Particle swarm optimization (PSO) is a population based stochastic optimization technique developed by Dr. Eberhart and Dr. Kennedy in 1995, inspired by social behaviour of bird flocking or fish schooling. The particle swarm optimization concept consists of, at each time step, changing the velocity of (accelerating) each particle toward its pbest and lbest locations (local version of PSO). In past several years, PSO has been successfully applied in many research and application areas. This paper reviews the applications of PSO algorithm in mechanical domain. The applications of PSO include optimal weight design of a gear train, Simultaneous Optimization of Design and Machining Tolerances, Process Parameter Optimization in Casting, and Machine Scheduling Problem. The paper also describes the improved version of PSO algorithm namely: Hybrid PSO, Multiobjective PSO, Adaptive PSO and Discrete PSO.