Deep generative Bayesian optimization for sensor placement in structural health monitoring

Optimal sensor placement (OSP) is essential for effective structural health monitoring (SHM). More recently, deep learning algorithms have shown great potential in sensor-based SHM. However, existing optimization frameworks, such as population-based algorithms, are often not suited for data-driven SHM. Evaluating a number of sensor layouts includes training on large datasets, which is computationally expensive. This paper proposes deep generative Bayesian optimization (DGBO) as a solution for a parallel optimization of black-box/expensive OSP objective functions. Conditional variational autoencoders are leveraged as generative models that transform the OSP problem into a lower-dimensional latent space. Additionally, DGBO utilizes a surrogate neural network to capture the probability distribution of the objective function space. The proposed method is validated on two case studies on a nine-story reinforced concrete moment frame. The first one serves as a proof of concept to show that DGBO can find the global optimum configuration. The second case study aims to maximize the semantic damage segmentation (SDS) accuracy using a fully convolutional neural network. Transfer learning is proposed in training the vibration-based SDS model, which reduces the evaluation times by more than 50%. Without compromising the performance, the number of accelerometers can be reduced by 52% and 43%, respectively, for damage location and severity predictions. It is also shown that DGBO can outperform genetic algorithm with the same number of function evaluations. DGBO can serve as a scalable solution to address the high-dimensionality challenge in OSP for large-scale civil infrastructure.