Modeling of pressure-flow in the flow facility based on support vector machine

In this paper, considering the valve opening and pump frequency, the pressure-flow model in the pipeline of the flow facility is established based on support vector machine (SVM), and the instantaneous flow value can be calculated by established SVM model using pressure in the pipeline measured by pressure sensors. Through the experimental test on the flow facility, the training samples and test samples are obtained to train and test the established SVM model. At the same time, in order to compare the calculation result of SVM model, a BP neural network model is established as a comparison. By comparing the SVM model with BP model, it is found that the calculation results of the SVM model is closer to the real value than calculation results of BP model, and the SVM model has good calculation ability and can accurately obtain the instantaneous flow value through the measured pressure in the pipeline.