本文提出基于遗传算法 (GA)的卷积码快速译码 ,进行格图上的单向 (U GA)和双向 (B GA)搜索译码 .它利用遗传算法的群体多样性好、搜索空间宽广 ,具有全局优化能力 ,提高译码质量 .通过模拟计算 ,分析了单向和双向的译码算法和群体规模M对误比特性能Pb 的影响 .模拟结果表明 :在相同译码复杂度下、Pb=10 -6时 ,与MA算法 (编码约束度K =19)相比 ,该译码算法约有 0 5dB性能增益 ;与VA算法 (K =7)相比 ,B GA大约有 1dB增益 . In this paper, a fast decoding of convolutional codes based on Genetic Algorithm (GA) is proposed, which performs unidirectional (UGA) and bidirectional (BGA) search and decoding on grids.It uses GA with wide population diversity and wide search space , Which has the ability of global optimization and improves the decoding quality.The effects of one-way and two-way decoding algorithms and population size M on the error performance Pb are analyzed by simulation.The simulation results show that under the same decoding complexity, Pb = 10 -6, this decoding algorithm has about 0 5 dB performance gain compared to the MA algorithm (encoding constraint degree K = 19); B GA has approximately 1 dB gain compared to the VA algorithm (K = 7).