Method, device, equipment and storage medium for intelligent forecasting of industrial process operation indicators

Abstract

The invention provides a method, device, equipment and storage medium for intelligent forecasting of industrial process operation indexes. The method for intelligently forecasting the operation index of the industrial process includes: using the characteristic that the change of the operation index depends on the dynamic characteristics of the industrial process control system, establishing a dynamic model of the operation index, and the dynamic model of the operation index includes two parts: an identifiable model and an unmodeled dynamic; Estimating the parameters of the identifiable models in the dynamic model of operating indicators; combining the identification errors of the parameters of the identifiable models in the dynamic model of operating indicators with the unmodeled parameters in the dynamic model of operating indicators dynamically merging into an unknown nonlinear dynamic system; establishing an online intelligent prediction model of the unknown nonlinear dynamic system; combining the output of the identifiable model in the operating index dynamic model with the described unknown nonlinear dynamic system The output of the online intelligent prediction model obtains the forecast value of the operation index. Aiming at the difficult problem of predicting industrial process operation indicators, the system identification method based on mechanism model and deep learning method based on big data are combined to propose an intelligent forecast method for industrial process operation indicators, which solves the problem of forecasting industrial process operation indicators.

Description

technical field [0001] The invention belongs to the technical field of industrial artificial intelligence, and in particular relates to an intelligent forecasting method, device, equipment and storage medium of industrial process operation indicators. Background technique [0002] The accurate forecast of the operational indicators that characterize the product quality, efficiency, and consumption of industrial process processing is crucial to realizing the operational optimization control of the industrial process. Due to the strong nonlinearity, strong coupling of multi-variables, changes in operating conditions, fluctuations in raw materials, etc. between the operation index and the input and output of the industrial process control system that affect the operation index, the mechanism is unclear, and it is difficult to establish a dynamic model. Existing system identification methods and forecasting methods based on mechanism models establish forecasting models for opera...

AI Technical Summary

Problems solved by technology

Due to the comprehensive complexity of the operation index and the input and output of the industrial process control system that affects the operation index, such as strong nonlinearity, multi-variable strong coupling, operating condition changes, and raw material fluctuations, the mechanism is unclear and it is difficult to establish a dynamic model. The existing system identification method and forecast method based on the mechanism model establishes the forecast model of the operation index

Due to the dynamic changes in the industrial process in the production process, the operating indicators and the input and output data of the industrial process control system are in a changing, open, and uncertain information space, which cannot be established by using the existing deep learning technology with a complete information space. Forecasting Models for Running Indicators

Images