In this prospective work, a machine learning (ML) model based on multiple independent random forest models to predict the configuration of binary composite bars is developed. The input variables to the ML model are elastic wave signals collected at one end of the composite bar, while the targets of the ML model are binary vectors representing the configuration of the bars.This study results indicate: First, a short period of elastic wave propagated through a composite bar can collect and carry the detailed information of the entire bar; second, the patterns hidden in the collected signals can be detected, extracted, and used by the ML model; finally, the ML model can be well trained using a relatively small dataset pool (less than 0.1% of all possible samples), and make accurate predictions. For the 30 sections of bars used in this study, the average prediction accuracy for each section of this bar can reach 95% and even higher. This ML guided technique can be modified and used in different functionalities and applications such as composites characterization, structure health monitoring, limestone determination, and archaeological detection.
Composites have been widely used in the field of acoustics due to their extraordinary ability of sound insulation. To date, the design of acoustic composites relies primarily on the expertise of engineers and experimental tests. This preliminary study outlines a deep learning (DL) based approach to optimize the microstructure of the composite bars to achieve the best performance in sound insulation. This approach first trains DL networks using data generated using finite element simulation to predict the pressure amplitude and energy of the output waves, then a genetic algorithm (GA) uses the DL model as its evaluation function and generates new designs. The results indicate that a combination of DL and GA can generate Pareto-optimal designs to satisfy the specific needs of engineering projects. We demonstrate that starting with a quite small data set (less than of all possible designs) and applying a DL approach is an efficient and robust method to obtain optimal designs. The DL model is accurate in its predictions which enables the GA to find unique composite designs that are optimal for sound insulation.
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.