多点随机搜索算法估计反应动力学参数  

Multipoint random optimization approach for the estimation of Kinetic parameters.

作　　者：颜学峰[1] 钱锋[1] 

机构地区：[1]华东理工大学自动化研究所,上海200237

出　　处：《计算机与应用化学》2004年第3期329-332,共4页Computers and Applied Chemistry

基　　金：国家973计划(2002CB312200);国家自然科学基金(60074027);国家863计划(2001AA413130);国家863计划(2002AA412110);十五国家科技攻关项目(2001BA201A04)

摘　　要：提出一种多点随机搜索算法,一方面它汲取随机搜索算法的优点以克服陷入局部最优点;另一方面它通过判断搜索过程目标函数变化趋势,从而能在响应曲面的下降方向上前进,加快寻优进程。与遗传算法相比较,多点随机搜索算法能以更快的速度找到全局最优解;与梯度下降算法相比较,它能以更高的概率找到全局最优解。本文将多点随机搜索算法应用于2-氯苯酚在超临界水中氧化反应动力学参数的估算,获得动力学模型对实验数据拟合的相对误差绝对值之和比文献报道降低了14.1%。Muhipoint random optimization approach,which possesses a joint advantage of random optimization approaches(i.e.ge-netic algorithm)and gradient descent optimization approaches,was proposed to make the search of optimal values more effective andfaster.The two experiments of analytical functions demonstrated multipoint random optimization approach was faster on searching globaloptimum than genetic algorithm,and higher probability to obtain the global optimum than gradient descent optimization approaches.Further,multipoint random optimization approach was applied to estimate the kinetic parameters of the 2-hloropheol oxidation in super-critical water.The result shows that the sum of absolute relative deviation of the obtained kinetic model is 14.1% less than that in liter-ature.

关 键 词：多点随机搜索算法 反应动力学 参数估计 遗传算法 2-氯苯酚 超临界水氧化反应 梯度下降算法 

分 类 号：TQ015.9[化学工程] O221.5[理学—运筹学与控制论]