Papers by Keyword: Neural Network (NN)

Paper TitlePage

Authors: Zhong Gan, Zhi Wei Qian, Yu Shan Xia
Abstract: This paper proposes a more accurate springback prediction method of ageing forming for 2124 aluminum alloy. In age forming of panels, pre-bending radius, aging time and wall thickness of panels are selected as three parameters, make use of uniform design to arrange experiment and obtain springback radius using ABAQUS simulation. By means of regression analysis, the data is processed to get the influence caused by parameters on springback radius. Regression and BP neural network forecasting method are used respectively to predict springback radius and maximum prediction error is less than 31%. Combination method based on BP neural network is adopted and this method gets the satisfying prediction results that prediction error is within 5%. So conclusion can be drawn that prediction accuracy of combination method is much better than that of regression and BP neural network forecasting.
Authors: Aniruddha Ghosh, N.K. Singh, Somnath Chattopadhyaya
Abstract: An attempt has been made in this paper to develop a appropriate model for predicting the output responses of Submerged Arc Welding (SAW) process with the help of neural network technique. Also a mathematical model has been developed to study the effects of input variable (i.e. current, voltage, travel speed) on output responses (i.e. reinforcement height, weld bead width, metal deposition rate). SAW process has been chosen for this application because of the complex set of variables involved in the process as well as its significant application in the manufacturing of critical equipments which have a lot of economic and social implications. Under this study the neural network model is trained according to the actual inputs and outputs. When the training is completed then the desired inputs are given to the model and it gives the estimated output value. And according to this we can also estimate the error between the actual and predicted results. Side by side accurecy of mathematical model has been checked.
Authors: Zhong Fu Wang, Han Dong Liu, Tong Jiang, Si Wei Wan
Abstract: Based on geological condition of underground factory building in Hohhot pumped storage power station, research and analysis are taken for the fundamental element which affect initial stress field, 3D finite element model of underground factory building is build for the analysis. Beigin with regrssion analysis, adopt linear elasticity caculation of finite element method to take linear regression analysis, and obtain range of optimized parameters. Adopt homogeneous design to definite various assemblies of optimized parameters at different levels. Obtain training sample by elasto plastic caculation of finite element, train for RBF model in oder to get inverse model of ground stress field. The calculation result shown that: RBF model overcome the disadvantages such as slow calculating speed and overfitting of BP model, and it could obtain distrubution rule of initial stress filed by inverse analysis in a reasonable way.
Authors: Zhi Min Chen, De An Zhao
Abstract: The substantial difficulties are encountered as the huge computation of complex three-dimensional finite element model. Network parallel computing is one of the most compelling topics at the forefront in the current field of parallel computing, the size and the speed of structural analysis can be increased by the combination of both, so that large and complex three-dimensional finite element calculation can be carried out smoothly. According to Wushaoling tunnel, three-dimensional finite element model is established and implement under the support of the finite element parallel computing environment of Deep Comp 1800 cluster system based on the analysis of neural network. The realization of 3D geostress analysis is also depend on the artificial neural network computation program ANNBP and MEBAC, which is an interface program connecting ANNBP and ANSYS. The results show that the computation efficiency is highly improved by the Deep Comp 1800cluster system, the distribution of the initial geostress field is compacted significantly by the faults and there is a vertical extrusion characteristic with the tunnel at the fault zone.
Authors: Wen Qing Huang, Wen Jie Li, Hai Yan Hu, Ya Ming Wang, Ming Feng Jiang
Abstract: In this paper we use the method of MRF and neural network to solve the problem of parameters estimation in non-rigid 3D movement. Firstly, the method of MRF is used for modeling the local motion correlation of each feature point, and the 3D coordinates of each feature point are obtained. Then the method of neural network is used for clustering the feature points according to their motion situation. When the neural network reaches stabilization, we can get the motion parameters of each feature point. Finally, we correct the neighborhoods of each feature point according to motion parameters. The experimental results show that our algorithm can correctly estimate the non-rigid motion parameters.
Authors: Fan Jun Liu, Bin Gang Cao
Abstract: We present a 3D(three-dimensional)-modeling disparity-map optimization algorithm using a neural network and image segments for stereo navigation. We decompose the optimization algorithm problem into two sub-problems: initial stereo matching and depth optimization. A two-step procedure is proposed to solve the sub-problems sequentially. The first step is a region based NCC(normalized cross-correlation) matching process. But we use fast Fourier transformation and inverse fast Fourier transformation to eliminate redundant calculations in NCC, and we create a high-confidence disparity map by cross checking. In the second step, the reference image (the left image of the inputted stereo pair) is segmented into regions according to homogeneous color. A neural network is then built to model the three dimensional surface and applied to refine disparities in each image segment. The experimental results obtained for Middlebury test datasets and real stereo road images indicate that our method is competitive with the best stereo matching algorithms currently available. In particular, the approach has significantly improved performance for road images used in navigation and the disparity maps recovered by our algorithm are similar to ground truth data.
Authors: Chien Hsun Chen, Chin Fa Chen, Ming Hua Hsu, Iuon Chang Lin
Abstract: Volleyball is a popular exercise. There are not only lots of sports enthusiasts but also many professional athletes. In a variety of tactics and globalization of volleyball sport, the match situation becomes complex and intense a lot in the relative. However, for the professional athletes, the focus of training is still just the specific skills and fitness training, so only doing the traditional training courses will make the athletes more difficult to get the winning. Therefore, in this paper, a new training conception is proposed to enhance the volleyball players successful blocking rate by neural network.
Authors: Jun Zhou, Tao Xia, Ting Ting Wang, Hua Li Li, Yu Ping Fu
Abstract: This paper presents a new calibration method for binocular vision system, based on CPSO-BP neural network. Firstly, the training set of the back propagation (BP) neural network is formed by the image feature point extracted from the binocular vision system. Then the cooperate particle swarm optimization (CPSO) algorithm is introduced to optimize the weights of the BP neural network, making the network with a stronger ability of the global optimization. Experimental results demonstrate that the proposed CPSO-BP-based algorithm has a higher calibration precision than the traditional BP-based calibration method.
Authors: Hong Jun Chen, Jin Feng Bai
Abstract: Due to the complexity of coking coal, as well as the mixed nature of some single coal procured, the error is significantly larger to predict coke quality only through coal conventional indicators. Thus the coking enterprises urgently need a coke prediction method using many blend coal-related data. In view of the complexity of coking, there are some limitations as to the regression prediction method and neural network learning methods. On the base of the conventional indicators of single coal and coal rock indicators, the paper utilizes support vector machine to predict the cold and hot strength of coke. The experiments show that the accurate prediction of this method can meet the requirements of enterprises.
Authors: Yu Hua Zhu, Dian Zheng Zhuang, Ping Li, Wei Yan Tong
Abstract: It will be face some problems about the complicated reaction mechanism, environment uncertainty, serious nonlinear in nitric acid process .a method of creating steady-state model of nitric acid process using neural network. and used genetic algorithm to optimize parameter on neural network model. The result can provide reference for analyzing and optimizing the parameters of nitric acid process.
Showing 1 to 10 of 1234 Paper Titles