Multi-objective optimization method using an improved NSGA-II algorithm for oil–gas production process

• A multi-objective optimization model is proposed with maximizing overall oil production, minimizing overall water production and comprehensive energy consumption.
• An improved fast elitist non-dominated sorting genetic algorithm II (I-NSGA-II) is proposed.
• A new hybrid chaotic mapping model is established for population initialization.
• Hybrid operator is proposed to produce a new generation of population.
• Substitution operation of chaotic population candidate is used to select the new population.
• Actual production process of an oil production operation area is taken as background for simulation study.

By analyzing the characteristics of oil–gas production process and the relationship between subsystems, a multi-objective optimization model is proposed with maximizing the overall oil production, and minimizing the overall water production and comprehensive energy consumption for per ton oil. And then the non-dominated sorting genetic algorithm-II (NSGA-II) is used to solve the mode1. In order to further improve the diversity and convergence of Pareto optimal solutions obtained by NSGA-II algorithm, an improved NSGA-II algorithm (I-NSGA-II) is proposed. The algorithm is based on the basic NSGA-II, and the main improvements are as follows: Firstly, a new hybrid chaotic mapping model is established for population initialization. Secondly, the gradient operator is introduced, and it combines with the crossover and mutation operator to compose the hybrid operator by which a new generation of population is produced. Lastly, substitution operation of chaotic population candidate is used to select the new population. Finally, the performances of the proposed algorithm are demonstrated in actual production process of an oil recovery operation area studies, the results verify the effectiveness of the model and the algorithm.

Figure optionsDownload as PowerPoint slide