针对简单遗传算法的局限性，提出了基于粒子群算法的遗传算法。
According to the limitations of simple genetic algorithms, design genetic algorithms based on particle swarm.
同时，通过实验证明了该系统的较简单遗传算法生成测试数据的优越性。
And by the experiment that is designed in this paper, the advantage of the system is proved.
该算法对简单遗传算法的编码方式、选择策略、交叉和变异操作进行了改进，使搜索效率有了很大的提高，有效地避免了早期收敛。
This algorithm improves on encoding, selection, crossover and mutation operations of SGA. It enhances searching efficiency greatly, and avoids effectively premature convergence.
就一个简单算例，着重探讨如何将遗传算法应用于解决多目标模糊问题。
Takes a simple question for example to discuss how to apply the genetic algorithms to solve the multi-objectives and fuzzy problems.
这种算法在有些地方与遗传算法或竞争算法相类似，但是计算量更小，而且源程序更简单。
It is similar in some ways to genetic algorithms or evolutionary algorithms, but requires less computational cost and generally only a few lines of code.
最后用一个简单的实例说明了使用遗传算法生成基本数据类型测试数据的过程。
At last we use a simple example to show the process of test data of basic type generation with GA.
遗传算法主要的特点在于：简单、通用、鲁棒性强。
The main characteristic of the GA is that it is simple, universal and robust.
遗传算法是一种模拟自然进化而提出的简单高效的优化组合方法。
Genetic algorithms is an efficiently combined and optimized method by simulating the nature evolution.
将优化后的BP神经网络模型和简单的BP神经网络进行比较，实验结果表明，基于遗传算法优化的BP神经网络模型在耕地分等评价工作中的应用完全可行。
After the comparison of optimized BPNN model and simple BPNN model, the result shows that, it is completed feasible to use optimized BPNN model in cultivated land classification work.
将遗传算法应用于网格结构杆件下料优化，经过工程实例分析表明。该方法简单易行，且效果明显。
Genetic algorithms is used for optimization cutting of lattice structure members. Some project examples indicate that this method is simple and practicable and effective.
遗传算法优化的BP神经网络在收敛速度和泛化能力上都较简单的BP神经网络要好，模拟结果更接近于真实值。
The constringency speed and generalization ability of optimized BPNN model are better than that of simple BPNN model, and the simulation result is close to reality.
遗传算法优化的BP神经网络在收敛速度和泛化能力上都较简单的BP神经网络要好，模拟结果更接近于真实值。
The constringency speed and generalization ability of optimized BPNN model are better than that of simple BPNN model, and the simulation result is close to reality.
应用推荐