Beijing University of Chemical Technology - China
Author Profile
SCOPUS
ORCID
Early academic pursuits 📖
Liuyang song embarked on his academic journey with a strong foundation in engineering at beijing university of chemical technology. he earned his bachelor’s degree in engineering in 2010, followed by a master’s degree in 2013, both from the same institution. his passion for mechanical and electrical engineering led him to pursue a doctorate at mie university, japan, where he completed his doctoral studies in 2017. during his phd, he delved deep into advanced mechanical systems, honing his expertise in fault diagnosis and intelligent machine learning applications.
Professional endeavors 🏛️
Liuyang song has built a distinguished career in academia, holding key positions at beijing university of chemical technology. he started as a postdoctoral researcher in 2018, gradually rising through the ranks to become a lecturer, associate professor, and ultimately, a full professor in 2024. he also gained international experience as a postdoctoral researcher and temporary researcher at mie university, japan. his extensive experience in mechanical and electrical engineering has contributed to the development of cutting-edge diagnostic techniques and performance evaluation methodologies.
Contributions and research focus 🔬
Liuyang song's research primarily focuses on intelligent fault diagnosis, machine learning applications in engineering, and vibro-acoustic signal processing. he has been at the forefront of developing innovative algorithms for aeroengine spindle bearing diagnostics using multi-task neural networks and graph-structured data. his work also explores adaptive sparse Condition Based Maintenance representation methods for vibro-acoustic multi-source signal separation, lightweight convolutional neural networks, and small-sample machine learning for rail transit train equipment diagnostics. his research has significantly improved the accuracy and efficiency of fault detection in complex mechanical systems.
Accolades and recognition 🏅
Throughout his career, liuyang song has been recognized for his outstanding contributions to mechanical and electrical engineering. his research has been supported by prestigious funding Condition Based Maintenance bodies such as the national natural science foundation of china and the beijing natural science foundation. he has successfully led multiple research projects that have advanced the field of intelligent diagnostics. his contributions to academia have solidified his reputation as a leading researcher in his domain.
Impact and influence 🌍
Liuyang song's research has had a significant impact on industrial applications, particularly in aerospace and rail transit systems. his advanced diagnostic methodologies have enhanced the Condition Based Maintenance reliability and performance of critical mechanical components, reducing operational failures and maintenance costs. his work in machine learning-driven fault diagnosis has influenced both academic and industrial research, paving the way for more intelligent and efficient monitoring systems in engineering applications.
Legacy and future contributions 🔮
With a commitment to advancing mechanical and electrical engineering, liuyang song continues to push the boundaries of research in fault diagnostics and intelligent systems. his future work aims to integrate cutting-edge artificial intelligence techniques with mechanical diagnostics to further improve the precision and adaptability of predictive maintenance strategies. as a professor, he is dedicated to mentoring the next generation of engineers and researchers, ensuring that his legacy in intelligent fault diagnosis and machine learning applications continues to thrive.
Notable Publications
- Task-adaptive unbiased regularization meta-learning for few-shot cross-domain fault diagnosis
Authors: Huaqing Wang, Dongrui Lv, Tianjiao Lin, Changkun Han, Liuyang Song
Journal: Engineering Applications of Artificial Intelligence
- Representations aligned counterfactual domain learning for open-set fault diagnosis under speed transient conditions
Authors: Shen Liu, Jinglong Chen, Zhen Shi, Liuyang Song, Shuilong He
Journal: Knowledge-Based Systems
- A bearing fault diagnosis method with an improved residual Unet diffusion model under extreme data imbalance
Authors: Wang H., Zhang W., Han C., Fu Z., Song L.
Journal: Measurement Science and Technology
- A Convolutional Neural Network with Hybrid Loss Function for Bearing Fault Diagnosis
Authors: Lv D., Fu Z., Su Z., Ni H., Wang H., Song L.
Journal: Mechanisms and Machine Science
- A lightweight improved residual neural network for bearing fault diagnosis
Authors: Wang H., Fu Z., Lin T., Han C., Zhang W., Song L.
Journal: Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science