THE RELIABILITY-BASED OPTIMUM DESIGN OF SHIP'S STRUCTURE BASED ON NEURAL NETWORK THEORY

This paper applies neural network theory to the reliability-based optimum design of a ship's longitudinal structure and adopts the simulated annealing method and Boltzmann machine principle by which the local optimum can be avoided and the approximate global optimum of the system can be found. Since only one approximate global optimum can be reached using neural network theory for optimum designs, an approach which sets a memory in the optimization process is developed and precision is improved efficiently. Some new improvements are introduced to the simulated annealing method which greatly reduce the design time. The validity and general applicability of these methods and program are verified by the results of the reliability-based optimum design of a midship cross section.

  • Supplemental Notes:
    • Shipbuilding of China, n 132, Feb 1996, p 59 [9 p, 8 ref, 1 tab, 4 fig]
  • Authors:
    • Yu, Junwei
    • Xu, Hongli
  • Publication Date: 1996

Language

  • Chinese

Subject/Index Terms

Filing Info

  • Accession Number: 00727891
  • Record Type: Publication
  • Source Agency: British Maritime Technology
  • Files: TRIS
  • Created Date: Nov 4 1996 12:00AM