介绍了一种基于改进适应度函数的遗传单神经元控制方法。
A single neural node control based on genetic algorithm with improving fitness function is presented.
提出了一种新的改进的粒子群优化算法，并以水轮机转速偏差的加权ITAE指标作为改进粒子群优化算法的适应度函数。
An improved particle swarm optimization (PSO) algorithm was designed. And a weighted ITAE index of turbine speed error was taken as the fitness function of the improved PSO algorithm.
该算法采用了混合编码，改进了适应度函数和交叉操作，扩大了搜索范围。
The algorithm adopts hybrid coding, does non-monotonic transformation to the fitness function and improves the crossover operation, expanding the searching scope.
在遗传操作过程中，改进了编码方法，构造的适应度函数不但以一定的零陷深度为目标，还考虑副瓣的增益维持在一定的水平。
In the process of genetic manipulation, encoding method is improved, fitness function is constructed not only considering nulling depth, but also the side lobe gain to maintain a certain level.
该方法设定适应度函数阈值改进了蚁群算法的信息素更新机制；
The pheromone-updating mechanism is improved by threshold of the fitness function in presented method;
其次改进了一种基于神经网络的三维机器人路径规划环境原型系统，为混合路径规划算法的提出准备了较精确的适应度函数。
Next, improves one three dimensional robot path planning environment prototype system kind based on the neural network, prepares the precise sufficiency function for the mixed algorithm.
其次改进了一种基于神经网络的三维机器人路径规划环境原型系统，为混合路径规划算法的提出准备了较精确的适应度函数。
Next, improves one three dimensional robot path planning environment prototype system kind based on the neural network, prepares the precise sufficiency function for the mixed algorithm.
应用推荐