NEUROFUZZY MODELING OF NATURAL FREQUENCIES OF CYLINDRICAL SHELLS APPLIED TO EVOLUTIONARY BASED OPTIMAL DESIGN OF SR MOTORS

摘要: A thorough analysis of cylindrical shells' dynamical behavior is essential in many different industrial design problems, and particularly electric motor design. Shell vibration equations form a set partial differential order eight, where their closed solution only known for few special cases with boundary conditions along not necessarily realistic assumptions. On the other hand, finite element based numerical solutions does yield lumped model that can be regarded as general natural frequencies shells. In this paper, neurofuzzy shells developed. At first, are calculated wide range dimensions, using either or method. Gathered data exploited training Locally Linear Neurofuzzy Network, which yields calculation While developed may used problems deals shells, case study, proposed an evolutionary algorithm utilized optimal Switched Reluctance motor.