Neural network combined with evolutionary algorithm for Knowledge Management in Electricity Supply Industry

Abstract

A new method of designing BP neural networks based on evolutionary algorithm (EA) is proposed for Knowledge Management in Electricity Supply Industry. The mechanisms of diversity maintaining and antibody density regulation exhibited in evolutionary system are introduced into evolutionary algorithm (EA). The proposed algorithm overcomes the problems of EA on search efficiency, individual diversity and premature and enhances the convergent performance effectively. In order to solve the problem of random initial weights, neuro fuzzy system for diversity is used to initialize weight vectors, and the detailed design steps of the algorithm are given. Simulated results show that the BP neural networks designed by EA have better performance in convergent speed and global convergence compared with hybrid evolutionary algorithm and the method is more accurate than other ones.

A Fault-Tolerant Filtering Algorithm for SINS/DVL/MCP Integrated Navigation System

“…Moreover, the artificial neural network (ANN), optimized by evolutionary programming, not only overcomes the obstacle of conventional ANN which may easily plunge into local minimum and requires long training time, but also avoids the problem in genetic algorithms caused by binary-coded and cross operation. Thanks to its superiorities, ANN has been applied in many fields such as financial forecasting [21], breast cancer diagnosis [22], and electricity supply industry [23], and so forth [24].…”