KR-102963375-B1 - Apparatus for Generative AI-based Delivery Prediction and Abnormal Situation Response Simulation and Driving Method Thereof, and System

KR102963375B1KR 102963375 B1KR102963375 B1KR 102963375B1KR-102963375-B1

Abstract

The present invention relates to a generative AI-based delivery time prediction and abnormal situation response simulation device, a method for operating the device, and a system. The generative AI-based delivery time prediction and abnormal situation response simulation device according to an embodiment of the present invention may include a storage unit that collects and stores factory data related to production in a manufacturing plant to predict the production delivery time of a product produced in a manufacturing plant and to respond to abnormal situations, and a control unit that analyzes the collected and stored factory data using generative artificial intelligence (AI), calculates the delivery time prediction and delay probability of the product based on the analysis results, automatically generates response scenarios according to the abnormal situation that has occurred when an abnormal situation related to product production occurs, and calculates an optimal schedule related to product production based on the evaluation results of a plurality of automatically generated scenarios.

Inventors

김두석
신동호

Assignees

엠에스이주식회사

Dates

Publication Date: 20260511
Application Date: 20250929

Claims (11)

A storage unit that collects and stores factory data related to production in a manufacturing plant to predict the production delivery time of products produced in a manufacturing plant and to respond to abnormal situations; and A control unit that analyzes the factory data collected and stored above using generative artificial intelligence (AI) to calculate product delivery predictions and delay probabilities based on the analysis results, automatically generates response scenarios according to the abnormal situation when an abnormal situation related to the production of the product occurs, and calculates an optimal schedule related to product production based on the evaluation results of the multiple automatically generated scenarios; The above control unit is, An anomaly response simulation module that automatically generates response scenarios for abnormal situations such as equipment failure, material shortage, or poor quality; and It includes a schedule update module that evaluates the above multiple response scenarios based on preset performance indicators (KPIs) and calculates an optimal schedule based on the evaluation results; The above-mentioned anomaly response simulation module generates scenarios reflecting equipment switching, line distribution, and additional work input as the plurality of response scenarios, and the optimal scenario selected among the plurality of response scenarios is reflected in the schedule update module, a generative AI-based delivery date prediction and anomaly response simulation device.
In paragraph 1, The above control unit is, A generative AI-based delivery prediction and abnormal situation response simulation device further comprising a delivery prediction module that calculates a delivery prediction and delay probability using the generative AI above.
In paragraph 2, The above-mentioned delivery prediction module is a generative AI-based delivery prediction and abnormal situation response simulation device that provides a prompt to a generative AI model to predict the expected completion time for each production batch (LOT) currently in progress and outputs the possibility of delivery delay as a probability value as a prediction result.
delete
In paragraph 2, The above delivery prediction module is a generative AI-based delivery prediction and abnormal situation response simulation device that increases prediction accuracy by reflecting the DQS provided by a data normalization module, which normalizes the collected data and performs a quality evaluation to calculate the Data Quality Index (DQS), as a weight.
A storage unit collects and stores factory data related to the production of a manufacturing plant to predict the production lead time of products produced in a manufacturing plant and to respond to abnormal situations; and The control unit analyzes the collected and stored factory data using generative artificial intelligence (AI) to calculate the product delivery prediction and delay probability based on the analysis results, and automatically generates response scenarios according to the abnormal situation when an abnormal situation related to the production of the product occurs, and calculates an optimal schedule related to product production based on the evaluation results of the multiple automatically generated scenarios; wherein The step of calculating the optimal schedule above is, The abnormal response simulation module automatically generates response scenarios based on abnormal situations such as equipment failure, material shortage, or quality defects; and The schedule update module includes the step of evaluating the automatically generated plurality of corresponding scenarios based on preset performance indicators (KPIs) and calculating an optimal schedule based on the evaluation results; The step of automatically generating the above response scenario is, A method for operating a generative AI-based delivery time prediction and abnormal situation response simulation device, wherein a scenario reflecting equipment switching, line distribution, and additional work input is generated as a plurality of response scenarios, and the optimal scenario selected among the plurality of response scenarios is reflected in the schedule update module.
In paragraph 6, The step of calculating the optimal schedule above is, A method for operating a generative AI-based delivery prediction and abnormal situation response simulation device, further comprising the step of a delivery prediction module calculating a delivery prediction and delay probability using the generative AI.
In Paragraph 7, The step of calculating the above delivery date prediction and delay probability is, A method for operating a generative AI-based delivery time prediction and abnormal situation response simulation device, which provides a prompt to a generative AI model to predict the expected completion time for each production batch (LOT) currently in progress and outputs the possibility of delivery delay as a probability value as a prediction result.
delete
In Paragraph 7, The step of calculating the above delivery date prediction and delay probability is, A method for operating a generative AI-based delivery time prediction and abnormal situation response simulation device, which increases prediction accuracy by reflecting the DQS provided by a data normalization module, which normalizes the collected data and performs a quality evaluation to calculate the Data Quality Index (DQS), as a weight.
A factory equipment device that provides factory data related to the production of a manufacturing plant to predict the production lead time of products produced in a manufacturing plant and to respond to abnormal situations; and A simulation device comprising: analyzing factory data collected from the above-mentioned factory equipment using generative artificial intelligence (AI) to calculate product delivery predictions and delay probabilities based on the analysis results, and automatically generating response scenarios according to the abnormal situation when an abnormal situation related to the production of the above-mentioned product occurs, and calculating an optimal schedule related to product production based on the evaluation results of the multiple automatically generated scenarios; The simulation device comprises a control unit including: an abnormal response simulation module that automatically generates response scenarios for abnormal situations such as equipment failure, material shortage, or quality defects; and a schedule update module that evaluates the plurality of response scenarios based on preset performance indicators (KPIs) and calculates an optimal schedule based on the evaluation results. The above-mentioned anomaly response simulation module generates scenarios reflecting equipment switching, line distribution, and additional work input as the plurality of response scenarios, and the optimal scenario selected among the plurality of response scenarios is reflected in the schedule update module, thereby creating a generative AI-based delivery date prediction and anomaly response simulation system.

Description

Apparatus for Generative AI-based Delivery Prediction and Abnormal Situation Response Simulation and Driving Method Thereof, and System The present invention relates to a generative AI-based delivery date prediction and abnormal situation response simulation device, a method for operating the device, and a system. More specifically, the invention relates to a generative AI-based delivery date prediction and abnormal situation response simulation device, a method for operating the device, and a system that combines real-time production data with generative artificial intelligence to predict delivery delays and provide optimal simulations for responding to abnormal situations (e.g., equipment failure, material shortage, urgent order, etc.), particularly in fields such as production planning and manufacturing scheduling. In multi-product, small-batch production environments, including PCB manufacturing plants, problems frequently occur such as unpredictable events like sudden equipment breakdowns, quality defects, and material shortages; complex delivery constraints; an increase in customized customer orders; and the low responsiveness to real-time changes resulting from existing APS (Advanced Planning & Scheduling) and ERP/MES systems operating on static rules. Consequently, issues such as delivery delays, increased costs, and quality degradation arise, and real-time response is difficult with existing scheduling engines. Accordingly, there is an urgent need to develop a system to improve the aforementioned problems. FIG. 1 is a block diagram showing the overall configuration of a generative AI-based delivery time prediction and abnormal situation response simulation system according to an embodiment of the present invention. FIG. 2 is a flowchart illustrating a schedule update procedure through generative AI-based delivery prediction and abnormal situation response simulation according to an embodiment of the present invention. FIG. 3 is a block diagram illustrating a generative AI analysis procedure using prompt variables and token weights according to an embodiment of the present invention. FIG. 4 is a diagram showing a generative AI-based delivery time prediction and abnormal situation response simulation system according to another embodiment of the present invention. Figure 5 is a block diagram illustrating the detailed structure of the simulation device of Figure 4. Figure 6 is a flowchart showing the operation process of the simulation device of Figure 4. The present invention is not limited to the embodiments described below but can be implemented in various different forms. These embodiments are merely illustrative of the content of the invention and are provided to inform those skilled in the art of the scope of the invention in detail. The present invention is defined only by the scope of the claims. Throughout the specification, the same reference numerals refer to the same components. The embodiments described herein will be described with reference to cross-sectional and/or plan views, which are exemplary illustrations of the invention. In the drawings, the illustrated regions are depicted for the effective description of the technical content. Accordingly, the regions illustrated in the drawings are schematic in nature, and the shapes of the regions illustrated in the drawings are intended to illustrate specific forms of the device regions and are not intended to limit the scope of the invention. Although terms such as first, second, third, etc., have been used to describe various components in the various embodiments of this specification, these components should not be limited by such terms. These terms are used merely to distinguish one component from another. The embodiments described and illustrated herein also include their complementary embodiments. The terms used in the specification are for describing embodiments and are not intended to limit the invention. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. As used in the specification, "comprises" and/or "comprising" do not exclude the presence or addition of one or more other components, steps, actions, and/or elements to the mentioned components, steps, actions, and/or elements. Unless otherwise defined, all terms used in this specification (including technical and scientific terms) may be used in a meaning that is commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise. Hereinafter, the concept of the present invention and embodiments according thereto will be described in detail with reference to the drawings. FIG. 1 is a block diagram showing the overall configuration of a generative AI-based delivery time prediction and abnormal situation response simulation system according