Swarm intelligence in mechanical engineering

Swarm intelligence (SI) is an artificial intelligence technique based on the study of cooperation behaviors of simple individuals (e.g. ant colonies, bird flocking, animal herding, and bees gathering honey) in various decentralized systems. The population, which consists of simple individuals, can usually solve complex tasks in nature by individuals interacting locally with one another and with their environment. Although a simple individual’s behavior is primarily characterized by autonomy, distributed functioning, and self-organizing capacities, local interactions among the individuals often lead to a global optimal. Therefore, SI is a promising way to develop powerful solution methods for complex optimization problems in mechanical engineering. Recently, SI algorithms have attracted much attention of researchers and have also been applied successfully to solving optimization problems in mechanical engineering. However, for large and complex problems, SI algorithms often consume too much computation time due to the stochastic features of their searching approaches. Thus, there is a potential requirement to develop efficient algorithms that are able to find solutions under limited resources, time and money in realworld applications. The aim of this Special Issue is to highlight the most significant recent developments on the topics of SI and to apply SI algorithms in real-life scenarios. Contributions containing new insights and findings in this field are welcome. Papers selected for this Special Issue present new findings and insights into this field. A broad range of topics are discussed, especially in the following areas: SI algorithms for scheduling of machinery production line, mechanical parameters adjustment based on SI, application of SI algorithms in mechanical fault diagnosis and SI and mechatronics. In the paper titled ‘‘Pareto optimal train scheduling for urban rail transit using generalized particle swarm optimization,’’ W. Chu et al. established a bi-objective optimization model to study the Pareto optimal urban rail train scheduling problem. The aim of the model was to minimize the passengers’ total travel time and the number of used train stocks at the same time. A Pareto-based particle swarm optimization procedure was designed to solve the model. Finally, two different scaled urban rail lines were applied to test the model and the algorithm. In the paper titled ‘‘Estimation of vessel collision risk index based on support vector machine,’’ L. Gang et al. proposed a collision risk index estimation model based on support vector machine and applied genetic algorithm to optimize the corresponding parameters. And the comparison between cross-validation-support vector machine, particle swarm optimization–support vector machine, and genetic algorithm–support vector machine models showed that genetic algorithm–support vector machine model generally provided a better performance for collision risk index estimation. In the paper titled ‘‘Automobile chain maintenance parts delivery problem using an improved ant colony algorithm,’’ J. Gao et al. solved the automobile chain maintenance parts delivery problem by transferring the multi-depot vehicle routing problem with time windows to multi-depot vehicle routing problem with the virtual central depot. Then an improved ant colony optimization with saving algorithms, mutation operation, and adaptive ant-weight strategy was proposed to solve the problem. And the computational results indicated that the proposed algorithm was effective to solve the problem. In the paper titled ‘‘Pareto front–based multiobjective real-time traffic signal control model for intersections using particle swarm optimization algorithm,’’ P. Jiao et al. proposed a Pareto front–based multi-objective traffic signal control model to obtain real-time signal parameters and evaluation indices. The objectives of the model were to minimize delay time, minimize number of stops, and maximize effective capacity. In addition, a step-by-step particle swarm optimization algorithm based on Pareto front was