期刊
COMPOSITES PART B-ENGINEERING
卷 92, 期 -, 页码 420-433出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.compositesb.2016.02.008
关键词
Glass fibres; Polymer-matrix composites (PMCs); Debonding; Statistical properties/methods; Numerical analysis
资金
- ND NASA EPCoR [FAR0023941]
- ND NSF EPSCoR [FAR0022364]
- US DOT [FAR0025913]
- Hughes Brother Inc.
- Office Of The Director
- Office of Integrative Activities [1355466] Funding Source: National Science Foundation
Anchorage is of critical importance in the glass fibre-reinforced polymer (GFRP) bar reinforced concrete structures to allow reinforcing GFRP bars to provide sufficient bond to concrete. This study presents a new strategy for anchorage reliability assessment of GFRP bars to concrete by integrating superiorities of artificial neural network (ANN) and genetic algorithm (GA). The new methodology harnesses not only the strong nonlinear mapping ability in the ANN to approximate the performance function (PF) and solve its partial derivatives in terms of the design variables, but also global searching ability in the GA to explore the optimal initial weights and biases of the ANN to avoid falling into local minima during the network training. The ANN-based first order second moment (FOSM) method and Monte Carlo simulation (MCS) method were first derived. Implementation of the proposed hybrid ANN-GA procedures for GFRP bar anchorage reliability analysis were then achieved by the targeted reliability index and development length. Both the ANN-based FOSM and MCS methods were utilized for determining the reliability index and probability of failure of GFRP bar anchorage. The further implementation of the proposed strategy was achieved by a graphical user interface toolbox in Matlab environment for practical use. (C) 2016 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据