The aim of this paper is to demonstrate the use of regression-based neural network (RBNN) method to study the problem of the natural frequencies of the rotor blade for micro-unmanned helicopter [3]. The training of the traditional artificial neural network (ANN) model and proposed RBNN model has been implemented in the MATLAB environment using neural network tools (NNT) built-in functions. The graphs for angular velocity (Omega) of the micro-unmanned helicopter are plotted for estimation of the natural frequencies (f1, f2, f3) of transverse vibrations. The results obtained in this research show that the RBNN model, when trained, can give the vibration frequency parameters directly without going through traditional and lengthy numerical solutions procedures. Succeeding this, the numerical results, when plotted, show that with the increase in Omega, there is increase in lagging motion frequencies. Additionally, it is found that the increase in the lower mode natural frequencies is smaller than that of the higher modes. This finding is in agreement with the results reported in earlier research [3–5] carried out by employing Rayleigh– Ritz and FEM, respectively.
CITATION STYLE
Sahu, A., & Chakravarty, S. (2016). Regression-based neural network simulation for vibration frequencies of the rotating blade. In Springer Proceedings in Mathematics and Statistics (Vol. 171, pp. 17–24). Springer New York LLC. https://doi.org/10.1007/978-981-10-1454-3_2
Mendeley helps you to discover research relevant for your work.