Application of CNN-LSTM in Gradual Changing Fault Diagnosis of Rod Pumping System

Abstract

Owing to the importance of rod pumping system fault detection using an indicator diagram, indicator diagram identification has been a challenging task in the computer-vision field. The gradual changing fault is a special type of fault because it is not clearly indicated in the indicator diagram at the onset of its occurrence and can only be identified when an irreversible damage in the well has been caused. In this paper, we proposed a new method that combines the convolutional neural network (CNN) and long short-term memory (LSTM) network to perform a gradual changing fault classification. In particular, we employed CNN to extract the indicator diagram multilevel abstraction features based on its hierarchical structure. We considered the change in the time series of indicator diagrams as a sequence and employed LSTM to perform recognition. Compared with traditional mathematical model diagnosis methods, CNN-LSTM overcame the limitations of the traditional mathematical model theoretical analysis such as unclear assumption conditions and improved the diagnosis accuracy. Finally, 1.3 million sets of well production were set as a training dataset and used to evaluate CNN-LSTM. The results demonstrated the effectiveness of utilizing CNN and LSTM to recognize a gradual changing fault using the indicator diagram and characteristic parameters. The accuracy reached 98.4%, and the loss was less than 0.9%.