Online energy source predicting system and method for integrated iron & steel enterprise

Abstract

A system and method for online energy forecasting of integrated steel enterprises belong to in the field of forecast technologies of energy. The energy forecast system is composed of the PCS layer which is constituted by sensors, PLC and DCS (1) and located in the site, site monitor terminal HMI (2), interface management server (3), database server (4), application layer server (5), Web, anti-virus server (6), workstation to client terminal (7), network which connects all the computer equipment, controllers and sensors. The energy forecast method includes: the extraction of energy data, preprocess of energy data, modeling of energy, algorithm library of modeling, forecast of energy. The advantages of the invention are: the use of a variety of energy forecasting algorithms, and adopting the way of combined model for forecasting, overcoming the limit of using a single or two methods to forecast the energy demand, improving the accuracy and reliability, and suiting for the present and interim energy forecasting.

Description

technical field [0001] The invention belongs to the technical field of iron and steel energy forecasting, and in particular provides an integrated online energy forecasting system and method for iron and steel enterprises, which are used for short-term and medium-term energy forecasting for iron and steel enterprises. Background technique [0002] At present, the energy forecasting of most domestic iron and steel enterprises is based on artificial short-term experience forecasting, which requires relatively high expert experience for forecasters and lacks the support of forecasting models; although some scientific research institutes or universities have also carried out energy forecasting. However, they all focus on offline data forecasting of a single energy forecasting model or one or two energy forecasting models, and cannot provide a complete set of energy forecasting processes and methods including data collection, data collation, modeling analysis, and forecasting. Th...

AI Technical Summary

Problems solved by technology

However, using the regression model has the following obvious disadvantages: (1) When the regression equation is used for estimation and prediction, the dependent variable can only be estimated from the independent variable, and the independent variable is not allowed to be estimated from the dependent variable

(3) The regression equation should only be used for interpolation calculations, not for extrapolation predictions, especially for remote extrapolation predictions

At the same time, there are obviously the following deficiencies; ①G(1,1) model is an exponential growth model, when a short time series is used to predict a long time series, it will produce large errors or values ​​that do not conform to the actual situation , ②For the original data containing negative value items, if the data generated after multiple accumulations cannot obtain non-negative incremental data, theoretically speaking, the modeling of such data should be abandoned, ③When the GM(1,1) model When the accuracy cannot meet the requirements, it is necessary to build a GM(1,1) model on the residual to co

Images