Prediction method based on immediate least square support vector regression centrifugal pump external characteristics

Abstract

The invention discloses a prediction method based on immediate least square support vector regression centrifugal pump external characteristics and belongs to the technical field of centrifugal pump external characteristic prediction. The method comprises the following steps of 1) data acquisition; 2) data processing, analyzing the recorded data, and performing normalization processing to obtain input data of the model; 3) selecting similar samples; and 4) establishing an external characteristic prediction model of the centrifugal pump. The invention relates to application of a model composedof operation data processing, instant learning and least square support vector regression of a centrifugal pump to prediction of external characteristics of the centrifugal pump, meanwhile, the optimal regularization coefficient and the optimal nuclear parameter are obtained through a reserved cross validation method, and analysis and external characteristic prediction of existing centrifugal pumpoperation data can be carried out through combination of the three, the data in the starting interval is eliminated, so the risk that the model is disturbed is relatively small, and a similarity measurement criterion in instant learning is adopted in the instant least square support vector regression model, so the generalization performance of the model can be better.

Description

technical field [0001] The invention belongs to the technical field of prediction of external characteristics of centrifugal pumps, and in particular relates to a method for predicting external characteristics of centrifugal pumps based on a combined model of instant learning and least squares supported regression. Background technique [0002] The external characteristics of the centrifugal pump reflect the working characteristics of the centrifugal pump when it is working, and reflect the overall performance of the centrifugal pump when it is running. The external characteristics of the centrifugal pump include its head, efficiency, and power. operating conditions. When the centrifugal pump is working, its working state will change due to the influence of the external working environment. At the same time, due to the leakage, backflow, and secondary flow of the centrifugal pump, it is difficult to accurately predict the external characteristics of the centrifugal pump. ...

AI Technical Summary

Problems solved by technology

When the centrifugal pump is working, its working state will change due to the influence of the external working environment. At the same time, due to the leakage, backflow, and secondary flow of the centrifugal pump, it is difficult to accurately predict the external characteristics of the centrifugal pump.

[0003] In addition, the working environment of the centrifugal pump is changeable, and the centrifugal pump is often under severe working conditions. At the same time, the efficiency-flow curve of the external characteristic curve of the centrifugal pump tends to have a hump area, which also increases the difficulty of predicting the external characteristics of the centrifugal pump.

[0004] At present, most methods for predicting centrifugal pumps use computational fluid dynamics (CFD) to predict the external characteristic curve of centrifugal pumps, but due to the above problems, the prediction error is relatively large. , grid division, and setting of boundary conditions all require design experience, and it is difficult to have a unique standard, and the simulation process is complex and requires high calculations. Using computational fluid dynamics to predict centrifugal pumps is relatively time-consuming and laborious

Images