基于混合型遗传算法的森林可燃物热解动力学参数优化方法  

Method for Optimizing the Kinetic Parameters for the Thermal Degradation of Forest Fuels Based on a Hybrid Genetic Algorithm

作　　者：牛慧昌[1,2] 姬丹[2] 刘乃安[1] 

机构地区：[1]中国科学技术大学火灾科学国家重点实验室,合肥230026 [2]广州中国科学院工业技术研究院,城市公共安全技术研究中心,广州511458

出　　处：《物理化学学报》2016年第9期2223-2231,共9页Acta Physico-Chimica Sinica

基　　金：国家自然科学基金(51476156);广东省科技计划项目(2015B010118001,2014B010125003)资助;中国科学技术大学火灾科学国家重点实验室开放课题(HZ2015-KF10)项目资助~~

摘　　要：森林可燃物热解动力学参数的优化计算是构建综合热解模型的关键步骤。传统的基于梯度的优化方法收敛速度快但全局寻优能力不足,基于"生物进化理论"的遗传算法具有全局寻优能力但收敛速度慢。本研究首先探讨了单纯的遗传算法对初始值设置的依赖,发现设定合适的初始值能够稳定计算结果,加快算法的收敛速度。针对初始值未知的情况,本文提出了将单纯的遗传算法与迭代算法相结合构建混合型遗传算法的流程。然后以樟子松松枝为例,采用热重分析仪开展了森林可燃物热解实验。假设可燃物热解失重过程遵循三步一级平行反应模型,通过对比单纯遗传算法和混合型遗传算法的收敛过程,发现混合型遗传算法能够快速地获取全局最优的动力学参数,显著地提高遗传算法的优化性能。For thermal degradation of forest fuels, the optimization of kinetic parameters is a crucial step for the construction of comprehensive pyrolysis model. Traditional gradient-based optimization methods are characterized by strong converging speed, but with weak global optimization capability. The Darwinian survival- of-the-fittest theory based genetic algorithm （GA） is a good tool for global optimization, but with weak converging speed because of the general principles of this algorithm. In this study we evaluated the dependence of the pure GA on the setting of the initial values （IVs）, and found that the use of the correct initial values accelerated the converging speed and stabilized the results of the GA. A hybrid genetic algorithm （HGA） was used when the IVs were unknown. This algorithm shares the merits of iterative algorithms and GA. Thermogravimetric experiments were performed using the branches of Pinus Sylvestris and the results were used to compare the converging performances of GA and HGA under the assumption of a three-step, first-order pyrolysis model. The results of these analyses verified the validity and reliability of the HGA.

关 键 词：混合型遗传算法 非线性拟合 森林可燃物 热解 动力学 

分 类 号：O643.1[理学—物理化学]