【摘要】 混凝土柱采用FRP横向缠绕加固可有效改善其抗震性能.对于FRP抗震加固混凝土柱的破坏模式,目前尚无有效预测方法.文章全面分析了影响FRP抗震加固混凝土柱破坏模式的主要因素,基于人工神经网络理论,建立了其破坏模式BP网络预测模型,并对35个FRP加固柱在水平荷载作用下的破坏模式进行了预测,结果表明,与试验观测值相比,所建BP网络模型预测值的符合率超过了90%,可用于FRP抗震加固混凝土柱的破坏模式预测.更多还原

【Abstract】 FRP jacketing can be used to improve the seismic behavior of reinforced concrete columns effectively. However, no practical method is available for predicting the failure mode of FRP-jacketed concrete columns. The main factors that influence the failure mode of such columns are comprehensively analyzed. A predictive model for failure mode is then developed based on the Theory of Neural Network, and used to forecast the failure mode of 35 columns strengthened in that way. The results show that the predictions by the proposed model agree well with the experimental observations with an conformity ratio of over 90%, indicating that the model is applicable for the prediction of the failure mode of FRP-jacketed concrete columns under seismic loads.更多还原