【作者】 逯静洲； 林皋； 李庆斌；

【Author】 Lu Jingzhou , Lin Gao , Li Qingbin(Department of Civil Engineering, Yantai University, Yantai 264005, China;Department of Hydraulic and Hydropower Engineering, Tsinghua University, Beijing 100084, China;Department of Civil Engineering, Dalian University of Technology. Dalian 116024, China)

【机构】 烟台大学土木系； 大连理工大学土木系； 清华大学水利系；

【摘要】 本文采用混凝土立方体试件,对其施加多种三轴受压荷载历史作用,分别测量载前和载后的抗压强度、劈拉强度及超声波速,并将载后抗压和抗拉强度的劣化定义为抗压和抗拉损伤。然后运用径向基函数神经网络方法,对混凝土载后损伤特性与超声波速降低之间的关系进行研究。研究结果表明,基于径向基函数神经网络的超声波探伤模型具有较高的预测能力,为研究混凝土损伤提供了一条新的途径,在实际工程结构领域将有较大发展前景。更多还原

【Abstract】 The damage trial of concrete cube was experimentally studied. The damage of concrete due to triaxial compressive loading history is defined as the reduction of compressive strength and tensile strength. The relationship between the damage and the descent of ultrasonic velocity is investigated using redial basis function neural network. A good agreement between the measured data and predicted results demonstrates that the model is able to capture significant variability inherent in the concrete samples. It is concluded that the application of RBF neural network in supersonic inspection is a new method to evaluate damage of concrete, and has promising applications in structural engineering problems.更多还原