Study On The Method Of Intelligent Technologies For Fault Diagnostic Of Rod Pumped Wells

In the opening up oilfields, it's an important task in petroleum industry to predict and diagnose the fault under the oilfields, to understand and master working-pump's condition of oilfields, and to realize automatic monitor and scientific management in a exploit oil well. Because the accordant rate of intelligent diagnosis is low, and it is difficult to satisfy the production requirement of oil well, the following aspects are researched.Kinematics and hydraulics basic theory of oil pump well, the movement of plunger piston and the compressibility of the liquid are comprehensively considered, a new continuous flow equation of the fluid in the pump cylinder is setup. On the basis of improved continuous flow equation, the mathematical model that expresses the interrelationship of the liquid pressure, the movement of plunger piston and the leakage clearance is setup, and simulating models of the liquid instantaneous pressure in the pump barrel and the pump dynamometer are established. Further more, the simulating models of the instantaneous leakage rate and the accumulating leakage volume of liquid are setup.By using wave equation, the fault diagnosis model based on the pump dynamometers is setup. It is realized conversion that rod dynamometers to pump dynamometers. The characteristic extracting is obtained based on the geometric characteristic of working-pump's graph, and the calculated model that select feature of failure of the subsurface equipment is setup.The Elman network is adopted, and the diagnosis models of artificial neural networks is setup. The 14 characteristics extracting are obtained as input signals of neural networks. Then the neural networks keep the knowledge in nets in the form of weigh and threshold by learning from samples. Final the outputs of nets are 12 kind typical models of the fault. After network is trained, the fault diagnosis method is validated with examples, we can get better diagnosis result.Using Visual Basic 6.0 and Matlab to develop " Intelligent technologies system for fault diagnostic of oil well pump " computer software. The result shows this software has highly simulation and diagnosis precision, and can satisfy the request of practical application.