• Structural Monitoring and Maintenance
• /
• 제9권4호
• /
• pp.337-357
• /
• 2022

The objective of this study is to present a data-driven machine learning (ML) framework for predicting ultimate shear strength and failure modes of reinforced concrete ledge beams. Experimental tests were collected on these beams with different loading, geometric and material properties. The database was analyzed using different ML algorithms including decision trees, discriminant analysis, support vector machine, logistic regression, nearest neighbors, naïve bayes, ensemble and artificial neural networks to identify the governing and critical parameters of reinforced concrete ledge beams. The results showed that ML framework can effectively identify the failure mode of these beams either web shear failure, flexural failure or ledge failure. ML framework can also derive equations for predicting the ultimate shear strength for each failure mode. A comparison of the ultimate shear strength of ledge failure was conducted between the experimental results and the results from the proposed equations and the design equations used by international codes. These comparisons indicated that the proposed ML equations predict the ultimate shear strength of reinforced concrete ledge beams better than the design equations of AASHTO LRFD-2020 or PCI-2020.

• Asian-Australasian Journal of Animal Sciences
• /
• 제28권9호
• /
• pp.1335-1344
• /
• 2015

A set of prediction equations to estimate the nitrogen-corrected apparent metabolizable energy (AMEn) of individual ingredients and diets used in the poultry feed industry was evaluated. The AMEn values of three energy ingredients (maize, sorghum and defatted maize germ meal), four protein ingredients (soybean meal, maize gluten meal 60% crude protein, integral micronized soy and roasted whole soybean) and four diets (three containing four feedstuffs, complex diets, and one containing only corn-soybean meal, basal diet) were determined using a metabolism assay with male broilers from 1 to 7, 8 to 21, 22 to 35, and 36 to 42 days old. These values were compared to the AMEn values presented in the tables of energy composition or estimated by equation predictions based on chemical composition data of feedstuffs. In general, the equation predictions more precisely estimated the AMEn of feedstuffs when compared to the tables of energy composition. The equation AMEn (dry matter [DM] basis) = 4,164.187+51.006 ether extract (% in DM basis)-197.663 ash-35.689 crude fiber (% in DM basis)-20.593 neutral detergent fiber (% in DM basis) ($R^2=0.75$) was the most applicable for the prediction of the energy values of feedstuffs and diets used in the poultry feed industry.

• Safety and Health at Work
• /
• 제2권3호
• /
• pp.236-242
• /
• 2011

Objectives: To determine the feasibility of predicting static and dynamic peak back-compressive forces based on (1) static back compressive force values at the lift origin and destination and (2) lifting speed. Methods: Ten male subjects performed symmetric mid-sagittal floor-to-shoulder, floor-to-waist, and waist-to-shoulder lifts at three different speeds (slow, medium, and fast), and with two different loads (light and heavy). Two-dimensional kinematics and kinetics were captured. Linear regression analyses were used to develop prediction equations, the amount of predictability, and significance for static and dynamic peak back-compressive forces based on a static origin and destination average (SODA) backcompressive force. Results: Static and dynamic peak back-compressive forces were highly predicted by the SODA, with R2 values ranging from 0.830 to 0.947. Slopes were significantly different between slow and fast lifting speeds (p < 0.05) for the dynamic peak prediction equations. The slope of the regression line for static prediction was significantly greater than one with a significant positive intercept value. Conclusion: SODA under-predict both static and dynamic peak back-compressive force values. Peak values are highly predictable and could be readily determined using back-compressive force assessments at the origin and destination of a lifting task. This could be valuable for enhancing job design and analysis in the workplace and for large-scale studies where a full analysis of each lifting task is not feasible.

• Asian-Australasian Journal of Animal Sciences
• /
• 제18권5호
• /
• pp.643-648
• /
• 2005

Near infrared reflectance spectroscopy (NIRS) has become increasingly used as a rapid, accurate method of evaluating some chemical constituents in cereal grains and forages. If samples could be analyzed without drying and grinding, then sample preparation time and costs may be reduced. This study was conducted to develop robust NIRS equations to predict fermentation quality of corn (Zea mays) silage and to select acceptable sample preparation methods for prediction of fermentation products in corn silage by NIRS. Prior to analysis, samples (n = 112) were either oven-dried and ground (OD), frozen in liquid nitrogen and ground (LN) and intact fresh (IF). Samples were scanned from 400 to 2,500 nm with an NIRS 6,500 monochromator. The samples were divided into calibration and validation sets. The spectral data were regressed on a range of dry matter (DM), pH and short chain organic acids using modified multivariate partial least squares (MPLS) analysis that used first and second order derivatives. All chemical analyses were conducted with fresh samples. From these treatments, calibration equations were developed successfully for concentrations of all constituents except butyric acid. Prediction accuracy, represented by standard error of prediction (SEP) and $R^2_{v}$ (variance accounted for in validation set), was slightly better with the LN treatment ($R^2$ 0.75-0.90) than for OD ($R^2$ 0.43-0.81) or IF ($R^2$ 0.62-0.79) treatments. Fermentation characteristics could be successfully predicted by NIRS analysis either with dry or fresh silage. Although statistical results for the OD and IF treatments were the lower than those of LN treatment, intact fresh (IF) treatment may be acceptable when processing is costly or when possible component alterations are expected.

• 한국산림과학회지
• /
• 제96권1호
• /
• pp.40-47
• /
• 2007

본 연구는 전라북도 진안 지역의 낙엽송을 대상으로 지위지수 추정과 지위지수곡선 유도 및 간재적식 개발을 목적으로 하였다. 지위지수에 대한 식은 대수차분 방정식에 의해 개발되었다. 기초 연령 40년으로 한 다형 지위지수 패밀리 곡선은 Schumacher 수고 방정식을 기초로 표현하였다. 최적의 간재적 추정식은 $V=0.00260+0.00000399D^2H$로 판명되었다. 이 방정식에 사용한 동시 F-검정에서 추정된 간재적량은 모델 평가에 관한 실측된 간재적량과 유의(${\alpha}=0.05$)하게 다르지 않음을 보여주었다. 지위지수 곡선과 재적 추정식의 결과는 지위와 수확표 조제시 기초 자료로 제공할 수 있고, 진안지역 낙엽송 임분의 지역 산림경영에 사용될 수 있을 것이다.

• 한국강구조학회 논문집
• /
• 제14권4호
• /
• pp.549-556
• /
• 2002

바닥구조의 진동을 평가하는데 있어 기존의 고유진동수 예측식에 의한 방법이 사용되어지고 있다. 그러나, 이러한 예측식들은 재료에 따른 구분이 없기 때문에 실제와느나 다른 결과를 보이게 된다. 또한, 합성데크 플레이트 슬래브의 경우, 고유진동수를 예측하기 위해 슬래브의 단면을 환산해야 하는데, 각 데크 플레이트의 특성상 그 형태가 상이함으로 인하여 많은 어려움을 느끼게 된다. 따라서, 본 논문에서는 슬래브의 단면을 환산하기 위한 새로운 단순화된 방법을 제시하였다. 그리고, 실제 측정값과 가장 오차율이 적은 "LRFD"에 제안된 고유진동수 산출식을 보정하여 기존 예측시에 비해 약 14.3%의 오차율을 개선하는 새로운 예측보정식을 제안하고, 이에 대한 일반적인 적용가능성을 검증하였다.

• 한국건축시공학회지
• /
• 제16권4호
• /
• pp.297-303
• /
• 2016

콘크리트 건조수축 균열을 제어하기 위하여 수축저감제(SRA)가 개발되었다. SRA는 콘크리트 미세공극의 표면장력을 작게 하여 수축량을 감소시키며, 콘크리트의 품질향상을 위하여 SRA의 사용이 증가되고 있다. 하지만 건조수축을 예측하기 위한 다양한 모델이 존재함에도 불구하고, SRA의 영향을 고려할 수 있는 예측방법이 아직까지 없는 실정이다. 따라서 SRA 콘크리트의 건조수축에 의해 발생하는 인장응력을 정확히 예측할 수 없고, 콘크리트 구조물의 정량적인 사용성 한계의 검토가 불가능하다. 본 연구에서는 SRA 콘크리트의 정량적인 건조수축 변형률 예측가능성을 제시하기 위하여, 건조수축실험값과 기존 모델에 의한 예측값을 비교하였다. 기존 모델에는 SRA의 영향을 고려할 수 없으므로, 실험결과에 근거하여 SRA 첨가율에 따른 수축저감계수를 도출하였고 기존 모델에 수축저감계수를 적용하여 예측값을 구하였다. 그 결과 AIJ 모델, ACI 모델, GL2000 모델은 ${\pm}10%$의 오차범위 내에서 예측값과 실측값이 전반적으로 양호한 상관관계를 보였지만, CEB-FIP 모델과 B3 모델은 예측값이 실측값을 과소평가 하는 것으로 나타났다.

• 해양환경안전학회지
• /
• 제25권7호
• /
• pp.851-857
• /
• 2019

본 연구는 운항선의 운항 빅데이터를 활용하여 머신러닝 기법의 선박 마력 예측에 관한 것이다. 현재 신조선에는 ISO15016법을 이용하여 외부환경 요인에 대하여 수식을 통해 저항을 예측하나 관련 계산식이 복잡하고 요구하는 입력변수들이 많아 운항하는 실선 적용에 많은 시간과 비용이 필요하다. 본 연구에서는 최근 예측, 인식 등에서 우수한 성능을 보이는 SVM(Support Vector Machine) 알고리즘을 이용하여 우수한 성능의 선박 출력 예측이 가능한 모델을 제안한다. 제안 예측 모델은 실선 운항 빅데이터만 확보된다면 ISO15016법 대비 우수한 성능의 예측이 가능한 장점이 있다. 본 연구에서는 178K 벌크캐리어의 운항 DATA를 활용하여 ISO15016 기법과 본 연구에서 제안하는 SVM 알고리즘 기반의 마력해석법을 비교하여 ISO15016의 단점인 선박 모델 데이터 준비 부분을 줄이고 부정확한 마력 예측 성능을 개선하였다.

• Tribology and Lubricants
• /
• 제36권6호
• /
• pp.371-377
• /
• 2020

In In this study, we compared the results of a ball bearing life prediction model based on rolling element loads with the results of fatigue life prediction of ball bearings when a stress-based contact fatigue life prediction technique is applied to the ball bearing. We calculate the load acting on each rolling element by the external load of the bearing and apply the result to the Lundberg-Palmgren (LP) theory to calculate ball bearing life based on the rolling element. We also calculate stress-based ball bearing life through contact and fatigue analyses based on contact modeling of the ball and raceway while considering the fatigue test results of AISI 52100 steel. In stress-based life prediction, we use three high-cycle fatigue-determination equations that can predict the fatigue life when multi-axis proportional loads such as rolling-slide contact conditions are applied. These equations are derived from the stress invariant and critical plane methods and the mesoscopic approach. Life expectancy results are compared with those of the LP model. Results of the analysis indicated that the fatigue life was predicted to be lower in the order of the Crossland, Dang Van, and Matake models. Of the three, the Dang Van fatigue model was found to be the closest to the LP life.

• 한국항해항만학회지
• /
• 제30권2호
• /
• pp.125-130
• /
• 2006

Waves, which are the main source of ship motions in a seaway, considerably affect the performance of a ship. The study of waves and their impact on ship motions within harbors is an important aspect of the design and operation of harbors. The prediction of incoming groups of waves is particularly important for evaluating ship motion within a harbor. Such a prediction makes it possible to evaluate ship safety more accurately. The wave transformation model reported here is applied to actual ports based on Boussinesq wave equations both non-linear and dispersive wave processes be considered in order to capture physical effects such as wave shoaling, refractions, reflection and diffraction in variable depth environments. The prediction of incoming groups of waves is particularly important for evaluating ship motion within a harbor, Such a prediction makes it possible to evaluate ship safety more accurately and provide safe wave informations for navigation. Furthermore, a wave information support system is proposed for entering ships as one technique for improving the safety of ship operations. This system predicts the run of waves and reduces the danger by identifying the most dangerous point near the harbor entrance at the small wave groups.