A Gudermannian neural network performance for the numerical environmental and economic model

Abstract

The present work is to exploit the Gudermannian neural network (GNN) using the global competency of genetic algorithm (GA) and quick local refinements of sequential quadratic programming approach (SQPA), i.e., GNNGA-SQPA for the nonlinear economic and environmental system. The differential form of the nonlinear system depends upon three classes, system capability of industrial elements, implementation cost of control values and a new diagnostics technical elimination cost. An error-based fitness function is constructed using the differential system and then optimized by using the hybrid competency of the GA-SQPA. Ten numbers of neurons, a merit Gudermannian function, and the suitable weight vectors are presented in the neural network construction. The accuracy of the GNN-GA-SQPA is assessed through the comparisons and the negligible performances of absolute error. The statistical observations using single and multiple trials validate the stability of the scheme.