基于神经网络的传热法测量气固两相流中固体流量的研究

Neural Networks for On-line Prediction of the Solid Flowrate in Gas-solid TwoPhase Flow Based on Heat Transfer

利用人工神经网络优良的非线性映射能力,设计了一个3层前馈式神经网络用于传热法预测气固两相流中的固相流量,预测结果和实验结果吻合较好,为稀相气固两相流中固相流量的测量提供了一种简单、可靠的新方法。

In this paper, a methodology is introduced to use neural networks for online measure-ment of the solid flowrate in gas-solid two-phase flow based on heat transfer. An electrically heatedprobe was put in a gas-solid two-phase flow. The flow mediums with different velocity of flow,densities and diameters of particles produced different results of heat transfer. For a certain veloc-ity of conveyer air, the solid flow rate could be determined by the heating electric power and thesuperficial temperature of the probe. Experiments were made on a pilot gas-solid conveyer device.Prediction results prove that the method works effectively and reliably.