桥梁结构的未标记模态特征稀疏编码深度学习监测*

由于建筑物结构健康问题大部分是累积性损害,很难被检测到,实际结构和环境噪声的复杂性使得结构健康监测更加困难,并且现有方法在训练模型时需要大量的数据,但是实际中对于数据的标记是很复杂的。为克服该问题,通过配备无线传感器网络,并采用稀疏编码实现桥梁结构健康监测,然后通过大量未标记实例在实现特征提取基础上进行稀疏编码算法训练,实现数据维度压缩和无标记数据预处理。其次,利用深度学习算法实现桥梁结构健康监测类别预测,同时基于线性共轭梯度对Hessian优化进行改进,利用半正定高斯-牛顿曲率矩阵替换不确定Hessian矩阵,进行二次目标组合,以实现深度学习算法效率提升；实验结果表明,所提深度学习桥梁结构安全检测算法实现了环境噪声稀疏编码水平下的高精度结构健康监测。

Unlabeled modal characteristics of the bridge structure sparse coding depth study monitoring

Due to health problems most of the building structure damage is cumulative, it is difficult to be detected, the complexity of the actual structure and the ambient noise makes it more difficult structural health monitoring, and the existing method requires a lot of data in the training model, but in practice for the tag data it is very complex. To overcome this problem, by with wireless sensor networks, and here use the sparse coding to achieve bridge structural health monitoring, and through a large number of unlabeled examples of feature extraction in achieving sparse coding algorithms based on training, it realizes the data dimensionality reduction and unlabeled data preprocessing. Secondly, it uses the deep learning algorithm to predict the bridge structural health monitoring category, while it uses the linear conjugate gradient-based optimization algorithm to improve the Hessian optimization, and uses the semi definite Gauss - Newton Hessian matrix to replace uncertain Hessian matrix, which uses the secondary target combinations to achieve deep learning algorithm efficiency; Experimental results show that the depth of the structural safety of the bridge learning detection algorithms achieves a high-precision structural health monitoring of ambient noise levels under sparse coding mentioned.