| Summary: | 碩士 === 國立臺灣科技大學 === 電子工程系 === 107 === A surveillance system is one of the most interesting research topics for an unmanned aerial vehicle (UAV). However, the problem of planning an energy-efficient path for the surveillance purpose while anticipating disturbances and predicting energy consumptions during the path tracking is still a challenging problem in recent years. In this thesis, a complete UAV energy consumption prediction, optimal path planning, and disturbance rejection control for a UAV surveillance system is investigated. The setup consists of ArduPilot with Mission Planner Firmware installed to a custom-built hexarotor. First, a mission-based black box modelling of UAV energy consumption prediction is designed via the elastic net regression. The method consists of three consecutive steps: data collection, data preprocessing, and regression. First, to collect the required data, flight patterns that contain several type of movements are defined where then the flight data log that contain missions, global position system (GPS), and battery information are collected. Afterward, the preprocessing includes the movement separation, and the acceleration and deceleration of the horizontal movement. The model then is trained and tested on two flight patterns to simulate a surveillance application of a UAV, and can predict with 98.773% mean of energy accuracy of the missions which are started from the take off and ended with the return to the launch command. Moreover, the trained and tested regression model is used to be the cost function of an optimal path planning scheme, which is designed from a clustered 3D real pilot flight pattern with the proposed k-agglomerative clustering method, and is processed via A-star and set-based particle-swarm-optimization (S-PSO) algorithm with adaptive weights. In addition, an online adaptive neural network (ANN) controller with varied learning rates is then designed and tested in this thesis to ensure the control stability while having a reliably fast disturbance rejection response. The effectiveness of the proposed framework is verified by numerical simulations and experimental results. By applying the proposed optimal path planning scheme, the energy consumption of the optimal path is only 72.3397 Wh while the average consumed energy of real pilot flight data is 96.593Wh. Moreover, the proposed ANN control improves average root-mean-square error (RMSE) of horizontal and vertical tracking performance by 49.083% and 37.50% in comparison with a proportional-integral-differential (PID) control and a fuzzy control under the occurrence of external disturbances. According to all of the results, the combination of the proposed energy consumption prediction model, optimal path planning scheme, and ANN controller can achieve a complete energy-efficient UAV surveillance systems with fast disturbance rejection response.
|
|---|
