Dynamic liquid level prediction in oil wells during oil extraction based on WOA-AM-LSTM-ANN model using dynamic and static information

Accurately predicting the dynamic liquid level is the key to energy efficient operation of oil wells, however, the dynamic liquid level of oil wells in the same area varies widely, and the existing methods cannot achieve uniform modeling of the dynamic liquid level of multiple wells with high accuracy. To this end, based on the parameters of the multi-wells production process, this paper proposes method for predicting the dynamic liquid level of oil wells based on a Long short-term memory (LSTM) with attention mechanism (AM) and artificial neural network (ANN) optimized by the whale optimization algorithm (WOA). First, the factors significantly related to the change in the dynamic liquid level are identified and divided into dynamic and static information. Dynamic features are extracted using AM-LSTM. AM can enhance the impact of important information when extracting dynamic features using LSTM; Static features are extracted through ANN; Finally, both dynamic and static features are used as inputs to ANN to predict the dynamic liquid level. Solve the prediction model parameter selection problem with WOA. Using historical oilfield data collected in the field for validation, the experiment proves that the proposed method in this paper is effective for predicting the dynamic liquid level of multi-wells. Therefore, this prediction model can be used as a tool to detect the dynamic liquid level, which can achieve the purpose of reducing energy consumption and improving efficiency during oil extraction.

Automated summary

This paper proposes a method based on AM-LSTM, ANN, and WOA for predicting the dynamic liquid level of multiple wells. By extracting dynamic and static features and using neural networks for prediction, it can achieve accurate and efficient operation of oil wells.