The invention relates to the technical field of power monitoring, in particular to a
big data analysis-based
power equipment state evaluation method, which comprises the following steps of S10, determining a basic parameter
system; removing parameters with small correlation with the fault defects, and constructing a key parameter
system for state evaluation; S20, checking the quality of the data in the key parameter
system, and conducting data cleaning work when the quality of the data does not meet the requirement; S30, judging the
equipment state and the abnormal change of the association relationship of the
equipment state by utilizing the correlation, and carrying out equipment
abnormality detection by analyzing the association relationship and the change rule of the multi-dimensionalstate data; and S40, screening out the abnormal key performance according to the related characteristic parameters of the
power transmission and transformation equipment, and obtaining the evaluationvalue of each key performance. Fusion analysis and
deep mining are performed on the multi-
source data of
power equipment state monitoring so that
rapid detection and personalized state evaluation of an abnormal state can be realized, and the health state of the key performance can be comprehensively, timely and accurately mastered.