information identifying the execution time of the process performed after the predetermined process,
The output unit outputs the specified executable process information as information on a production process of the acquired product.
The production support system according to claim 1. A production support method for supporting production of a product produced by performing a plurality of processes,
An information processing apparatus comprising a processor and a memory
Store process knowledge information, which is the relationship between the product and the timing of each process performed to produce the product,
Get information on the products to produce,
Based on the acquired product information and the process knowledge information, generate execution process information that is information regarding the execution time of each process to be performed for production of the acquired product,
Obtain constraint condition information that is information on conditions set for each of the steps,
Based on the acquired constraint condition information, generate executable process information that is information related to the execution timing of each process in manufacturing the acquired product that satisfies the set conditions.
Update the process knowledge information based on the generated executable execution process information,
The generated feasible process information is output as information on the acquired product production process.
Production support method. The information processing apparatus is
Generating a plurality of executable process information,
The similarity between each of the generated executable process information and the generated execution process information is calculated, and the executable process information most similar to the executed process information is identified based on the calculated similarity. And
Outputting the specified executable process information as information on the production process of the acquired product;
The production support method according to claim 6. The information processing apparatus is
Obtaining an index for generating the execution process information, and generating the execution process information according to the acquired index;
The production support method according to claim 6. The information processing apparatus is
Update the process knowledge information by generating information identifying the execution time of the process before the predetermined process based on the information about the predetermined process, or based on the information about the predetermined process, Updating the process knowledge information by generating information identifying the execution time of a process performed after a predetermined process;
The production support method according to claim 6. The information processing apparatus is
As an index when generating the execution process information, obtain information on the quantity of products, or production completion time of the product, generate the execution process information according to the acquired index,
As the constraint condition information, obtain information including information on the use conditions of equipment used in the process,
As the feasible process information, generating a plurality of the feasible process information that satisfies the use conditions of the equipment,
The similarity between each of the generated executable process information and the generated execution process information is calculated, and the executable process information most similar to the executed process information is identified based on the calculated similarity. And
Update the process knowledge information by generating information identifying the execution time of the process before the predetermined process based on the information about the predetermined process, or based on the information about the predetermined process, Updating the process knowledge information by generating information identifying the execution time of a process performed after a predetermined process;
Outputting the specified executable process information as information on the production process of the acquired product;
The production support method according to claim 6. A production support program for supporting production of products produced by performing a plurality of processes,
In an information processing apparatus including a processor and a memory,
A process knowledge information storage process for storing process knowledge information, which is a relationship between a product and the execution time of each process performed for production of the product;
Order information acquisition processing to acquire information on products to be produced;
Based on the acquired product information and the process knowledge information, an execution process information generation process for generating execution process information that is information related to the execution timing of each process to be performed for production of the acquired product;
Restriction condition acquisition processing for acquiring restriction condition information that is information on conditions set for each of the steps;
Based on the acquired constraint condition information, an executable process information generation process that generates executable process information that is information related to the execution timing of each process in manufacturing the acquired product that satisfies the set conditions;
A learning process for updating the process knowledge information based on the generated executable execution process information;
An output process for outputting the generated executable process information as information on a production process of the acquired product;
A production support program that runs The executable process information generation process is:
Generating a plurality of executable process information,
The similarity between each of the generated executable process information and the generated execution process information is calculated, and the executable process information most similar to the executed process information is identified based on the calculated similarity. And
The output unit is a process of outputting the specified executable process information as information on a production process of the acquired product.
The production support program according to claim 11. The implementation process information calculation process is a process of acquiring an index when generating the implementation process information and generating the implementation process information according to the acquired index.
The production support program according to claim 11. The learning process updates the process knowledge information by generating information specifying the execution time of the process before the predetermined process based on the information regarding the predetermined process, or relates to the predetermined process Based on the information, it is a process of updating the process knowledge information by generating information specifying the execution time of the process performed after the predetermined process.
The production support program according to claim 11. The execution process information calculation process is a process of acquiring information relating to the product quantity or product production completion time as an index when generating the execution process information, and generating the execution process information according to the acquired index. Yes,
The constraint condition acquisition process is a process of acquiring information including information on a use condition of equipment used in the process as the constraint condition information.
The executable process information generation process is:
As the feasible process information, generating a plurality of the feasible process information that satisfies the use conditions of the equipment,
The similarity between each of the generated executable process information and the generated execution process information is calculated, and the executable process information most similar to the executed process information is identified based on the calculated similarity. Process
The learning process updates the process knowledge information by generating information specifying the execution time of the process before the predetermined process based on the information regarding the predetermined process, or relates to the predetermined process Based on the information, the process knowledge information is updated by generating information identifying the execution time of the process performed after the predetermined process,
The output unit is a process of outputting the specified executable process information as information on a production process of the acquired product.
The production support program according to claim 11.

Images