Deputy Director of Department at China University of Petroleum, Beijing
Dr. Dandan Zhu is an Associate Professor at the College of Artificial Intelligence, China University of Petroleum, Beijing. She holds a Ph.D. in Precision Engineering from the University of Tokyo and a Master’s in Aircraft Design from Beihang University. she has advanced pioneering research that connects artificial intelligence with petroleum engineering, specializing in intelligent drilling, trajectory control, and geosteering. Her expertise extends to reinforcement learning, geological modeling, and automation technologies that optimize drilling operations under uncertainty.Dr. Zhu has become a recognized name in intelligent automation. She has collaborated with leading energy enterprises such as CNPC, Sinopec, and CNOOC, ensuring her research achieves practical industry impact. Through her academic leadership, cross-disciplinary collaborations, and contributions to applied AI systems, she has established herself as a forward-looking researcher contributing to innovation in parametric design, energy engineering, and computational intelligence.
Professional Profile
Google Scholar
Education
Dr. Zhu’s academic foundation is built upon two of Asia’s most prestigious universities. She completed her Master’s degree in Aircraft Design at Beihang University, where she gained expertise in structural mechanics, system design, and advanced computational modeling. Driven by her commitment to precision and innovation, she pursued a Ph.D. in Precision Engineering at the University of Tokyo, one of the world’s leading centers for advanced engineering research. Her doctoral studies focused on integrating computational methods, optimization techniques, and AI-based modeling, giving her a strong interdisciplinary foundation. This unique educational background allowed her to bridge the gap between traditional engineering and emerging computational technologies. Her academic journey reflects a balance of theory and applied learning, preparing her to apply parametric design, reinforcement learning, and automation methods to real-world challenges in petroleum engineering. This solid academic training has been instrumental in shaping her contributions to intelligent drilling, trajectory optimization, and automated decision-making systems.
Experience
Dr. Zhu has served as an Associate Professor at the China University of Petroleum, Beijing .Over the course of her career, she has led more than 40 research projects and collaborated with leading global enterprises. Her work has contributed to 27 consultancy projects, directly influencing the development of intelligent drilling and geosteering systems deployed by CNPC, Sinopec, and CNOOC. She has authored 39 peer-reviewed journal articles, presented her findings at international conferences, and actively participates in professional communities such as IEEE, ACM, and SPE. Her experience spans both academia and industry, enabling her to merge advanced computational research with applied petroleum engineering practices. Dr. Zhu’s mentoring of graduate students and supervision of doctoral research further highlight her commitment to cultivating the next generation of engineers and researchers. Her professional journey reflects a blend of academic innovation, technical expertise, and practical solutions, all contributing to advancements in parametric design and energy technologies.
Research Focus
Dr. Zhu’s research is focused on integrating artificial intelligence with petroleum engineering to create intelligent, adaptive, and sustainable drilling solutions. She specializes in reinforcement learning, parametric design, trajectory control, and real-time decision-making algorithms that address complex geological conditions. Her work leverages simulation-driven optimization and generative models to improve the robustness of drilling strategies. One of her major contributions is the development of a high-interaction learning framework that unites offline training, real-time decision-making, and post-operation knowledge transfer. She has also advanced AI-driven geosteering and subsurface automation frameworks, enhancing exploration efficiency and operational safety. By combining data-driven modeling with practical field-tested systems, her research strengthens automation in petroleum exploration. Looking forward, Dr. Zhu’s vision includes extending parametric design methodologies into sustainable energy technologies, creating intelligent systems that can adapt to future energy transitions. Her work exemplifies the fusion of computational intelligence, applied AI, and design optimization in engineering innovation.
Publication Top Notes
Title: End-to-end multiplayer violence detection based on deep 3D CNN
Authors: C. Li, L. Zhu, D. Zhu, J. Chen, Z. Pan, X. Li, B. Wang
Summary: This study introduced a deep 3D Convolutional Neural Network (CNN) for activity recognition. The approach enhanced the detection of multiplayer violent behaviors in video sequences, demonstrating improvements in accuracy and robustness. Its applications extend to public safety, surveillance systems, and automated monitoring in complex environments.
Title: Investigation on automatic recognition of stratigraphic lithology using ensemble learning
Authors: K. Gong, Z. Ye, D. Chen, D. Zhu, W. Wang
Summary: This paper proposed an ensemble learning framework to automatically recognize stratigraphic lithology from well logging data. By integrating multiple models, it improved drilling decision-making accuracy and provided reliable geological insights. The work contributes to more efficient and precise subsurface exploration.
Title: Target-aware well path control via transfer reinforcement learning
Authors: Z. Dandan, Q. Xu, F. Wang, D. Chen, Z. Ye, H. Zhou, K. Zhang
Summary: This research applied transfer reinforcement learning for adaptive well path control. By dynamically adjusting trajectories under uncertain geological conditions, the method improved drilling efficiency and accuracy. The framework demonstrated the potential of AI in real-time wellbore guidance.
Title: Reinforcement learning-based 3D guided drilling
Authors: H. Liu, D. Zhu, Y. Liu, A. Du, D. Chen, Z. Ye
Summary: The study introduced a reinforcement learning method for 3D guided drilling. It moved beyond conventional ground control by enabling intelligent automation in drilling operations. This advancement provided a foundation for safer and more efficient drilling practices.
Title: Deep learning for drilling decisions using APC-LSTM
Authors: D. Zhu, X. Dai, Y. Liu, F. Wang, X. Luo, D. Chen, Z. Ye
Summary: This work developed the APC-LSTM deep learning model for drilling decision-making in subhorizontal drain geosteering. The model significantly improved predictive accuracy in complex geological formations. It enhanced decision support systems for real-time drilling applications.
Title: Surface dynamometer card reproduction using periodic current data
Authors: D. Zhu, X. Luo, Z. Zhang, X. Li, G. Peng, L. Zhu, X. Jin
Summary: This research proposed an AI-based approach to reproduce surface dynamometer cards using periodic electric current data. The method provided a cost-effective diagnostic tool for petroleum production monitoring. Its outcomes improved operational reliability and efficiency in field applications.
Title: Comprehensive control system for gathering pipe networks using reinforcement learning
Authors: Q. Wu, D. Zhu, Y. Liu, A. Du, D. Chen, Z. Ye
Summary: The paper designed a reinforcement learning-based control system for pipeline gathering networks. It optimized energy flow and minimized operational inefficiencies in petroleum transport. The system showed promise in enhancing automation and sustainability in energy infrastructure.
Title: Gait coordination feature modeling for recognition
Authors: D. Zhu, L. Ji, L. Zhu, C. Li
Summary: This study introduced a multi-scale gait representation framework for gait recognition. By modeling coordination features, the method improved recognition performance across varying walking styles. It contributed to advancements in biometric identification and security systems.
Conclusion
Dr. Dandan Zhu is a strong candidate for the Best Researcher Award. Her record reflects innovation, productivity, and significant contributions to AI-driven petroleum engineering, with tangible outcomes in both academic and industrial contexts. With further growth in international outreach, leadership positions, and wider academic visibility, she has the potential to establish herself as a global leader in intelligent energy systems research.