基于BP神经网络的PRC简支梁的预应力识别

Identification of the prestressing force in PRC beam based on BP networks

为了对预应力混凝土(PRC)结构中预应力值进行检测与评价,采用神经网络技术,基于自振特性对PRC简支梁的预应力识别进行了数值仿真研究.分别在不同预应力水平上计算预应力梁的前10阶自振频率,经过归一化处理构造网络的训练样本,由网络输出指示预应力大小.采用3层BP网络,通过15个训练样本的训练,网络展示了良好的收敛性.对3种不同预应力水平的仿真测试表明,最大相对误差仅为2.08%,具有较高的识别精度.

The detection and assessment of prestressing force in prestressed reinforced concrete（PRC） structure with natural frequencies were carried out based on BP network. Ten natural frequencies of PRC simply supported beam were calculated under different prestressing force conditions and normalized as input vectors of the training sample, and prestressing force was chosen as out vectors. Three-tier BP networks were trained, and the convergence of iterative sequence was admissible. Simulation on three different prestressing force shows that the maximum relative error is only 2.08 %. Test results verify the feasibility of the proposed method.