基于新奇检测技术在桥梁结构异常识别中的研究

摘要

To identify the abnormal status and location of the bridge structure,and avoid the influence of the bridge mode⁃ling,the status identification method using the improved novel detection technology based on BP neural network is proposed. To verify the feasibility of the method,this method is applied to the T⁃beam model test to identify the cracking status and abnormal location. The effectiveness of the method was proved by engineering test. The method was applied to the damage location identifi⁃cation of the large⁃span arch bridge,and verified with field measuring data.%为了实现桥梁结构的异常状态和位置识别，并避免桥梁模型的建立带来的影响，提出采用基于BP神经网络的改进型新奇检测技术进行状态识别的方法。为了验证该方法的可行性，首先将该方法应用于T梁模型试验中开裂状态与异常位置的识别，工程试验验证效果良好。随后将该方法应用于大跨度拱桥损伤位置的识别，也得到了现场实测数据的验证。