论文部分内容阅读
探讨了应用基于BP神经网络的新奇检测技术进行斜拉索状态评估的方法。通过对监测系统采集数据分析处理,生成训练神经网络需要的样本数据,按要求训练网络,建立了基于新奇检测技术的多阶段状态评估的神经网络模型,实现了斜拉索状态评估的两个阶段:状态预警、状态异常位置识别。状态异常位置识别采用逐步分区识别的方法,最终将损伤拉索的位置确定在较小的范围内。用有限元模型和实测数据进行了检验,结果表明,在不同的环境温度条件下,该方法能准确进行状态预警,有效地识别出状态异常的位置。
This paper discusses the method of using the novel detection technology based on BP neural network to evaluate the status of stay cables. By analyzing and processing the collected data of the monitoring system, the sample data needed to train the neural network is generated, and the network is trained according to the requirements. The neural network model of multi-stage state assessment based on the novel detection technology is established and the two stages : Pre-alarm, abnormal position identification. Abnormal position identification using step by step zone identification method, the final position of the lesion will be determined in a smaller range. The finite element model and the measured data are used to test the results. The results show that the method can accurately predict the state of anomaly under different ambient temperatures and effectively identify the location of the abnormal state.