Contact temperature prediction of high voltage switchgear based on multiple linear regression model

Targeted at switchgear's contact temperature prediction, this paper is based on the contact temperature data of high voltage switchgear. Using the Map-reduce model to analyze and process a monitoring point data, Wthe regression model of temperature is established by using multiple linear regression method. The prediction result is analyzed by the criterion of the significance of F regression. The result shows that the longitudinal regression in multivariate linear regression can fit the temperature of the high-voltage switchgear contact well with small deviation, suitable for long-term temperature forecast.