The metal bush assembling process is a process of inserting and compressing a metal bush that serves to reduce the occurrence of noise and stable compression in the rotating section. In the metal bush assembly process, the head diameter defect and placement defect of the metal bush occur due to metal bush omission, non-pressing, and poor press-fitting. Among these causes of defects, it is intended to prevent defects due to omission of the metal bush by using signals from sensors attached to the facility. In particular, a metal bush omission is predicted through various data mining techniques using left load cell value, right load cell value, current, and voltage as independent variables. In the case of metal bush omission defect, it is difficult to get defect data, resulting in data imbalance. Data imbalance refers to a case where there is a large difference in the number of data belonging to each class, which can be a problem when performing classification prediction. In order to solve the problem caused by data imbalance, oversampling and composite sampling techniques were applied in this study. In addition, simulated annealing was applied for optimization of parameters related to sampling and hyper-parameters of data mining techniques used for bush omission prediction. In this study, the metal bush omission was predicted using the actual data of M manufacturing company, and the classification performance was examined. All applied techniques showed excellent results, and in particular, the proposed methods, the method of mixing Random Forest and SA, and the method of mixing MLP and SA, showed better results.

경상남도 고성군에 위치한 삼산제일 삼봉 동광산 주변지역의 중금속 오염현황을 조사하기 위하여 하천수와 하상퇴적물을 채취하여 화학적 분석을 수행하였다. 이와 더불어, 중금속 오염도와 환경위해성을 평가하기 위하여 왕수분해법과 연속추출법을 이용하여 분석된 하상퇴적물 내 중금속의 총 농도와 화학적 존재형태에 따른 농도를 바탕으로 한 오염지수와 위험지수를 산정하였다. 삼봉광산 지역보다는 삼산제일광산 지역에서 중금속 오염도도 높게 나타났을 뿐만 아니라 그 환경위해성도 훨씬 심각한 것으로 밝혀졌다. 이렇게 두 지역에서 오염현황, 오염도, 환경위해성 등이 다르게 나타나는 이유는 갱내수와 같은 광산 오염원의 존재여부와 지질학적 특성에 기인하는 것으로 사료된다. 삼산제일광산 지역의 경우 산성광산배수가 지속적으로 유출되어 하류 수계로 유입되고 있기 때문에 갱내수가 존재하지 않은 삼봉광산지역보다는 하류 수계에 대한 중금속 오염이 보다 더 악화되어 나타나는 것으로 보인다. 또한, 삼산제일광산 지역 주변 지질은 주로 안산암질 암류로 이루어져 있는데, 이들 안산암질 암류 내에는 산성광산배수를 중화시킬 수 있는 pH 완충력이 큰 탄산염 광물 등의 함량이 크지 않기 때문에 수계에서 중금속 오염이 자연적으로 정화되는 정도가 상대적으로 낮은 것으로 보인다. 이에 비해, 삼봉광산 지역의 지질은 방해석과 같은 탄산염 광물을 다량 함유한 화산쇄설성 퇴적암층인 고성층으로 이루어져 있어서, 이들 탄산염 광물들에 기인한 높은 pH 완충력에 의하여 중금속 오염이 하류 수계 방향으로 확산되지 못하는 것으로 판단된다.

Electrokinetic technique was considered in removing arsenic from the abandoned mining tails. In order to estimate the removal characteristics of arsenic, the sequential extraction analysis and desorption experiment were carried out prior to the application of electrokientic process. The result of sequential extraction analysis indicated that the water soluble and exchangeable fraction, easily leachable to ground water, were very low as much as about 2.5% and the fraction except residual (38.3%), possibly extractable under very acidic or alkalic environment, was about 59%. In the result of desorption test using four different kinds of electrolytes, the mixture of citric acid and sodium dodecyl sulfate (SDS) showed the highest desorption efficiency as much as 77.3%. The removal efficiencies of arsenic from mining tailings by electrokinetic process under the different electrolyte environments were slightly low and resulted in the following order: citric acid + SDS (18.6%) > 0.1 NHNO3 (8.1%) > HAc (7.4%) > Distilled water(6.6%). Also, arsenic in soil matrix was moved favorably in the direction of anodic rather than cathodic region, which is opposite trend with cationic metal ions generally existing in soil, because anionic form of arsenic is dominated in acidic soil caused by the movement of acid front form anode.

Electrokinetic remediation technique offers the opportunity to extract heavy metals from soils with high plasticity. The experiment demonstrated the applicability of electrokinetic remediation on metal-mining deposit and the decision of the enhancement method for four kinds of bench-scale studies. According to the sequential extraction of heavy metals in the "I" mining deposit, Pb and Cu were mostly associated with residual fraction and Zn and Cd were associated with water soluble and residual fraction. Therefore, removable fractions by electrokinetic technology was determined by the sum of the fraction of water soluble and exchangeable, which is Cu : 19.53 %, Pb : 1.42 %, Cd : 52.82 %, Zn : 57.28 %, respectively. When considering electrical potential, volume of effluent, soil pH, and eliminated rate of contaminant, results determined by sum of each weight were Citric aic+SDS (13) > 0.1N HNO3 (10) > HAc (8) > DDW (4). Therefore, citric acid and SDS mixed solution was determined the best enhancing agent for the remediation of metal mining deposit.