Digital factory monitoring big data processing system

The invention relates to the technical field of data processing, in particular to a digital factory monitoring big data processing system, which comprises a historical power consumption data acquisition module, an association linear equation construction module, an association weight acquisition module, an energy consumption classification result acquisition module, a time attenuation factor introduction module and a data processing module, constructing a correlation linear equation of the equipment parameters and the average energy consumption; calculating a first abnormal rate of each equipment parameter every day, clustering all average energy consumption and completion rates, calculating a second abnormal rate every day according to a clustering result, and obtaining an association weight of each equipment parameter every day; the method comprises the following steps: acquiring a residual term of each day in historical power consumption data, performing polynomial fitting on the residual term and average