• Nuclear Engineering and Technology
• /
• 제54권1호
• /
• pp.310-317
• /
• 2022

The mass attenuation coefficient is the primary physical parameter to model narrow beam gamma-ray attenuation. A new machine learning based approach is proposed to model gamma-ray shielding behavior of composites alternative to theoretical calculations. Two fuzzy logic algorithms and a neural network algorithm were trained and tested with different mixture ratios of vanadium slag/epoxy resin/antimony in the 0.05 MeV-2 MeV energy range. Two of the algorithms showed excellent agreement with testing data after optimizing adjustable parameters, with root mean squared error (RMSE) values down to 0.0001. Those results are remarkable because mass attenuation coefficients are often presented with four significant figures. Different training data sizes were tried to determine the least number of data points required to train sufficient models. Data set size more than 1000 is seen to be required to model in above 0.05 MeV energy. Below this energy, more data points with finer energy resolution might be required. Neuro-fuzzy models were three times faster to train than neural network models, while neural network models depicted low RMSE. Fuzzy logic algorithms are overlooked in complex function approximation, yet grid partitioned fuzzy algorithms showed excellent calculation efficiency and good convergence in predicting mass attenuation coefficient.

• 한국수자원학회논문집
• /
• 제38권7호
• /
• pp.565-574
• /
• 2005

평창강 수질자동측정망 실시간 자료를 이용하여 강우시와 무강우시로 구분하여 분석하였다. 강우시에 측정된 TOC 자료는 무강우시 측정된 자료에 비해 평균값, 최대값, 표준편차가 크게 나타났으며, 강우시의 DO 자료는 무강우시에 측정된 자료보다 낮아 유량이 수질변화에 영향을 미치는 것으로 분석되었다. 신경망 모형과 뉴로-퍼지 모형으로 수질예측 모형을 구성하고, 적용하였다. LMNN, MDNN, ANFIS 모형은 TOC 모의에서 DO 예측에서는 LMNN, MDNN 모형이 ANFIS 모형보다 좋은 결과를 보였으며, 정량적 자료에 정성적 자료인 시간을 학습한 MDNN 모형이 가장 작은 오차를 보였다. 하천의 실시간적 관리를 위해서는 유량과 수질의 측정이 동일한 지점에서 동시간적으로 이루어져야 보다 효과적이다. 그러나 수질자동측정망 지점과 T/M 수위관측소가 원거리에 위치한 경우들이 있으며, 평창강 수질자동측정망 지점이 그 중 하나이다. 연구에서는 평창강 수질자동측정망 지점의 유출예측을 위한 신경망 모형을 구성하여 수질예측 모형과 연계하였으며, 연계된 모형은 수질예측에 개선된 결과를 보였다.

• International Journal of Precision Engineering and Manufacturing
• /
• 제3권4호
• /
• pp.24-30
• /
• 2002

In grinding operations, one of the most important problems is to increase efficiency of process. In order to achieve this purpose, it is necessary to administer the tool lift of grinding wheel and to optimize grinding conditions. Frequently dressing result in lowering the process efficiency remarkably and makes production cost high. On the other hand, grinding with a worn wheel causes the workpiece surface roughness to increase and often results in the occurrence of such troubles as chatter vibration and homing.

• Computers and Concrete
• /
• 제32권2호
• /
• pp.119-138
• /
• 2023

Concrete carbonation is a prevalent phenomenon that leads to steel reinforcement corrosion in reinforced concrete (RC) structures, thereby decreasing their service life as well as durability. The process of carbonation results in a lower pH level of concrete, resulting in an acidic environment with a pH value below 12. This acidic environment initiates and accelerates the corrosion of steel reinforcement in concrete, rendering it more susceptible to damage and ultimately weakening the overall structural integrity of the RC system. Lower pH values might cause damage to the protective coating of steel, also known as the passive film, thus speeding up the process of corrosion. It is essential to estimate the carbonation factor to reduce the deterioration in concrete structures. A lot of work has gone into developing a carbonation model that is precise and efficient that takes both internal and external factors into account. This study presents an ML-based adaptive-neuro fuzzy inference system (ANFIS) approach to predict the carbonation depth of fly ash (FA)-based concrete structures. Cement content, FA, water-cement ratio, relative humidity, duration, and CO2 level have been used as input parameters to develop the ANFIS model. Six performance indices have been used for finding the accuracy of the developed model and two analytical models. The outcome of the ANFIS model has also been compared with the other models used in this study. The prediction results show that the ANFIS model outperforms analytical models with R-value, MAE, RMSE, and Nash-Sutcliffe efficiency index values of 0.9951, 0.7255 mm, 1.2346 mm, and 0.9957, respectively. Surface plots and sensitivity analysis have also been performed to identify the repercussion of individual features on the carbonation depth of FA-based concrete structures. The developed ANFIS-based model is simple, easy to use, and cost-effective with good accuracy as compared to existing models.

• 한국습지학회지
• /
• 제13권3호
• /
• pp.547-565
• /
• 2011

수위예측을 위해 개념적, 물리적 모형들을 포함한 다양한 유형의 기법들이 사용되고 있다. 그럼에도 불구하고 이러한 기법들 중 수위예측을 위해 단일의 우수한 모형을 선정하는 것은 매우 어려운 일이다. 최근에는 수문학적 과정의 복잡성으로 인해 기존 물리적 기반의 강우-유출 모형이 가지고 있는 단점들을 극복하고자 자료 지향형 수위예측 모형이 널리 도입되고 있다. 본 연구의 목적은 이러한 자료 지향형 모형 중 뉴로-퍼지와 회귀분석 모형의 수위예측에 대한 성능을 비교하는 것이다. 제안된 두 모형을 한강수계의 왕숙천에 대해 적용하였다. 제안된 두 모형의 성능을 평가하기 위해 평균제곱근오차, Nash-Suttcliffe 효율계수, 평균절대오차, 수정 결정계수와 같이 4개의 통계지표들을 사용하였다. 모의결과 뉴로-퍼지 수위예측 모형이 다중선형회귀 수위예측 모형보다 좀 더 나은 예측 결과를 나타내는 것을 확인할 수 있었다. 본 연구결과는 향후 중소하천에서 충분한 선행시간을 확보한 정확도 높은 홍수정보시스템의 구축에 활용할 수 있을 것으로 판단된다.

• 대한토목학회논문집
• /
• 제29권1D호
• /
• pp.33-40
• /
• 2009

횡단보행자의 임계간격은 비신호 횡단보도에서의 교통운영분석에 중요한 파라메타이나 국내에서는 이 분야의 연구가 빈약한 실정이다. 이에 본연구의 목적은 횡단보행자의 임계간격 추정을 위한 모형을 개발하는데 있다. 이를 위해, 이 임계간격 에 영향을 미치는 인자들 중 퍼지적 성격을 가진 보행자 연령과 횡단보도의 연장, 거절되거나 수락되는 간격이 연장 3.5m에서 10.5m 범위의 행단보도에서 수집되었다. 이들 횡단보도에서의 임계간격은 2.56초에서 5.56초 범위의 값을 보였다. 연령과 횡단보도 연장이 각각 3개의 퍼지변수로 구분되고 각 경우에 대하여 Raff의 기법에 의한 임계간격이 추정되어 총 9개의 퍼지규칙이 설정되었다, 이들 규칙에 기초하여 횡단보행자 임계간격을 추정할 수 있는 ANFIS모형이 구축되었다. 모형의 예측력은 실측치와 추론치를 비교함으로써 평가되었다. 결정계수 $R^2$와 오차 및 분산정도를 나타내는 척도인 평균절대 오차(MAE) 및 평균제곱근 오차(MSE)가 각각 0.96, 0.097, 0.015로 나타나 본 모형의 설명력이 높은 것으로 평가된다. 본 연구의 과정에서 보행자의 연령 40세 이후 임계간격의 증가율이 높음을 볼 수 있었다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 추계학술대회 학술발표 논문집
• /
• pp.46-50
• /
• 2001

Voice is one of the most efficient communication media and it includes several kinds of factors about speaker, context emotion and so on. Human emotion is expressed in the speech, the gesture, the physiological phenomena (the breath, the beating of the pulse, etc). In this paper, the method to have cognizance of emotion from anyone's voice signals is presented and simulated by using neuro-fuzzy model.

• Computers and Concrete
• /
• 제32권1호
• /
• pp.27-44
• /
• 2023

The current study targets to apply the adaptive neuro-fuzzy inference system (ANFIS) for the estimation of the shear resistance offered by the externally bonded fiber-reinforced polymer (EB-FRP) U-jackets. A total of 202 groups of data cumulated from previous investigations, were employed for the development and evaluation of the ANFIS model. A relative appraisal between the ANFIS predictions and the results of experiments has shown that the assessments by current ANFIS model are in good concurrence with the latter. In addition, assessment of the accuracy of the ANFIS model was done by relating the ANFIS predictions with the forecasts of eight extensively used design guidelines. Based on the examination of various performance measures, it has been derived that the adequacy of the ANFIS model is better than the available guidelines. A parametric investigation has additionally been done to reconnoiter the influence of individual parameters as well as their combined effects on the shear contribution of EB-FRP. Based on the observations made from the parametric study, it has been witnessed that the ANFIS model has incorporated the effect of different parameters more competently than the considered design guidelines.

• Geomechanics and Engineering
• /
• 제31권4호
• /
• pp.339-352
• /
• 2022

Studying slope stability is an important branch of civil engineering. In this way, engineers have employed machine learning models, due to their high efficiency in complex calculations. This paper examines the robustness of various novel optimization schemes, namely equilibrium optimizer (EO), Harris hawks optimization (HHO), water cycle algorithm (WCA), biogeography-based optimization (BBO), dragonfly algorithm (DA), grey wolf optimization (GWO), and teaching learning-based optimization (TLBO) for enhancing the performance of adaptive neuro-fuzzy inference system (ANFIS) in slope stability prediction. The hybrid models estimate the factor of safety (F_S) of a cohesive soil-footing system. The role of these algorithms lies in finding the optimal parameters of the membership function in the fuzzy system. By examining the convergence proceeding of the proposed hybrids, the best population sizes are selected, and the corresponding results are compared to the typical ANFIS. Accuracy assessments via root mean square error, mean absolute error, mean absolute percentage error, and Pearson correlation coefficient showed that all models can reliably understand and reproduce the F_S behavior. Moreover, applying the WCA, EO, GWO, and TLBO resulted in reducing both learning and prediction error of the ANFIS. Also, an efficiency comparison demonstrated the WCA-ANFIS as the most accurate hybrid, while the GWO-ANFIS was the fastest promising model. Overall, the findings of this research professed the suitability of improved intelligent models for practical slope stability evaluations.

• 제어로봇시스템학회논문지
• /
• 제5권8호
• /
• pp.907-913
• /
• 1999

For an automated transportation system like PRT(Personal Rapid Transit) system or IVHS, an efficient vehicle-merging algorithm is required for smooth operation of the network. For management of merging, collision avoidance between vehicles, ride comfort, and the effect on traffic should be considered. This paper proposes an unmanned vehicle-merging algorithm that consists of two procedures. First, a longitudinal control algorithm is designed to keep a safe headway between vehicles in a single lane. Secondly, 'vacant slot and ghost vehicle' concept is introduced and a decision algorithm is designed to determine the sequence of vehicles entering a converging section considering energy consumption, ride comfort, and total traffic flow. The sequencing algorithm is based on fuzzy rules and the membership functions are determined first by an intuitive method and then trained by a learning method using a neural network. The vehicle-merging algorithm is shown to be effective through simulations based on a PRT model.