Neural Network Control for Fuel Cell Boost Converter Based on Particle Swarm Optimization

The stable control of disturbance rejection in direct current-direct current (DC-DC) boost converters is critical for fuel cells to meet load demands. However, uncertainties and disturbances can negatively impact the output performance of these converters. To address this challenge, an adaptive neural network control strategy utilizing adaptive particle swarm optimization (APSO) is proposed. First, the uncertainties introduced by variations in the inductor, capacitor, input voltage, and load are estimated using neural network observers. Next, a control scheme that integrates the APSO algorithm is introduced to improve the convergence of the output voltage in the DC-DC boost converter. Finally, quantitative analyses confirm the effectiveness of the proposed control strategy in enhancing the performance of the output system.