Design of a MIMO Controller for a Multimodal DcDc Converter Based on Particle Swarm Optimized Neural Network In this project a MIMO controller scheme based on Artificial Neural Network (ANN) is developed for an inputseries and outputparallel (ISOP) DcDc converter. The proposed MIMO controller is trained using Particle Swarm Optimization (PSO). Using PSO to train the ANN based controller, eliminates the need for a prior knowledge of the system dynamics. The latter merit shows its significant usefulness when the under study system is a large multimodule system and consequently the derivation if its dynamic equations is a tedious and time consuming work.
Usually the backpropagation (BP) algorithm which applies the gradient descent method is used for training the ANN. But by using the gradient descent method, the neural network is easily trapped to local optimum, which leads to descent of global performance. On the other hand, the gradient descent method needs dynamic equations which represent the system model to train the ANN. But when the under study system is a large multimodule system for example the ISOP converter which is studied in this research, the derivation of dynamic equations needs complicated calculations and is a tedious and time consuming work. As an alternative for the gradient descent method, nature inspired optimization techniques can be used to optimize the parameters of the ANN controller (including the weights and biases) such as Genetic Algorithm (GA) or Particle Swarm Optimization (PSO) technique. Such optimization techniques do not need the prior knowledge of the system dynamics to train the ANN based controller. On account of the fact that the PSO has a higher velocity of convergence, this algorithm is used in this research in order to expedite the simulation process. Improved Large SignalPerformance of Linear Controlled InputSeries and OutputParallel DcDc Converter UsingGenetic Algorithm Optimization In this project, linear controllers including Lead, Lag, and LeadLag are designed for Inputseries and OutputParallel DcDc (ISOP) converter using Genetic Algorithm (GA). An ISOP connected converter is one of the recently developed multimodule converters. The suitable control scheme for this type of converter necessitates equal voltage sharing for inputseries connected modules and output current sharing for the outputparallel connected modules for all operating conditions even with existence of dissimilarity in devices and components used in each module. Such control scheme consisting of several controllers can be implemented using analog controllers. This project presents a GA which optimizes the parameters of analog controllers for each control loop in the control scheme of an ISOP connected converter. Using GA eliminates the need for tedious and time consuming small signal analysis of multimodule converters. Moreover, because GA chooses the best value for each parameters in different control loops simultaneously it can best consider the interaction among all loops and results in better large signal performance especially in the case of large variations in the parameters or considerable difference among modules of converter. Design of Broadband Microwave Amplifiers Using Genetic Algorithm In this project, a new approach to design of the broadband amplifiers based on compensated matching method was proposed using Genetic Algorithm. Compensated matching method was formulated as an optimization problem. In this case using GA, the parameter of input and output matching networks were determined in way that desired gain and band width was achieved. Power Network Compensating Using Genetic Algorithm
In this project the properties of capacitor bank in a power network were obtained using Genetic Algorithm. Using GA the number and the value of capacitors for each bus in power network were obtained in such a way that the desired reactive power was achieved, considering financial point of view. Winding Design of One Phase Electrical Motor Using Particle Swarm Optimization Algorithm
In this project number of winding turns in rotor of the motor were obtained using Particle Swarm Optimization in such a way that the harmonics of current were minimized.
Papers:

Research >