Parallelvector computation for structural analysis and nonlinear unconstrained optimization problems
Abstract
Practical engineering application can often be formulated in the form of a constrained optimization problem. There are several solution algorithms for solving a constrained optimization problem. One approach is to convert a constrained problem into a series of unconstrained problems. Furthermore, unconstrained solution algorithms can be used as part of the constrained solution algorithms. Structural optimization is an iterative process where one starts with an initial design, a finite element structure analysis is then performed to calculate the response of the system (such as displacements, stresses, eigenvalues, etc.). Based upon the sensitivity information on the objective and constraint functions, an optimizer such as ADS or IDESIGN, can be used to find the new, improved design. For the structural analysis phase, the equation solver for the system of simultaneous, linear equations plays a key role since it is needed for either static, or eigenvalue, or dynamic analysis. For practical, largescale structural analysissynthesis applications, computational time can be excessively large. Thus, it is necessary to have a new structural analysissynthesis code which employs new solution algorithms to exploit both parallel and vector capabilities offered by modern, high performance computers such as the Convex, Cray2 and CrayYMP computers. The objective of this research project is, therefore, to incorporate the latest development in the parallelvector equation solver, PVSOLVE into the widely popular finiteelement production code, such as the SAP4. Furthermore, several nonlinear unconstrained optimization subroutines have also been developed and tested under a parallel computer environment. The unconstrained optimization subroutines are not only useful in their own right, but they can also be incorporated into a more popular constrained optimization code, such as ADS.
 Publication:

NASA STI/Recon Technical Report N
 Pub Date:
 September 1990
 Bibcode:
 1990STIN...9227874N
 Keywords:

 Algorithms;
 Finite Element Method;
 Nonlinearity;
 Parallel Computers;
 Parallel Processing (Computers);
 Structural Analysis;
 Structural Design;
 Vector Processing (Computers);
 Displacement;
 Eigenvalues;
 Fortran;
 Nonlinear Equations;
 Simultaneous Equations;
 Supercomputers;
 Structural Mechanics