Production plan establishment method and device

Abstract

A production plan establishment method according to an embodiment of the present invention comprises the steps of: obtaining production data of a product produced in a plurality of production lines; generating a derived variable on the basis of the obtained production data of the product; inputting the derived variable to an artificial neural network model, and learning, by the artificial neural network model, the input derived variable to predict a production operation rate of the product; and establishing an optimal production plan by reflecting the predicted production operation rate.

Description

Method for establishing a production plan and its device

[0001] Embodiments of the present invention relate to a production plan establishment method and apparatus therefor.

[0002] In a manufacturing plant comprised of multiple production lines, such as a PCB manufacturing plant using SMT equipment, production planning is crucial for efficiently managing each line's output. Specifically, a high degree of consistency between production plans and actual production results allows for more efficient management of factory resources, enhancing production efficiency. Furthermore, precise allocation of work across multiple production lines can enhance productivity.

[0003] Typically, when planning product production, users manually review production history data and calculate approximate operating rates based on this data to establish production plans. This often leads to significant discrepancies with actual production results. Production line operating rates can be defined as product production volume * (theoretical production cycle time / actual production time).

[0004] At this point, key indicators determining operating rates are determined by a variety of factors, including time, equipment, work file characteristics, and workers. This makes it increasingly difficult for users to predict the actual operating rate or product production volume of the factory. Consequently, production plans based on user intuition and relatively low accuracy can often lead to planning errors. Furthermore, imbalances between multiple production lines can lead to a decline in the factory's overall production efficiency.

[0005] According to one aspect of the present invention, the main task is to provide a production planning method and device for establishing an optimal production plan through more accurate prediction of production operation rate.

[0006] However, these tasks are exemplary, and the tasks to be solved by the present invention are not limited thereto.

[0007] A method for establishing a production plan according to one embodiment of the present invention comprises the steps of: acquiring production data of products produced in a plurality of production lines; generating derived variables based on the acquired production data of the products; inputting the derived variables into an artificial neural network model, and having the artificial neural network model learn the input derived variables to predict the production operation rate of the products; and establishing an optimal production plan by reflecting the predicted production operation rate.

[0008] The above production data may include production equipment characteristics, production time characteristics, mounting point characteristics, and production cycle time characteristics.

[0009] The step of acquiring production data of the product from the above-mentioned multiple production lines can adjust the time for acquiring production data of the product to suit the operating characteristics of the factory.

[0010] The step of generating a derived variable based on the production data of the product obtained above may include a step of setting the order of importance of the derived variable based on the production data of the product.

[0011] The step of generating a derived variable based on the production data of the product obtained above may include a step of setting importance weights of the derived variable based on the production data of the product.

[0012] A production plan establishment device according to one embodiment of the present invention includes: a data acquisition unit that acquires production data of products produced in a plurality of production lines; a data preprocessing unit that generates derived variables based on the acquired production data of the products; an artificial neural network unit that learns the input derived variables to predict the production operation rate of the products; and a production plan establishment unit that establishes a production plan for the products based on the production operation rate predicted by the artificial neural network unit.

[0013] The above artificial neural network unit may include a derived variable learning unit that inputs derived variables generated through the data preprocessing unit and performs learning of an artificial neural network model using the input derived variables; and an operating rate prediction unit that predicts the production operating rate of a product using the artificial neural network model learned through the derived variable learning unit.

[0014] The above artificial neural network model may be a GBM (Gradient Boosting Model).

[0015] The above data acquisition unit may include a data acquisition period adjustment unit that adjusts the time for acquiring production data of the product to suit the operating characteristics of the factory.

[0016] The above data preprocessing unit may include a derived variable importance order setting unit that sets the importance order of derived variables based on the production data of the product.

[0017] The above data preprocessing unit may include a derived variable importance weight setting unit that sets the importance weight of the derived variable based on the production data of the product.

[0018] Other aspects, features and advantages other than those described above will become apparent from the following detailed description, claims and drawings for carrying out the invention.

[0019] A production plan establishment method according to one embodiment of the present invention uses production data of products produced through multiple production lines to more accurately predict the production line operating rate through an artificial neural network model, thereby establishing an optimal production plan based on the predicted operating rate.

[0020] The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

[0021] FIG. 1 is a hardware configuration diagram for explaining the internal configuration of a production plan establishment device according to one embodiment of the present invention.

[0022] FIG. 2 is a block diagram for explaining the configuration and operation of a production plan establishment device according to one embodiment of the present invention.

[0023] Figure 3 is a block diagram for explaining the configuration and operation of an artificial neural network unit according to one embodiment of the present invention.

[0024] FIG. 4 is a block diagram for explaining the configuration and operation of a data acquisition unit according to one embodiment of the present invention.

[0025] FIG. 5 is a block diagram for explaining the configuration and operation of a data preprocessing unit according to one embodiment of the present invention.

[0026] FIG. 6 is a table exemplifying production data, derived variables, importance order, and importance weights according to one embodiment of the present invention.

[0027] Figure 7 is a flowchart showing a production plan establishment method according to one embodiment of the present invention.

[0028] The present invention is susceptible to various modifications and embodiments. Specific embodiments are illustrated in the drawings and described in detail in the description. However, this is not intended to limit the present invention to specific embodiments, but rather to encompass all modifications, equivalents, and alternatives falling within the spirit and technical scope of the present invention. In describing the present invention, identical components are identified by the same reference numerals even when illustrated in different embodiments.

[0029] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. When describing with reference to the drawings, identical or corresponding components are given the same reference numerals and redundant descriptions thereof will be omitted.

[0030] In the examples below, the terms first, second, etc. are not used in a limiting sense, but are used for the purpose of distinguishing one component from another.

[0031] In the examples below, singular expressions include plural expressions unless the context clearly indicates otherwise.

[0032] In the examples below, terms such as “include” or “have” mean that a feature or component described in the specification is present, and do not preclude the possibility that one or more other features or components may be added.

[0033] For convenience of explanation, the sizes of components in the drawings may be exaggerated or reduced. For example, the sizes and thicknesses of each component shown in the drawings are arbitrarily indicated for convenience of explanation, and thus the present invention is not necessarily limited to what is shown.

[0034] In some embodiments, where implementations are otherwise feasible, specific process sequences may be performed in a different order than described. For example, two processes described in succession may be performed substantially simultaneously, or in a reverse order from the described order.

[0035] The terminology used in this application is only used to describe specific embodiments and is not intended to limit the present invention. In this application, terms such as "comprise" or "have" are intended to indicate the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but should be understood to not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0036] The following detailed description of the present invention refers to the accompanying drawings, which illustrate specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention, while different from each other, are not necessarily mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be modified and implemented from one embodiment to another without departing from the spirit and scope of the present invention. Furthermore, it should be understood that the positions or arrangements of individual components within each embodiment may also be modified without departing from the spirit and scope of the present invention. Accordingly, the following detailed description is not to be taken in a limiting sense, and the scope of the present invention is to be construed to encompass the scope of the claims and all equivalents thereof. Like reference numerals in the drawings represent the same or similar elements throughout the several aspects. Artificial intelligence (AI) as disclosed in the present invention may refer to a field that studies artificial intelligence or the methodologies for creating it, and machine learning is a field of artificial intelligence technology that enables a computing device to learn from data to understand a specific object or condition, or a technical method that finds and classifies patterns in data, and may be an algorithm that enables a computer to analyze data. Machine learning as disclosed in the present invention may be understood to include an operating method for learning an artificial intelligence model.

[0037] Hereinafter, with reference to FIGS. 1 to 6, a production planning device according to one embodiment of the present invention will be described.

[0038] FIG. 1 is a hardware configuration diagram for explaining the internal configuration of a production plan establishment device according to an embodiment of the present invention. FIG. 2 is a block diagram for explaining the configuration and operation of a production plan establishment device according to an embodiment of the present invention. FIG. 3 is a block diagram for explaining the configuration and operation of an artificial neural network unit according to an embodiment of the present invention. FIG. 4 is a block diagram for explaining the configuration and operation of a data acquisition unit according to an embodiment of the present invention. FIG. 5 is a block diagram for explaining the configuration and operation of a data preprocessing unit according to an embodiment of the present invention. FIG. 6 is a table exemplarily showing production data, derived variables, importance order, and importance weights according to an embodiment of the present invention.

[0039] Referring to FIGS. 1 to 6, a production plan establishment device according to one embodiment of the present invention includes a data acquisition unit (110) that acquires production data of products produced in a plurality of production lines, a data preprocessing unit (120) that generates derived variables based on the acquired production data of products, an artificial neural network unit (130) that learns input derived variables to predict a production operation rate of products, and a production plan establishment unit (140) that establishes a production plan of products based on the production operation rate predicted through the artificial neural network unit.

[0040] Typically, when producing a product using multiple production lines, users plan production by predicting the operating rate based on the previous production history of the same product. However, actual production operating rates vary significantly depending on factors such as the skill level of production workers, time of day, day of the week, break times, shift times, equipment failures and repair times, and worker errors. Estimating operating rates based on these factors and planning production across multiple production lines can result in significant discrepancies from actual production results. Predicting production results can be even more difficult for initial production runs of previously unproduced products.

[0041] Furthermore, users typically rely on intuition to create production plans that reflect low-precision production efficiency. This problem frequently leads to actual production ending earlier or later than planned, necessitating abrupt changes to production plans. Furthermore, if production proceeds on an unplanned production line, the required pre-production preparation time and worker fatigue can increase. Furthermore, inaccurate production plans can lead to increased production times and missed deadlines, potentially resulting in missed delivery dates.

[0042] Accordingly, according to one embodiment of the present invention, various derived variables are created based on production data previously produced in a production plant, and the derived variables are input into an artificial neural network model for training, thereby enabling a more accurate prediction of production operation rates. At this time, a production plan is created based on the predicted production operation rates, and through a more accurate production plan, the possibility of the production plan being disrupted or having to be changed suddenly is minimized, and the maximum operating time of the entire factory is minimized, thereby providing a method for improving the overall productivity of the factory.

[0043] Referring to FIG. 1, in one embodiment of the present invention, a production planning device (100) may include a processor (101), a memory (102), an input / output unit (103), and a communication unit (104). The memory (102) may be a computer-readable recording medium, and may include a non-perishable large-capacity storage device such as a random access memory (RAM), a read only memory (ROM), and a disk drive. In addition, the memory (202) may temporarily or permanently store program codes and settings for controlling the organ volume measurement device (200), camera images, and pose data of an object.

[0044] The processor (101) may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processor (101) by the memory (102) or the communication unit (104). For example, the processor (101) may be configured to execute instructions received according to program code stored in a recording device such as the memory (102).

[0045] The communication unit (104) may provide a function for communicating with an external server via the network (10). The external server described above may be, for example, a factory server that provides product production data. For example, a request generated by the processor (101) of the production planning device (100) according to a program code stored in a recording device such as a memory (102) may be transmitted to an external server via the network (10) under the control of the communication unit (104). Conversely, control signals, commands, contents, files, etc. provided under the control of the processor of the external server may be received by the production planning device (100) via the communication unit (104) via the network (10). For example, control signals, commands, etc. of the external server received via the communication unit (104) may be transmitted to the processor (101) or the memory (102), and contents, files, etc. may be stored in a storage medium that the production planning device (100) may further include. In addition, the communication method of the communication unit (104) is not limited, but the network (10) may be a short-range wireless communication network. For example, the network (10) may be a Bluetooth, BLE (Bluetooth Low Energy), or Wi-Fi communication network.

[0046] The input / output unit (103) can receive user input and display output data. According to one embodiment, the input / output unit (103) can display a predicted operating rate on the display.

[0047] Furthermore, in other embodiments, the production planning device may include more components than those illustrated in FIG. 1. However, it is not necessary to explicitly illustrate most conventional components. For example, the production planning device (100) may include a battery and a charging device that power the internal components of the user terminal, and may be implemented to include at least some of the input / output devices described above, or may further include other components such as a transceiver, a Global Positioning System (GPS) module, various sensors, a database, etc.

[0048] Referring to FIGS. 2 and 4, in one embodiment of the present invention, a production planning device (210) may include a data acquisition unit (110). The data acquisition unit (110) may acquire production data of products produced in multiple production lines.

[0049] The production data of a product may include, for example, production equipment data related to production equipment, production time data related to production time, mounting point data related to mounting points of parts, and cycle time data related to the cycle time of the product being produced. The above-described production data may use production data of products already produced in a factory. Since the production data of products already produced and the production operating rate of products already produced are used to infer an operating rate prediction value through an artificial neural network unit to be described later, the artificial neural network model of the artificial neural network unit according to embodiments of the present invention can perform supervised learning using the production data of products already produced as described above.

[0050] Referring to FIG. 4, the data acquisition unit (110) according to the present embodiment may include a data acquisition period adjustment unit (111). The data acquisition period adjustment unit (111) may adjust the time for acquiring product production data to suit the operating characteristics of the factory.

[0051] Because factory productivity fluctuates over time, it's important to continuously capture production data within the factory. For example, new production data can be collected at a set time each week to reflect the latest factory operating rates.

[0052] However, as the amount of production data from the factory increases, the accuracy of operating rate prediction may improve due to the increase in data samples. However, conversely, as the amount of production data that has been around for a long time increases, the accuracy of operating rate prediction may decrease. Therefore, it is necessary to adjust and set the data acquisition period according to the production characteristics of the factory's products.

[0053] Referring to FIGS. 2, 5, and 6, in one embodiment of the present invention, the production planning device (100) may include a data preprocessing unit (120). The data preprocessing unit (120) may generate derived variables based on the acquired product production data.

[0054] At this time, the data preprocessing unit (120) may include a derived variable importance order setting unit (121) that sets the importance order of derived variables based on the product production data, and a derived variable importance weight setting unit (122) that sets the importance weight of derived variables.

[0055] Here, the artificial neural network unit (130) can learn the derived variables to predict the production operation rate of the product. At this time, the importance order of the derived variables through the derived variable importance order setting unit (121) and the importance weight of the derived variables through the derived variable importance weight setting unit (122) are also input to the artificial neural network unit (130) together with the derived variables, and the artificial neural network unit (130) can output a predicted production operation rate of the product by learning the derived variables, the importance order of the derived variables, and the importance weight of the derived variables.

[0056] Referring to Figure 6, multiple derived variables can be created for each piece of production data. For example, derived variables for production equipment data can include variables for production equipment, production lines, and production equipment placement order. Furthermore, derived variables for production time data can include variables for operating days, holidays, production hours, and production shift times.

[0057] Derived variables for mounting point data can be used, for example, when producing PCBs using SMT equipment. In this case, the mounting point data can be derived from variables such as the number of mounting points, the total number of mounting points during a job, and the difference between the number of mounting points on the bottleneck equipment (the equipment with the highest cycle time on the production line) and the number of mounting points on the current equipment.

[0058] Derived variables for production cycle time data can be, for example, when producing PCBs using SMT equipment. In this case, the production cycle time data can be cycle time, front and back cycle time (there are two lanes, front and back, in one production line), bottleneck time, maximum number of PCBs produced in 1 hour based on lane bottleneck time, maximum number of PCBs produced in 1 hour based on line bottleneck time, maximum number of PCBs produced in 1 hour based on cycle time (time taken to produce one PCB per equipment), unique CPH (Chips per hour, number of chips that can be mounted per hour) of equipment, unique CPH ratio of current equipment to bottleneck equipment, difference between equipment cycle time and bottleneck time, maximum lane cycle time between lines, bottleneck lane cycle time between lanes, lane CPH, maximum CPH between lines, order of bottleneck mounting points, relative distance to bottleneck mounting points, etc.

[0059] Here, the maximum lane cycle time between lines is the maximum cycle time for the two lanes in front and behind each line, and a derived variable can be created for each line. In addition, the bottleneck lane cycle time between lanes can refer to the lane cycle time of the bottleneck equipment for each lane. The lane CPH can refer to the maximum number of chips that can be installed per hour per equipment for each lane. The maximum CPH between lines can refer to the maximum number of chips that can be installed per hour per equipment for each line. The bottleneck mounting point order can represent the order of the bottleneck equipment. For example, if the third equipment among four equipment is the bottleneck, the derived variable of the bottleneck mounting point order can be 3. The relative distance to the bottleneck mounting point can be the relative distance value between the bottleneck equipment and the equipment currently performing the aggregation.

[0060] Also, referring to Figure 6, the importance order and weights for each derived variable can be displayed. These importance orders and weights set for each derived variable can be adjusted to suit the production characteristics of the factory.

[0061] Referring to FIGS. 2 and 3, the artificial neural network unit (130) may include an artificial neural network model. The artificial neural network unit (130) may include a derivative variable learning unit (131) and an operating rate prediction unit (132).

[0062] The derived variable learning unit (131) can input derived variables generated through the data preprocessing unit (120) and perform learning of an artificial neural network model using the input derived variables. The operating rate prediction unit (132) can predict the production operating rate of a product using the artificial neural network model learned through the derived variable learning unit.

[0063] The artificial neural network model according to this embodiment may be a GBM (Gradient Boosting Model). That is, based on the derived variables extracted through the data preprocessing unit (120), the production operating rate can be predicted by training the derived variables with an artificial neural network model of the GBM series. The GBM series artificial neural network model boasts superior performance and, compared to other models, uses relatively few training resources, thereby reducing the time required to predict the operating rate.

[0064] In addition, according to this embodiment, the more valid derivative variables are created, the better the performance of operating rate prediction can be. However, as the number of derivative variables increases, the time required to predict the operating rate can increase. Therefore, learning can be conducted with a focus on derivative variables that have a high importance reflected in the prediction or a high importance weight.

[0065] The operating rate prediction data generated through the operating rate prediction unit (132) can be transmitted to the production planning unit (140). The production planning unit can establish an optimal production plan by reflecting the operating rate prediction value output through the artificial neural network unit (130) in the production candidate line and production candidate time of the product to be produced in the future.

[0066] As an experimental example, when a user generally predicts the operating rate and establishes a production plan for a product, the prediction accuracy of the operating rate is calculated to be 50 to 70 percent, but when the operating rate is predicted using an artificial neural network model according to this embodiment, the prediction accuracy of the operating rate is 81 to 90 percent, showing that the accuracy of the prediction accuracy of the operating rate is dramatically improved.

[0067] When planning production on multiple lines in this way, more accurate production planning can minimize production delays, increase work efficiency, and enable unlimited production of products on the required delivery date.

[0068] Additionally, the time required for high-accuracy production planning will be shortened compared to before, which can increase the convenience of changing existing production plans.

[0069] Additionally, since production proceeds according to the planned time when producing the actual product, the preparation of materials and resources required for production in advance can also proceed efficiently.

[0070] Hereinafter, with reference to FIG. 7, a method for establishing a production plan according to one embodiment of the present invention will be described. Contents not illustrated in FIG. 7 may be referenced to the contents illustrated in FIGS. 1 to 6 and their corresponding descriptions.

[0071] Figure 7 is a flowchart showing a production plan establishment method according to one embodiment of the present invention.

[0072] Referring to FIG. 7, a method for establishing a production plan according to an embodiment of the present invention may include a step of obtaining production data of a product produced in a plurality of production lines (S100), a step of generating a derived variable based on the obtained production data of the product (S200), a step of inputting the derived variable into an artificial neural network model, and the artificial neural network model learning the input derived variable to predict the production operation rate of the product (S300), and a step of establishing an optimal production plan by reflecting the predicted production operation rate (S400).

[0073] The step (S100) of acquiring production data of the product from the above-mentioned multiple production lines can adjust the time for acquiring the production data of the product to suit the operating characteristics of the factory.

[0074] The step (S200) of generating a derived variable based on the production data of the product obtained above can set the order of importance of the derived variable based on the production data of the product.

[0075] In addition, the step (S300) of generating a derived variable based on the production data of the product obtained above can set the importance weight of the derived variable based on the production data of the product.

[0076] The devices described above may be implemented as hardware components, software components, and / or a combination of hardware components and software components. For example, the devices and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing instructions and responding to them. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device is sometimes described as being used alone; however, one of ordinary skill in the art will recognize that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, a processing unit may include multiple processors, or a processor and a controller. Other processing configurations, such as parallel processors, are also possible.

[0077] Software may include a computer program, code, instructions, or a combination of one or more of these, and may configure a processing device to perform a desired operation or, independently or collectively, command the processing device. The software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave, for interpretation by the processing device or for providing instructions or data to the processing device. The software may also be distributed over networked computer systems and stored or executed in a distributed manner. The software and data may be stored on one or more computer-readable recording media.

[0078] The method according to the embodiment may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the medium may be those specially designed and configured for the embodiment or may be those known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands, such as ROMs, RAMs, and flash memories. Examples of the program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc. The above-mentioned hardware devices may be configured to operate as one or more software modules to perform the operations of the embodiment, and vice versa.

[0079] Although the embodiments described above have been described by way of limited examples and drawings, those skilled in the art will appreciate that various modifications and variations can be made based on the above teachings. For example, appropriate results can still be achieved even if the described techniques are performed in a different order than described, and / or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents.

[0080] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims described below.

Claims

1. A step of acquiring production data of products produced on multiple production lines; A step of creating derived variables based on the production data of the acquired product; A step of inputting the above-mentioned derived variables into an artificial neural network model, and the artificial neural network model learning the input derived variables to predict the production operation rate of the product; and A method for establishing a production plan, comprising a step of establishing an optimal production plan by reflecting the predicted above production operation rate.

2. In paragraph 1, A method for establishing a production plan, wherein the above production data includes production equipment characteristics, production time characteristics, mounting point characteristics, and production cycle time characteristics.

3. In paragraph 1, The step of obtaining production data of the product from the above multiple production lines is: A production planning method that adjusts the time for acquiring product production data to suit the operating characteristics of the factory.

4. In paragraph 1, The step of generating a derived variable based on the production data of the product obtained above is: A method for establishing a production plan, comprising a step of establishing the order of importance of derived variables based on the production data of the product.

5. In paragraph 1, The step of generating a derived variable based on the production data of the product obtained above is: A method for establishing a production plan, comprising a step of setting importance weights of derived variables based on production data of a product.

6. A data acquisition unit that acquires production data of products produced on multiple production lines; Data preprocessing unit that creates derived variables based on the production data of the acquired product; An artificial neural network unit that learns the input derived variables to predict the production operation rate of a product; and A production planning device including a production planning unit that establishes a production plan for a product based on the production operation rate predicted through the artificial neural network unit.

7. In paragraph 6, The artificial neural network unit includes a derived variable learning unit that inputs derived variables generated through the data preprocessing unit and performs learning of an artificial neural network model using the input derived variables; and A production planning device including an operating rate prediction unit that predicts the production operating rate of a product through an artificial neural network model learned through the above-mentioned derived variable learning unit.

8. In paragraph 7, The above artificial neural network model is a production planning device called GBM (Gradient Boosting Model).

9. In paragraph 6, A production planning device, wherein the data acquisition unit includes a data acquisition period adjustment unit that adjusts the time for acquiring the production data of the product to suit the operating characteristics of the factory.

10. In paragraph 6, A method for establishing a production plan, wherein the above data preprocessing unit includes a derived variable importance order setting unit that sets the importance order of derived variables based on the production data of the product.

11. In paragraph 6, A method for establishing a production plan, wherein the above data preprocessing unit includes a derived variable importance weight setting unit that sets the importance weight of the derived variable based on the production data of the product.

Images