KR-102963449-B1 - AI-based Self-Adjustment and Remotely Managed Guide Roll System

Abstract

The present invention is an AI-based autonomous adjustment and remotely managed guide roll system, which may include a management server that manages modular rolls.

Inventors

• 조예찬
• 김영기
• 김영애
• 고정왕
• 정용제
• 정용민
• 김영자
• 고정일
• 전애선
• 김권록

Assignees

• (주)와이씨솔루션

Dates

Publication Date

20260513

Application Date

20250422

Priority Date

20250409

Claims (2)

1. An AI-based autonomous adjustment and remotely managed guide roll system comprising a management server that manages modular rolls used in a secondary battery manufacturing process, The above management server is, A monitoring unit that collects real-time status data of the modular roll, including temperature, vibration, and wear status, through an AI-based sensor mounted on the modular roll, and detects abnormal conditions of the modular roll by analyzing the real-time status data; A maintenance unit that predicts the possibility of failure using a machine learning algorithm for abnormal situations of the modular roll detected by the monitoring unit, calculates the expected lifespan and maintenance timing of the modular roll, and recommends the optimal replacement time; An autonomous adjustment unit that automatically adjusts the tension and rotational speed of each modular roll using an AI algorithm based on the real-time status data collected by the monitoring unit; and A factory system for managing the modular roll and a remote management unit that communicates with the AI-based sensor and connects with the production process of the factory system to provide real-time monitoring data on the status of the modular roll to a manager terminal; The above modular roll is, It refers to a guide roll designed to accurately and stably process, move, and align separator materials in the secondary battery manufacturing process to produce separators for secondary batteries, and It is characterized by being designed so that the roll core and the outer shell are separable so that only the outer shell can be replaced in the event that the roll surface is damaged, and It is characterized by being formed with a precision fastening structure based on a fixing system that prevents detachment or shaking between modules, and The above separator is, It refers to a material located between the positive and negative electrodes of a secondary battery that prevents electrical short circuits and controls the flow of ions, and The above AI-based sensor is, It includes a temperature sensor already provided inside the modular roll, a vibration sensor already provided on the outer surface, and a wear sensor already provided near the rotation axis. Each sensor data generated from the temperature sensor, the vibration sensor, and the wear sensor is collected with time synchronization and transmitted to the monitoring unit, characterized by. The above maintenance department is, The real-time status data collected by the monitoring unit is accumulated and stored to construct a database, and The above machine learning algorithm is, It refers to an AI algorithm that predicts the probability of failure of a modular roll by learning past state data already stored in the above database, and The above machine learning algorithm is, It includes a time series analysis-based LSTM (Long Short-Term Memory) or a Random Forest model for defect classification, and is characterized by improving the prediction accuracy of failure probability by utilizing real-time status data and historical status data including failure history, abnormal patterns, and external environmental conditions. The above maintenance department is, If the predicted probability of failure exceeds a preset threshold, an alert is automatically sent to the administrator terminal, and a management protocol document including a maintenance manual or inspection procedure based on the failure type of the modular roll is generated. It is characterized by providing the generated management protocol document to the autonomous coordination unit, The above-mentioned autonomous adjustment unit is, Automatically adjust the tension and rotational speed of a modular roll whose predicted failure probability, based on the management protocol document provided by the maintenance department and an AI algorithm that has learned and analyzed the management protocol document, exceeds a preset threshold, thereby maintaining the performance of the said modular roll and preventing production stoppage due to failure, When the change in tension of the above modular roll exceeds a preset allowable threshold, the rotational speed is corrected using a controller, and the tension balance between multiple modular rolls is automatically adjusted to minimize material alignment deviation. The above remote management unit is, Detecting and managing the status of the above modular roll in real time, and If a problem with the above modular roll is predicted or detected as requiring maintenance, management data including problem resolution methods and maintenance information is generated and sent to the above administrator terminal, and The above monitoring unit is, An anomaly analysis index (A anomaly) is calculated based on the internal roll temperature at the current time (T(t)), reference temperature (T ref ) , vibration value at the current time (V(t)), reference vibration value (V ref ), current wear rate (M(t)), humidity inside the factory (H f ), and weights (w 1 , w 2 ), and The above monitoring unit is, It is characterized by calculating the abnormal state analysis index (A anomaly) by computing a formula designed using a logarithmic function together with the internal temperature of the roll at the current time (T(t)) and the reference temperature (T ref ) so as to react sensitively to the abnormal state of the modular roll, but to react less sensitively to sensor noise by reducing the range of change when the value becomes too large . The above monitoring unit is, It is characterized by calculating the anomaly state analysis index (A anomaly) by computing a formula designed using the trigonometric function sin together with the vibration value at the current time (V(t)) and the reference vibration value (V ref ) to reflect changes based on how much the vibration of the modular roll deviates from the reference, while effectively detecting periodic vibration anomalies . The above monitoring unit is, Since the probability of failure of the modular roll increases as the wear of the modular roll becomes more severe, the method is characterized by calculating the abnormal state analysis index (A anomaly ) by operating a formula designed so that the relationship between the current wear rate (M(t)) and the abnormal state analysis index (A anomaly ) is proportional. The abnormal situation of the above modular roll is, Includes overheating and imbalance, The above factory system is, Including ERP and MES, The above secondary battery is, Includes a lithium-ion battery, The above controller is, PID, an AI-based autonomous adjustment and remotely managed guide roll system, which refers to a device that automatically adjusts to reduce the difference when the target value and the actual value differ.
2. delete

Description

AI-based Self-Adjustment and Remotely Managed Guide Roll System The present invention relates to an AI-based autonomous adjustment and remotely managed guide roll system. A guide roll for the production of separators for secondary batteries refers to a high-precision roller device designed to accurately and stably process, move, and align separator materials in the secondary battery manufacturing process. Separators are important materials located between the positive and negative electrodes of secondary batteries (such as lithium-ion batteries) to prevent electrical short circuits and control the flow of ions. Although mass production of rolls has become widespread due to the acceleration of industrialization, various problems are arising as a result. Consumers of guide rolls tend to prefer products that are relatively free from durability issues and allow for proactive responses when problems arise. However, roller systems used in industrial processes frequently experience surface wear or internal functional failures due to prolonged use, making it common to have an inefficient maintenance method that requires replacing the entire product. Since these existing technologies cannot selectively replace only the damaged parts, they result in the waste of unnecessary resources and manpower, and cause prolonged downtime for the entire process. In particular, structural limitations that allow failures to be detected only after a problem occurs during the process inevitably lead to reduced productivity and quality defects. Consequently, there is an increasing demand for intelligent systems capable of partial replacement of roller systems and real-time status detection. Meanwhile, the aforementioned background technology is technical information that the inventor possessed for the derivation of the present invention or acquired during the process of deriving the present invention, and it cannot necessarily be considered publicly known technology disclosed to the general public prior to the filing of the present invention. FIG. 1 is a conceptual diagram of an AI-based autonomous adjustment and remotely managed guide roll system according to one embodiment of the present invention. FIG. 2 is a conceptual diagram of a management server according to one embodiment of the present invention. The following detailed description of the invention refers to the accompanying drawings, which illustrate specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that various embodiments of the invention are different but need not be mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be implemented in other embodiments without departing from the spirit and scope of the invention in relation to one embodiment. When it is stated that one component is "connected" or "contracted" to another component, it should be understood that while it may be directly connected or contracted to that other component, there may also be other components in between. Conversely, when it is stated that one component is "directly connected" or "directly contracted" to another component, it should be understood that there are no other components in between. Furthermore, it should be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the invention. Accordingly, the following detailed description is not intended to be taken in a limiting sense, and the scope of the invention is limited only by the appended claims, including all equivalents thereof, provided appropriately described. Similar reference numerals in the drawings refer to the same or similar functions across various aspects. Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the drawings. FIG. 1 is a conceptual diagram of an AI-based autonomous adjustment and remotely managed guide roll system according to one embodiment of the present invention. Referring to FIG. 1, an AI-based autonomous adjustment and remote management guide roll system according to one embodiment of the present invention may include a management server (100), an AI-based sensor (300) of a modular roll, and a manager terminal (500). The management server (100) can manage the modular roll according to the present invention. The aforementioned modular roll is designed to accurately and stably process, move, and align separator materials in a secondary battery manufacturing process, and may refer to a guide roll for producing separators for secondary batteries. A modular roll according to one embodiment of the present invention may be characterized by being designed so that the roll core and the outer shell are separable so that only the outer shell can be replaced when