中文摘要：

针对标准类电磁机制算法中电荷溢出和参数敏感的问题，提出了新的电荷计算公式；基于电磁场中的吸引．排斥原理，引导粒子沿着合力方向向较优的区域移动；为提高算法的局部搜索能力，结合邻域搜索技术来改进种群中的粒子．在此基础上，提出了求解无约束优化问题的类电磁机制算法．理论分析表明新算法以概率1收敛到问题的ε-最优解集．对28个标准测试函数进行了仿真实验，并和已有算法对比，结果表明新算法具有收敛快、求解性能好的优点．

英文摘要：

In order to avoid the overflow and parameter sensitivity in standard electromagnetism-like mechanism algorithm, a formula for particle charge is presented. Based on the attraction-repulsion principle in the dectronic space, the particle is moved towards favorable region along the direction of total force exerted on it. The neighbor search is adopted to improve the particles in the population in order to enhance the local exploration ability.Based on these,a modified electromagnetism-like mechanism algorithm is proposed and its convergence to the vicinity of global optimum with probability one is proved. Simulation results on 28 benchmark problems demonstrate that the novel algorithm has the fast convergence and good performance in comparison with other existing algorithms.