Intelligent filtering of field data

   In the oil and gas industry, the measured parameters during oil and gas production are often affected by noise, which contributes to complex and non-monotonic dynamics. This makes manual analysis and interpretation extremely difficult.   Therefore, this article aims to develop an algorithm capable of identifying and removing noise (signal changes without a clear cause) in the production parameters of well operation.   The article examines data smoothing methods, including moving average, exponential smoothing, Kalman filter, Wiener filter, Savitzky-Golay filter, Fourier transform, and wavelet transform. The authors identified advantages and limitations. An alternative approach is proposed, combining machine learning methods with standard data filtering tools. The developed algorithm restores the true dynamics of well performance metrics and filters out and smooths noise related to technical malfunctions. The novelty of the algorithm lies in using an LSTM neural network to extract the trend component from noisy dynamics, taking into account events occurring at the well itself as well as events happening at surrounding wells.

neural networks, production data filtering, field development