Dalian, China

Song Ma

This inventor holds 1 USPTO granted patent and 1 published patent application. Top assignee: Dalian University of Technology. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Song Ma. Retrieved from https://idiyas.com/inventor/song-ma-typ4nnnn

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Calculating rank
USPTO Granted Patents = 1 

Average Co-Inventor Count = 1.0

ph-index = 1


Company Filing History:


Years Active: 2026

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Song Ma and Aero-Engine Remaining Useful Life Prediction.

Introduction

Song Ma is an inventor associated with Dalian, China, and Dalian University of Technology. His patent work addresses predictive health management for aero-engines, focusing on estimating remaining useful life from sample data.

Latest Patents

Ma is associated with 1 patent: “Multi-scale hybrid attention mechanism modeling method for aero-engine remaining useful life prediction.” The method preprocesses data to create samples and assign remaining useful life labels, then uses a model with position encoding, feature extraction, and regression prediction layers. The model is trained by minimizing the difference between its predictions and the true remaining useful life until a stopping criterion is met. The trained model then predicts remaining useful life, combining information across different time steps within a sample while accounting for correlations among samples.

Career Highlights

Ma’s listed work connects machine-learning modeling with aero-engine health management. The patent describes a multi-scale hybrid attention approach intended to support remaining useful life prediction.

Collaborations

Zhi Li is identified as Ma’s coworker. Ma is associated with Dalian University of Technology.

Conclusion

Song Ma’s patent presents an attention-based method for predicting aero-engine remaining useful life by integrating information across time steps and samples.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…