Font Size: a A A

Study On The Oil Extraction Control System In The Oil Field Based On Neural Network And Genetic Algorithms

Posted on:2005-11-10Degree:MasterType:Thesis
Country:ChinaCandidate:Y LiFull Text:PDF
GTID:2168360125950730Subject:Control theory and control engineering
Abstract/Summary:PDF Full Text Request
Oil extraction control system in the oil field is mainly used to measure the level of the oil underground and extract oil intelligently. According to the geology of oil field in our country, most of the oil well appears empty after exploitation for some time. But when this happens, the electromotor still works on all day and all night that results in the phenomenon of "a big horse hauling a small garage". So it makes the difficulties in retrenching the energy sources because of the large amount of the power energy used. Overall this system in the dissertation is essential that it can not only meet with the need of intelligent oil extraction, also offer the effective plan of design for the research, development and production of the new-type oil extraction control system.This System can be designed in various scales, complying with the request of the user. It is concerned that in this dissertation the rating current of the electromotor is 50 Amperes. It is in the highest flight to set up such a system in China and is very significant to study on it. In order to build such a system, many theoretical and technological problems have to be solved in designing system, designing technics structure of the equipment, installing equipments, developing VEGA configuration and so on. Some of them are innovative work. Based on the practices in engineering, in this dissertation some key technological problems are deeply studied and discussed on the principle of the oil extraction control system, in demonstrating the scheme, designing the whole technics structures and hardware, designing software algorithms, and developing VEGA configuration for this system.First, considering the technological requirements of the system and based on the study and absorption of relative theories and technologies for the key problems, the whole structure of this system is designed to be satisfied with the requirements of high reliability, safety, efficiency, practicality and convenience operations and the principle of the control system is demonstrated.Secondly, considering the working characteristic of the control system for oil extraction and specific requirement, the research of the system's hardware is carried on thoroughly and particularly. Then, in this dissertation the key research is focused greatly on the software algorithms. On the one hand the general BP neural network is adopted on the system modeling, based on which the normalization method of the original training data is studied, in order to resolve the problems of the tardy convergency velocity and easily getting into the local minimum, homotopic and nonlinear homotopic BP algorithm are done deeply. In the end, nonlinear homotopic algorithm including nonlinear normalization method to original samples is used to model the relation between height and current, current and time, and the curve of the oil cumulation. On the other hand, in order to optimize the outwork time of the electromotor, the general GA is researched thoroughly. At last the simulations to the all algorithms are studied, and the validity of the algorithms is proved. All referred above are significant and valuable to the theoretical guidance and application.Finally, the configuration, interior structure, and installation of the control system are designed, which offer an agressive potent to the actualization of the system. After that the visual interface of software developing platform named VEGA between control system and the computer is designed for the analysis and demonstration of the system, containing the corresponding control function. In the dissertation, developing platform may be used to analyze the experiment data and demonstrate the high efficiency, accuracy and practicality of the hardware, software algorithms scheme. The above methods are all realized depending on the hardware, software and VEGA platform. Ultimately, the oil extraction control system is successfully built, and the requirement of technology of the system is satisfied.
Keywords/Search Tags:oil extraction control system, neural network, normalization, nonlinear homotopic BP NN, genetic algorithms, visual software developing platform
PDF Full Text Request
Related items