Estimation of UAV flight time and Battery Consumption for photogrammetric application using multiple machine learning algorithms

Abstract

ABSTRACT In recent years, important research has been conducted in Machine Learning (ML), especially on Artificial Neural Networks (ANN). Adaptive-Network Based Fuzzy Inference Systems (ANFIS) and Particle Swarm Optimization-Fuzzy Inference System (PSO-FIS) algorithms are popular ML algorithms like ANN. In terms of their working architecture and results, ANN, ANFIS, and PSO-FIS algorithms can obtain useful solutions for different nonlinear problems. This study evaluated the performance of the ANN, ANFIS, and PSO-FIS algorithms and compared the estimation results. Regarding the application, the test and target data was obtained from the flights performed with Unmanned Aerial Vehicles (UAV), including how long the UAV operates (i.e., Flight Time, FT) and how much battery the UAV consumes during the flight (i.e., Battery Consumption, BC). To obtain FT and BC outputs, sixty-five pre- and post-flight data tables were created. The best iterations for estimating the outputs using the three ML algorithms (considering the minimum/maximum values, RMSE, R, and R2) were determined and discussed based on the training, validation, and test estimations.