• Journal of Korea Multimedia Society
• /
• 제10권8호
• /
• pp.1004-1016
• /
• 2007

In this paper we proposed a Weight-Update-Control Adaptive Noise Canceller which improves speech when environmental noise is stationary and it is hard to acquire a reference signal. Adaptive Noise Canceller(ANC) needs a reference signal, but it is not easy to measure pure noise without voice for reference in factory. Because there are mixed various mechanical noise and workers' voice. Therefore ANC is not suitable to reduce background noise. So we proposed the method that uses an arbitrary constant as an input signal and inputs microphone signal to the reference signal. The noise is eliminated using updated weights in non-speech range. In speech range the weight is fixed and the modified voice is acquired then voice is restored through transversal filter. The proposed method is based on facts that the factory noise is stationary and the noise is not changed in short conversation range. As a result of simulation using MATLAB, we confirmed that the proposed method is effective for reducing factory noise and has high signal to noise ratio(SNR).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제21권11호
• /
• pp.2167-2175
• /
• 2017

In recent years, an IoT is dramatically developing according to the enhancement of AI, the increase of connected devices, and the high-performance cloud systems. Huge data produced by many devices and sensors is expanding the scope of services, such as an intelligent diagnostics, a recommendation service, as well as a smart monitoring service. The studies of edge computing are limited as a role of small server system with high quality HW resources. However, there are specialized requirements in a smart factory domain needed edge computing. The edges are needed to pre-process containing tiny filtering, pre-formatting, as well as merging of group contexts and manage the regional rules. So, in this paper, we extract the features and requirements in a scope of efficiency and robustness. Our edge offers to decrease a network resource consumption and update rules and learning models. Moreover, we propose architecture of edge computing based on learning factors sharing with a cloud system in a smart factory.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• 제18권5호
• /
• pp.237-244
• /
• 2018

The Smart Factory level of manufacturing factories of SMEs now lacks a system for grasping the accurate inventory amount associated with inventory movements in managing warehouses at the basic level. Also, it is difficult to manage accurate materials for loss of data due to worker manual work and production method due to experience. In order to solve this problem, in this paper, automatic acquisition of inventory to minimize manual work to grasp workers' Inventory and improve automation is done. In the smart warehouse management system using the IoT-based autonomous mobile module, the autonomous mobile module acquires the data of the inventory storage while moving through the line. In order to grasp the material of the Inventory storage, The Camera module recognizes the name of the inventory storage. And Then, If output matches, the data measured by the sensor is transferred to the server. This data can be processed, saved in a database, and real-time inventory quantity and location can be grasped in a web-based monitoring environment for administrators. The Real-time Automatic Inventory (RAIC) systems is reduce manual tasks and expect the effects of automated inventory management systems.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• 제12권4호
• /
• pp.189-194
• /
• 2012

The main purpose of reactive power compensation monitoring system is to manage factory electrical installation efficiently by On-Off switching reactive power compensation equipment. The existing reactive power compensation monitoring system is only able to be managed by operator whenever electrical installation needed reactive power. Therefore, it may be possible for propagating the installation's faults when operator make the unexpected mistakes. To overcome the unexpected mistakes, in this paper, the author presents a reactive power compensation monitoring system for factory electrical installation using active database. by using active database production rule, stated system can minimize unexpected mistake and can operate centralized monitoring system efficiently. Test results on the five factory electrical installations show that performance is efficient and robust.

• IE interfaces
• /
• 제21권3호
• /
• pp.322-332
• /
• 2008

Digital Virtual Manufacturing is a technology to facilitate effective product developments and agile productions by digital model representing the physical and logical schema and the behavior of real manufacturing system, and it includes product, resources, processes and plant. For successful applications of this technology, a digital virtual factory as a well-designed and integrated environment is essential. In this research, we constructed a sophisticated digital virtual factory of a Korean automotive company's press shop. For efficient constructions of a digital virtual factory useful to kinematic simulations and visualizations, we analyzed entire business process and detailed activities of press engineering. Also, we evaluated geometries, structures, characteristics and motions of a plant and machines in press shop. The geometric model and related data of a virtual press shop are built and managed by a modeling standard defined in this paper. The virtual manufacturing simulation of press machines is conducted to evaluate kinematic motions, cycle time and locations of components using geometric models and related data. It's for interference checks and productivity improvements. We expect that this virtual press shop helps us to achieve great savings in time and cost in many manufacturing preparation activities in the new car development process of automotive companies.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국정보통신학회 2018년도 추계학술대회
• /
• pp.69-71
• /
• 2018

Looking at Korea's manufacturing industry, there are many old manufacturing plants. In fact, the manufacturing process of the product inventory management and the unit price of the product are all created by using Excel, and the factory is operated by using it. Also, the operator can not predict the failure of the equipment in order to produce the product at work. Problems related to this may result in the loss of the documents during the instruction and work process between the manager and the worker, and the communication between the manager and the worker can not be properly performed, There is appear a situation in which the operation is continued by using the equipment without recognizing in the failure. In this paper, we propose a method for upgrading the aging manufacturing plant to improve the productivity and productivity of the product by predicting the efficient inventory management, unit price management, production volume, and the operator's failure prediction.

• Industrial Engineering and Management Systems
• /
• 제2권1호
• /
• pp.9-27
• /
• 2003

In a wafer fabrication factory, the completion time of an order is affected by many factors related to the specifics of the order and the status of the system, so is difficult to predict precisely. The level of influence of each factor on the order completion time may also depend on the production system characteristics, such as the rules for releasing and dispatching. This paper presents a method to identify those factors that significantly impact upon the order completion time under various combinations of scheduling rules. Computer simulations and statistical analyses were used to develop effective due date assignment models for improving the due date related performances. The first step of this research was to select the releasing and dispatching rules from those that were cited so frequently in related wafer fabrication factory researches. Simulation and statistical analyses were combined to identify the critical factors for predicting order completion time under various combinations of scheduling rules. In each combination of scheduling rules, two efficient due date assignment models were established by using the regression method for accurately predicting the order due date. Two due date assignment models, called the significant factor prediction model (SFM) and the key factor prediction model (KFM), are proposed to empirically compare the due date assignment rules widely used in practice. The simulation results indicate that SFM and KFM are superior to the other due date assignment rules. The releasing rule, dispatching rule and due date assignment rule have significant impacts on the due date related performances, with larger improvements coming from due date assignment and dispatching rules than from releasing rules.

• Journal of Digital Convergence
• /
• 제16권11호
• /
• pp.313-327
• /
• 2018

In this era that technology is replacing human labor is coming. Like the introduction of Factory Automation and Smart Factory to enhance the productivity in manufacturing works in companies, RPA (Robotic Process Automation) is being applied to strengthen the competiveness in service & office work of companies. But, RPA itself is not mature enough to be the specific technology or solution, but burgeoning as the conceptual technology alternatives to automate the business process harnessed with the concept of software robots, artificial intelligence etc. The biggest difference that the introduction of RPA can make is the transition of the work based on 'human labor', to the 'digital labor' that could result in the replacement of human labor itself with that. Considering this kind of impact to change the concept of labor, the discussion for the future policy for this is inevitable. In this paper, beginning from the overview of RPA, relevant concerns & consideration for the application of RPA will be described based on the understanding of industrial & technology trends and expected future of RPA.

• KIPS Transactions on Computer and Communication Systems
• /
• 제9권8호
• /
• pp.171-180
• /
• 2020

Smart Factory consists of digital automation solutions throughout the production process, including design, development, manufacturing and distribution, and it is an intelligent factory that installs IoT in its internal facilities and machines to collect process data in real time and analyze them so that it can control itself. The smart factory's equipment works in a physical combination of numerous hardware, rather than a virtual character being driven by a single object, such as a game. In other words, for a specific common goal, multiple devices must perform individual actions simultaneously. By taking advantage of the smart factory, which can collect process data in real time, if reinforcement learning is used instead of general machine learning, behavior control can be performed without the required training data. However, in the real world, it is impossible to learn more than tens of millions of iterations due to physical wear and time. Thus, this paper uses simulators to develop grid sortation systems focusing on transport facilities, one of the complex environments in smart factory field, and design cooperative multi-agent-based reinforcement learning to demonstrate efficient behavior control.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• 제15권4호
• /
• pp.257-270
• /
• 2022

In this paper, we design a smart factory risk improvement system and risk improvement method using AI edge devices. The smart factory risk improvement system collects, analyzes, prevents, and promptly responds to the worker's work performance process in the smart factory using AI edge devices, and can reduce the risk that may occur during work with improving the defect rate when workers perfom jobs. In particular, based on worker image information, worker biometric information, equipment operation information, and quality information of manufactured products, it is possible to set an abnormal risk condition, and it is possible to improve the risk so that the work is efficient and for the accurate performance. In addition, all data collected from cameras and IoT sensors inside the smart factory are processed by the AI edge device instead of all data being sent to the cloud, and only necessary data can be transmitted to the cloud, so the processing speed is fast and it has the advantage that security problems are low. Additionally, the use of AI edge devices has the advantage of reducing of data communication costs and the costs of data transmission bandwidth acquisition due to decrease of the amount of data transmission to the cloud.