Machine Learning Based Dynamic Mode Decomposition of Vector Flow Field Around Mosquito-Inspired Flapping Wing

This chapter introduces a novel approach to understanding the aerodynamics of mosquito-inspired flapping wings through the application of machine learning and Dynamic Mode Decomposition (DMD) techniques. The vector flow field surrounding the flapping wing is analyzed to extract coherent structures and gain insights into the flight dynamics of these agile insects. Traditional methods of vector flow field analysis are often time-consuming and costly. In contrast, this research leverages advances in machine learning to streamline the analysis process. The methodology involves data collection from experimental setups, data preprocessing to ensure data quality, machine learning algorithms for feature extraction, and DMD for coherent structure identification. The results of this study demonstrate the effectiveness of machine learning techniques in feature extraction and classification within the vector flow field data. Additionally, DMD reveals coherent structures, shedding light on the spatial and temporal dynamics of mosquito-inspired wing flapping. Comparative analysis with traditional methods underscores the advantages of this novel approach in terms of efficiency and depth of analysis. This research contributes to the fields of machine learning, aerodynamics, and bio-inspired robotics. It opens doors to further exploration, such as refining machine learning algorithms, applying these techniques to other bio-inspired systems, and implementing findings in aerospace engineering. The combination of machine learning and DMD not only aids in understanding insect flight but also holds promise for applications in micro air vehicles, bio-inspired robotics, and unmanned aerial vehicles. This research paves the way for a deeper understanding of complex flight dynamics in the natural world, offering insights that can revolutionize the design of future flight systems.