Papers
3
Total Citations
81
H-Index
3
About
Lu-Kai Song is a leading researcher at the intersection of artificial intelligence, digital twin systems, and advanced probabilistic engineering. His work focuses on developing intelligent computational methods for the transient probabilistic analysis and design of complex flexible multibody systems—critical for ensuring reliability in high-performance machinery. Song’s most influential contribution is the dynamic neural network method, which integrates improved Particle Swarm Optimization (PSO) and Bayesian Regularization (BR) algorithms to dramatically enhance the efficiency and accuracy of probabilistic analysis. This foundational work, published in 2017, has garnered 55 citations and remains a key reference in the field. Building on this, he proposed a distributed collaborative strategy using dynamic fuzzy neural networks for transient probabilistic design, further advancing the state of the art. More recently, Song has pioneered the convergence of AI-enhanced digital twin systems engineering with the emerging paradigm of the Industrial Metaverse in the era of Industry 5.0, a visionary 2025 paper already attracting significant attention. His research uniquely bridges rigorous mechanical reliability analysis with cutting-edge artificial intelligence, offering transformative tools for smart manufacturing and human-machine collaboration.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3