Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Multilayer perceptron for nonlinear programming.

Journal Article · · Comput. Oper. Res.

A new method for solving nonlinear programming problems within the framework of a multilayer neural network perceptron is proposed. The method employs the Penalty Function method to transform a constrained optimization problem into a sequence of unconstrained optimization problems and then solves the sequence of unconstrained optimizations of the transformed problem by training a series of multilayer perceptrons. The neural network formulation is represented in such a way that the multilayer perceptron prediction error to be minimized mimics the objective function of the unconstrained problem, and therefore, the minimization of the objective function for each unconstrained optimization is attained by training a single perceptron. The multilayer perceptron allows for the transformation of problems with two-sided bounding constraints on the decision variables x, e.g., a{<=}x{sub n}{<=}b, into equivalent optimization problems in which these constraints do not explicitly appear. Hence, when these are the only constraints in the problem, the transformed problem is constraint free (i.e., the transformed objective function contains no penalty terms) and is solved by training a multilayer perceptron only once. In addition, we present a new Penalty Function method for solving nonlinear programming problems that is parameter free and guarantees that feasible solutions are obtained when the optimal solution is on the boundary of the feasible region. Simulation results, including an example from operations research, illustrate the proposed methods.

Research Organization:
Argonne National Laboratory (ANL)
Sponsoring Organization:
SC; LDRD
DOE Contract Number:
AC02-06CH11357
OSTI ID:
943019
Report Number(s):
ANL/RA/JA-36747
Journal Information:
Comput. Oper. Res., Journal Name: Comput. Oper. Res. Journal Issue: 9 ; Aug. 2002 Vol. 29; ISSN CMORAP; ISSN 0305-0548
Country of Publication:
United States
Language:
ENGLISH

Similar Records

Application of the recurrent multilayer perceptron in modeling complex process dynamics
Journal Article · Mon Feb 28 23:00:00 EST 1994 · IEEE Transactions on Neural Networks (Institute of Electrical and Electronics Engineers); (United States) · OSTI ID:7204331

Nonlinear programming with feedforward neural networks.
Conference · Wed Jun 02 00:00:00 EDT 1999 · OSTI ID:11194

Design optimization of multi-coil resistive magnets
Journal Article · Mon Jul 01 00:00:00 EDT 1996 · IEEE Transactions on Magnetics · OSTI ID:287689