• 제어로봇시스템학회논문지
• /
• 제9권10호
• /
• pp.768-773
• /
• 2003

Injection molding has been widely used for the mass production of a plastic product. With the development of the relative technique, various injection molding techniques have been developed and we could get more precise plastic product. The temperature of a melting resin is an important factor in the injection molding and this temperature has direct influence on the quality of a plastic product. In the present injection molding machine, the deriation of a temperature controlled by PID control method is within 2$^{\circ}C$ in the injection molding machine but PID control method takes too much time to stabilize after preheating and its overshoot is so big. We applied fuzzy control to alleriate the problem. In this research, we experimented the fuzzy temperature control with the usage of PC based PLC.

• 한국안전학회지
• /
• 제20권2호
• /
• pp.140-145
• /
• 2005

The PL(Product Liability) Law has been going into effect in Korea since July 2002. Accordingly, a company's responsibility for customers who are damaged by the defect in the product safety has been gradually strict and imposed burden on management. Not only general consumers but also labors who work with machine in the field of production are included in the concept of victim of the PL Law. That is to say, when a worker is damaged by the defect of machine he can institute a PL lawsuit more aggressively, not just get the industrial accident compensation as usual, only if not his own fault but the defect of machine used in the course of production can be demonstrated. This paper intends to present suggestions to PL prevention of manufacturing companies of industrial machine through the case research of PL accidents in the area of industrial safety.

• 한국지능시스템학회논문지
• /
• 제11권2호
• /
• pp.173-177
• /
• 2001

We introduce cascade products, wreath products, sums and joins of TL-finite state machines and investigate their algebraic structures. Also we study the relations with other products of TL-finite state machines.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2003년도 춘계학술대회논문집
• /
• pp.371-374
• /
• 2003

The bending process for the "ㄱ" section product can be developed by the hot metal extrusion machine with the two punches moving in the different velocity. The bending phenomenon can be controlled by difference of velocity at the die exit section by the different velocity of billets through the two-hole container. The results of the experiment show that "ㄱ" section product can be bended by the extrusion process and that the curvature of the product can be controlled by the velocity of punch and that the defects such as the distortion of section and the thickness change of the product and the folding and wrinkling of the product did not happen after the bending processing by the extrusion bending machine.

• 동력기계공학회지
• /
• 제14권5호
• /
• pp.76-82
• /
• 2010

This paper investigates the optimum operating conditions to construct total automatic control system with high energy efficiency of a newly developed seawater ice machine. The machine has an electronic expansion valve(EEV) and a variable speed rotating drum with an evaporator installed inside. The coefficient of performance(COP) was used as an index to evaluate energy efficiency of the machine. At first, the opening angle of EEV was adjusted to obtain COP of the machine at a constant speed of the drum. Then, we checked seawater ice product versus opening angles of the EEV. Finally, effect of drum's rotating speed in response to product of seawater ice and seawater ice temperature were considered.

• 융합정보논문지
• /
• 제7권1호
• /
• pp.55-60
• /
• 2017

사물인터넷 환경에서 인간의 개입 없는 지능화된 서비스를 위해서는 IoT 디바이스에서 생성되는 빅데이터로 부터 정상 패턴을 학습하고 이를 기반으로 불량, 오작동과 같은 이상 징후에 대해 예측하는 과정이 요구된다. 본 연구의 목적은 제품 공정의 다양한 기기에서 발생되는 빅데이터를 분석함으로써 제품 불량을 예측할 수 있는 기계 학습모델을 구현하는 것이다. 기계 학습 모델은 어느 정도 볼륨을 가진 기존 데이터를 기반으로 분석을 해야 하므로 빅데이터 분석도구 R을 사용하였으며, 제품 공정에서 수집된 데이터에는 제품에 대한 불량 여부가 포함되어 있으므로 지도 학습 모델을 활용하였다. 연구의 결과, 제품 불량에 영향을 주는 변수 및 변수 조건을 분류하였고, 의사결정 트리를 기반으로 제품의 불량 여부에 대한 예측 모델을 제시하였다. 또한, ROC Curve를 이용한 모델의 적합성 및 성능평가 분석에서 모델의 예측력은 상당히 높게 나타났다.

• 산업경영시스템학회지
• /
• 제34권4호
• /
• pp.152-161
• /
• 2011

The operation of vending machine system presents a decision-making problem which consists of determining the product allocation to vending-machine storage compartments, replenishment intervals of vending machines, and vehicle routes, all of which have critical effects on system profit. Especially, it becomes more difficult to determine the operation variables optimally when demand for a product that is out-of-stock spills over to another product or is lost. In this paper, we propose a heuristic for solving the operation problem of the vending machine system and evaluate it by comparing with Yang's algorithm on various test problems with respect to system profit via a computer simulation. The results of computational experiments show a substantial profit increase of the proposed heuristic over Yang's algorithm. Sensitivity analysis indicates that some input variables impact the profit increase significantly.

• International Journal of Computer Science & Network Security
• /
• 제21권4호
• /
• pp.214-222
• /
• 2021

Recently, the growth of e-commerce in Saudi Arabia has been exponential, bringing new remarkable challenges. A naive approach for product matching and categorization is needed to help consumers choose the right store to purchase a product. This paper presents a machine learning approach for product matching that combines deep learning techniques with standard artificial neural networks (ANNs). Existing methods focused on product matching, whereas our model compares products based on unstructured descriptions. We evaluated our electronics dataset model from three business-to-consumer (B2C) online stores by putting the match products collectively in one dataset. The performance evaluation based on k-mean classifier prediction from three real-world online stores demonstrates that the proposed algorithm outperforms the benchmarked approach by 80% on average F1-measure.

• 한국컴퓨터정보학회논문지
• /
• 제21권2호
• /
• pp.71-77
• /
• 2016

There has been unknown polynomial time algorithm for cellular formation problem (CFP) that is one of the NP-hard problem. Therefore metaheuristic method has been applied this problem to obtain approximated solution. This paper shows the existence of polynomial-time heuristic algorithm in CFP. The proposed algorithm performs coarse-grained and fine-grained cell formation process. In coarse-grained cell formation process, the cell can be formed in accordance with machine frequently used that is the number of other products use same machine with special product. As a result, the machine can be assigned to most used cell. In fine-grained process, the product and machine are moved into other cell that has a improved grouping efficiency. For 35 experimental data, this heuristic algorithm performs better grouping efficiency for 12 data than best known of meta-heuristic methods.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회/대한산업공학회 2005년도 춘계공동학술대회 발표논문
• /
• pp.854-861
• /
• 2005

The functional behavior of a portable consumer electronic (PCE) product is nearly all expressed with human-machine interaction (HMI) tasks. Although physical prototyping and computer aided design (CAD) software can show the appearance of the product, they cannot properly reflect its functional behavior. In this paper, we propose a virtual prototyping (VP) system that incorporates virtual reality and HMI functional simulation in order to enables users to capture not only the realistic look of a PCE product but also its functional behavior. We obtain geometric part models of the product and their assembly and kinematics information with the help of CAD and reverse engineering tools, and visualize them with various display tools. We adopt state transition methodology to capture the HMI functional behavior of the product into a state transition chart, which is later used to construct a finite state machine (FSM) for the functional simulation of the product. The FSM plays an important role to control the transition between states of the product. The proposed VP system receives input events such as mouse clicks on buttons and switches of the virtual prototype model, and it reacts to the events based on the FSM by activating associated activities. The VP system provides the realistic visualization of the product and the vivid simulation of its functional behavior. It can easily allow users to perform functional evaluation and usability testing. Moreover, it can greatly reduce communication errors occurring in a typical product development process. A case study about VP of an MP3 player is given to show the usefulness of the proposed VP system.