Expansion behaviour for a bed of binary mixture of the irregularly shaped particle in Newtonian liquid was measured in two different circular columns. Variations in the physical parameters on the expansion behaviour have been reported. Bed expansion increases with an increase in liquid velocity and a decrease in particle diameter. Static bed height and expansion of the bed are low for higher diameter columns. An empirical correlation has been developed for predicting the ratio of bed height at the fluidized condition to the initial bed height as a function of the physical and dynamic variables related to the system for the binary particle mixtures. The correlation coefficient and variance of the estimate are 0.9299 and 0.0013, respectively, which is acceptable statistical accuracy. A hybrid of the genetic algorithm and neural network modelling for the prediction of the same has also been attempted where the input parameters are optimized using the Levenberg–Marquardt algorithm. With a relative error of 1.46%, the genetic algorithm performed well. So, the modelling has successfully predicted the bed height ratio at fluidized conditions to the initial bed height.

中文翻译：

---

固液流化中不规则颗粒二元混合物的床膨胀：实验、经验相关性和 GA-ANN 建模

在两个不同的圆柱中测量了牛顿液体中不规则形状颗粒的二元混合物床的膨胀行为。已经报道了关于膨胀行为的物理参数的变化。床膨胀随着液体速度的增加和颗粒直径的减小而增加。对于较大直径的色谱柱，静态床层高度和床层膨胀较低。已经开发了一种经验相关性，用于预测流化条件下的床高与初始床高的比率，作为与二元颗粒混合物系统相关的物理和动态变量的函数。估计的相关系数和方差分别为 0.9299 和 0.0013，这是可以接受的统计精度。还尝试了遗传算法和神经网络模型的混合预测，其中使用 Levenberg–Marquardt 算法优化了输入参数。相对误差为 1.46%，遗传算法表现良好。因此，该模型成功地预测了流化条件下的床高与初始床高的比值。