This work presents a modified version of the Particle Swarm Optimization (PSO) based on improved parameters, Opposite-Based-Learning parametrization, and constraints based on forbidden locations in the search space. The method exhibits fast convergence and stability in the search for optimal parameter values. It has been tested on classical test functions proposed in the literature and compared with the performance of the seminal method and a recently proposed one. Representative results demonstrate the method’s potential to be applied in realistic situations.