Research On General Aviation Emergency Rescue Task Allocation Problem Based On Market-based Approaches

Under the lead of National Ministry of Science and Technology's key special project Public Security Risk Prevention and Emergency Technology and Equipment,its sub-project the Key Technology Research of Aviation Emergency Rescue and Application Demonstration has pushed general aviation emergency rescue to the focus of research of emergency management.Aviation emergency rescue system is a complex system to complete the emergency response by the number of aircrafts through collaboration.Along with the continuous and dynamic rescue mission released,a large number of heterogeneous rescue aircrafts with a certain autonomy implement a series of decision-making of tasks negotiation and execution of rescue activities.Due to the suddenness and randomness of emergency events,the dynamics and uncertainty of the aviation rescue system are strong,and the factors that affect the task assignment are numerous.With the increase of the number of system aircrafts,the control and negotiation of the distributed system will become more and more difficult.Due to the lag of the development of general aviation in China,the study of effectiveness evaluation of emergency rescue of general aviation has become an urgent demand for the development of emergency rescue in China.Based on fuzzy neural network,this study explores the calculation problem of airworthiness quantify of specific rescue operations.After that,the market mechanism based on contract net protocol is introduced as the task allocation framework.On the basis of this,a multi-aircrafts cooperation decision-making method for the assignment of rescue tasks is designed.The purpose of this study is to form a rescue mission allocation mechanism that has professional general aviation and enough support for multi machine dynamic negotiation,and provides support for multi Aircraft cooperative rescue under large-scale rescue scene.Aiming at the problem of quantification assessment of flightworthiness for rescue flight operation,this study starts from the perspective of the mechanical properties of the aircraft itself,and use a fuzzy neural network model for rescue operations of airworthiness evaluation modeling.The rescue historical data of the EC-135 helicopter model is used for model training,in order to form a quantitative model of airworthiness assessment for flight operation.On the one hand,the quantitative output results provide qualitative guidance for aircraft's competency,and on the other hand,it provides a basis for comparing the advantages and disadvantages of multitask allocation schemes.After that,a task allocation framework based on market method is introduced.Based on contract net protocol,a negotiation mechanism of rescue task allocation under multi-aircrafts cooperative scene is designed.The method uses the thought of task auction,distributing the sub-task of the rescue process to the autonomous rescue subsystem,and simulating the auction process to complete the task execution power competition.Optimization of the whole system task allocation effect is formed through the best way of individual utility.Aiming at the heterogeneous problem for rescue system,this paper introduces the concept of task ability vector,quantitative representing the ability of heterogeneous aircrafts and requirements of mission.The comprehensive ability of quantitative calculation of multi-aircrafts alliance is discussed,as well as the single and multi-aircrafts cooperative task ability.The design of task allocation method based on market mechanism is suitable for task assignment scene of multi-aircrafts cooperative of large-scale emergency rescue,able to complete the negotiation process between multi-aircrafts under highly dynamic task environment.The distributed control method has a great adaptability to the changing situation of the rescue scene and the dynamic situation of the task,and is easy to implement and apply.At the same time,this paper solves the problem of the integration of knowledge rules and rescue experience by using FNN's quantitative calculation method of rescue operation adaptability,and supplements and improves the weaknesses of the existing methods of market task assignment in domain knowledge.