固体废弃物热解产物的神经网络预测模型

The prediction mode of neural net on pyrolysis product of solid waste

本文采用3层BP神经网络建立了固体废弃物热解产物的产率和特性的预测模型,采用遗传BP算法来优化隐层节点数和学习速率ηo与回归方法相比,其预测误差明显小于回归公式的预测误差。

In this paper,a prediction model is constructed to anticipate the productivity and characteristics of pyrolysis product of MSW by use of three layer BP neural net. The GA - BP method is introduced to optimize the number of hidden nodes and learning rate(η). Comparing with regress equation,the errors of predicted results of network are much smaller.