基于遗传算法的人体能量代谢分析系统辨识

System Parameter Identification Method of Indirect Calorimeter Based on Genetic Algorithms

把遗传算法应用于人体能量代谢分析仪气体流量系统的辨识问题,克服了传统辨识方法无法同时得到系统的时延和参数辨识结果的缺点。同时对非等长子基因串的交叉操作进行了改进,提出了一种基于概率的扩大种群基因类型的改进方法。经过计算机仿真后的结果表明,应用遗传算法能有效克服有色噪声的干扰,获得稳定的辨识结果,说明了该方法的有效性。

Genetic algorithm is applied to identify the parameters of airflow system in indirect calorimeter,which solves the problem that traditional methods cannot identify the delay and parameters at the same time. As to the child-chromosomes with unequal code length, a modified approach based on probability is proposed in crossover operator. The result of simulation shows that genetic algorithms has a good performance in solving the problem of system parameter optimization when being subject to color noise.