| With the development of automation and artificial intelligence technologies,unmanned aerial vehicles are widely used in various industries.In the field of military operations,UAVs gain intelligence through real-time reconnaissance of suspicious targets.However,UAVs have limited battery capacity,which prevents them from operating stably for long periods of time to accomplish the required reconnaissance missions,so it is necessary and important to study the charging problem of UAVs while performing their missions.In order to overcome the disadvantage of limited battery capacity of UAVs and enable them to perform long-time and long-distance missions such as reconnaissance stably,we need to take necessary measures to provide sufficient power supply guarantees for UAVs during their missions.Based on this paper,the multi-objective optimization study of UAV power supply guarantees for reconnaissance mission is carried out with two objectives: cost and benefit.Specifically,this paper accomplishes the following two main aspects.In order to overcome this drawback of UAVs,it is necessary to provide sufficient power supply guarantees during UAV missions,which makes UAVs perform long time and long distance missions more efficiently.This paper firstly analyzes the UAV power supply guarantee problem,summarizes the current research related to UAV charging technology and power supply guarantee planning,analyzes two objectives in terms of cost and benefit,and combines this problem with multi-objective optimization methods.Aiming at the multi-objective optimization research of UAV reconnaissance mission power supply guarantees,this paper mainly accomplishes the following two aspects.First,this paper proposes a novel power supply guarantee model based on mobile charging vehicles.In this model,the charging vehicle travels to the charging point located in the path of the UAV to wirelessly charge it,and maximally ensures that the UAV completes its reconnaissance mission.Focusing on the scheduling and routing of the charging vehicle,this paper achieves cooperation between multiple systems by constructing two sub-models,namely the UAV reconnaissance routing model and the vehicle charging routing model.In addition,this paper proposes an improved coevolutionary framework for constrained multi-objective optimization problems based on a generalized opposition-based learning strategy to optimize the two objectives of electrical energy security input cost and reconnaissance mission time window deviation.In order to verify the effectiveness and applicability of the proposed model and algorithm,this paper constructs a variety of UAV reconnaissance mission scenarios with different levels of complexity to carry out case studies,optimizes the charging vehicle routes with various algorithms and conducts comparative experiments.Second,by considering both UAV reconnaissance mission routing and power supply guarantee scheduling,this paper builds a joint two-stage multi-objective optimization model for UAV and mobile charging vehicle routes,and analyzes the computational complexity of the model.In order to reduce the computational cost and ensure the dominance and diversity of solutions,a two-stage multi-objective optimization model for UAV routing and power supply guarantee scheduling is proposed.Specifically,in the first stage of the model,for each searched solution of the outer optimization problem representing the UAV route,a corresponding solution of the inner optimization problem,i.e.,the solution representing the power supply guarantee scheduling,is generated by a rule-based heuristic charging strategy,and the optimal solution set of the outer optimization problem is finally optimized;in the second stage,the solutions in the solution set obtained in the first stage are used as known conditions to carefully optimize the inner optimization problem solutions representing the power supply guarantee scheduling,respectively.The good solution performance of the proposed two-stage optimization method is verified through case studies and comparison tests with other solution strategies and other algorithms. |
