Diagnosing sucker-rod pumping units by means of a neural network module implemented on the basis of an oilwell controller

Currently, sucker-rod pumping (SRP) units are widely used in oil wells, due to two important factors: costs and ease of use. To optimize production using sucker rod pumps, well Rod Pump Controllers (RPC) have been used for more than 20 years. Today the main method of controlling the sucker-rod pumping unit is the analysis of dynagraph card (determination of the state and mode of operation of the pump based on the dependence of the rod’s load on its position). The qualitative analysis of a dynagraph (DMG) comes down to diagnostics, which detects and identifies signs of possible malfunctions of the pump and the well as a whole. The task of determining malfunctions by a dynagraph is considered difficult for a computer analysis and involves the evaluation of a dynagraph card by a qualified technologist. This article discusses methods and algorithms for determining malfunctions from obtained RPC dynagraphs, implemented directly on base of the well controller. These methods can be divided into analytical and neural network methods. Analytical algorithms describe the DMG defect in the form of formulas or logical dependencies. Neural network methods approach the problem of defect recognition as recognizing a set of unrelated data. This helps to work with a system with a large number of parameters, such as a (SRP). The Naftamatika took into account the pros and cons of previous approaches and developed its own neural network model. The development consisted of selecting the type of network, the number of its layers, creating a spatial structure of neurons, creating conditions for training the network and selecting an adequate training sample. To train the controller, a program was used in which thousands of dynamograms with various defects and conditions were loaded. This network model is implemented in a Wellsim pump controller, which provides sufficient performance, the algorithm successfully detects insufficient filling, gas factor and other faults with an accuracy of 96 %.