A cooperative expert based support vector regression (Co-ESVR) system to determine collar dimensions around bridge pier
نویسندگان
چکیده
In this study, a new procedure to determine the optimum dimensions for a rectangular collar to minimize the temporal trend of scouring around a pier model is proposed. Unlike previous methods of predicting collar dimensions around a bridge pier, the proposed approach concerns the selection of different collar dimension sizes around a bridge scour in terms of the flume's upstream (Luc/D), downstream (Ldc/D) and width (Lw/D) of the flume. The projected determination method involves utilizing Expert Multi Agent System (E-MAS) based Support Vector Regression (SVR) agents with respect to cooperative-based expert SVR (Co-ESVR). The SVR agents (i.e. SVRLuc, SVRLdc and SVRLw) are set around a rectangular collar to predict the collar dimensions around a bridge pier. In the first layer, the Expert System (ES) is adopted to gather suitable data and send it to the next layer. The multi agent-based SVR adjusts its parameters to find the optimal cost prediction function in the collar dimensions around the bridge pier to reduce the collar around the bridge scour. The weighted sharing strategy was utilized to select the cost optimization function through the root mean square error (RMSE). The efficiency of the proposed optimization method (Co-ESVR) was explored by comparing its outcomes with experimental results. Numerical results indicate that the Co-ESVR achieves better accuracy in reducing the percentage of scour depth (re) with a smaller network size, compared to the non-cooperative approaches. & 2014 Elsevier B.V. All rights reserved.
منابع مشابه
Effect of collar on time development and extent of scour hole around cylindrical bridge piers
An experimental approach was carried out to study the time development and extension of scouring around a circular pier protected by a collar. The experiments included the study of scouring around an unprotected pier as well as the pier protected with collars located at different levels. Width of collars was 3 times the pier diameter. It was found that with collars, though the scour depth and t...
متن کاملتاثیر لایه ژئوتکستایل در کاهش آبشستگی موضعی پایه استوانهای پل
Flood currents are considered threatening factors by creating local scour along bridge piers. One method for decreasing local scour is to strengthen the bed against imposed tensions. Among methods which can directly be appropriate in decreasing and controlling local scour of bridge piers is to employ geotextile around bridge piers. In the present study, the effect of geotextile layer in decreas...
متن کاملEffect of Collars and Bars in Reducing the Local Scour Around Cylindrical Bridge Piers
In the present work, the efficiency of single and double collar in reducing scour rate and depth around cylindrical bridge piers was studied experimentally. In order to reduce the strength of wake vortices, different numbers of bars were also installed at the downstream face of the pier in combination with a single collar. The best result was achieved for double collar when the collars were ins...
متن کاملبررسی آزمایشگاهی اثر طوقه در کنترل آبشستگی اطراف پایه پل استوانهای در قوس 180 درجه رودخانه
Every year river flooding causes serious damage to the bridges at the time needed most. One of the most effective factors causing bridge failure is scouring around the piers in a river bend. One of the methods to decrease scouring around the bridge piers is fitting them with a coller on the piers. The collars protect the river bed against vortex flow in the vicinity of the pier base. An experim...
متن کاملExtreme Support Vector Regression
Extreme Support Vector Machine (ESVM), a variant of ELM, is a nonlinear SVM algorithm based on regularized least squares optimization. In this chapter, a regression algorithm, Extreme Support Vector Regression (ESVR), is proposed based on ESVM. Experiments show that, ESVR has a better generalization ability than the traditional ELM.Furthermore, ESVMcan reach comparable accuracy as SVR and LS-SV...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Neurocomputing
دوره 140 شماره
صفحات -
تاریخ انتشار 2014