Industrial data feature selection and abnormal value detection method, system, equipment and medium

The invention discloses an industrial data feature selection and abnormal value detection method and system, equipment and a medium, which are in one-to-one correspondence schemes, and in the scheme, part of process variables having great influence on an industrial production result can be identified from massive industrial production process variables; the number of model input features can be effectively reduced, and the working efficiency is greatly improved; meanwhile, abnormal values in the original data can be detected through a filtering method, manual work can be replaced by the part, the abnormal data can be quickly picked out from the original data set, and the data set manufacturing efficiency is greatly improved; besides, two parts of feature selection and abnormal value detection are instrumentalized, the development work of the two parts can be reduced in engineering application, and the engineering delivery work efficiency is improved. 本发明公开了一种工业数据特征选择与异常值检测方法、系统、设备与介质，它们是一一对应的方案，方案中：可以从海量的工业生产