Thrust-to-Weight Ratio Optimization for Multi-Rotor Drones Using Neural Network with Six Input Parameters

This study analyzes the thrust-to-weight ratio of a multi-rotor drones with respect to six different parameters using neural network. The parameters are the model weight, number of propellers, frame size, propeller diameter, propeller pitch and number of blades. An online calculation tool called eCalc is used to collect data to build a neural network model. The model has an accuracy of 97% when compared to an eCalc computed data. From this model, we optimize the thrust-to-weight ratio using gradient descent method initialized from the collected eCalc data. We ran another optimization computation by fixing two parameters to satisfy available components in the market. Optimization results are showed and analyzed.