GET THE APP

Distributed collaborative reliability optimization for mechanical | 5123
Journal of Aeronautics & Aerospace Engineering

Journal of Aeronautics & Aerospace Engineering
Open Access

ISSN: 2168-9792

+44-20-4587-4809

Distributed collaborative reliability optimization for mechanical dynamic assembly relationship with support vector machine regression


3rd International Conference and Exhibition on Mechanical & Aerospace Engineering

October 05-07, 2015 San Francisco, USA

Cheng-Wei Fei, Wen-Zhong Tang and Guang-Chen Bai

BeiHang University, P R China The Hong Kong Polytechnic University, P R China

Posters-Accepted Abstracts: J Aeronaut Aerospace Eng

Abstract :

Mechanical dynamic assembly relationship seriously influences the reliability and work efficiency of complex machinery. To design a more reasonable mechanical dynamic assembly relationship involving multiply objects and multiply disciplines, a novel optimization method (called as SR-DCRSM) and a optimization model (multilayer model) are proposed for mechanical dynamic assembly reliability optimal design. The SR-DCRSM is developed by integrating Support Vector Machine Regression (SR) and Distributed Collaborative Response Surface Method (DCRSM). To validate the proposed approach and model, the reliability optimal design of gas turbine high pressure turbine Blade-Tip Radial Running Clearance (BTRRC), as a representative mechanical dynamic assembly relationship, was completed by considering nonlinear material parameters and dynamic heat load and mechanical load. The optimization results demonstrate that all optimal solutions satisfy the requirements of reliability optimal design of BTRRC and assembly objects, and the optimized BTTRC deformation is reduced by 10% approximately, which are promising to improve BTRRC design and control. As shown in the comparison of methods and model, the presented SR-DCRSM holds higher computational efficiency and precision, and the multilayer model possesses higher precision for mechanical dynamic assembly reliability optimal design. The presented efforts not only improve the performance and reliability of gas turbine, but also provide a promising approach and a valuable optimization model for mechanical dynamic assembly reliability optimal design. Besides, the present works enrich mechanical reliability design theory and method.

Top