Metaheuristics has attained increasing interest for solving complex real-world problems. This paper studies the principles and the state-of-the-art of metaheuristic methods for engineering optimization. Both the classic and emerging approaches to optimization using metaheuristics are reviewed and analyzed. All the methods are discussed in three basic types: trajectory-based, in which in each step a new solution is created from the previous one; multi-trajectory-based, in which a multi-start mechanism is used; and population-based, where multiple new solutions are created considering a population of approximate solutions. We further discuss algorithms and strategies to handle multi-modal and multi-objective optimization tasks as well as methods for parallel implementation of metaheuristic algorithms. Then, different software frameworks for metaheuristics are introduced. Finally, several interesting directions are pointed out as future research trends.