Server and method for providing artificial intelligence-based factory design tool

Abstract

The present disclosure relates to a server for providing a factory design tool, the server comprising: a storage module in which a three-dimensional model for each of multiple first configurations used in a process of a factory, a dataset of a factory layout, a process flow template for each process of the factory, and information of each process step are stored; and a control module for displaying a list of at least one second configuration that matches a process in a target factory to be designed by a user, from among the multiple first configurations, and displaying a three-dimensional model of the second configuration selected from the displayed list and dragged and dropped on the layout.

Description

Server and method for providing an AI-based factory design tool

[0001] The present disclosure relates to a server providing an artificial intelligence-based factory design tool.

[0002] With the advent of the Fourth Industrial Revolution, the digital transformation of the manufacturing industry is accelerating.

[0003] To maximize manufacturing efficiency and secure global competitiveness, manufacturing companies are adopting data-driven decision-making systems and, based on these systems, are making various attempts to optimize processes and improve productivity.

[0004] Existing management systems used in manufacturing have limitations in real-time processing, multidimensional analysis, and optimization of process data. Most systems rely on static data analysis, making it difficult to dynamically analyze interrelationships between data or immediately reflect them in a simulation environment.

[0005] In addition, existing supply chain management has the problem of not being able to perform quantitative big data analysis and visualization of the collaborative network, which prevents strategic management of the entire network and key nodes.

[0006] Cyber-physical systems (CPS) and digital twin technologies are emerging as powerful tools for addressing these challenges. CPS enables real-time interaction between physical systems and the cyber world, while digital twins provide a mirror image of the real world through virtualization of manufacturing processes and systems. This is expected to enable new ways to integrate and analyze manufacturing process data, supply chain management (SCM), and APS data. However, specific technologies capable of implementing this approach are currently unavailable.

[0007] The purpose of the embodiment disclosed in this disclosure is to provide a server providing an artificial intelligence-based factory design tool.

[0008] The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0009] A factory design tool providing server according to one embodiment of the present disclosure for solving the above-described problem comprises: a storage module in which a three-dimensional model for each of a plurality of first configurations used in a factory process, a dataset of a factory layout, a process flow template for each process of the factory, and information on each process step are stored; - The plurality of first configurations include equipment and materials for performing the process - A control module for displaying a list of at least one second configuration that matches a process of a target factory that a user wants to design among the plurality of first configurations, and displaying a three-dimensional model of a second configuration selected from the displayed list and dragged and dropped onto a layout, wherein the control module automatically arranges a path of equipment and materials on the layout using the process flow template based on a process set for the target factory, and performs the arrangement by calculating a distance and space utilization between processes based on map data of the target factory and the set process, and creates a virtual factory model for the target factory based on the configurations arranged on the layout, and performs a process simulation for the target factory using the virtual factory model according to input variables, - the variables include temperature, humidity, process speed, equipment operating time, maintenance cycle, and energy consumption - and can calculate a process completion time and cost based on a result of performing the process simulation.

[0010] Additionally, the control module can control at least one preset event to occur while performing the process simulation according to a preset event occurrence probability.

[0011] At this time, the event includes at least one of a change in production speed, an occurrence of equipment failure, an occurrence of a material shortage, a change in temperature, and a change in humidity.

[0012] In addition, the control module can obtain changes in the production schedule, changes in the defect rate of the process output, changes in the quality of the process output, delays in shipment, changes in inventory, occurrence and location of bottlenecks in facility operation, changes in energy consumption, changes in costs, and occurrences of accidents based on the results of the process simulation performed when the event occurs.

[0013] In addition, the factory design tool providing server inputs event occurrence history and event occurrence result data according to the operation of multiple actual factories into an artificial intelligence model to train the model, and the control module generates an event while performing the process simulation through the virtual factory using the artificial intelligence model and obtains the result of the process simulation, and when an abnormal result that deviates from a preset standard is obtained among the obtained process simulation results, the control module determines whether the abnormal result is a design error or a simulation error of the virtual factory using the artificial intelligence model and provides a notification, and stores a log record of the abnormal result and the notification details.

[0014] In addition, the control module inputs manufacturing site process data, data related to SCM (Supply Chain Management) and APS (Advanced Planning and Scheduling) required to perform the artificial intelligence-based simulation for the target factory into a first virtual factory model created based on a digital twin for the target factory using the factory design tool to perform the simulation, obtains an output value based on the simulation performance result, and visualizes the simulation result of the first virtual factory model in a virtual space based on the obtained output value.

[0015] In addition, the control module selects at least one major facility among the facilities of the target factory based on the process type and facility type of the target factory, provides a dashboard that can check the status of the major facility and the process status of the target factory, and obtains a preset periodic result value for at least one indicator based on the simulation result, and the at least one indicator includes production volume, defect rate, delivery volume, power usage, material consumption, and material purchase volume.

[0016] In addition, the server includes a factory design model learned based on map data of a plurality of factories, space partition data by process of the plurality of factories, equipment layout data of the plurality of factories, and process evaluation scores of the plurality of factories, and using the factory design model, partitions the space of the target factory by process performed in the target factory based on the map data of the target factory and the process type of the target factory, and arranges equipment corresponding to each of the partitioned spaces in consideration of the safety distance between equipment and the process speed, thereby displaying a virtual factory model for the target factory on the layout.

[0017] In addition, the control module may provide a plurality of questions to obtain information necessary for designing the target factory, receive the user's answers to the plurality of questions, input the received answers into an artificial intelligence model that has learned a method for writing a command prompt, and request the user to generate a command prompt for inputting requirements for designing the target factory into a generative model, and input the command prompt obtained from the artificial intelligence model into the generative model to obtain design information for the target factory, and display the design of the target factory on the layout based on the obtained design information.

[0018] In addition, the plurality of questions include information on the area of ​​the target factory, the type of at least one good to be produced at the target factory, the type and number of equipment to be installed at the target factory, the type of at least one process to be performed at the target factory, the degree of automation of the target factory, the daily production volume of the target factory, the number of employees at the target factory, power consumption, and budget.

[0019] In addition, when map data of the target factory is received, the control module can generate area information based on the received map data, compare the area information with the number of equipment to be installed in the target factory to determine whether installation is possible, and compare the daily production volume and the number of equipment to be installed in the target factory with the number of employees to determine whether implementation is possible.

[0020] In addition, the control module may calculate the spacing between the equipment based on the area information of the target factory, the type and number of equipment to be installed in the target factory, and the daily production volume, and may generate a notification requesting a setting change if the calculated spacing violates the minimum safety distance set for the equipment.

[0021] In addition, the control module can receive a user's requirement for the target factory that the user wants to design, input the received requirement into an explainable AI (XAI) to request the creation of a command prompt for inputting the requirement into a generative model, input the command prompt obtained from the explainable AI into the generative model to request design information of the target factory, and display the design information for the target factory obtained from the generative model on the layout.

[0022] In addition, the control module can generate a first virtual factory model optimized for the target factory by learning a common virtual factory model that has been learned in advance based on the type of process, process process, and process singularity performed in the target factory based on information of the target factory using a transfer learning technique.

[0023] In addition, the control module can obtain a first analysis result based on the SCM data after performing the simulation, and can obtain a second analysis result based on the APS data after performing the simulation.

[0024] At this time, the first analysis result includes demand forecast information, appropriate inventory optimization information, and material requirement forecast information, and the second analysis result includes lead time information, delivery schedule analysis information, and production schedule planning information.

[0025] In addition, a method for providing a factory design tool according to an embodiment of the present disclosure for solving the above-described problem is a method performed by a server, comprising: a step of displaying a list of at least one second configuration that matches a process of a target factory that a user wishes to design among a plurality of first configurations used in a process of a factory; a step of displaying a three-dimensional model of a second configuration selected from the displayed list and dragged and dropped onto a layout; a step of automatically arranging a path of equipment and materials on the layout using the process flow template based on a process set for the target factory; a step of performing the arrangement by calculating a distance and space utilization between processes based on map data of the target factory and the set process;

[0026] A step of creating a virtual factory model for the target factory based on the configurations arranged on the layout; A step of performing a process simulation for the target factory using the virtual factory model according to input variables; -The variables include temperature, humidity, process speed, equipment operation time, maintenance cycle, and energy consumption; -A step of calculating a process completion time and cost based on the performance result of the process simulation; The server stores a 3D model for each of the plurality of first configurations, a dataset of the factory layout, a process flow template for each process of the factory, and information on each process step. -The plurality of configurations include equipment and materials for performing the process-

[0027] In addition, a computer program stored in a computer-readable recording medium for executing a method for implementing the present disclosure may be further provided.

[0028] In addition, a computer-readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

[0029] According to the aforementioned problem solving means of the present disclosure, an effect of providing an artificial intelligence-based factory design tool providing server is provided.

[0030] The effects of the present disclosure 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 below.

[0031] FIG. 1 is a schematic diagram of a factory design tool providing system according to an embodiment of the present disclosure.

[0032] FIG. 2 is a diagram illustrating a representative effect of a factory design tool providing system according to an embodiment of the present disclosure.

[0033] Figure 3 is a drawing illustrating the factory configuration concept.

[0034] FIG. 4 is a diagram illustrating a factory operation simulation service provision system in an embodiment of the present disclosure.

[0035] FIG. 5 is a block diagram of a factory design tool providing server according to an embodiment of the present disclosure.

[0036] FIG. 6 is a flowchart of a method for providing a factory design tool according to an embodiment of the present disclosure.

[0037]

[0038] *Figure 7 is a diagram illustrating how a server generates design information for a target factory using an artificial intelligence model.

[0039] FIG. 8 is a diagram illustrating a detailed simulation structure of a server according to an embodiment of the present disclosure.

[0040] Figure 9 is a diagram illustrating a process for acquiring three-dimensional data on the process of a target factory and implementing virtualization thereof.

[0041] Figure 10 is a diagram illustrating the microstructure of a recurrent neural network.

[0042] Figure 11 is a diagram illustrating the sensitivity analysis process.

[0043] Figure 12 is a diagram illustrating tracking of cumulative reward and reward histogram for each episode to derive value chain optimization values ​​in a deep reinforcement learning network.

[0044] Figure 13 is a diagram illustrating the linkage between the SCM, APS system and the factory operation simulation service provider.

[0045] Figure 14 is a diagram illustrating a demand forecasting AI analysis process based on manufacturing data.

[0046] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and any content that is common in the technical field to which this disclosure pertains or that overlaps between embodiments is omitted. The terms "part, module, element, block" used in the specification may be implemented in software or hardware, and depending on the embodiments, multiple "parts, modules, elements, blocks" may be implemented as a single component, or a single "part, module, element, block" may include multiple components.

[0047] Throughout the specification, when a part is said to be "connected" to another part, this includes not only direct connection but also indirect connection, and indirect connection includes connection via a wireless communication network.

[0048] Additionally, when a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

[0049] Throughout the specification, when we say that an element is "on" another element, this includes not only cases where the element is in contact with the other element, but also cases where another element exists between the two elements.

[0050] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0051] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0052] The identification codes for each step are used for convenience of explanation and do not describe the order of each step. Each step may be performed in a different order than specified unless the context clearly indicates a specific order.

[0053] The operating principle and embodiments of the present disclosure are described below with reference to the attached drawings.

[0054] In this specification, the term "factory design tool providing server according to the present disclosure" encompasses various devices capable of performing computational processing and providing results to users. For example, the factory design tool providing server according to the present disclosure may include a computer, a server device, and a portable terminal, or may be any one of them.

[0055] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0056] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0057] The above portable terminal may include, for example, all kinds of handheld-based wireless communication devices such as PCS, GSM, PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminals, smart phones, etc., as well as wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted devices (HMD).

[0058] The artificial intelligence-related functions according to the present disclosure are operated through a processor and a storage unit. The processor may be composed of one or more processors. In this case, one or more processors may be a general-purpose processor such as a CPU, an AP, a Digital Signal Processor (DSP), a graphics-only processor such as a GPU or a Vision Processing Unit (VPU), or an artificial intelligence-only processor such as an NPU. One or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in the storage unit. Alternatively, if one or more processors are artificial intelligence-only processors, the artificial intelligence-only processor may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0059] The predefined operation rules or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that the basic artificial intelligence model is learned by a learning algorithm using a plurality of learning data, thereby creating the predefined operation rules or artificial intelligence models set to perform a desired characteristic (or purpose). This learning may be performed on the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and / or system. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0060] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weights, and performs neural network operations through operations between the operation results of the previous layer and the multiple weights. The multiple weights of the multiple neural network layers may be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model is reduced or minimized during the learning process. The artificial neural network may include a deep neural network (DNN), and examples thereof include, but are not limited to, a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or a deep Q-network.

[0061] According to an exemplary embodiment of the present disclosure, a processor can implement artificial intelligence. Artificial intelligence refers to a machine learning method based on an artificial neural network that mimics human neurons (biological neurons) to enable machines to learn. Artificial intelligence methodologies can be categorized into supervised learning, where input and output data are provided together as training data, thereby determining the solution (output data) to a problem (input data); unsupervised learning, where only input data is provided without output data, so that the solution (output data) to a problem (input data) is not determined; and reinforcement learning, where a reward is provided from an external environment each time an action is taken in the current state, and learning proceeds in a direction that maximizes this reward. Furthermore, artificial intelligence methodologies can be categorized by the architecture of the learning model. The architectures of widely used deep learning technologies can be categorized into convolutional neural networks, recurrent neural networks, transformers, and generative adversarial networks.

[0062] The device may include an artificial intelligence model. The artificial intelligence model may be a single artificial intelligence model or may be implemented as multiple artificial intelligence models. The artificial intelligence model may be composed of a neural network (or artificial neural network) and may include statistical learning algorithms that mimic biological neurons in machine learning and cognitive science. A neural network may refer to a model in general that has problem-solving capabilities by changing the binding strength of synapses through learning, formed by artificial neurons (nodes) that form a network by combining synapses. The neurons of the neural network may include a combination of weights or biases. The neural network may include one or more layers composed of one or more neurons or nodes. For example, the device may include an input layer, a hidden layer, and an output layer. The neural network constituting the device can infer a desired outcome from an arbitrary input by changing the weights of the neurons through learning.

[0063] The processor can create a neural network, train (or learn) a neural network, perform a calculation based on received input data, generate an information signal based on the calculation result, or retrain the neural network. The models of the neural network can include various types of models such as CNN, R-CNN, RPN, RNN, S-DNN, S-SDNN, Deconvolution Network, DBN, RBM, Fully Convolutional Network, LSTM Network, Classification Network, etc., such as GoogleNet, AlexNet, VGG Network, etc., but are not limited thereto. The processor can include one or more processors for performing calculations according to the models of the neural network. For example, the neural network can include a deep neural network.

[0064] Neural networks include CNN, RNN, perceptron, multilayer perceptron, Feed Forward (FF), Radial Basis Network (RBF), Deep Feed Forward (DFF), Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Auto Encoder (AE), Variational Auto Encoder (VAE), Denoising Auto Encoder (DAE), Sparse Auto Encoder (SAE), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Depp Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), GAN (Generative Adversarial Network), LSM (Liquid State Machine), ELM (Extreme Learning) Machine), ESN (Echo State Network), DRN (Deep Residual Network), DNC (Differentiable Network) It will be understood by those skilled in the art that the neural network may include any neural network, including but not limited to a Neural Computer (NN), a Neural Turning Machine (NTM), a Capsule Network (CN), a Kohonen Network (KN), and an Attention Network (AN).

[0065] According to an exemplary embodiment of the present disclosure, the processor may be configured to perform a process for generating a CNN (Convolution Neural Network) such as GoogleNet, AlexNet, VGG Network, Region with Convolution Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restrcted Boltzman Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA for natural language processing, Text Analysis, Dialog System, GPT-3, GPT-4, Visual Analytics for vision processing, Visual Understanding, Video Synthesis, ResNet for data intelligence, Anomaly Detection, Prediction, Time-Series Forecasting, Various artificial intelligence structures and algorithms, including optimization, recommendation, and data creation, can be utilized, but are not limited thereto. Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0066] FIG. 1 is a schematic diagram of a factory design tool providing system according to an embodiment of the present disclosure.

[0067] Referring to FIG. 1, a factory design tool providing system (1) according to an embodiment of the present disclosure is performed by a server (100), and the server (100) provides a factory design tool service.

[0068] The factory design tool providing system (1) according to the embodiment of the present disclosure can provide a factory design tool in web form using XR Web 3D technology.

[0069] The server (100) provides a service to a terminal (200) of a user who has accessed the server (100) through a communication network, and provides a tool that allows the user to design a target factory that he or she wishes to design from the terminal (200).

[0070] At this time, the server (100) provides a service based on the web or app, receives and inputs various control signals through a user interface, and operates a program according to the control signals to reflect the design information of the target factory on the layout and display it on the screen of the terminal (200).

[0071] And, when the design of the target factory is completed according to the control signal received from the terminal (200), the server (100) can output a 2D or 3D drawing (300) of the target factory as a result.

[0072] FIG. 2 is a diagram illustrating a representative effect of a factory design tool providing system according to an embodiment of the present disclosure.

[0073] Referring to FIG. 2, the factory design tool providing system (2) according to an embodiment of the present disclosure provides a web- or app-based factory design tool, enabling users to design more easily and work more quickly than before, while also providing CSG function linkage and single-system collaborative design effects. Furthermore, by providing this service, the system (2) facilitates the utilization and analysis of design data.

[0074] Figure 3 is a drawing illustrating the factory configuration concept.

[0075] Referring to Fig. 3, a factory configuration diagram (3) is illustrated, and the server (100) provides a function for designing a production line (production, route, inspection, detection, packaging) through a production line editor service. In addition, the server (100) provides a function for designing various process lines of the factory through a Building Maker service.

[0076] FIG. 4 is a diagram illustrating a factory operation simulation service provision system in an embodiment of the present disclosure.

[0077] Referring to FIG. 4, in the embodiment of the present disclosure, the system (4) can implement a digital twin for a real world factory.

[0078] More specifically, the system (1) uses a data set manager to input manufacturing site process data, SCM (Supply Chain Management) data, and APS (Advanced Planning and Scheduling) data according to conditions.

[0079] In addition, the system (1) can apply data flow by performing 2D and 3D simulations in a virtual space based on data input through the data mapping manager.

[0080] Next, the system (4) performs module linkage through the Real-META virtual equipment editor and layout maker, and applies process optimization simulation through the AI ​​analysis data linkage module, thereby implementing a virtual digital twin for the factory.

[0081] According to an embodiment, the factory operation simulation service providing device is configured to include a server device and can operate as a server (100) capable of providing a factory operation simulation service.

[0082] That is, the server (100) can provide a factory design tool that can design a factory, as well as a service that performs a simulation of operating a factory.

[0083] FIG. 5 is a block diagram of a factory design tool providing server according to an embodiment of the present disclosure.

[0084] A server (100) according to an embodiment of the present disclosure includes a control module (110), a communication module (120), a storage module (130), a data management module (140), an editor module (150), a layout maker module (160), a simulation module (170), a display module (180), and an artificial intelligence model (190).

[0085] However, in some embodiments, the server (100) may include fewer or more components than those illustrated in FIG. 5.

[0086] The control module (110) includes at least one process.

[0087] The processor may be implemented as a storage module that stores data regarding an algorithm for controlling the operation of components within the device or a program that reproduces the algorithm, and at least one processor that performs the aforementioned operations using the data stored in the storage module. In this case, the storage module and the processor may be implemented as separate chips. Alternatively, the storage module and the processor may be implemented as a single chip.

[0088] Additionally, the processor may control any one or a combination of the components described above to implement various embodiments of the present disclosure described in the drawings below on the device.

[0089] In addition to application-related operations, the processor can typically control the overall operation of the device. The processor processes signals, data, and information input or output through the components discussed above, or runs applications stored in storage modules, thereby providing or processing appropriate information or functions to the user.

[0090] Additionally, the processor may control at least some of the components of the device to run an application program stored in the storage module. Furthermore, the processor may operate at least two or more of the components included in the device in combination to run the application program.

[0091] A processor may be implemented as one or more processors. Hereinafter, even if a processor is expressed as singular, it may be considered plural. A processor may control the configurations of a server. A processor may refer to a data processing device embedded in hardware that has a physically structured circuit to perform a function expressed by a code or instruction included in a program. As such, a processor is an example of a data processing device embedded in hardware, and may encompass processing devices such as a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), or a field programmable gate array (FPGA), but the scope of the present invention is not limited thereto. The processor may separately include a learning processor for performing artificial intelligence operations, or may include a learning processor on its own.

[0092] In various embodiments, the processor may include one or more of a central processing unit (CPU), an application processor (AP), or a communication processor (CP). At least a portion of the processor may be hardware capable of accessing memory and performing functions related to instructions stored in the memory.

[0093] The communication module (120) may include one or more modules that connect the server to one or more networks.

[0094] The communication module (120) may include one or more components that enable communication with an external device, and may include, for example, at least one of a broadcast reception module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0095] The wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as a Universal Serial Bus (USB), a High Definition Multimedia Interface (HDMI), a Digital Visual Interface (DVI), RS-232 (recommended standard 232), power line communication, or plain old telephone service (POTS).

[0096] The wireless communication module may include a wireless communication module that supports various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G, in addition to a WiFi module and a Wireless Broadband module.

[0097] The wireless communication module may include a wireless communication interface including an antenna and a transmitter for transmitting communication signals. Furthermore, the wireless communication module may further include a signal conversion module that modulates a digital control signal output from the processor through the wireless communication interface into an analog wireless signal under the control of the processor.

[0098] The short-range communication module is for short-range communication, and can support short-range communication using at least one of Bluetooth, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra-Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies.

[0099] The communication module (120) may also use the name of the communication interface.

[0100] The communication module (120) can establish communication between the electronic device and an external device. For example, the communication module (120) can communicate with the external device via wireless communication (e.g., Wi-Fi (Wireless Fidelity), Bluetooth, NFC (Near Field Communication), MST (Magnetic Stripe Transmission), etc.) or wired communication.

[0101] The storage module (130) can store data supporting various functions of the device. The storage module can store a number of application programs (or applications) running on the device, data for the operation of the device, and commands. At least some of these application programs may exist for the basic functions of the device. Meanwhile, the application programs can be stored in the storage module, installed on the device, and driven by the processor to perform operations (or functions).

[0102] The storage module (130) can store data supporting various functions of the device, programs for the operation of the processor, input / output data (e.g., music files, still images, moving images, etc.), and a plurality of application programs (or applications) run on the device, data for the operation of the device, and commands. At least some of these application programs can be downloaded from an external server via wireless communication.

[0103] The storage module (130) may include at least one type of storage medium among a flash memory type, a hard disk type, an SSD (Solid State Disk type), an SDD (Silicon Disk Drive type), a multimedia card micro type, a card type memory (e.g., an SD or XD storage module, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. In addition, the storage module may be a database that is separate from the device but is connected by wire or wirelessly.

[0104] Memory can be electrically connected to a processor and store at least one piece of code executed by the processor. Memory can collectively refer to various types of storage devices. Memory can store information necessary for performing computations using artificial intelligence, machine learning, and artificial neural networks.

[0105] Memory can store various learning models. Learning models stored in memory can infer output values ​​for new input data other than the training data, and these inferred values ​​can be used as the basis for decisions regarding certain actions. Learning models stored in memory can be trained based on label information, and various backpropagation algorithms can be applied to ensure that the loss function corresponds to the target value to improve learning accuracy.

[0106] The data management module (140) inputs manufacturing site process data, data related to SCM (Supply Chain Management) and APS (Advanced Planning and Scheduling) required to perform an artificial intelligence-based simulation of a factory into a first virtual factory model based on a digital twin of the factory, performs a simulation, and obtains output values ​​based on the simulation results. In addition, the data management module (140) can visualize the simulation results of the first virtual factory model in a virtual space based on the obtained output values.

[0107] More specifically, the data management module (140) may include a data set manager module, a data mapping manager module, and a data linkage module.

[0108] The data set manager module can input factory manufacturing process data, SCM (Supply Chain Management) data, and APS (Advanced Planning and Scheduling) data according to conditions.

[0109] The Data Mapping Manager module can perform 2D and 3D simulations in virtual space based on data entered through the Data Mapping Manager.

[0110] Additionally, the data mapping manager module can be utilized as a node-based data mapping tool.

[0111] The data linkage module can link manufacturing data that has undergone AI-based analysis on manufacturing process data, SCM data, and APS data.

[0112] Additionally, the data linkage module can visualize the factory's manufacturing-related data in 2D and 3D formats based on the analyzed data, and specifically, can design a digital twin in virtual space.

[0113] The editor module (150) provides a function to edit virtual equipment through the UI provided in the device (100).

[0114] Additionally, the editor module (150) can optimize and register optimized realistic 3D facility data. The editor module (150) can utilize 3D scan data of collected factory facility data.

[0115] The layout maker module (160) can register virtual factory space data extracted based on collected factory space data and place virtual equipment in a virtual factory.

[0116] Additionally, the layout maker module (160) can be utilized as a virtual factory and facility layout tool to perform simulations such as production optimization.

[0117] Through the configuration of the layout maker module (160) as described above, it is possible to conduct a simulation under the same conditions as the target factory, as well as to change various options and conditions to perform a simulation and check options and conditions that can optimize the factory operation and factory process.

[0118] The simulation module (170) can apply the manufacturing data stream to at least one of the editor module (150) and the layout maker module (160).

[0119] The simulation module (170) can perform, save, and export process optimization and SCM, APS-related simulations of the factory in conjunction with the data management module (140).

[0120] The control module (110) can operate cross-platform by controlling the communication module (120). Specifically, the control module (110) can provide a real-time data synchronization network function between heterogeneous devices through the communication module (120), thereby providing a multi-user access function for real-time collaboration and decision-making.

[0121] FIG. 3 is a drawing illustrating a detailed simulation structure diagram (3) of a server according to an embodiment of the present disclosure.

[0122] Referring to FIG. 3, a server (100) according to an embodiment of the present disclosure constructs a manufacturing big data warehouse by preprocessing various data stored in a manufacturing big data storage, and thereby performs sales management, control chart analysis, cluster analysis, time series analysis, regression analysis, decision tree, artificial neural network, and optimization, thereby providing at least one service among a corporate level decision support service, a factory level decision support service, a process level decision support service, and a facility level decision support service.

[0123] In addition, the server (100) according to the embodiment of the present disclosure provides a heterogeneous, multi-protocol supporting industrial gateway and can systematically collect various manufacturing big data required for each service.

[0124] The display module (180) can visually output the design (design information) of a factory designed on a layout through a user interface according to a control signal received from the terminal (300).

[0125] The artificial intelligence model (190) may be learned from event occurrence history and result data according to event occurrence according to the operation of multiple actual factories.

[0126] The artificial intelligence model (190) may be trained on how to design a factory.

[0127] The artificial intelligence model (190) can generate a factory design according to the type of factory process and the type of output to be produced.

[0128] The artificial intelligence model (190) may be trained on how to design a command prompt.

[0129] In the embodiment of the present disclosure, various models such as a factory design design model, a command prompt writing model, an explainable artificial intelligence model, and a generative model can be used as the artificial intelligence model (190). The artificial intelligence model (190) can be stored and used on a server, stored on a separate cloud server, or an artificial intelligence model (190) provided by an external server can be used.

[0130] FIG. 6 is a flowchart of a method for providing a factory design tool according to an embodiment of the present disclosure.

[0131] Referring to FIGS. 6 and 7, the operation process of the factory design tool providing server (100) according to the embodiment of the present disclosure will be described.

[0132] Figure 7 is a diagram illustrating a server generating design information for a target factory using an artificial intelligence model.

[0133] The control module (110) displays a list of configurations that match the process of the target factory. (S610)

[0134] The storage module (130) stores a two-dimensional or three-dimensional model for each of a plurality of first configurations used in the factory process, a dataset of the factory layout, a process flow template for each process of the factory, and information on each process step. In this case, the plurality of first configurations include equipment and materials for performing the process.

[0135] The control module (110) displays a list of at least one second configuration that matches the process of the target factory that the user wishes to design among a plurality of first configurations.

[0136] At this time, the control module (110) can receive at least one type of process that the user wants to perform in the target factory that the user wants to design from the input unit or the user's terminal (300), and based on this, can select a configuration that matches the target factory from among the first configurations and output it through the user interface.

[0137] This has the effect of allowing users to skip the process of having to select the equipment they need from a list of numerous equipment.

[0138] The control module (110) displays a three-dimensional model of the configuration selected from the list on the layout. (S620)

[0139] The control module (110) displays a three-dimensional model of a second configuration selected by the user from a list displayed through the user interface in S610 on a layout.

[0140] At this time, the control module (110) can control the second configuration to be displayed at the corresponding location when a specific second configuration is displayed on the layout by dragging and dropping from the list displayed on the user interface.

[0141] The control module (110) automatically arranges the path of equipment and materials on the layout using the process flow template. (S630)

[0142] The control module (110) calculates the distance between processes and space utilization to perform placement. (S640)

[0143] The control module (110) can automatically arrange the path of equipment and materials on the layout using a process flow template based on the process set for the target factory.

[0144] At this time, the control module (110) can perform the arrangement by calculating the distance between processes and space utilization based on the map data of the target factory and the set process.

[0145] The control module (110) can calculate space utilization by considering the size, type, and number of workers of the equipment used in the process. In this case, the control module (110) can calculate space utilization by considering the area of ​​the target factory and the size of the space where the process is performed.

[0146] The control module (110) can perform relocation when the distance between processes becomes less than a safe distance. The control module (110) can perform relocation when space utilization does not meet a preset standard.

[0147] In addition, the control module (110) can receive map data for the factory during the process of designing the factory design and request that the drawing size to be designed be specified.

[0148] Additionally, the control module (110) may request to set up an exterior wall for the design planning of the factory.

[0149] The control module (110) can provide the following functions through the factory design design tool.

[0150] The control module (110) can provide drawing and grid, saving, loading, production line site setting, line drawing, view switching (2D or 3D switching), camera viewpoint control, memo insertion function, virtual driving function, grid size setting function, etc.

[0151] The control module (110) creates a virtual factory model for the target factory based on the configurations arranged on the layout. (S650)

[0152] The control module (110) performs process simulation for the target factory using a virtual factory model. (S660)

[0153] The control module (110) can perform process simulation for a target factory using a virtual factory model based on input / received variables. At this time, the variables may include at least one of temperature, humidity, process speed, equipment operating time, maintenance cycle, and energy consumption.

[0154] In addition, any variable required to perform a simulation using a virtual factory model can be applied.

[0155] In addition, the control module (110) can calculate at least one of process completion time, process speed, daily production volume, energy consumption, and cost based on the results of the process simulation.

[0156] In one embodiment, the control module (110) can control the control module to cause at least one preset event to occur while performing a process simulation according to a preset event occurrence probability.

[0157] At this time, the event may include at least one of a change in production speed, an occurrence of equipment failure, an occurrence of a material shortage, a change in temperature, and a change in humidity.

[0158] The control module (110) can obtain at least one of the following based on the results of the process simulation performed when an event occurs: changes in the production schedule, changes in the defect rate of the process output, changes in the quality of the process output, delays in shipment, changes in inventory, occurrence and location of bottlenecks in facility operation, changes in energy consumption, changes in costs, and occurrences of accidents.

[0159] In one embodiment, the server (100) can input event occurrence history and result data according to event occurrence according to the operation of multiple actual factories into an artificial intelligence model to train the model.

[0160] The control module (110) can generate events and obtain the results of the process simulation while performing process simulation through a virtual factory using an artificial intelligence model.

[0161] In addition, when an abnormal result that deviates from a preset standard is obtained among the acquired process simulation results, the control module (110) uses an artificial intelligence model to determine whether the abnormal result is a design error of the virtual factory or a simulation error, and provides a notification, and can store a log record and notification details of the abnormal result.

[0162] In one embodiment, the control module (110) inputs manufacturing site process data, data related to SCM (Supply Chain Management) and APS (Advanced Planning and Scheduling) necessary for performing an artificial intelligence-based simulation for a target factory into a first virtual factory model created based on a digital twin for the target factory using a factory design tool, performs a simulation, and obtains an output value based on the simulation performance result.

[0163] In addition, the control module (110) can visualize the simulation results of the first virtual factory model in a virtual space based on the acquired output values.

[0164] In one embodiment, the control module (110) may select at least one major facility among the facilities of the target factory based on the process type and facility type of the target factory, and provide a dashboard that can check the status of the major facility and the process status of the target factory.

[0165] In addition, the control module (110) can obtain a preset period-by-period result value for at least one indicator based on the simulation result.

[0166] At this time, at least one indicator includes at least one of production volume, defect rate, delivery volume, power usage, material consumption, and material purchase volume.

[0167] In one embodiment, the server (100) may use a factory design model learned based on map data of multiple factories, process-specific space partition data of multiple factories, equipment layout data of multiple factories, and process evaluation scores of multiple factories.

[0168] The control module (110) uses a factory design model to divide the space of the target factory by the process being performed in the target factory based on the map data of the target factory and the process type of the target factory, and places equipment corresponding to each divided space in consideration of the safety distance between equipment and the process speed, thereby displaying a virtual factory model for the target factory on the layout.

[0169]

[0170] *In one embodiment, the control module (110) provides a plurality of questions to obtain information necessary for designing a target plant, and receives user responses to the plurality of questions.

[0171] In addition, the control module (110) can input the received response into an artificial intelligence model that has learned how to write a command prompt, and request the user to generate a command prompt for inputting requirements for designing a target factory into a generative model.

[0172] Next, the control module (110) inputs command prompts obtained from the artificial intelligence model into the generative model to acquire design information for the target factory. Furthermore, the control module (110) can display the design of the target factory on a layout based on the acquired design information.

[0173] At this time, multiple questions include at least one of the following: area information of the target factory, at least one type of product to be produced at the target factory, the type and number of equipment to be installed at the target factory, at least one type of process to be performed at the target factory, the degree of automation of the target factory, the daily production volume of the target factory, the number of employees at the target factory, power consumption, and budget.

[0174] In one embodiment, when map data of a target factory is received, the control module (110) can generate area information based on the received map data.

[0175] In one embodiment, the control module (110) can compare the area information and the number of equipment to be installed in the target factory to determine whether installation is possible, and can compare the daily production volume and the number of equipment to be installed in the target factory with the number of employees to determine whether implementation is possible.

[0176] In one embodiment, the control module (110) calculates the spacing between facilities based on the area information of the target factory, the type and number of facilities to be installed in the target factory, and the daily production volume. However, if the calculated spacing violates the minimum safety distance set for the facility, a notification requesting a setting change can be generated.

[0177] In one embodiment, the control module (110) can receive the user's requirements for the target factory that the user wants to design through the communication module (120).

[0178] Then, the control module (110) inputs the received requirements into an explainable AI (XAI) and requests the creation of a command prompt for inputting the requirements into a generative model. Next, the control module (110) inputs the command prompt obtained from the explainable AI into the generative model to request design information of the target factory. Then, the control module (110) can display the design information for the target factory obtained from the generative model on the layout.

[0179] In one embodiment, the control module (110) can generate a first virtual factory model optimized for the target factory by learning a common virtual factory model that has been learned in advance based on the type of process, process process, and process singularity performed in the target factory based on information about the target factory using a transfer learning technique.

[0180] In one embodiment, the control module (110) can obtain a first analysis result based on SCM data after performing a simulation, and can obtain a second analysis result based on APS data after performing a simulation.

[0181] At this time, the first analysis result may include at least one of demand forecasting information, appropriate inventory optimization information, and material requirement forecasting information, and the second analysis result may include at least one of lead time information, delivery schedule analysis information, and production schedule planning information.

[0182] FIG. 8 is a diagram illustrating a detailed simulation structure of a server according to an embodiment of the present disclosure.

[0183] Figure 9 is a diagram illustrating a process for acquiring three-dimensional data on the process of a target factory and implementing virtualization thereof.

[0184] Figure 10 is a diagram illustrating the microstructure of a recurrent neural network.

[0185] Figure 11 is a diagram illustrating the sensitivity analysis process.

[0186] Figure 12 is a diagram illustrating tracking of cumulative reward and reward histogram for each episode to derive value chain optimization values ​​in a deep reinforcement learning network.

[0187] Figure 13 is a diagram illustrating the connection between the SCM, APS system and the server.

[0188] Figure 14 is a diagram illustrating a demand forecasting AI analysis process based on manufacturing data.

[0189] Below, with reference to FIGS. 8 to 14, the server (100) will create a virtual factory model and perform various simulations using the same in more detail.

[0190] Referring to FIG. 8, this is a drawing illustrating a detailed simulation structure diagram (8) of a server according to an embodiment of the present disclosure.

[0191] Referring to the structural diagram (8) of FIG. 8, the server (100) builds a manufacturing big data warehouse by preprocessing various data stored in a manufacturing big data storage, and through this, performs sales management, control chart analysis, cluster analysis, time series analysis, regression analysis, decision tree, artificial neural network, and optimization, thereby providing at least one service among a corporate level decision support service, a factory level decision support service, a process level decision support service, and a facility level decision support service.

[0192] In addition, the factory operation simulation service providing device (100) according to the embodiment of the present disclosure provides a heterogeneous, multi-protocol supporting industrial gateway and can systematically collect various manufacturing big data required for each service.

[0193] The control module (110) receives process data from the manufacturing site and data related to SCM and APS necessary to perform artificial intelligence-based simulation for the target factory.

[0194] The control module (110) inputs the acquired data into the first virtual factory model based on the digital twin of the target factory to perform a simulation.

[0195] The control module (110) obtains output values ​​based on the simulation performance results.

[0196] The simulation results of the first virtual factory model are visualized in a virtual space based on the output values ​​obtained from the control module (110).

[0197] In one embodiment, the control module (110) may provide real-time collaboration and communication capabilities between users connecting through different devices or different operating systems via the communication module.

[0198] Figure 9 is a drawing illustrating a process (9) for acquiring three-dimensional data on the process of a target factory and implementing virtualization thereof.

[0199] Referring to FIG. 9, the control module (110) can obtain three-dimensional data on the process of the target factory through the communication module (120) and implement virtualization thereof.

[0200] In one embodiment, the control module (110) receives 3D scanned data (510) via a lidar. Then, the control module (110) can optimize the point cloud (520) by generating the point cloud (520) based on the scanned data and then removing noise (530).

[0201] Next, the control module (110) generates a three-dimensional model based on the optimized point cloud, applies a physically based rendering (PBR Material, 540) material to the three-dimensional model, applies animation (550) to the three-dimensional model to generate a virtual space corresponding to the target factory, and performs a simulation to thereby obtain a solution (560).

[0202] Figure 10 is a drawing illustrating a recurrent neural network microstructure (10).

[0203] Referring to FIG. 10, the control module (110) can analyze the location of equipment and the movement of workers within the factory and perform a simulation.

[0204] The control module can build a CPS environment by digitally transforming the actual collected field data.

[0205] The control module (110) can perform facility condition environment analysis and verification to establish an optimal process environment, and can perform facility location and worker movement analysis and verification to establish an optimal process environment.

[0206] In addition, the control module (110) can analyze and build a plan to be introduced into the solution by considering variable factors such as process-to-process transfer time and worker movement time through verification.

[0207] The control module (110) can analyze the location of equipment and the movement of personnel within the factory and perform simulations.

[0208] Referring to FIG. 10, the control module (110) can perform a 'Finite Difference method' simulation such as FTCS, Crank-Nicolson, etc. to derive the total lead time, quality value of output, etc. in each simulation route after comprehensively modeling various costs such as lead time and goods consumed in each section.

[0209] In addition, the control module (110) can appropriately reflect the minute factors for the characteristics and process variables of each facility and perform fine adjustments to the network components to prevent the vanishing gradient of the network itself.

[0210] In one embodiment, the control module (110) may perform a simulation based on the finite difference method (FDM) by considering the location of equipment and the movement path of workers within the target factory. In this case, the FDM includes the Forward Time Centered Space (FTCS) method and the Crank-Nicolson method.

[0211] Additionally, the control module (110) can derive at least one process tuning condition to minimize the total processing time of the production process based on the simulation results.

[0212] In one embodiment, the control module (110) can fine tune the virtual factory model to match the target factory based on information of the target factory.

[0213] Information on the target factory may include at least one of map data of the target factory, information on the process performed at the target factory, the type of equipment used at the target factory, sensing data of the equipment, and data scanned according to the process performed at the target factory.

[0214] In addition, the control module (110) can identify equipment in the scanned data through a marker equipped on the equipment used in the target factory.

[0215] The control module (110) can calculate the location of the equipment within the target factory, the movement route and movement time of the workers, and the transfer time between processes based on the map data of the target factory, the information on the process, and the scanned data.

[0216] In addition, the control module (110) can input information and calculated results of the target factory into the first virtual factory model to perform a simulation, identify at least one improvement based on the results of the simulation, and calculate an improvement effect score for each identified improvement.

[0217] In one embodiment, the control module (110) can calculate the location of the equipment within the target factory, the movement route and movement time of the workers, and the transfer time between processes based on the map data of the target factory, the information on the process, and the scanned data.

[0218] In addition, the control module (110) can input information and calculated results of the target factory into the first virtual factory model to perform a simulation, identify at least one improvement based on the results of the simulation, and calculate an improvement effect score for each identified improvement.

[0219] At this time, the control module (110) can perform the above process based on the mathematical expression 1 below.

[0220]

[0221] ΔTprocess = Difference in process time after improvement

[0222] ΔDpath = The difference in the distance traveled by workers after the improvement

[0223] ΔTtransfer = Difference in material transfer time between processes after improvement

[0224] (w1, w2, w3: Weights set for each item according to the process of the target factory)

[0225] In one embodiment, the device (100) may utilize a common virtual factory model.

[0226] For example, the device (100) may store a common virtual factory model that is specialized and learned in advance according to the process field, and when information on the target factory is received, the common virtual factory model may be learned based on this to generate a first virtual factory model specialized / optimized for the target factory.

[0227] In one embodiment, the control module (110) can generate a first virtual factory model optimized for the target factory by learning a common virtual factory model that has been learned in advance based on the type of process, process process, and process singularity performed in the target factory based on information about the target factory using a transfer learning technique.

[0228] Figure 11 is a diagram illustrating a sensitivity analysis process (11).

[0229] The device (100) can build an APS that integrates and analyzes field data (equipment, process) and supply chain data (order, order, BOM, delivery date, lead time, etc.).

[0230] The control module (110) can perform quadratic convex optimization after configuring a convex affine combination for the entire supply chain network in order to perform an integrated analysis of the entire supply chain network. At this time, the control module (110) can perform optimization with time cost, such as lead time, as an objective function and a quality maintenance threshold as a minimum constraint.

[0231] In addition, the control module (110) can derive optimal constraint conditions by comprehensively considering the Karush-Kuhn-Tucker condition, etc. after considering and analyzing various duality problems such as Lagrange duality and Strong / weak duality while performing the redundancy calculation to derive better results.

[0232] In addition, the control module (110) can perform a preliminary analysis on perturbation and sensitivity to ensure the stability of optimization and simulation for the entire supply chain to be performed in the final stage.

[0233] Additionally, the control module (110) can conduct an actual experience using XR in an environment where the constructed APS plan scenario has been digitally transformed, thereby verifying variable factors for a solution that has been analyzed only numerically.

[0234] Figure 12 is a diagram illustrating a method (12) for tracking cumulative reward and reward histogram for each episode to derive a value chain optimization value in a deep reinforcement learning network.

[0235] Referring to FIG. 12, the control module (110) can build an APS system to derive horizontal value chain optimization.

[0236] The control module (110) can build an APS system capable of deriving horizontal value chain optimization by integrating previously performed optimal process CpK calculation and flow scenario.

[0237] The control module (110) can configure a 'Deep reinforcement learning' learning network based on reinforcement learning to derive horizontal value chain optimization.

[0238] The control module (110) can track cumulative reward and reward histogram for each episode to derive a value chain optimization value in a deep reinforcement learning network.

[0239] Figure 13 is a drawing illustrating the linkage between the SCM, APS system and the factory operation simulation service provider (13).

[0240] In one embodiment, the control module (110) can build a linkage system between SCM, APS DB / server and 'Real-META' digital twin.

[0241] In one embodiment, the control module (110) may implement a digital twin for a target factory in a digital twin server based on the first virtual factory model created, transmit / collect process data of equipment used in the target factory to an OPC UA server, transmit data collected in the OPC UA server to the digital twin server through communication with an OPC client, and control virtual equipment data of the first virtual factory model in the digital twin to be driven according to equipment sensor data of the target factory received through the communication module (120).

[0242] For example, the control module (110) can obtain a first analysis result based on SCM data after performing a simulation, and can obtain a second analysis result based on APS data after performing a simulation.

[0243] At this time, the first analysis result includes demand forecast information, appropriate inventory optimization information, and material requirement forecast information, and the second analysis result includes lead time information, delivery schedule analysis information, and production schedule planning information.

[0244]

[0245] *For example, the control module (110) can derive improvements for multiple items for improving the operation and process of the factory based on the simulation results, calculate an expected improvement score when the derived improvements are improved for each of the multiple items, and set the improvement priority of the multiple items based on the derived improvement scores.

[0246] For example, if all improvements derived from the device (100) are provided together, it may be practically impossible for the target plant manager to simultaneously reflect multiple improvements. In such cases, improvements can be provided by setting priorities to address these issues.

[0247] In one embodiment, the control module (110) can configure an SCM database (DB) based on the manufacturer's order and production plan information, logistics traffic and location information, and the supplier's production plan information.

[0248] In one embodiment, the control module (110) can store data such as product BOM, LOT reference information, and schedule plan in the APS database (DB) and use it as reference information.

[0249] In one embodiment, the control module (110) can design a server communication protocol and build a communication layer for linking an SCM database (DB) and an APS database (DB).

[0250] In one embodiment, the control module (110) can design communication rules and link DB for each device (Mobile, Smart tab, PC, VR HMD, MR Glass).

[0251] In one embodiment, the control module (110) can visualize SCM, APS linkage data in at least one of 2D or 3D.

[0252] In one embodiment, the control module (110) can classify SCM and APS data by item and develop visualizations and scripts according to the item characteristics.

[0253] In one embodiment, the control module (110) can visualize graph types (circles, bars, broken lines, etc.) and histogram charts.

[0254] In one embodiment, the control module (110) can link and visualize relational network (SNA) and distributed node data.

[0255] In one embodiment, the control module (110) can output data by distinguishing between a fixed interface and a selective interface.

[0256] Figure 14 is a diagram illustrating a manufacturing data-based demand forecasting AI analysis process (14).

[0257] Referring to FIG. 14, the control module (110) can perform a data collection process, a data pre-processing procedure process, and a result derivation process.

[0258] In one embodiment, the control module (110) may apply artificial intelligence techniques such as ARIMA, ANN, SVR, RNN, and LSTM to predict patterns such as demand patterns.

[0259] In addition, the control module (110) can construct a model by configuring a learning dataset based on time series inventory data, taking seasonal factors and temporal variability into consideration.

[0260] In addition, the control module (110) can perform fine adjustments to the Gate Parameter in order to detect and analyze minute elements in the order and purchase data in order to further enhance the existing APS.

[0261] In addition, the control module (110) can derive at least one of demand forecasting, optimal order quantity, customer need identification, inventory management, and customer demand response in the conclusion derivation process.

[0262] In one embodiment, the control module (110) can perform transfer learning on an already established APS system to expand it to a similar company supply chain network and conduct APS-based scenario analysis on the entire vendor.

[0263] The method according to one embodiment of the present disclosure described above can be implemented as a program (or application) and stored in a medium to be executed in combination with a hardware server.

[0264] The above-mentioned program may include codes coded in a computer language, such as C, C++, JAVA, or machine language, that can be read by the computer's processor (CPU) through the computer's device interface, so that the computer reads the program and executes the methods implemented as the program. Such codes may include functional codes related to functions that define the functions necessary to execute the methods, and may include control codes related to execution procedures necessary for the computer's processor to execute the functions according to a predetermined procedure. In addition, such codes may further include memory reference-related codes that indicate where in the computer's internal or external memory (address address) additional information or media required for the computer's processor to execute the functions should be referenced. In addition, if the computer's processor needs to communicate with any other remote computer or server in order to execute the functions, the codes may further include communication-related codes that indicate how to communicate with any other remote computer or server using the computer's communication module, and what information or media should be sent and received during the communication.

[0265] The storage medium refers to a medium that permanently stores data and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, examples of storage media include, but are not limited to, ROM, RAM, CD-ROM, magnetic tape, floppy disks, and optical data storage devices. In other words, a program can be stored on various storage media on various servers accessible by a computer or on various storage media on a user's computer. Furthermore, the media can be distributed across network-connected computer systems, allowing computer-readable code to be stored in a distributed manner.

[0266] The steps of a method or algorithm described in connection with the embodiments of the present disclosure may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in a random access memory (RAM), a read only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, a hard disk, a removable disk, a CD-ROM, or any other form of computer-readable recording medium well known in the art to which the present disclosure pertains.

[0267] While the embodiments of the present disclosure have been described with reference to the attached drawings, those skilled in the art will appreciate that the present disclosure can be implemented in other specific forms without altering the technical spirit or essential features thereof. Therefore, the embodiments described above should be understood to be illustrative in all respects and not restrictive.

[0268] [Explanation of symbols]

[0269] 100: Server

[0270] 110: Control module 120: Communication module

[0271] 130: Storage Module 140: Data Management Module

[0272] 150: Editor Module 160: Layout Maker Module

[0273] 170: Simulation Module 180: Display Module

[0274] 190: Artificial Intelligence Model

Claims

1. Regarding the server that provides the factory design tool, A storage module storing a three-dimensional model for each of a plurality of first configurations used in the process of the factory, a dataset of the factory layout, a process flow template for each process of the factory, and information on each process step; -the plurality of first configurations include equipment and materials for performing the process- A control module is included that displays a list of at least one second configuration that matches the process of a target factory that the user wants to design among the plurality of first configurations, and displays a three-dimensional model of the second configuration selected from the displayed list and dragged and dropped onto the layout. The above control module, Automatically arrange the path of equipment and materials on the layout using the process flow template based on the process set for the target factory, and perform the arrangement by calculating the distance between processes and space utilization based on the map data of the target factory and the set process. A virtual factory model for the target factory is created based on the configurations arranged on the above layout, A process simulation for the target factory is performed using the virtual factory model according to the input variables, and the variables include temperature, humidity, process speed, equipment operation time, maintenance cycle, and energy consumption. Calculate the process completion time and cost based on the results of the above process simulation. Server providing factory design tools.

2. In paragraph 1, The above control module, Controlling so that at least one preset event occurs during the process simulation according to a preset event occurrence probability, -the event includes at least one of a change in production speed, an occurrence of a facility failure, an occurrence of a material shortage, a change in temperature, and a change in humidity- Based on the results of the above process simulation performed when the above event occurs, it is characterized in that changes in the production schedule, changes in the defect rate of the process output, changes in the quality of the process output, delays in shipment, changes in inventory, occurrence of bottlenecks in facility operation and their locations, changes in energy consumption, changes in costs, and occurrences of accidents are obtained. Server providing factory design tools.

3. In paragraph 2, The above factory design tool providing server is, Event occurrence history and result data according to the operation of multiple actual factories are input into the artificial intelligence model and trained. While performing the process simulation through the virtual factory using the artificial intelligence model, an event is generated and the result of the process simulation is obtained. In the case where an abnormal result that deviates from the preset standard is obtained among the obtained process simulation results, the artificial intelligence model is used to determine whether the abnormal result is a design error or a simulation error of the virtual factory and provide a notification, and the log record of the abnormal result and the notification details are stored. Server providing factory design tools.

4. In paragraph 3, The above control module, In order to perform the artificial intelligence-based simulation for the above target factory, the manufacturing site process data, data related to SCM (Supply Chain Management) and APS (Advanced Planning and Scheduling) required for the above target factory are input into the first virtual factory model created based on a digital twin for the above target factory using the above factory design tool to perform the simulation, and the output value is obtained based on the simulation performance results. Characterized in that the simulation results of the first virtual factory model are visualized in a virtual space based on the acquired output values. Server providing factory design tools.

5. In paragraph 1, The above control module, Based on the process type and equipment type of the target factory, at least one major equipment is selected from the equipment of the target factory, and a dashboard is provided that can check the status of the major equipment and the process status of the target factory. Based on the above simulation results, obtain a preset period-by-period result value for at least one indicator, At least one of the above indicators includes production volume, defect rate, delivery volume, power usage, material consumption and material purchase volume. Server providing factory design tools.

6. In paragraph 1, The above server, A factory design model learned based on map data of multiple factories, process-specific space partition data of the multiple factories, equipment layout data of the multiple factories, and process evaluation scores of the multiple factories is included. Using the above factory design model, the space of the target factory is divided into sections according to the processes performed in the target factory based on the map data of the target factory and the process types of the target factory, and the equipment corresponding to each of the divided spaces is arranged while considering the safety distance between the equipment and the process speed, thereby displaying a virtual factory model for the target factory on the layout. Server providing factory design tools.

7. In paragraph 1, The above control module, Provide multiple questions to obtain the information required for designing the above target plant, Receive the user's answers to the above multiple questions, The method of writing a command prompt is requested to input the received answer into an artificial intelligence model that has learned how to write a command prompt, and to generate a command prompt for the user to input requirements for designing the target plant into a generative model. The command prompt obtained from the above artificial intelligence model is input into the above generative model to obtain design information for the target factory, Characterized in that the design of the target factory is displayed on the layout based on the design information acquired above. Server providing factory design tools.

8. In paragraph 7, The above multiple questions include information on the area of ​​the target factory, at least one type of goods to be produced at the target factory, the type and number of equipment to be installed at the target factory, at least one type of process to be performed at the target factory, the degree of automation of the target factory, the daily production volume of the target factory, the number of employees at the target factory, power consumption, and budget. Server providing factory design tools.

9. In paragraph 8, The above control module, When the map data of the above target factory is received, the area information is generated based on the received map data, Compare the above area information and the number of equipment to be installed in the target factory to check whether installation is possible. It is characterized by comparing the above daily production volume and the number of facilities to be installed in the target factory with the above staff size to check whether implementation is possible. Server providing factory design tools.

10. In paragraph 8, The above control module, A method for calculating the spacing between the facilities based on the area information of the target factory, the type and number of facilities to be installed in the target factory, and the daily production volume, and generating a notification requesting a setting change if the calculated spacing violates the minimum safety distance set for the facility. Server providing factory design tools.

11. In paragraph 1, The above control module, Receive the user's requirements for the target factory that the user wishes to design, Input the above received requirements into an explainable AI (XAI) and request the creation of a command prompt to input the above requirements into a generative model. Requesting design information of the target factory by inputting a command prompt obtained from the above-described AI into the above-described generative model, Characterized in that the design information for the target factory obtained from the generative model is displayed on the layout. Server providing factory design tools.

12. In paragraph 1, The above control module, Based on the information of the target factory, a common virtual factory model that has been learned in advance based on the type of process, process process, and process singularity performed at the target factory is learned using a transfer learning technique, thereby generating a first virtual factory model optimized for the target factory. Server providing factory design tools.

13. In paragraph 4, The above control module, After performing the above simulation, the first analysis result based on the above SCM data is obtained, -the first analysis result includes demand forecast information, appropriate inventory optimization information, and material requirement forecast information- After performing the above simulation, a second analysis result based on the above APS data is obtained, -the second analysis result includes lead time information, delivery schedule analysis information, and production schedule planning information- Server providing factory design tools.

14. In a manner performed by the server, A step of displaying a list of at least one second configuration that matches the process of a target factory that the user wishes to design among a plurality of first configurations used in the process of the factory; A step of displaying a three-dimensional model of a second configuration selected from the above-mentioned list and dragged and dropped onto a layout; A step of automatically arranging the path of equipment and materials on the layout using the process flow template based on the process set for the target factory; A step of performing the layout by calculating the distance between processes and space utilization based on the map data of the target factory and the set process; A step of creating a virtual factory model for the target factory based on the configurations arranged on the above layout; A step of performing a process simulation for the target factory using the virtual factory model according to the input variables; -The variables include temperature, humidity, process speed, equipment operation time, maintenance cycle, and energy consumption- A step of calculating the process completion time and cost based on the results of the above process simulation, The above server, A three-dimensional model for each of the plurality of first configurations, a dataset of the factory layout, a process flow template for each process of the factory, and information on each process step are stored, -the plurality of configurations include equipment and materials for performing the process- How to provide factory design tools 15. A computer-readable recording medium having recorded thereon a computer program for performing the method of Article 14.

Images