粉煤灰特性与需水量比关系的神经网络模拟

Neural Network Simulation for the Relationship between Characteristic Parameters of Fly Ash and Its Water Demand Ratio

摘要:

通过建立BP神经网络模型，处理了粉煤灰颗粒群特征参数（比表面积、形状因子、分数维、烧失量）和流变学参数（屈服应力、塑性粘度等）与其需水量比之间的关系。结果表明：神经网络模型能很好地解决它们之间的非线性关系；同时，该模型经过不断地样本学习，还能由粉灰颗粒群特征参数和流变学参数预测粉煤灰需水量比，在粉煤灰应用研究和专家系统的建立方面均有着广泛应用。

Abstract:

Based on the method of neural network the relationship between the water demand ratio and the geometric and rheological characteristic parameters of fly ash was studied. The results show that: (1) It is feasible to apply the neural network to establish this relationship. (2) If trained by enough types of fly ash, the neural network can predict the water demand ratio by giving characteristic parameters of fly ash.