A FRAMEWORK FOR MANAGEMENT OF LEAKS AND EQUIPMENT FAILURE IN OIL WELLS

Abstract

Oil is a precious and critical natural energy resource that is used in numerous ways to drive various industries worldwide. The extraction of oil from underground reservoirs is a complex process that requires a lot of planning, careful execution, and risk management. In this paper, CNN is employed to extract relevant features from sensor primary data collected from various wells. Detecting undesirable events such as leaks and equipment failure in oil wells is crucial for preventing safety hazards, environmental damage and financial losses, making it challenging to identify issues in a timely and accurate manner. This dissertation describes a hybrid model for detecting undesirable events in oil and gas wells using a combination of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) techniques. The CNN architecture enables effective information extraction by applying convolutional layers and pooling operations to identify patterns and spatial dependencies in the data. The extracted features are then fed into an LSTM network, which can capture temporal dependencies and learning long-term patterns. By utilizing LSTM, the model can effectively analyse the time series data and detect the occurrence of undesirable events, such as abnormal pressure, fluid leakage, or equipment malfunction, in oil and gas wells. The hybrid model leveraging CNN for feature extraction and LSTM for detecting undesirable events in the oil and gas industry presents a comprehensive approach to enhance well monitoring and prevent potential hazards. Achieving high accuracy rates of 99.8% for training and 99.78% for testing demonstrates the efficacy of the proposed model in accurately identifying and classifying undesirable events in oil and gas wells.