生物焦吸附亚甲基蓝能力的ANN预测

Forecasting Adsorption Capacity of Bio-coke on Methylene Blue Based on ANN

以不同粒径、升温速率和终温条件下生物质热解残留物制得的生物焦为研究对象,考察生物焦的吸附能力;并基于人工神经网络的基本原理建立BP神经网络,从而训练并预测不同制备工艺下生物焦对亚甲基蓝的吸附能力。结果表明,BP神经网络有较高的预测精度,平均相对误差为3.58%,可以提前对生物焦吸附能力进行预测。

The adsorption capacities of bio^cokes obtained from biomass pyrolysis with different particle size, heating rate, and temperature were investigated. Further, based on the basic principle of artificial neural network, the BP neural network model was established to train and predict the adsorption capacity data on methylene blue of the biocake with different preparation technology. The result indicates that the BP neural network has high prediction accuracy and the average relative error of 3.58%, which means the BP network can be used to predict the adsorption capacity of bio-cake in advance.