Search

Highlights • A cointegration method is proposed to deal with heteroscedastic time series in SHM. • The TBATS (T rigonometric, B ox-Cox A RMA T rend, S easonal model is used to decompose a time series corrupted with seasonal noise. • A full-scale foot bridge is presented as one of the case studies. Abstract Heteroscedasticity, or time-dependent variance, is often observed in long-term monitoring data in the context of SHM, where it is normally induced by the seasonal variations of the ambient environment. In the effort to project out the environmental and operational variations, cointegration, a method originating in econometrics, has been successfully employed in various SHM studies. This paper will explore a possible enhanced approach to cointegration, to make it applicable to heteroscedastic data. The fact that the variance of heteroscedastic data is constantly changing has a significant negative impact on conventional damage detection algorithms, making it difficult to calculate accurate confidence intervals. Thus, in the current paper, an exponential smoothing method is presented to explore and deal with the complex seasonal patterns observed in SHM time series. More specifically, in this framework, a seasonally-corrupted time series can be decomposed into three components, namely, level, seasonal and residual terms. Subsequently, the series purged of seasonality will be fed into a cointegration analysis, in order to produce a more stationary residual series (damage indicator series). Two case studies, including a synthetic case and a real world SHM dataset, are demonstrated with results and discussions. [ABSTRACT FROM AUTHOR]

The deployment of systems experiencing high-rate dynamic events, such as hypersonic vehicles, advanced weaponry, and active blast mitigation systems, require high-rate structural health monitoring (HRSHM) capabilities in the sub-millisecond realm to ensure continuous operations and safety. However, the development of high-rate feedback systems is a complex task because these dynamic systems are uniquely characterized by (1) large uncertainties in their external loads, (2) high levels of non-stationarity and heavy disturbance, and (3) unmodeled dynamics from changes in system configuration. In this paper, we present a deep learning algorithm specifically engineered for HRSHM applications. It consists of an ensemble of recurrent neural networks (RNNs) constructed with long short-term memory (LSTM) cells with transfer learning capabilities to cope with the highly limited availability of training data as it is typical for high-rate systems. The use of an ensemble of RNNs empowers multi-rate sampling capability to capture multi-temporal features of the time series, thus enabling modeling of non-stationarities. Also, because the RNNs use short-sequence LSTMs and are arranged in parallel, the computation time is substantially reduced to the sub-millisecond range. The performance of the algorithm is investigated on experimental high-rate dynamic data produced from accelerated drop tower tests and benchmarked against results from a prior investigation using a purely on-the-edge algorithm termed variable input space observer (VIO) and its hybrid architecture (hybrid VIO) that incorporated physical knowledge and is considered as an upper bound on the algorithm performance. Numerical results show that the ensemble of RNNs, composed of five RNNs, significantly outperformed the VIO, with performance close to that of the hybrid VIO when it comes to the estimation error metrics, with an average computation time of 25 μ s per prediction step. Yet, the ensemble of RNNs exhibits chattering for low-amplitude excitations, likely attributable to the behavior of RNNs sampling at small time delays. An examination of the RNN weights and hidden states confirms that the algorithm can capture multi-temporal features, and an investigation with respect to noise in the training dataset showed that the algorithm is robust for signal-to-noise ratios up to 20 dB. • Machine learning-based architecture for non-stationary time-series analysis. • Transfer learning for accelerated training with limited data. • Ensemble-based system estimation using parallel recurrent neural networks integrated with attention mechanism is proposed. • Sib-millisecond estimation of a high-rate system is achieved though the proposed architecture. [ABSTRACT FROM AUTHOR]