Study On The Network Pavement Maintenance Fund Decision-making Based On NSGAⅡ+DRSA Method

With the continuous improvement of China’s highway network,the era of maintenance of highway is coming,and the increasing demand for pavement management from social development,pavement management not only needs to be responsible for the technical,but also has to take into account that the maintenance plan which has impact on society and the environment.In terms of impact,highway maintenance has gradually changed from the previous singular management to multi-objective and comprehensive management.However,due to the long-term prejudice of construction and ignorance of the maintenance,highway maintenance management in China has been in great trouble.On the other hand,under the pressure of increasing maintenance demand,there are still some problems in our country’s highway maintenance management.The specific manifestations are the shortage of conservation funds,the lack of comprehensive analysis of the use of conservation funds,and the short of effective multi-objective analysis tools for conservation funding decisions.Based on the above background,this paper comprehensively considers the impact of capital utilization efficiency,sustainable development requirements and user interest demands on network-level pavement maintenance funding decisions,and determines that the goal of the network-level pavement maintenance funding decision model is the largest ratio of pavement asset value to maintenance cost;the coefficient of variation of the maintenance workload in each year is the smallest;the user cost and the environmental cost are saved the most.Therefore,the highway network maintenance funding decision problem is described as a multi-objective optimization problem with multi-party participation,multi-party benefits,and conflicting interests of all parties.According to this characteristic,and in order to solve the problem of a large number of feasible solutions to the multi-objective optimization issues,this paper proposes an interactive preference multi-objective evolutionary algorithm framework that combines the non-dominated sorting genetic algorithm(NSGAII)with elite strategy and the dominance relation rough set theory(DRSA)collect and obtain the preference set by requesting the "exemplary decision" from the decision maker,so as to realize the preference solution of the multi-level decision-making model of the network-level pavement maintenance funds,and verify the decision using the highway network system in the S area The validity and practicality of the model.It has been proved by examples that the decision-making model can effectively assist decision-makers in making medium-and long-term pavement maintenance funding plans,and can effectively mediate multiple conflicting goals and achieve the best trade-offs to achieve the best maintenance of network-level pavement management;and integrate NSGAII and DRSA can effectively solve the problem that have a large number of feasible solutions to the multi-objective optimization problem.Compared with the traditional preference multi-objective evolutionary algorithm,it is easier to implement and the decision-making process is more transparent.