Dr. Dongfang Zhao is a dedicated researcher and lecturer at Shanghai Polytechnic University, specializing in artificial intelligence and mechanical fault diagnosis. Since 2014, he has advanced the frontiers of intelligent systems in industrial diagnostics. After completing his Ph.D. at Shanghai University in 2021, he pursued postdoctoral research at the Control Science and Engineering Research Station. Recognized nationally for his outstanding doctoral dissertation, Dr. Zhao continues to drive innovation in AI-enhanced fault detection. He has published 20+ SCI/EI-indexed papers, earning ~500 citations, and contributes significantly to academic and practical advancements. 📚🤖🔧
Dr Dongfang Zhao, Shanghai Polytechnic University, China
Profile
SCOPUS
🎓 Education
Dr. Zhao earned his Ph.D. in Measurement, Control, and Instrumentation from Shanghai University in 2021, where his dissertation was nominated for a national excellence award. He built his foundation in engineering and research through a series of rigorous academic training steps. Following graduation, he immediately joined a prestigious postdoctoral program in Control Science and Engineering. His academic path reflects a commitment to merging theoretical depth with applied innovation in intelligent diagnostics and control systems. 📖🎓🔍
💼 Experience
Currently serving as a lecturer and master’s supervisor at Shanghai Polytechnic University, Dr. Zhao is actively engaged in research and teaching. He completed a postdoctoral fellowship at the Control Science and Engineering Research Station of Shanghai University. Professionally, he has collaborated on several government and industrial research projects, including two National Natural Science Foundation of China initiatives and AI-enabled fault analysis programs. His diverse academic and industry-facing experiences reflect a holistic career in intelligent systems and real-world fault mitigation. 🏫🧪⚙️
🛠️ Contributions
Dr. Dongfang Zhao has developed three advanced AI models tailored to tackle diverse industrial diagnostic challenges. DRANet enhances fault detection accuracy under strong noise 💥, while DBANet ensures precise diagnosis under variable rotational speeds 🔄 using extreme multi-scale entropy. Furthermore, SCANet excels in unlabeled diagnostic scenarios 🚫🏷️, reducing domain confusion and boosting generalization 🌐. These innovations significantly advance smart maintenance, ensuring reliability, adaptability, and intelligence in complex mechanical systems—paving the way for next-generation predictive diagnostics in Industry 4.0 🔧🌍.
📡 Research Projects
Dr. Dongfang Zhao has led five significant research projects, including a prestigious Super Postdoctoral Incentive Program project in Shanghai, an AI-enabled initiative from the Shanghai Education Commission, and two provincial/ministerial key lab open funds. He also directed a school-level youth innovation project at Shanghai Polytechnic University. Additionally, as a technical backbone, he has contributed to two National Natural Science Foundation of China projects, a Shanghai Science & Agriculture program, and a classified aerospace project. These engagements demonstrate his leadership in AI-driven diagnostics and interdisciplinary collaboration across academia and high-impact industries. 🚀🧠📡🔍💼
🔬 Research Focus
Dr. Zhao’s research revolves around AI-based fault diagnosis for mechanical systems, particularly in complex and noisy environments. His work spans domain adaptation networks (DRANet, DBANet, SCANet) and advanced entropy-based methods for speed-invariant diagnostics. He develops frameworks that increase system robustness, generalization, and diagnostic precision under non-ideal conditions. This includes intelligent modeling for unlabeled or variable-speed environments—challenges typical in modern industrial systems. His research directly supports smart manufacturing, predictive maintenance, and Industry 4.0 frameworks. 🧠📡🔩
📘 Publications
Pearson Coefficient Enhanced Multi-Branch Joint Attention Network and Adaptive Decomposition Based Dual Adaptive Fault Diagnosis Scheme for Rolling Bearing
👨🔬 Authors: Dongfang Zhao, et al.
📘 Journal: Signal, Image and Video Processing
📅 Year: 2025
📌 Overview: This paper presents a novel dual adaptive fault diagnosis framework leveraging Pearson correlation coefficients and a joint attention mechanism, significantly improving the accuracy of bearing fault detection under complex conditions.
📊🧠🛠️
Multiscale Attention Feature Fusion Network for Rolling Bearing Fault Diagnosis Under Variable Speed Conditions
👨🔬 Authors: Dongfang Zhao, et al.
📘 Journal: Signal, Image and Video Processing
📅 Year: 2024
📌 Overview: This study introduces a multiscale attention-based deep learning model that enhances feature fusion and generalization in rolling bearing fault diagnosis, particularly effective under varying speed scenarios.
⚙️🔍📉