جستجو در تالارهای گفتگو

LEAST SQUARES SUPPORT VECTOR MACHINE FOR CONSTITUTIVE MODELING OF CLAY X. Zhou and J. Shen Abstract Constitutive modeling of clay is an important research in geotechnical engineering. It is difficult to use precise mathematical expressions to approximate stress-strain relationship of clay. Artificial neural network (ANN) and support vector machine (SVM) have been successfully used in constitutive modeling of clay. However, generalization ability of ANN has some limitations, and application of SVM in large scale function approximation problems is limited during optimization. In this paper, least squares support vector machine (LSSVM) is proposed to simulate stress-strain relationship of clay. LSSVM is a robust type of SVM, maintains the good features of SVM and also has its own unique advantages. LSSVM offers an effective alternative for mimicking constitutive modeling of clay. The good performance of the LSSVM models is demonstrated by learning and prediction of constitutive relationship of Fujinomori clay under undrained and drained conditions. In the present study, three versions of LSSVM models are built by considering more history points. The results prove that the LSSVM based models are superior to Modified Cam-clay model. Keywords Constitutive modeling, Artificial neural network (ANN), Support vector machine (SVM), Least squares support vector machine (LSSVM), Fujinomori clay چکیده مدل سازی ساختاری خاک رس از جمله تحقیقات مهم در مهندسی ژئوتکنیک است. استفاده از عبارات دقیق ریاضی برای تخمین رابطه تنش-کرنش خاک رس دشوار است. شبکه عصبی مصنوعی (ANN) و ماشین بردار پشتیبان (SVM) با موفقیت در مدل سازی ساختاری خاک رس استفاده شده اند. با این حال، توانایی تعمیم شبکه عصبی با برخی از محدودیتها روبروست و استفاده از SVM در مسائل تقریب تابع در مقیاس بزرگ در طول بهینه سازی محدود است. در این مقاله، حداقل مربعات ماشین بردار پشتیبانی (LSSVM) برای شبیه سازی رابطه تنش-کرنش خاک رس پیشنهاد شده است. LSSVM یک نوع قوی از SVM است که ویژگی های خوب SVM را حفظ کرده و همچنین دارای مزایای منحصر به فرد خود است. LSSVM جایگزین موثری برای تقلید مدل سازی ساختاری خاک رس ارائه می دهد. عملکرد خوب مدل LSSVM با یادگیری و پیش بینی رابطه ساختاری خاک رس Fujinomori تحت شرایط زهکشی نشده و خشک نشان داده می‌شود. در مطالعه حاضر، سه نسخه از مدل LSSVM با در نظر گرفتن نقاط تاریخی بیشتر ساخته شده است. نتایج ثابت می‌کند که مدل های بر اساس LSSVM نسبت به مدل بادامک خاک رس اصلاح شده برتری دارند. منبع دانلود 28-11-4.pdf

Estimations of Sediments in Mahabad Dam Using Artificial Neural Networks and Comparing the Results with Hydrometer Approach Original Article, D37 Khezri H, Merufinia E. J. Civil Eng. Urban. 4(3): 245-250. 2014 ABSTRACT: A deposition phenomenon is considered as one of the hydrometer processes which have ability to influence the most of the hydraulic structures and facility constructions. The exact assessment of the deposition of the rivers plays an important role not only in the management of the water sources, but also it is deemed that this factor also may have an influence on the designing, fabricating and planning phase of the utilization of Hydraulic Structures. In this survey, Neural Networks along with appropriate structure and self-training system is used as one of the methods of the estimating the amount of the sediments related to the Mahabad barrier, also the results of this survey are compared with the result of the hydrometer method. To this end, the discharge statistics of the water and sediments in two Cawter hydrometer station and Baitas village within the basin of Mahabad Dam catchment is investigated separately and at the end the estimation of the sediment load is compared and surveyed respectively by using neural networks in the Nero solution software via the multi-layer model of the Perceptron and the prevalent hydrometer approach. The results point out that the multi-layer networks in prognosticating a measure of the sediments is superior to hydrometer method. Keywords: Artificial Neural Network, Hydrometer Method, Nero solution, Sediments. منبع: [Hidden Content] دانلود: [Hidden Content].,%204%20(3)%20245-250,%202014.pdf J. Civil Eng. Urban., 4 (3) 245-250, 2014.pdf

Sediment load estimation by MLR, ANN, NF and Sediment Rating Curve (SRC) in Rio Chama River Original Article, C22 Ghorbani M.A, Hosseini S.H, Fazelifard M.H, Abbasi H. Journal. Civil Eng. Urban. 3(4):136-141. 2013 ABSTRACT:As the major part of river sediments is suspended sediment load, its estimation has important significance to manage of the water resources and environments. In this study, two conventional models: Sediment Rating Curve (SRC) and Multi Linear Regression (MLR) and two artificial intelligent models Artificial Neural Network (ANN) and Neuro-Fuzzy (NF) are applied to estimate suspended sediment load of the Rio Chama, a major tributary river of the Rio Grande, in the U.S. states of Colorado and New Mexico. Three statistical parameters–coefficient of determination (R2), root mean square error (RMSE) and Nash-Sutcliffe efficiency (NSE) are used to compare the results of models. The resul­­­­ts showed that ANN using only discharge as input and NF model using both discharge and sediment as inputs have better performance than other two models. Furthermore, in this study, mentioned models are applied to evaluate annual sediment load and the best results have been achieved from NF and ANN respectively. Results of this study may be useful in picking up the most suitable modeling approach for similar studies in other river basins. Keywords: artificial neural network; neuro-fuzzy; regression analysis; sediment rating curve; suspended sediment load منبع: [Hidden Content] دانلود: [Hidden Content].,22-136-141.pdf J. Civil Eng. Urban.,22-136-141.pdf

Optimization of Clay Core Dimensions in Earth Fill Dams Using Particle Swarm Algorithm Original Article, B31 Roshani E, Farsadizadeh D. Journal. Civil Eng. Urban. 2(5): 176-181. 2012. ABSTRACT: The flow rate from earth fill dam body mainly depends on the dimensions and characteristics of the clay core. Thus, finding the optimized dimensions for clay core in non-homogeneous earth fill dam is essential. In order to decrease water loss, the clay core should be expanded this leads to dramatic increment in construction volume and costs. The novelty of this issue could be expressed as an optimization material in which the total cost of lost water and earthwork should be minimized. The method serves us a simpler and an accurate solution for an earth fill dam to be in optimised dimensions. The objective function is consisting of two parts. The first part is to calculate the water seepage volume through the dam core with a combination of finite element method and artificial neural network (ANN) and the second part encounters the costs regarding to the volume of earth works. Finally the best answer from the economical view will be chosen according to the amount of seepage and core volume. Since calculating water seepage through soil using finite element method is time consuming, first a combination of 600 different potential shapes of the core has been modelled by finite element and then the result have been used to train an artificial neural network. Comparing this model with linear and logarithmic regression models proved that ANN evaluates water flow rate with more precession. Output data, including flow rate, entered to the particle swarm optimization (PSO) algorithm and the optimized dimensions were achieved. The proposed model for optimizing the clay core dimension can be applied for non-homogeneous earth fill dams with impervious foundation. Allavian earth fill dam was chosen to show the benefit of using the proposed optimization method in a real world case study. The results indicated that the construction cost could be dramatically less than what has been already spent on the case study. Keywords:Optimization, Clay core, Artificial neural network, Particle swarm optimization منبع: [Hidden Content] دانلود: [Hidden Content],%20B%2031%20176-181.pdf JCEU, B 31 176-181.pdf