A New Neural Network Training Algorithm Based on Artificial Bee Colony Algorithm for Nonlinear System Identification

Artificial neural networks (ANNs), one of the most important artificial intelligence techniques, are used extensively in modeling many types problems. A successful training process is required to create effective models with ANN. An algorithm essential for a process. In this study, new network called hybrid bee colony based on scout stage (HABCES) was proposed. The HABCES includes four fundamental changes. Arithmetic crossover solution generation mechanisms employed and onlooker stages. knowledge global best utilized by arithmetic crossover. Again, mechanism also has an adaptive step size. Limit control parameter. standard ABC algorithm, it constant throughout optimization. determined dynamically depending number generations. Unlike stage. Through these features, strong local convergence ability. Firstly, performance analyzed optimization Then, applications ANN were carried out. trained using identification nonlinear static dynamic systems. compared ABC, aABC ABCES algorithms. results showed that better terms quality speed. increase up 69.57% achieved This rate 46.82%