[论文解读] Deep Bayesian U-Nets for Efficient, Robust and Reliable Post-Disaster Damage Localization

Xiao Liang, Seyed Omid Sajedi|arXiv (Cornell University)|Sep 24, 2020

Infrastructure Maintenance and Monitoring参考文献 30被引用 5

一句话总结

本文提出深度贝叶斯U-Net，通过蒙特卡洛Dropout实现灾后结构损伤定位的不确定性量化。通过将不确定性视为可学习的输出，该模型在标准U-Net基础上提升了鲁棒性与可靠性，且类别方差与预测误差强相关，从而实现关键基础设施评估中的更安全部署。

ABSTRACT

Post-disaster inspections are critical to emergency management after earthquakes. The availability of data on the condition of civil infrastructure immediately after an earthquake is of great importance for emergency management. Stakeholders require this information to take effective actions and to better recover from the disaster. The data-driven SHM has shown great promises to achieve this goal in near real-time. There have been several proposals to automate the inspection process from different sources of input using deep learning. The existing models in the literature only provide a final prediction output, while the risks of utilizing such models for safety-critical assessments should not be ignored. This paper is dedicated to developing deep Bayesian U-Nets where the uncertainty of predictions is a second output of the model, which is made possible through Monte Carlo dropout sampling in test time. Based on a grid-like data structure, the concept of semantic damage segmentation (SDS) is revisited. Compared to image segmentation, it is shown that a much higher level of precision is necessary for damage diagnosis. To validate and test the proposed framework, a benchmark dataset, 10,800 nonlinear response history analyses on a 10-story-10-bay 2D reinforced concrete moment frame, is utilized. Compared to the benchmark SDS model, Bayesian models exhibit superior robustness with enhanced global and mean class accuracies. Finally, the model's uncertainty output is studied by monitoring the softmax class variance of different predictions. It is shown that class variance correlates well with locations where the model makes mistakes. This output can be used in combination with the prediction results to increase the reliability of this data-driven framework in structural inspections.

研究动机与目标

• 解决现有深度学习模型在灾后结构损伤评估中缺乏不确定性估计的问题。
• 提升数据驱动的结构健康监测（SHM）系统在安全关键应用中的可靠性。
• 开发一个既能提供损伤预测又能为每个预测提供置信度估计的框架。
• 在大规模非线性响应历史分析基准数据集上验证模型的鲁棒性与不确定性量化能力。
• 证明不确定性估计与预测误差相关，从而支持风险感知决策。

提出的方法

• 采用网格状数据结构，将U-Net架构适配于语义损伤分割（SDS）。
• 在推理阶段引入蒙特卡洛Dropout以估计模型不确定性，将其视为第二个输出。
• 使用标准交叉熵损失训练贝叶斯U-Net，并在测试阶段进行随机前向传播。
• 利用Dropout样本间的softmax类别方差作为预测不确定性的代理指标。
• 采用10层2D钢筋混凝土框架的10,800组非线性响应历史分析基准数据集进行训练与评估。
• 重新审视并优化语义损伤分割的概念，以满足结构诊断对高精度的需求。

实验结果

研究问题

• RQ1 贝叶斯深度学习技术能否提升结构健康监测中灾后自动化损伤定位的可靠性？
• RQ2 通过蒙特卡洛Dropout实现的不确定性量化在损伤分割任务中与预测误差的相关性如何？
• RQ3 贝叶斯U-Net在结构损伤评估中的全局准确率与平均类别准确率方面，相较于标准U-Net的性能提升程度如何？
• RQ4 不确定性估计能否通过突出高风险或模糊的预测区域，辅助人工检测人员？
• RQ5 所提出的框架在显著提升鲁棒性的同时，是否仍保持高效性，适用于现实世界灾难场景？

主要发现

• 所提出的贝叶斯U-Net在全局准确率与平均类别准确率方面均优于基准标准U-Net。
• 蒙特卡洛Dropout预测的类别方差与错误损伤分类强相关，表明不确定性估计具有可靠性。
• 模型的不确定性输出有效突出了预测置信度较低的区域，尤其是在模糊或复杂的结构区域。
• 由于具备不确定性感知的推理能力，该框架在多种地震荷载情景下表现出更强的鲁棒性。
• 不确定性量化的集成未影响推理效率，保持了近实时部署的适用性。
• 包含10,800组非线性响应历史分析的基准数据集，使得模型性能与可靠性的全面验证成为可能。