Recently, many studies have been conducted to improve quality by applying machine learning models to semiconductor manufacturing process data. However, in the semiconductor manufacturing process, the ratio of good products is much higher than that of defective products, so the problem of data imbalance is serious in terms of machine learning. In addition, since the number of features of data used in machine learning is very large, it is very important to perform machine learning by extracting only important features from among them to increase accuracy and utilization. This study proposes an anomaly detection methodology that can learn excellently despite data imbalance and high-dimensional characteristics of semiconductor process data. The anomaly detection methodology applies the LIME algorithm after applying the SMOTE method and the RFECV method. The proposed methodology analyzes the classification result of the anomaly classification model, detects the cause of the anomaly, and derives a semiconductor process requiring action. The proposed methodology confirmed applicability and feasibility through application of cases.

In this study, we intend to develop a control valve with oxidation resistance for hydrogen fluoride that can be applied to the semiconductor production process. Operated Valves currently in use is a form of assembling an air cylinder to the valve body. These valves generally have a cylinder body made of aluminum (Al), so they may corrode depending on the external environment, and the solution leaks along the rod inside the cylinder, causing damage to parts due to corrosion. To solve this problem, the valve plug shape was developed by devising and applying a plug using a valve different from the existing method, and it is possible to block the inflow of hydrogen fluoride into the valve control unit, thereby preventing damage to parts as well as maintaining stable valve operation.

The purpose of this study is to present a novel indicator for analyzing machine failure based on its idle time and productivity. Existing machine repair plan was limited to machine experts from its manufacturing industries. This study evaluates the repair status of machines and extracts machines that need improvement. In this study, F-RPN was calculated using the etching process data provided by the 2018 PHM Data Challenge. Each S(S: Severity), O(O: Occurence), D(D: Detection) is divided into the idle time of the machine, the number of fault data, and the failure rate, respectively. The repair status of machine is quantified through the F-RPN calculated by multiplying S, O, and D. This study conducts a case study of machine in a semiconductor etching process. The process capability index has the disadvantage of not being able to divide the values outside the range. The performance of this index declines when the manufacturing process is under control, hereby introducing F-RPN to evaluate machine status that are difficult to distinguish by process capability index.

본 연구는 반도체 제품과 설비기술을 대상으로 제품-공정기술 공진화를 교차영향분석(cross impact analysis)을 통해 구체화하고, 공진화 관계를 기술 인텔리전스의 대표적 도구 중 하나인 기술레이더에 통합하는 방법을 제시한다. 교차영향분석을 통해 공정기술 발전과 제품특성 개선이 반복되는 공진화 경로와 축이 되는 세부기술들을 파악했다. 또한 공진화 관계를 기술레이더의 기술가치평가 프로세스에 반영 해 가치평가와 연구개발 포트폴리오의 신뢰성을 제고했다. 학술적 측면에서 기술간 공진화를 세부기술 단위에서 구체화했으며, 기술 공진화 이론과 기술 인텔리전스의 접점을 제시했다는 의미가 있다. 실무적 측면에서는 반도체 관통전극-하이브리드 패키지 제품과 주요 후공정 기술간 공진화 및 기술레이더 분석 실례를 제시하고, 이를 통해 기술간 공진화 관계를 기존 기술전략 및 기획도구에 반영 해 기업의 미래준비역량과 전략기획의 신뢰성을 제고하는 방법을 구체화했다는 점에서 가치가 있다.

반도체용 초순수를 생산하는 공정에서 수질관리를 위해 카트리지 필터, 한외여과막, 역삼투막, 탈기막, 이온교환막, 최종생산수용 한외여과막 등 다양한 종류의 분리막이 적용되고 있다. 분리막 공정은 종래기술과 비교하여 동등이상의 성능과 운전의 용이함과 설치면적의 최소화 등 부수적인 장점을 가지고 있다. 유입수의 수질에 따라 전처리 필터의 종류 및 기능이 결정되며, 최종수의 폴리싱 부담을 줄이기 위한 분리막 공정의 구성 등이 중요하다. 본 연구에서는 반도체용 초순수 실증파일럿플랜트의 공정 최적화를 위해 분리막 공정의 구성 및 운전방법에 따른 성능 등을 평가하는 연구를 진행하였다.

반도체용 초순수를 생산하는 공정에서 다양한 종류의 멤브레인을 적용하고 있다. 정밀여과막, 한외여과막, 역삼투막, 탈기막, 이온교환막, 최종생산수용 한외 여과막 등이 있다. 멤브레인기술은 종래기술과 비교하여 동등이상의 성능과 운전의 용이함과 설치면적의 최소화 등 부수적인 장점이 있기 때문이다. 반도체산업에서 적용되고 있는 멤브레인은 주로 외산기술이 점유하고 있다. 본 연구에서는 국산화를 위해 설계공정과 일부 멤브레인 기자재 개발을 진행하 였다. 기자재 개발품의 실증을 위해 실증파일럿플랜트에 적용하여 국/외산 성능 비교와 운전방법에 따른 성능 등을 평가하는 연구를 진행하였다.

Semiconductor is one of the biggest export items in Korea and one of future foods. In this study, the development of the product due to the repetition of the engineer mistakes repeatedly occurred due to the experience and habit of the individual in the semiconductor design process until now, resulting in an increase in the development period of the product and the economic loss of sales. As a result, the need for database of engineers' knowledge and know-how has emerged. This study investigate show to integrate and utilize data that is not managed on On/off-line for semiconductor knowledge and know-how. To do this, we intend to construct a RCT(RootCauseTracker) system that enables statistical analysis of the data on design failure accumulated over the previous year in any company.

반도체 공정에서 에칭공정은 실리콘 기판위에 패턴된 절연층을 식각하는 공정으로 분진과 미반응 가스를 배출하며, 다량의 질소와 혼합되어 실질적으로 수 ppm으로 배출되어, 주로 Scrubber를 통하여 후처리가 수행되고 있으나, 처리효율이 저하되는 단점이 있다. 따라서 본 연구에서는 막분리 공정을 통하여 질소와 PFCs를 분리회수하는 통합시스템을 개발하여, PFCs 가스 분리,회수에 대한 평가를 수행하였으며, 회수율 95%, 농축비 1을 나타내었다.

본 연구에서는, 반도체, LCD 공정에서 금속막을 증착하기 위하여 PECVD장비에 화재, 폭발 위험성과 독성을 가진 Silane가스를 사용하게 되는 장비인 gas cabinet, pipeline, VMB(Valve manifold box), MFC(mass flow controller)장비 등, 전반적인 시스템에 대하여 영국 HES의 ALARP개념을 도입하여 위험성 평가를 실시하여 문제점을 도출하고 대책을 강구 하는데 목적이 있고, 여러 가지 문제점중

The power of semiconductor, Korea is continuously constructing semiconductor production line for keeping a front-runner status. however, studies and data about potential risks in semiconductor factory are still short. If fire does not initially suppressed, the fire causes a great damage. To decrease fire risk factors, in addition to fire fighting safety equipment, more important thing is how to design and construct fire protection system. The current fire protection codes about semiconductor factory come under functional law, and this law is short of consideration about particularity of factory. The existing prescriptive fire codes depending on experience compose without evident engineering verifications, thus equipments which is created by the current prescriptive fire code may bring about a variety of problems. For example, the design under the current regulation can not cope with the excessive investments, low efficiencies, and the diversifying construction designs and be applied to the quick changes of new technologies. Ergo, an optimal design for fire protection is to equip fire protection arrangements with condition and environment of production field. Manufacturing factory of semiconductors is a windowless airtight space. And for cleanliness, there exists strong flow of cooperation. Therefore, there is a need for fire safety design that meets the characteristic of a clean room. Accordingly, we are to derive smoke flow according to cooperation process within a clean room and construction plan of an optimal sensor system. In this study, in order to confirm the performance of proposed smoke-exhaust equipment and suggest efficient smoke exhaust device when there is a fire of 1MW of methane in the clean room of company H, we have implemented fire simulation using fluid dynamics computation.

Scheduling semi-conductor manufacturing process systems is a complicated and difficult job due to such characteristics as reentry into manufacturing processes, high uncertainty of processes, and products and technologies changing rapidly. They have carried out many studies to find the efficient ways for semi-conductor manufacturing systems with a view to accomplishing the goals of systems like saving cycling time and increasing production quantity per unit time. The production flow in the semi-conductor industry has the most unique characteristics and makes it difficult to plan production and to schedule semi-conductor manufacturing. Currently, the scheduling methods in semi-conductor assembly processes follow the dispatching rule by simple FCFS(first come first serve). And backlog is operated as a buffer based on daily production quantity. In this study, therefore, we will apply various dispatching rules by real time basis and verify the effect and result of exact scheduling through simulation, based on the assumption that competitive advantages in production come from efficient inventory control and exact scheduling.

Bi-Te게 열전재료는 200~400K 정도의 저온에서 에너지 변환 효율이 가장 높은 재료로써 열전냉각, 발전재료 등에 응용하기 위하여 제조방법 및 특성에 관한 많은 역구가 진행되어 왔다. 현재 산업화에 응용되고 있는 일방향응고법은 기계적 강도가 약하여 회수 율이 낮으며, 결정을 성장시키는데 비교적 장시간을 필요로 하기 때문에 제조 단가가 비싸다. 따라서 이와 같은 문제점을 보완하기 위하여 합금설계 및 가공공정에 대한 연구가 활발히 진행되고 있다. 이에

PFC (perfluorocompound) gases have an extremely high global warming potential (GWP). A study of the destruction of NF3, CF4 and SF6 gases emitted from the semiconductor industry was attempted by plasma power at 4.4 kW, 5.5 kW, 6.0 kW, 6.6 kW, 7.6 kW, 8.1 kW and 9.1 kW. As electric power increased, DRE (destruction and removal efficiency) of NF3, CF4 and SF6 was also increased. It was confirmed through experiment that the DRE of NF3 is 99% at 7.6 kW, 97% for CF4 at 9.14 kW and 100% for SF6 at 7.6 kW of plasma power. By-products formed by PFC destruction were mainly F2, SO2F2, NOx and CO gases. In addition, particulate matter was formed, and particle were proven to be AlF3.

반도체 소자가 초고집적화 되면서 제조 공정은 다양해지고 더욱 복잡해졌으며, 각 공정 후에는 많은 잔류물과 오염물이 웨이퍼 표면에 남게 된다. 따라서 이 잔류물과 오염물을 제거하는 세정공정은 반도체 공정에서 매우 중요한 과정 중 하나이다. 반도체 제조 공정은 약 400개 단계의 제조공정으로 이루어져 있으며 이들 중 적어도 20% 이상의 공정이 웨이퍼의 오염을 막기 위한 세정공정과 처리공정으로 이루어져 있다. 제조과정에서 발생하는 Water mark를 제거하기 위해 IPA(Iso propyl alcohol)를 사용하여 웨이퍼 표면을 세정 및 건조하는데, 공정 후 배출되는 IPA 폐액의 경우 그 독성으로 인해 미생물이 사멸되어 기존의 처리방법으로는 처리가 어려우며, 이를 폐기물로 위탁 처리하고 있다. IPA 세정공정에서 배출되는 폐액의 IPA농도는 30% 수준으로 기존 증류법을 통한 증발농축으로 IPA를 농축하는데 많은 Utility 비용이 소요된다. 따라서 본 연구에서는 이러한 IPA를 95%이상 고농도로 농축하기 위해 분리막을 이용한 증기투과 공정을 설계하였고, Lab scale 장치에서 다음과 같은 조건(공급 IPA 농도 30%, 조작온도 130℃, 유량 3kg/hr)에서 IPA 농도는 99% 수준으로 나타났다. 이를 토대로 Scale-up화하여 Pilot scale 장치에서 공급 IPA 농도, 온도, 유량 등의 운전인자를 변화시켜 IPA를 95%이상으로 농축하기 위한 최적조건을 도출해 보고자 하였다.

Sulfur hexa-fluoride has been used as a etching gas in semiconductor industry. From the globally environmental issues, it is urgent to control the emissions of this significant greenhouse gas. The main objective of this experimental investigation was to find the effective catalyst for SF6 decomposition. The precursor catalyst of hexa-aluminate was prepared to investigate the catalytic activity and stability. The precursor catalyst of hexa-aluminate was modified with Ni to enhance the catalytic activities and stability. The catalytic activity for SF6 decomposition increased by the addition of Ni and maximized at 6wt% addition of Ni. The addition of 6wt% Ni in precursor catalyst of hexa-aluminate improved the resistant to the HF and reduced the crystallization and phase transition of catalyst.

The hydroxyapatite(HAp) for the present study was prepared with the wastewater sludge from semiconductor fabrication process and it was crystallized in an electric furnace for 30 min at 900℃. The adsorption characteristics of HAp for phosphate ion in aqueous solution has been investigated. The adsorbed ratio of phosphate ion for HAp were investigated according to the reaction time, amount of HAp, concentration of standard solution, pH of solution, and influence of concemitant ions. The amount of adsorbed phosphate ion decreased with the increase of pH due to the mutual electrostatic repulsion between adsorbed phosphate ions and competitive adsorption between phosphate ion and OH- ion in aqueous solution. The maxium amount of the adsorption equilibrium for phosphate ion was about 24 mg/g of HAp. The HAp would likely to be a possible adsorbent for the removal of phosphate ion in the waste water.