Energy Consumption Prediction for Drilling Pumps Based on a Long Short-Term Memory Attention Method
Source abstract
Abstract
In the context of carbon neutrality and emission reduction goals, energy consumption optimization in the oil and gas industry is crucial for reducing carbon emissions and improving energy efficiency. As a key component in drilling operations, optimizing the energy consumption of drilling pumps has significant potential for energy savings. However, due to the complex and variable geological conditions, diverse operational parameters, and inherent nonlinear relationships in the drilling process, accurately predicting energy consumption presents considerable challenges. This study proposes a novel Long Short-Term Memory Attention model for precise prediction of drilling pump energy consumption. By integrating Long Short-Term Memory (LSTM) networks with the Attention mechanism, the model effectively captures complex nonlinear relationships and long-term dependencies in energy consumption data. Comparative experiments with traditional LSTM and Convolutional Neural Network (CNN) models demonstrate that the LSTM-Attention model outperforms these models across multiple evaluation metrics, significantly reducing prediction errors and enhancing robustness and adaptability. The proposed model achieved Mean Absolute Error (MAE) values ranging from 5.19 to 10.20 and R2 values close to one (0.95 to 0.98) in four test scenarios, demonstrating excellent predictive performance under complex conditions. The high-precision prediction of drilling pump energy consumption based on this method can support energy optimization and provide guidance for field operations.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Oil and Gas Production Techniques · Advanced Data Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Karamay Drilling Company of CNPC Western Drilling Engineering Co., Ltd., Karamay 834000, China
State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum, Beijing 102249, China
Funding
National Science Fund for Distinguished Young Scholars
References (20)
Show source-provided references
1. Multi-source information fusion-based dynamic model for online prediction of rate of penetration (ROP) in drilling process10.1016/j.geoen.2023.212187 ↗
2. A hybrid deep learning model towards fault diagnosis of drilling pump10.1016/j.apenergy.2024.123773 ↗
3. A novel method for fault diagnosis of fluid end of drilling pump under complex working conditions10.1016/j.ress.2024.110145 ↗
4. A parallel deep neural network for intelligent fault diagnosis of drilling pumps10.1016/j.engappai.2024.108071 ↗
5. Data-Driven Energy Consumption Prediction of a University Office Building using Machine Learning Algorithms10.1016/j.energy.2024.133242 ↗
6. Effect of pump start-stop operation in drilling of offshore Extreme-HPHT directional wells upon bottomhole transient fluctuating pressure10.1016/j.geoen.2024.212708 ↗
7. Intelligent energy consumption prediction for battery electric vehicles: A hybrid approach integrating driving behavior and environmental factors10.1016/j.energy.2024.132774 ↗
8. Short-term energy consumption prediction for university dormitory buildings based on energy consumption grouping by considering meteorological factors and teaching schedules10.1016/j.enbuild.2024.114219 ↗
9. Prediction of energy consumption for manufacturing small and medium-sized enterprises (SMEs) considering industry characteristics10.1016/j.energy.2024.131621 ↗
10. Prediction of drilling plug operation parameters based on incremental learning and CNN-LSTM10.1016/j.geoen.2024.212631 ↗
11. Comparative analysis of machine learning techniques for predicting drilling rate of penetration (ROP) in geothermal wells: A case study of FORGE site10.1016/j.geothermics.2024.103028 ↗
12. Developing GAN-boosted Artificial Neural Networks to model the rate of drilling bit penetration10.1016/j.asoc.2023.110067 ↗
13. The Geothermal Artificial Intelligence for geothermal exploration10.1016/j.renene.2022.04.113 ↗
14. Insight of low flammability limit on sustainable aviation fuel blend and prediction by ANN model10.1016/j.egyai.2024.100423 ↗
15. Using acoustic emission technique for structural health monitoring of laminate composite: A novel CNN-LSTM framework10.1016/j.engfracmech.2024.110447 ↗
16. FE-RNN: A fuzzy embedded recurrent neural network for improving interpretability of underlying neural network10.1016/j.ins.2024.120276 ↗
17. Efficient prediction framework for large-scale nonlinear petrochemical process based on feature selection and temporal-attention LSTM: Applied to fluid catalytic cracking10.1016/j.ces.2024.120733 ↗
18. Enhanced Hybrid LSTM and SLAR Modeling for In-Depth Analysis of Temporal and Spatial Patterns in Compositional Data for Environmental Monitoring10.1016/j.psep.2024.09.079 ↗
19. Attention mechanism enhanced LSTM networks for latency prediction in deterministic MEC networks
20. A novel algorithm system for wind power prediction based on RANSAC data screening and Seq2Seq-Attention-BiGRU model10.1016/j.energy.2023.128986 ↗