The Remote Self-Diagnostic System Of Pumping Unit Based On Analysis Of Indicator Card

The rapid development of Computer Science has significantly improved the automatic level of oil field. The pumping units break down as the awful working condition. And the artificially exception handle is difficult because of the complicated circumstance in the oil well and the equipments dispersing distribution. Therefore, it is very important to diagnose the fault of the pumping units, which means lot to the production efficiency and the energy saving of the oil field.The indicator card of pumping unit can be used to judge the work condition of the pumping unit. This paper discusses the technology of pumping unit diagnosis and the fault severity level judgment based on indicator card.First, the development of the diagnosis system and the operation principle of the pumping unit are introduced. And the generation of the indicator card, the sort of the indicator card and the characteristic of the indicator card are discussed particularly.Second, diagnosis relevant technology including preprocessing, feature extraction, fault classification of the indicator card are researched in the paper. A method using circumscribe rectangular separates the indicator card from coordinate, which makes the research dimensionless. As the common methods of feature extraction have insoluble problem, a method based on pattern recognition technology and gray system theory is proposed to extract features of the indicator cards. This method form the gray matrix, calculate the gray statistics characteristics of the fault, form the classification eigenvectors and create the diagnosis model based on grey correlation analysis.Finally, pumping unit diagnosis system is established based on the technology of MATLAB and VC++ mixed programming. The whole system including indicator card identify module, fault alarm module and diagnosing module are totally introduced.Experiments prove that the diagnosis system is adaptive, stable and high reliability. And the judgment of the fault severity level needs further confirm in practical application.