RESUMEN
This paper proposes a novel method for multi-class classification and uncertainty quantification of impact events on a flat composite plate with a structural health monitoring (SHM) system by using a Bayesian neural network (BNN). Most of the existing research in passive sensing has focused on deterministic approaches for impact detection and characterization. However, there are variability in impact location, angle and energy in real operational conditions which results in uncertainty in the diagnosis. Therefore, this paper proposes a reliability-based impact characterization method based on BNN for the first time. Impact data are acquired by a passive sensing system of piezoelectric (PZT) sensors. Features extracted from the sensor signals, such as their transferred energy, frequency at maximum amplitude and time interval of the largest peak, are used to develop a BNN for impact classification (i.e., energy level). To test the robustness and reliability of the proposed model to impact variability, it is trained with perpendicular impacts and tested by variable angle impacts. The same dataset is further applied in a method called multi-artificial neural network (multi-ANN) to compare its ability in uncertainty quantification and its computational efficiency against the BNN for validation of the developed meta-model. It is demonstrated that both the BNN and multi-ANN can measure the uncertainty and confidence of the diagnosis from the prediction results. Both have very high performance in classifying impact energies when the networks are trained and tested with perpendicular impacts of different energy and location, with 94% and 98% reliable predictions for BNN and multi-ANN, respectively. However, both metamodels struggled to detect new impact scenarios (angled impacts) when the data set was not used in the development stage and only used for testing. Including additional features improved the performance of the networks in regularization; however, not to the acceptable accuracy. The BNN significantly outperforms the multi-ANN in computational time and resources. For perpendicular impacts, both methods can reach a reliable accuracy, while for angled impacts, the accuracy decreases but the uncertainty provides additional information that can be further used to improve the classification.
RESUMEN
The author wishes to make the following correction to this paper [...].
RESUMEN
A parametric investigation of the effect of impactor stiffness as well as environmental and operational conditions on impact contact behaviour and the subsequently generated lamb waves in composite structures is presented. It is shown that differing impactor stiffness generates the most significant changes in contact area and lamb wave characteristics (waveform, frequency, and amplitude). A novel impact localisation method was developed based on the above observations that allows for variations due to differences in impactor stiffness based on modifications of the reference database method and the Akaike Information Criterion (AIC) time of arrival (ToA) picker. The proposed method was compared against a benchmark method based on artificial neural networks (ANNS) and the normalised smoothed envelope threshold (NSET) ToA extraction method. The results indicate that the proposed method had comparable accuracy to the benchmark method for hard impacts under various environmental and operational conditions when trained only using a single hard impact case. However, when tested with soft impacts, the benchmark method had very low accuracy, whilst the proposed method was able to maintain its accuracy at an acceptable level. Thus, the proposed method is capable of detecting the location of impacts of varying stiffness under various environmental and operational conditions using data from only a single impact case, which brings it closer to the application of data driven impact detection systems in real life structures.