An Improved K-Means Based Design Domain Recognition Method for Automotive Structural Optimization

Design optimization methods are widely used for weight reduction subjecting to multiple constraints in automotive industry. One of the major challenges is to search for the optimal design in an efficient manner. For complex design and optimization problems such as automotive applications, optimization algorithms work better if the initial searching points are within or close to feasible domains. In this paper, the k-means clustering algorithm is exploited to identify sets of reduced feasible domains from the original design space. Within the reduced feasible domains, the optimal design can be obtained efficiently. A mathematical example and a vehicle body structure design problem are used to demonstrate the effectiveness of the proposed method.

• Record URL:
  https://doi.org/10.4271/2018-01-1032
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/01487191
• Supplemental Notes:
  • Abstract reprinted with permission of SAE International.
• Authors:
  • Hu, Chen
  • Zhan, Zhenfei
  • Dong, Kuo
  • Xu, Wei
  • Zhao, Qingjiang
• Conference:
  • WCX World Congress Experience
  • Location: Detroit Michigan, United States
  • Date: 2018-4-10 to 2018-4-12
• Publication Date: 2018-4-3

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Serial:
  • SAE Technical Paper
  • Publisher: Society of Automotive Engineers (SAE)
  • ISSN: 0148-7191
  • EISSN: 2688-3627
  • Serial URL: http://papers.sae.org/

Subject/Index Terms

• TRT Terms: Algorithms; Automobiles; Mathematical models; Motor vehicle bodies; Optimization; Structural analysis; Vehicle design
• Subject Areas: Design; Highways; Vehicles and Equipment;

Filing Info

• Accession Number: 01728864
• Record Type: Publication
• Source Agency: SAE International
• Report/Paper Numbers: 2018-01-1032
• Files: TRIS, SAE
• Created Date: Jan 28 2020 9:47AM