A hierarchical deep convolutional regression framework with sensor network fail-safe adaptation for acoustic-emission-based structural health monitoring

Lamb wave-based signals from sparse-distributed sensors are complicated and difficult to process for structural health monitoring (SHM), not only due to their dispersive and multi-mode nature, but also due to the increasing complexity of materials and structures. Deep learning (DL) has attracted huge attention to help solve physical problems with a high level of automation and accuracy. However, its reliability and robustness are still questioned when performing the case -by-case model trained by inadequate datasets for practical scenarios, where many variables exist. In this study, a hierarchical deep convolutional regression framework is proposed to solve the impact source localization problem by acoustic emission signals. One-dimensional (1D) network is used due to its capability to process fast with raw time-series data. The window length of input data and the target of output results are discussed to improve the over-fitting issue. The sensor network fail-safe mechanism is designed via generalizing the model to handle abnormal situations with random faulty channels. Data augmentation and transfer learning techniques are utilized to train the fail-safe model without the need for additional experimental data. Pristine case and multiple random-faulty-channel cases are used to test and validate the adaptation performance of the fail-safe model. The whole framework combines both pristine and fail-safe models to achieve high accuracy of impact localization results of both a simple homogeneous plate and a complex inhomogeneous plate with geometric features. The proposed DL framework of greatly improved reliability and robustness, also short processing time, is well suitable for real-time and in-situ SHM applications.

Automated summary

This study proposes a hierarchical deep convolutional regression framework based on deep learning to solve the impact source localization problem using acoustic emission signals. The framework shows strong capability in processing time-series data and utilizes data augmentation and transfer learning techniques to enhance model reliability and robustness.