Study On Optimization Technology For Oilfield Surface Pipeline Network Based On Intelligence Computation

A reasonable layout design is the basis of oilfield surface construction, the quality of which will directly affect the economic benefit of the oilfield exploitation. The optimization design of oilfield surface pipeline network is a complex problem of large-scale hybrid optimization design, which involves discrete topological, non-linear parametric and multi-objective optimizations etc; some of them belong to NP hard problems. It is difficult to achieve good results by use of conventional optimization algorithms, thus at present the programming design is mainly based on the human experience. With the continuous development of optimization technology, intelligence computation method, such as simulated annealing, genetic algorithm and neural network etc, with its advantages of high-effective optimization performance, needing no special information for the problem and with its global search capacity, has received extensive attention, and has been widely applied to many domains. It has become a powerful instrument to solve project difficulties, and can be used as an effective alternative method for the optimization design for oilfield surface pipeline network. In the paper, based on careful and profound analysis and research on the oilfield surface pipeline network, by use of intelligence computation technology, mathematical models are established according to the practical needs, and a systematic optimization design is realized by designing proper algorithm and programming corresponding software. The following aspects are discussed in this paper: Firstly, the common MS, MRS and MST networks in surface pipeline network are mathematically and accurately defined, based on careful and profound analysis of the structural characteristics, relationships between layers, characters of network variation and other factors of oilfield surface pipeline network, and by use of graph theory and other corresponding knowledge. Then three multi-objective mathematic models are established according to the design of networks mentioned above, in which the minimal network systematic investment and annual operation expenses are taken as the objectives. The calculation difficulty of the model is analyzed by calculation complexity theory. Based on the structural characteristics of the model and practical design process, hierarchic optimization strategy adopted, the resolution of the model is decomposed into two sub problems, topology layout optimization and parameters optimization. Their coordination is achieved by iteration computation. Secondly, topology layout optimization of oilfield pipeline network is studied. The corresponding mathematic model of topology layout optimization, according to MS, MRS and MST networks mentioned above, is established, in which the minimal systematic investment is taken as the objective. Hierarchical optimization is adopted to meet the need of the structural characteristics of the model. The advantage of this method is that the resolution is rapid and efficient, but it is susceptible to be trapped into local optima. Because of the deficiency of this method, hierarchical optimization, genetic algorithm and simulated annealing algorithm are organically combined to form a resolution strategy of hybrid genetic simulated annealing algorithm. Practical cases'calculation indicate that compared with hierarchical optimization, the algorithm can be improved in optimization capacity, robustness of initial values and other aspects to some extent. For the obstacles in layout area, MS network is studied as an example, thus a secondary hybrid optimization model of obstacle topology layout is set up, a resolution strategy of hybrid genetic simulated annealing algorithm is also proposed, and the expression mode, feasibility adjustment and assessment calculation methods of chromosome are introduced, which is proved to have good effects in the practical applications. Parameter optimization design is an important problem in pipeline network layout design. According to the structure and technological process characteristics of oil-gas gathering and transporting network and water injection network, a calculation method of system hydraulic and thermodynamic analysis is performed by use of hydro-mechanical theory. Based on that, the mathematic models of multi-objective parameter optimization of the two systems are established, in which minimizing pipeline network investment and energy cost of operation is taken as the objective. The model is a large-scale hybrid optimization problem consisting of discrete and continuous variables. In order to effectively solve the model, a weighted way is used to transform the model into single object optimization problems first, and then solve them with hybrid genetic algorithm. Practical cases'calculation have proved the validity and feasibility of this algorithm. In this paper, problems of dropping load rate, efficiency and rising operation energy consumption of surface engineering system during oil field exploitation are studied. The mathematic models of operation scheme optimization for oil-gas gathering and transporting and water injection systems are established, with the minimal energy consumption in operation taken as the objective, SQP algorithm and hybrid genetic algorithm adopted to solve the models separately, which have gained economic benefit in practical applications. Finally, on the basis of the theory studied above, a set of software for the intelligence optimization of layout design of oilfield surface pipeline network system and operation scheme is made with c++ builder language. Application of the software to layout design can not only significantly curtail programming period of the scheme, but also can greatly improve the design quality of it. All of these indicate that it is of practical importance for oilfield.