以NGA训练的模糊网络模型，在收敛速度、寻优能力和辨别效果方面均优于BP、GA算法下的模型，符合缺陷识别的工程需要。

The FNN constituted by NGA, whose convergence rate, optimizing capability and distinguish effect are superior to those of GA and BP, is accorded with project need of discriminating.

youdao

传统的优化方法充分利用了目标问题的信息，局部寻优能力较强，收敛速度较快，但又会陷入局部最优的陷阱。

Traditional optimization methods use much more information of the target problem, so their convergence speed is much better, and the ability of finding local optimal is better.

youdao

比照传统遗传算法与生物界进化过程，分析了引起传统遗传算法收敛速度慢和寻优效率低的两个原因。

By contrasting the traditional genetic algorithms (TGA) with the biologic evolution, two kinds of reasons that the convergence speed and searching efficiency in TGA are both lower are concluded.

youdao