Research On Route Method Of Emergency Repair Of Electric Power Failure In Oil Field

Oilfield exploitation is an important part of modern energy production When encountering extreme weather or major natural disasters,once the oilfield power system encounters a failure,it will directly cause a large-scale shutdown of the oil well.The production of oil wells will be seriously affected,and the long-term interruption of oil well production will cause the oil well to be scrapped and the loss will be unpredictable.In the case of multiple failure points with varying degrees of impact and a limited number of emergency teams in the dispatch center,the traditional method usually relies on the intuition and experience of managers to assign teams to the scene.This solution has problems such as slow progress,low efficiency,and difficulty in meeting expectations for emergency repairs.First,when the road is driving normally,the multi-objective function optimization method with short repair time and small loss during repair time is studied in this paper.Then,the method of regenerating the path at the extreme road section was studied.Finally,the improved algorithm and virtual reality technology are combined to simulate the post-disaster scene and emergency repair process.The main work of this paper is as follows:Under the condition that the road can be driven normally,this paper combines the needs of the electric power repair task under the existing path,and summarizes it as a multi-objective optimization problem.The Non-dominated Sorting Genetic Algorithm with Elite Strategy is selected as the basic algorithm for task planning.In view of the limitations of the original algorithm's crowded distance screening method.which may lead to the deterioration of the uniformity and distribution of individuals,a fast search clustering algorithm is used to replace the crowded distance screening strategy in this paper.So as to achieve the advantages of eliminating poorly distributed individuals and improving individual distribution.Aiming at the problem of poor population diversity after the algorithm removes poorly distributed individuals,which leads to the problem of early convergence,a differential evolution algorithm is introduced to generate new individuals among individuals with better distribution in this paper,thereby increasing population diversity.And the convergence speed of the population is improved.The improved algorithm is tested on the ZDT and DTLZ test functions,and the performance is compared with other algorithms to verify the feasibility of the algorithm.In the extreme road conditions,a safe path needs to be re-planned.Aiming at the extreme road area phenomenon caused by natural disasters,the virtual reality technology is combined in this paper.In the stage of virtual space modeling,the navigation grid method is used to cover the extreme road sections.Eliminate the non-walkable area,and only keep the grid of the walkable area,which can truly describe the contour of the terrain.In the stage of path search,the A*algorithm is improved in this paper in response to the phenomenon that the actual environment changes after the disaster produce a narrow passage with a higher risk.The Artificial Potential Field Method Repulsion Force Field is combined to find a relatively safe path grid.The inflection point method is improved on the path grid,and the ideal path is generated under the condition of keeping a safe distance from the boundary of the obstacle and the shortest path The improved algorithm is tested in test scenarios,and the feasibility of the algorithm is verified through example simulation and performance index analysis.The application problem of the improved algorithm in the electric power repair taSk of the oil field.In this paper,a virtual scene is established and pumping units and electrical equipment are built,and the number and location of failure points are clarified.According to the hierarchical progressive planning idea,the overall steps of the oil field electric power energency repair task are studied and analyzed.First,the extreme road sections are manually marked,and the improved A*method is adopted Then the route is regenerated at the extreme road sections and the travel time between the points of failure is calculated.In the electric power repair task planning stage,first,according to the mathematical model and objective function of electric power repair,the improved multi-objective optimization algorithm in Chapter 3 is applied to obtain a set of optimal non-dominated solution individuals.Then,the fuzzy theory is combined to find a compromise solution with better comprehensive ability among this group of solution individuals.Finally,the results of the repair path are displayed in the virtual scene established before,and compared and analyzed with the running results of related algorithms.