A novel methodology for multiple flaw detection is presented in this study. It combines the dynamic extended finite element method (XFEM) with machine learning for the first time. The extreme learning machine (ELM) is chosen as a learning rule for modeling and prediction. The XFEM is employed to overcome the issues associated with the large quantity of input data required for ELM network training, whereas the ELM itself is used to bypass the time-consuming repeated analyses ordinarily required for the detection of multiple flaws. A large amount of potential flaw data for a structure is quasi-randomly generated by a Sobol sequence. For each effective flaw datum, the dynamic XFEM with circular/elliptical void enrichment is used to compute the structural dynamic characteristics (i.e., frequencies and displacement mode shapes), which is possible because re-meshing is not required for each flaw. The available data generated from the results of XFEM analyses are used for ELM network training. According to the measured dynamic characteristics, the trained ELM is then utilized to predict the size and location of flaws. The results show that the proposed novel methodology can identify accurately the location and size of circular or elliptical structural flaws. The method also is more efficient than previously proposed approaches, as it can avoid time-consuming iterative analyses, and it is robust against noise.
In this paper, an extreme learning machine (ELM) algorithm based on particle swarm optimization (PSO) is proposed to predict structural deformation. Taking an aqueduct located in Tiantai County, Zhejiang, China, as a case study, a series of observations of the aqueduct vertical displacements and crack openings were used to train a neural network. Then, variables representing environmental factors (air temperature), hydraulic factors (water level), and aging were selected as the influence factors input into the prediction model. Finally, the proposed PSO–ELM model was used to predict the vertical deformation and crack opening of the aqueduct, and the predicted results were compared with the monitored values using four evaluation indexes: mean absolute error ( MAE), mean squared error ( MSE), maximum absolute error ( S), and correlation coefficient ( R). The prediction results obtained using the PSO–ELM model were then compared with those obtained using the evolutionary ELM, conventional ELM, back propagation neural network, long short-term memory, and multiple linear regression models. The results indicate that the proposed PSO–ELM model has an evidently superior predictive ability, with higher values of R and lower values of MAE, MSE, and S. The proposed model can therefore be confidently used to serve as a tool similar to a “weather forecast” function to predict the vertical deformation and crack openings of an aqueduct and may be employed for other structural monitoring applications as well.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.