RF structure sensor data validity discrimination method based on multi-correlation coefficient characteristics

The invention relates to a multi-correlation coefficient characteristic RF structure sensor data validity discrimination method. The method comprises the following steps: S1, obtaining a data set collected by all sensors of a same to-be-detected structure; s2, performing data validity preliminary judgment on the data set obtained in the step S1 to obtain a valid data set; s3, performing feature extraction on the valid data set to obtain a validity quantitative index; s4, training a random forest model based on the validity quantitative index to obtain a validity discrimination random forest model; and S5, inputting to-be-detected sensor data into the validity discrimination random forest model to obtain a discrimination result. The method effectively reduces the requirements for domain knowledge, achieves the automation of the effectiveness discrimination of the sensor, and is high in prediction accuracy. 本发明涉及一种多相关性系数特征的RF构筑物传感器数据有效性判别方法，包括以下步骤：步骤S1:获取同一待测构筑物所有传感器采集的数据集；步骤S2:对步骤S1获取的数据集进行数据有效性初步判别，获得有效数据集；步骤