论文部分内容阅读
在三维冷态试验台架上对喷动流化床最小喷动流化速度进行实验研究,分析喷动流化床主要工作参数,如静止床高、颗粒粒径、颗粒密度、喷口直径、流化气率对最小喷动流化速度的影响。在实验研究的基础上,利用最小二乘支持向量机对最小喷动流化速度与喷动流化床主要设计参数之间的数值关系进行智能拟合,并利用自适应遗传算法优化最小二乘支持向量机的参数。通过15个预测样本的检验,最小二乘支持向量机模型的拟合性能优于常用的经验公式以及神经网络。
The minimum jetting fluidization velocity of spout-fluidized bed was experimentally studied on a three-dimensional cold test bench. The main operating parameters of spout-fluidized bed were analyzed, such as static bed height, particle size, particle density, nozzle diameter, flow Effect of gas rate on the minimum spout fluidization velocity. Based on the experimental study, the least square support vector machine (LS-SVM) is used to fit the numerical relationship between the minimum spout fluidization velocity and the main design parameters of the spout fluidized bed. The genetic algorithm is used to optimize the least square Support vector machine parameters. Through the test of 15 prediction samples, the fitting performance of LS-SVM model is better than the commonly used empirical formula and neural network.