|Table of Contents|

Intelligent Prediction of E4303 Electrode Mechanical Properties Based on Fuzzy Neural Network


Research Field:
Publishing date:


Intelligent Prediction of E4303 Electrode Mechanical Properties Based on Fuzzy Neural Network
HUANG JunXU Yue-lan
School of Materials Science and Engineering,NUST,Nanjing 210094,China
carbon steel electrodes fuzzy neural network mechanical properties intelligent prediction
To acquire a prediction model reflecting the relationship between primary materials formula and the deposited metal mechanical properties of electrodes,formula design and resurfacing welding experiments are made on E4303 carbon steel electrode.Mechanical properties indexes of deposited metal including tensile strength,yield strength,elongation percentage,impacting works are also measured.Using the method of adaptive fuzzy neural network,a model for predicting electrode mechanical properties directly from primary material components is built.The model is used to predict the experiment data except training samples.Results show that the prediction average relative errors of tensile strength and yield strength are all below 5%,the prediction average absolute error of elongation percentage is only 0.021,the predicting effect of impacting works is improved compared with that using the BP network.This fuzzy neural network prediction model can accurately predict the deposited metal mechanical properties directly from primary material components.


[1] Carlson N A. Federated filter for fault-tolerant integrated navigation systems[A]. Proceedings of Position Location and Navigation System’88[C]. Orlando: IEEE, 1988: 110 -119.
[2] Carlson N A. Federated square root filter for decentra-lized parallel processes[J]. IEEE Trans on Aerospace and Electric, 1990, 26( 3) : 517 -525.
[3] Carlson N A. Federated Kalman filter simulation results [J]. Navigation, 1994 41( 3) : 297 -321.
[4] 陶俊勇,邱静,温熙森,等. 自适应联合滤波模型及 其在车载SINS /GPS 组合导航系统中的应用[J]. 信 息与控制, 2000, 29( 2) : 168 - 172.
[5] 李夜华,房建成. 一种多模型自适应联邦滤波器及 其在INS /CNS /GPS 组合导航系统中的应用[J]. 航 天控制, 2003, 21( 2) : 33 - 38.
[6] Jamshaid Ali,Fang Jiancheng. SINS/ANS/GPS integration using federated Kalman filter based on optimized information- sharing coefficients[A]. AIAA Guidance,Navigation, and Control Conf[C]. Reston,VA,USA: AIAA, 2005: 6028 -6040.
[7] 吴训忠,周军,邱恺. 基于故障因子函数的鲁棒联邦 滤波算法研究[J]. 宇航学报, 2006, 27( 1) : 57 - 60.
[8] 李金梁,吴训忠,张宗麟. 基于矩阵摄动理论的联邦 滤波信息分配方法[J]. 系统工程与电子技术, 2007, 29( 11) : 1940 - 1944.
[9] 胡志强,张瑛,邱恺. 基于故障概率的联邦滤波鲁棒 信息分配方法[J]. 系统工程与电子技术, 2008,30 ( 9) : 1801 - 1804.
[10] Shortelle K J,Graham W R,Rabourn C. F-16 Flight tests of a rapid transfer alignment procedure[A]. IEEE Position Location and Navigation Symposium[C]. Piscataway, NJ,USA: IEEE, 1998: 379 - 386.
[11] Joon Lyou,Lim You-Chol. Transfer alignment error compensator design based on robust state estimation[A]. Transactions of the Japan Society for Aeronautical and Space Sciences[C]. Tokyo,Japan: Society for Aeronautical and Space Sciences, 2005: 143 - 151.
[12] 程向红,万德钧. 分布式系统中捷联惯性系统动基 座对准研究[J]. 中国惯性技术学报2004, 12( 6) : 8 - 12.
[13] Gu Dong-qing,Qin Yong-yuan,Peng Rong, et al. Rapid transfer alignment using federated kalman filter[J]. Transactions of Nanjing University of Aeronautics and Astronautics, 2005, 22( 2) : 139 - 143


Last Update: 2012-04-30