The Diagnostic System Of Pumping Unit Based On Analysis Of Indicator Card

The sucker-rod pumping accounts for a large proportion of the mechanical oil extraction. The diagnosis of sucker-rod pumping and fault treatment are delayed because of the oil wells* dispersed location in the wild and the complicated circumstance. All these make the diagnosis of sucker-rod pumping being a difficult problem in the oil production field for a long time. Therefore, it is very important to diagnose the fault of the pumping units timely and provide operation advices reliably, which means lot to for improving the production efficiency and economical operation in oil field.The indicator card obtained by direct measurement intuitively reflects the working condition of sucker-rod pumping unit, which is the basis of the analysis of the downhole condition. From other people's research, this paper presents a new method for extracting features of indicator card based on expert system. Then a new rule of fault diagnosis is utilized to diagnose the types of fault, calculate the limit oil production and provide advice for economical operation. Finally a fault diagnosis system based on down-hole indicator is realized. Main tasks in this paper are as follows:Firstly, this paper introduces the development and main method of fault diagnosis, and then describes the operation principle of pumping unit and the shaping process of indicator card, which is the foundation of solution and feature extracting in down-hole.Secondly, the down-hole indicator is shaped by the indicator card according to the simulation of down-hole indicator based on sucker-rod vibration model. Also this paper introduces expert system and extracts the features of indicator card in line with the requirement of rules base. And then rules base for expert system are established. In addition, this paper introduces the main indicators of economical operation, provide advice by oil production.Finally, the fault diagnosis system has been realized with the combined program of Java and MATLAB. This system can be divided into five modules: data receiving module, fault diagnostic module, economical operation analysis module, fault alarm module and Rule base maintenance module. At last the testing process and result are introduced with detailed fault diagnosis example. Experiments results show that this system has good precision for identification of frequent faults and provides treatment according to limit oil production and real oil production. At the same time this system has a good prospect in industrial field.