基于BP神经网络的熔融锌液流量检测

Flux-measuring Approach of Molten Zinc by Means of Neural Network

用神经网络算法建立质量与流量关系数学模型 ,研究称量锌液质量间接测量锌液流量的方法 ,实现锌液流量的在线检测。结果表明 ,平均流量 5 14 4mL/min的情况下 ,测量平均绝对误差为 73mL/min ,相对误差为 1 42 % ,满足实际生产要求的精度要求。研究成果已成功应用于某冶炼厂。

In order to measure the flowage of molten zinc in smelting process, the indirect method substituting mass determination for flowage measurement are investigated by use of relationship model of mass and flowage established with neural network algorithm. The results show that the average deviation is 73mL/min, and the relative error is 1.42% under the average flowage of 5144mL/min. It can be consonant with the production requirements. This technology has been applied to some zinc smelter.