• Geomechanics and Engineering
• /
• 제34권5호
• /
• pp.547-559
• /
• 2023

We evaluated the applicability of machine learning techniques and the Kuz-Ram model for predicting the mean fragmentation size in open-pit mines. The characteristics of the in-situ rock considered here were uniaxial compressive strength, tensile strength, rock factor, and mean in-situ block size. Seventy field datasets that included these characteristics were collected to predict the mean fragmentation size. Deep neural network, support vector machine, and extreme gradient boosting (XGBoost) models were trained using the data. The performance was evaluated using the root mean squared error (RMSE) and the coefficient of determination (r²). The XGBoost model had the smallest RMSE and the highest r² value compared with the other models. Additionally, when analyzing the error rate between the measured and predicted values, XGBoost had the lowest error rate. When the Kuz-Ram model was applied, low accuracy was observed owing to the differences in the characteristics of data used for model development. Consequently, the proposed XGBoost model predicted the mean fragmentation size more accurately than other models. If its performance is improved by securing sufficient data in the future, it will be useful for improving the blasting efficiency at the target site.

• 한국토양비료학회지
• /
• 제23권1호
• /
• pp.8-14
• /
• 1990

토양수분함량(土壤水分含量)이 다른 조건(條件)에서 물이 이동(移動)할 때 동반(同伴)되는 용질(溶質)의 이동특성(移動特性)을 결정(決定)하는 지연계수(遲延係數)와 수리동적(水理動的) 분산계수(分散係數)를 수학적(數學的)으로 해석(解析)하고 일차원수평계(一次元水平系)의 사양토(砂壤土)에서 실험적(實驗的)으로 측정(測定)하였다. 용적밀도(容積密度)를 $1,350{\pm}50kg/m^3$인 사양토(砂壤土) 토양(土壤)에 수평(水平)으로 침투(浸透)되는 0.05% $CaSO_4$ 용액(溶液)의 수분전진(水分前進)을 Boltzman transform으로 나타내고 이를 표준(標準)으로 하였을 때 0.5% KCl, $CaCl_2$ 및 $KH_2PO_4$ 용액(溶液)의 용질전진(溶質前進)을 비농도(比濃度)로 표시(表示)하여 비교(比較)하였다. 용질농도(溶質濃度)의 분포(分布)와 수분분포(水分分布)로 부터 Laryea법(法)에 의하여 수리동적(水理動的) 분산계수(分散係數)를 계산(計算)하였다. 토양(土壤)-용액계(溶液系)에서 비반응성(比反應性) 용질(溶質)인 $Cl^-$의 전진(前進)은 물의 전진(前進)보다 늦었으며, 음(陰)ion 배제효과(排除效果)는 무시(無視)되었고 지연(遲延)은 초기수분함량(初期水分含量) ${\theta}_n$의 함수(函數)로 ${\theta}/({\theta}-{\theta}_n)$로 해석(解析)되었다. 토양입자(土壤粒子)에 의하여 흡착(吸着)이 일어나는 $K^+$, $Ca^{{+}{+}}$, $H_2PO^-_4$의 전진(前進)은 초기수분함량(初期水分含量)과 지연계수(遲延係數) R의 함수(函數)로 $\frac{1}{1+R}{\cdot}\frac{{\theta}}{{\theta}-{\theta}_n}$으로 해석(解析)되며 R치(値)는 $Cl^-$를 1.0으로 보았을 때 $K^+$는 0.64, 0.80 및 2.6이었다. Langmuir 등온흡착식(等溫吸着式)을 이용(利用)한 지연계수(遲延係數) 계산(計算)은 다소의 차이(差異)가 있었으나 적용가능성(適用可能性)이 있었다. 수분분포곡선(水分分布曲線)으로부터 산출(算出)된 물의 확산계수(擴散係數) $D({\theta})$는 초기수분함량(初期水分含量)에 관계(關係)없이 토양수분함량(土壤水分含量)과 단일지수함수관계(單一指數函數關係)로 표시(表示)되었다. $$log\;D({\theta})=13.448{\theta}-9.288$$ $Cl^-$의 수리동적분포계수(水理動的分布係數)는 수분함량(水分含量) 0.36 이상(以上)에서는 물의 확산계수(擴散係數)와 비슷하였고 그 이하(以下)에서는 급격히(急激)히 감소(減少)하여 수분함량(水分含量) 0.2부근에서 자기확산계수(自己擴散係數)와 비슷한 값을 보였다. $K^+$, $Ca^{{+}{+}}$ 및 $H_2PO^-_4$의 수리동적분산계수(水理動的分散係數)는 수분함량(水分含量) 0.38에서 각각(各各) $5.5{\times}10^{-6}$, $2.4{\times}10^{-6}$ 및 $7.1{\times}10^{-7}m^2/sec$의 값을 보였고 0.36% 이하(以下)의 수분함량(水分含量)에서 급격(急激)히 감소(減少)하였으며 감소(減少) 경향(傾向)은 $H_2PO^-_4$가 가장 심(甚)하였다.

• Asian-Australasian Journal of Animal Sciences
• /
• 제19권9호
• /
• pp.1225-1228
• /
• 2006

A total of 1,367 first lactation records of daughters of 81 sires, having 5 or more progeny were used to evaluate sires by 3 different methods viz., least squares (LS), best linear unbiased prediction (BLUP) and derivative free restricted maximum likelihood (DFREML) method. The highest and lowest overall average breeding value of sires for first lactation 305 days or less milk yield was obtained by BLUP (1,520.72 kg) and LS method (1,502.22 kg), respectively. The accuracy, efficiency and stability of different sire evaluation methods were compared to judge their effectiveness. The error variance of DFREML method was lowest ($191,112kg^2$) and its coefficient of determination of fitting the model was highest (33.39%) revealing that this method of sire evaluation was most efficient and accurate as compared to other methods. However, the BLUP method was most stable amongst all the methods having coefficient of variation (%) very near to unadjusted data (18.72% versus 19.89%). The higher rank correlations (0.7979 to 0.9568) between different sire evaluation methods indicated that there was higher degree of similarity of ranking sires by different methods ranging from about 80 to 96 percent. However, the DFREML method seemed to be the most effective sire evaluation method as compared to other methods for the present set of data.

• 분석과학
• /
• 제23권1호
• /
• pp.54-59
• /
• 2010

액체크로마토그래피/질량분석법(LC/MS)을 이용하여 화장품에 들어있는 파라벤류등을 동시 분석하였다. 화장품 시료를 메탄올에 직접 용해시키고 $0.45\;{\mu}m$ 필터로 여과하여 메탄올/물을 이동상으로 하여 Extend $C_{18}$의 비극성 컬럼을 사용하여 기울기 용리 조건에서 12분 안에 분리하여 SIM(selected ion monitoring)방법으로 정량하였다. LC/MS 분석결과 검량선은 $0.05-10\;{\mu}g$/mL 농도범위에서 $r^2$=0.9993의 상관계수를 갖는 좋은 직선성을 나타내었으며, 검출한계는 $0.01\;{\mu}g$/mL 이었다.

• Advances in environmental research
• /
• 제5권4호
• /
• pp.213-224
• /
• 2016

This paper presents a numerical model based on a UTCHEM simulator to simulate surfactant flushing process to remediate diesel contaminated sand column. For this purpose, we modeled remediation process under 10000 and 20000 ppm initial concentrations of diesel. Various percent-mass sodium dodecyl sulfate (SDS) considered in our model. The model results indicated that 0.3 percent-mass of SDS at 10000 ppm and 0.1 percent-mass of SDS at 20000 ppm initial diesel concentration had maximum removal perdition which is in agreement with the experiment results. For 10000 ppm diesel concentrations, the coefficient of determination ($R^2$) and index of agreement (IA) between the model result and the experimental data were 0.9952 and 0.9695, respectively, and for 20000 ppm diesel concentrations, $R^2$ and IA were 0.9977 and 0.9935, respectively. The sensitivity analysis of permeability illustrated that in all diesel concentrations and SDS percent-mass with increasing permeability the model resulted in more removal efficiency.

• Environmental Engineering Research
• /
• 제25권3호
• /
• pp.418-425
• /
• 2020

In this study soft computing techniques including, Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were investigated for the prediction of Cr(VI) transport efficiency by novel Polymer Inclusion Membranes (PIMs). Transport experiments carried out by varying parameters such as time, film thickness, carrier type, carier rate, plasticizer type, and plasticizer rate. The predictive performance of ANN and ANFIS model was evaluated by using statistical performance criteria such as Root Mean Standard Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R²). Moreover, Sensitivity Analysis (SA) was carried out to investigate the effect of each input on PIMs Cr(VI) removal efficiency. The proposed ANN model presented reliable and valid results, followed by ANFIS model results. RMSE and MAE values were 0.00556, 0.00163 for ANN and 0.00924, 0.00493 for ANFIS model in the prediction of Cr(VI) removal efficiency on testing data sets. The R² values were 0.973 and 0.867 on testing data sets by ANN and ANFIS, respectively. Results show that the ANN-based prediction model performed better than ANFIS. SA demonstrated that time; film thickness; carrier type and plasticizer type are major operating parameters having 33.61%, 26.85%, 21.07% and 8.917% contribution, respectively.

• 분석과학
• /
• 제18권6호
• /
• pp.453-459
• /
• 2005

물중에 존재하는 11종의 페놀류를 benzoyl chloride를 사용하여 물에서 직접 유도체화한 후 추출하여 동시 분석하였다. 즉, 수용액 시료에 수산화나트륨 용액을 가하여 pH 13으로 조절한 다음 여기에 benzoyl chloride를 $500{\mu}L$을 가하여 15분간 흔들어 반응시키고 정치한 후 diethyl ether로 추출하여 GC/MS-SIM으로 정량하였다. 검량선은 $0.05-5.0{\mu}g/mL$ 농도범위에서 상관계수가 $r^2=0.9915$로 직선성이 좋았으며 상대표준편차는 8.5% 이하였고 이 방법의 회수율은 58.4-114.0% 이었다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2011년도 학술발표회
• /
• pp.19-19
• /
• 2011

The appraisals of hydrology model behavior for flow and water quality are generally performed through comparison of simulated data with observed ones. To perform appraisal of hydrology model, some criteria are often used, such as coefficient of determination ($R^2$), Nash and Sutcliffe model efficiency coefficient (NSE), index of agreement (d), modified forms of NSE and d, and relative efficiency criteria NSE and d. These criteria are used not only for hydrology model estimations also for various comparisons of two data sets; This NSE has been often used for SWAT calibration. However, it has been known that the NSE value has some limitations in evaluating hydrology at watersheds under monsoon climate because this statistic is largely affected by higher values in the data set. To overcome these limitations, the SWAT auto-calibration module was enhanced with K-means clustering and direct runoff/baseflow modules. However the NSE is still being used in this module to evaluate model performance. Therefore, the SWAT Auto-calibration module was modified to incorporate alternative efficiency criteria into the SWAT K-means/direct runoff-baseflow auto-calibration module. It is expected that this enhanced SWAT auto-calibration module will provide better calibration capability of SWAT model for all flow regime.

• 한국기계가공학회지
• /
• 제11권4호
• /
• pp.118-124
• /
• 2012

In this study, we turning mold steel (SKD61) using whisker reinforced ceramic tool (WA1) to get affected factor to surface roughness and regression equation. For this study, we adapt system of experiments. Results are follows; From the analysis of variance, it was found that affected factor to surface roughness was feed rate, cutting speed, depth of cut in order. From multi-regression analysis, we calculated regression equation and the coefficient of determination($R^2$). $R^2$ was 0.978 and It means regression equation is significant. Regression equation means if feed rate increase 0.039mm/rev, surface roughness will increase $0.8391{\mu}m$, if cutting speed increase 50m/min, surface roughness will decrease $0.034{\mu}m$, if depth of cut increase 0.1mm, surface roughness will increase $0.0203{\mu}m$. From the experimental verification, it was confirmed that surface roughness was predictable by system of experiments.

• Corrosion Science and Technology
• /
• 제22권1호
• /
• pp.55-63
• /
• 2023

The aim of this study was to propose a multiple linear regression (MLR) equation to predict ultimate tensile strength (UTS) of 316L stainless steel with unspecified pit corrosion. Tensile specimens with pit corrosion were prepared using a potentiostatic acceleration test method. Pit corrosion was characterized by measuring ten factors using a confocal laser microscope. Data were collected from 22 tensile tests. At 85% confidence level, total pit volume, maximum pit depth, mean ratio of surface area, and mean area were significant factors showing linear relationships with UTS. The MLR equation using these three significant factors at a 85% confidence level showed considerable prediction performance for UTS. Determination coefficient (R²) was 0.903 with training and test data sets. The yield strength ratio of 316L stainless steel was found to be around 0.85. All specimens with a pit corrosion presented a yield ratio of approximately 0.85 with R² of 0.998. Therefore, pit corrosion did not affect the yield ratio.