Deputy Director of Department at China University of Petroleum, Beijing, China
Professional Profile
Summary
Dr. Dandan Zhu is an Associate Professor in the College of Artificial Intelligence at China University of Petroleum, Beijing (CUPB). With a solid background in precision engineering and aircraft design, she specializes in integrating artificial intelligence with petroleum engineering. Since joining CUPB in 2015, she has led numerous national and industry-supported projects, focusing on intelligent drilling, geological modeling, and data-driven automation in subsurface energy exploration. Her work bridges fundamental research and field-based application, contributing to advancements in digital oilfield technologies.
Educational Details:
Dr. Zhu holds a Ph.D. in Precision Engineering from the University of Tokyo, Japan, and a Master’s degree in Aircraft Design from Beihang University, China. Her interdisciplinary academic training provides a unique foundation for innovation at the intersection of engineering mechanics, AI systems, and petroleum technology.
Professional Experience:
Since 2015, Dr. Zhu has been serving as Associate Professor at CUPB’s College of Artificial Intelligence. She has directed over 40 research projects and 27 consultancy collaborations, often partnering with major energy enterprises such as CNPC, Sinopec, and CNOOC. Her initiatives span intelligent trajectory control systems, hydraulic fracturing optimization, and 3D geological simulations. She is also a contributing reviewer and participant in technical forums under IEEE, ACM, and SPE.
Research Interests:
Her core research areas include reinforcement learning, trajectory control algorithms, wellbore guidance systems, and generative simulation environments. Dr. Zhu has developed an integrated learning framework for intelligent drilling that combines offline training, real-time decision-making, and post-drilling optimization. This system improves adaptability in uncertain geological formations and supports automation in energy extraction operations.
Author Metrics:
Dr. Zhu has authored 39 peer-reviewed journal publications indexed in SCI and Scopus. Her work has received a total of 62 citations since 2020. She has published 1 academic book (ISBN: 978-7-3025-3524-9) and holds 5 patents in the domain of AI-enhanced petroleum engineering technologies. Her Google Scholar profile can be accessed here.
Awards and Honors:
Dr. Zhu’s contributions have earned recognition through national-level research grants and industry partnerships. She has been instrumental in building interdisciplinary teams and field-tested innovations that have enhanced both academic understanding and operational performance in petroleum systems. She is actively involved in professional networks such as IEEE, ACM, and SPE, contributing to peer reviews and international conferences.
Publication Top Notes
1. End-to-End Multiplayer Violence Detection Based on Deep 3D CNN
Conference: Proceedings of the 2018 VII International Conference on Network Technology (ICNT)
Publication Date: 2018
Contributors: C. Li, L. Zhu, D. Zhu, J. Chen, Z. Pan, X. Li, B. Wang
Citations (as of latest record): 19
Abstract Summary: This study introduces an end-to-end multiplayer violence detection system utilizing deep 3D convolutional neural networks (CNNs). By analyzing spatial-temporal features in video frames, the model effectively detects violent interactions in multiplayer scenarios, offering potential applications in surveillance and security systems.
2. Investigation on Automatic Recognition of Stratigraphic Lithology Based on Well Logging Data Using Ensemble Learning Algorithm
Conference: SPE Asia Pacific Oil and Gas Conference and Exhibition (Paper ID: D021S016R003)
Publication Date: 2018
Contributors: K. Gong, Z. Ye, D. Chen, D. Zhu, W. Wang
Citations: 12
Abstract Summary: This paper presents an ensemble learning-based methodology for automatically identifying stratigraphic lithology using well logging data. The integration of multiple machine learning models significantly improves lithology classification accuracy, providing intelligent support for geological interpretation in drilling operations.
3. A Reinforcement Learning Based 3D Guided Drilling Method: Beyond Ground Control
Conference: Proceedings of the 2018 VII International Conference on Network Technology (ICNT)
Publication Date: 2018
Contributors: H. Liu, D. Zhu, Y. Liu, A. Du, D. Chen, Z. Ye
Citations: 8
Abstract Summary: The study introduces a reinforcement learning-based 3D guided drilling method to improve directional control in subsurface operations. The framework leverages real-time learning and environmental feedback to optimize drilling paths in complex geological settings, advancing autonomy in petroleum engineering.
4. A Target-Aware Well Path Control Method Based on Transfer Reinforcement Learning
Journal: SPE Journal
Publication Date: 2024
Contributors: Dandan Zhu, Q. Xu, F. Wang, D. Chen, Z. Ye, H. Zhou, K. Zhang
Citations: 6
Abstract Summary: This paper proposes a novel well path control strategy using transfer reinforcement learning to enhance adaptability in trajectory optimization. The model incorporates prior knowledge from similar geological environments to accelerate convergence and ensure target-aware control in complex drilling tasks.
5. Deep Learning Approach of Drilling Decision for Subhorizontal Drain Geosteering Based on APC-LSTM Model
Journal: SPE Drilling & Completion, Volume 38, Issue 01, Pages 1–17
Publication Date: 2023
Contributors: D. Zhu, X. Dai, Y. Liu, F. Wang, X. Luo, D. Chen, Z. Ye
Citations: 6
Abstract Summary: The article introduces an APC-LSTM (Adaptive Prediction and Control with Long Short-Term Memory) deep learning model to enhance real-time decision-making in subhorizontal geosteering operations. This approach improves trajectory accuracy and decision response under uncertain formation conditions.
Conclusion
Assoc. Prof. Dr. Dandan Zhu is a strong and deserving candidate for the Best Researcher Award in Artificial Intelligence. Her innovative, interdisciplinary research, leadership in AI-driven drilling automation, and commitment to real-world applications make her stand out. With a growing publication record, industrial collaboration, and dedication to AI advancement in energy, she embodies the qualities of a forward-thinking and impactful researcher. Strategic international exposure and editorial roles can further enhance her already impressive research trajectory.