Based on the level of factory procedure fault Detection and diagnosis method of distributed data model

The invention discloses a kind of level of factory procedure fault Detection and diagnosis method based on distributed data model.For the large-scale level of factory production run of complexity, fault detection and diagnosis method conventional is at present all be based upon on the basis of data-driven model mostly.Wherein, typical method first whole level of factory process is divided into multiple submodule according to operating unit and function the most, then sets up corresponding fault detection and diagnosis model for different submodules respectively.But these class methods often depend on procedural knowledge to a great extent, for the level of factory process of complexity, this requirement is very harsh.The present invention proposes a kind of completely based on the submodule division new method of data analysis, and construct corresponding fault detection and diagnosis method on this basis, realize monitoring the overall situation of typical level of factory process.The present invention has important using value to the fault detection and diagnosis performance and product quality that improve level of factory chemical process.