A two-stage optimization method for unmanned aerial vehicle inspection of an oil and gas pipeline network

Yamin Yan, Yongtu Liang, Haoran Zhang, Wan Zhang, Huixia Feng, Bohong Wang, Qi Liao
2019 Petroleum Science  
Oil and gas pipeline networks are a key link in the coordinated development of oil and gas both upstream and downstream. To improve the reliability and safety of the oil and gas pipeline network, inspections are implemented to minimize the risk of leakage, spill and theft, as well as documenting actual incidents. In recent years, unmanned aerial vehicles have been recognized as a promising option for inspection due to their high efficiency. However, the integrated optimization of unmanned
more » ... vehicle inspection for oil and gas pipeline networks, including physical feasibility, the performance of mission, cooperation, real-time implementation and three-dimensional (3-D) space, is a strategic problem due to its large-scale, complexity as well as the need for efficiency. In this work, a novel mixed-integer nonlinear programming model is proposed that takes into account the constraints of the mission scenario and the safety performance of unmanned aerial vehicles. To minimize the total length of the inspection path, the model is solved by a two-stage solution method. Finally, a virtual pipeline network and a practical pipeline network are set as two examples to demonstrate the performance of the optimization schemes. Moreover, compared with the traditional genetic algorithm and simulated annealing algorithm, the self-adaptive genetic simulated annealing algorithm proposed in this paper provides strong stability. Keywords Pipeline network · Unmanned aerial vehicle inspection · Mixed-integer nonlinear programming · Two-stage solution Abbreviations UAV Unmanned aerial vehicle MINLP Mixed-integer nonlinear programming GA Genetic algorithm SA Simulated annealing algorithm AGASA Self-adaptive genetic simulated annealing algorithm PSO Particle swarm optimization ACO Ant colony optimization P L m Probability of selection of an individual p m Probability of mutation T 0 Initial temperature, °C w Temperature update coefficient M Size of population G max Maximum evolution generation T end Termination temperature, °C
doi:10.1007/s12182-019-0305-y fatcat:fvbj6tlidjeple2k3nqosg3rla