Research on Fault Diagnosis Method of Axial Flow Induced Draft Fan of Power Plant Based on Machine Learning

Abstract

A fault diagnosis model based on machine learning is proposed for the fault diagnosis of axial flow induced draft fans. The data of the time series data in the PI database is matched and filtered by the historical fault data in the SAP database of the power plant, and the feature and data preprocessing are further extracted to construct a fault diagnosis model for machine learning. Finally, the model diagnosis results are evaluated by the confusion matrix, and the fault diagnosis of the axial flow induced draft fan of a power plant is realized.