Research on Shape-Performance Integrated Monitoring Technology for Planetary Gearboxes Based on the Integration of...

Area of Science:

• Mechanical Engineering
• Computational Engineering
• Artificial Intelligence

Background:

• Planetary gearboxes face challenges in performance monitoring under high-speed and high-load conditions.
• Gear tooth damage is a significant concern, difficult to assess during operation.

Purpose of the Study:

• To develop a digital twin system for operational state recognition and performance prediction of planetary gearboxes.
• To integrate morphological and functional characteristics for a comprehensive virtual model.

Main Methods:

• Utilized finite element analysis (FEA), multibody dynamics (MBD) simulation, and artificial intelligence (AI) algorithms.
• Created a virtual mapping of gearbox geometry, structure, and dynamics using experimental data.
• Developed a system combining a structural performance surrogate model, a system-driven model, and a dynamic performance database.

Main Results:

• The structural performance model exhibited a maximum error of 3% under specific conditions, with negligible impact on sun gear meshing evaluation.
• The dynamic performance prediction showed a maximum error of 1.68%, demonstrating strong consistency with experimental data.
• The digital twin system successfully mapped gearbox behavior and enabled state recognition.

Conclusions:

• The proposed digital twin system provides accurate performance prediction and operational state recognition for planetary gearboxes.
• The system effectively addresses challenges in monitoring under extreme operating conditions.
• This approach enhances the reliability and predictive maintenance capabilities for critical gearbox components.