High-precision precession vortex flowmeter based on deep learning

The invention designs a high-precision precession vortex flow meter, in particular to a precession vortex flow meter integrating a multi-mode sensor and a time domain convolutional network (TCN) for prediction. The sensor part is composed of a temperature sensor and a pressure sensor which are respectively used for measuring the temperature and the pressure when fluid passes through. A time domain convolutional network is adopted to extract the characteristics of a temperature signal collected by a sensor and a processed pressure signal layer by layer for characteristic fusion, and a Slodhaar number is taken as a label value, so that a coefficient K in flow calculation of the precession vortex flow meter is corrected, and the effect of improving the measurement precision and the measurement range of the precession vortex flow meter is achieved. 本发明设计了一种高精度的旋进旋涡流量计，特别是融和了多模态传感器和时域卷积网络(TCN)进行预测的旋进旋涡流量计。其传感器部分由温度传感器和压力传感器两部分组成，分别用于测量流体通过时的温度和压力。并采用时域卷积网络逐层提取传感器采集的温度信号和处理后的压力信号的特征进行特征融合，以斯特劳哈尔数为标签值，从而对旋进旋涡流量计流量计算