Tienfuan Kerh

Neural network estimation of ground peak acceleration at stations along Taiwan high-speed rail system

It is essential to understand the characteristics of strong motion for reducing the negative impacts in a high-risk area. In this work, a combination of seismic parameters including epicentral distance, focal depth, and magnitude from historical records at 30 checking stations were used in back-propagation neural network model, to estimate peak ground acceleration at ten train stations along the high-speed rail system in Taiwan. The estimation was verified with available microtremor measurement at a specified station, and the calculated horizontal acceleration was checked with the existing building code requirements. A potential hazardous station was identified from the neural network estimation, which exhibited a significantly higher acceleration than that of the design value. The obtained results might be useful for revising the currently applied building code at this region to further fit in the actual earthquake response.

Neural networks approach and microtremor measurements in estimating peak ground acceleration due to strong motion

Peak ground acceleration is a very important factor that must be considered in construction site for examining the potential damage resulting from earthquake. The actual records by seismometer at stations related to the site may be taken as a basis, but a reliable estimating method may be useful for providing more detailed information of the strong motion characteristics. Therefore, the purpose of this study was by using back-propagation neural networks to develop a model for estimating peak ground acceleration at two main line sections of Kaohsiung Mass Rapid Transit in Taiwan. Additionally, the microtremor measurements with Nakamura transformation technique were taken to further validate the estimations. Three neural networks models with different inputs including epicentral distance, focal depth and magnitude of the earthquake records were trained and the output results were compared with available nonlinear regression analysis. The comparisons exhibited that the present neural networks model did have a better performance than that of the other methods, as the calculation results were more reasonable and closer to the actual seismic records. Besides, the distributions of estimating peak ground acceleration from both of computations and measurements might provide valuable information from theoretical and practical standpoints.

Neural networks forecasting of flood discharge at an unmeasured station using river upstream information

Abstract Based upon information at stations upstream of a river, a back-propagation neural network model was employed in this study to forecast flood discharge at station downstream of the river which lacks measurement. The performance of the neural network model was evaluated from the indices of root mean square error, coefficient of efficiency, error of peak discharge, and error of time to peak. The verification results showed that the neural network model is preferable, which performs relatively better than that of the conventional Muskingum method. Furthermore, the developed model with different input parameters was trained to check the sensitivity of physiographical factors. The results exhibited that flood discharge and water stage, are two factors to dominate the accuracy of estimation. Meanwhile, the physiographical factors had a slight and positive influence on the accuracy of the prediction. The time varied flood discharge forecasting at an unmeasured station might provide a valuable reference for designing an engineering project in the vicinity of the investigation region.

A mixture neural methodology for computing rice consumptive water requirements in Fada N’Gourma Region, Eastern Burkina Faso

Crop consumptive water requirement (Crop-ET) is a key variable for developing management plans to optimize the efficiency of water use for crop production particularly in semiarid zone. In Burkina Faso, the unfavorable climatic conditions characterized by the low and unevenly distribution of rainfall have pushed water resources management to the forefront of the crop production issue. Crop-ET is extremely required in rainwater effective management for mitigating the impact of water deficit on the crops. Basically, Crop-ET determination involves reference evapotranspiration (ETo) and crop coefficient (Kc) which required complete climatic data and specific site crop information, respectively. ETo estimation with the recommended FAO56 Penman–Monteith (PM) equation is limited in Burkina Faso due to the numerous meteorological data required which are not always available in many production sites. In such circumstances, research to compute directly Crop-ET as an alternative to the two-step approach of calculating ETo and determining site specific Kc, seems desirable. Therefore, this study aims to evaluate the performance of a mixture principal component analysis neural network (PCANN) model for computing rice Crop-ET directly from temperatures data in Fada N’Gourma region located in Eastern Burkina Faso, Africa. From the statistical results, rice Crop-ET can be successfully computed by using PCANN methodology, when only temperatures data are available in this African semiarid environment. Thus, in poor data situation, Crop-ET direct computation can be rapidly addressed through PCANN model for agricultural water management in African semiarid regions.

Neural computing with genetic algorithm in evaluating potentially hazardous metropolitan areas result from earthquake

In this study, neural network models improved by genetic algorithm were employed to estimate peak ground acceleration (PGA) at seven metropolitan areas in the island of Taiwan, which is frequently subject to earthquakes. By considering a series of historical seismic records, and using the seismic design value in the current building code as the evaluation criteria, two metropolitan areas, Taichung and Chiayi, were identified by computational results as having higher estimated horizontal PGAs than the recommended design values. The approach implemented in this study provides a new and good basis for solving this type of seismic problems in the region studied.

Analysis of a deformed three-dimensional culvert structure using neural networks

Abstract Applying dynamic backpropagation neural networks with energy function as minimization index, the deformed behaviors for culvert structure under a static loading are analyzed in this paper. The training process is avoided by using stiffness matrix and force vector of the structure instead of using weighting matrix and bias vector in the neural networks calculations. The ability of neural networks is verified by comparing the results with analytical solutions and finite element solutions. In order to improve the numerical accuracy, three grid systems are used to model the problem and to check the grid independence. From the concept of energy, the existence of an attractor for the three grid systems is proved and the solution is obtained accordingly. In addition, from the numerical experiments, the convergence rate can be accelerated significantly by introducing a relaxation factor in the calculation. Based on the displacement profile and the three-dimensional displacement plot, the results reasonably show that more downward deformations occur at the centerline of the whole culvert structure, particularly at the top surface of the centerline. The obtained information may provide a better understanding of typical structural problems frequently found in the field of civil engineering.

Neural Network Approach for Analyzing Seismic Data to Identify Potentially Hazardous Bridges

Examining the effect of strong ground motions on civil engineering structures is important as it concerns public safety. The present study initially selects twenty-one bridges with lengths over 500 m in the Formosa freeway of Taiwan and collects a series of recorded seismic data from checking stations near these bridges. Then, three seismic parameters including focal depth, epicenter distance, and local magnitude are used as the input data sets, and a model for estimating the key seismic parameter—peak ground acceleration—for each of bridge site is developed by using the neural network approach. This model is finally combined with a simple distribution method and a new weight-based method to estimate peak ground acceleration at each of the bridges along the freeway. Based on the seismic design value in the current building code as the evaluation criteria, the model identifies five bridges, out of all the bridges investigated, as having the potential to be subjected to significantly higher horizontal peak ground accelerations than that recommended for design in the building code. The method presented in this study hence provides a valuable reference for dealing with nonlinear seismic data by developing neural network model, and the approach presented is also applicable to other areas of interest around the world.

Predictions of confined shear flows over a wall obstacle

The conventional penalty function finite element model and balancing diffusivity upwind scheme are adopted to simulate shear flows over a surface-mounted obstacle within flow domain. Experimental data and flow visualization made available by previous investigators are ued to assess applicability of the present numerical scheme. With a nonuniform grid system, both schemes have been shown to eliminate numerical oscillations that are generated from nonlinear advection. The computational results reveal that strength of recirculaating zone behind the wall obstacle is in proportion to width/height ratio of the obstacle, and the pressure loss coefficient increases rapidly as the ratio is increased

Finite element analysis of fluid motion with an oscillating structural system

Abstract Analysis of unsteady flow through an oscillating structural system is carried out by using consistent penalty function finite element method and Newmark approach for both fluid and solid. Physical variables including displacement, velocity, and acceleration are presented as a function of time to describe movements of the solid system. The resulting flow fields such as velocity vectors and pressure distributions are displayed for various time steps. The shear stress along channel walls and the pressure coefficient versus time are also shown in this paper. The results revealed that motion of the solid body which becomes a moving boundary had a significant influence on the flow fields. In a steady inlet flow, the structural system can be balanced by the fluid force, and steady-state responses for both fluid and solid are then reached for a sufficiently long time.

Seismic Design Value Evaluation Based on Checking Records and Site Geological Conditions Using Artificial Neural Networks

This study proposes an improved computational neural network model that uses three seismic parameters (i.e., local magnitude, epicentral distance, and epicenter depth) and two geological conditions (i.e., shear wave velocity and standard penetration test value) as the inputs for predicting peak ground acceleration—the key element for evaluating earthquake response. Initial comparison results show that a neural network model with three neurons in the hidden layer can achieve relatively better performance based on the evaluation index of correlation coefficient or mean square error. This study further develops a new weight-based neural network model for estimating peak ground acceleration at unchecked sites. Four locations identified to have higher estimated peak ground accelerations than that of the seismic design value in the 24 subdivision zones are investigated in Taiwan. Finally, this study develops a new equation for the relationship of horizontal peak ground acceleration and focal distance by the curve fitting method. This equation represents seismic characteristics in Taiwan region more reliably and reasonably. The results of this study provide an insight into this type of nonlinear problem, and the proposed method may be applicable to other areas of interest around the world.