Prediction Method of Drum Strength of Sintered Ore

Abstract

A method for predicting sinter tumbler strength comprises the steps of building a prediction model and using the built prediction model to predict the tumbler strength. The step of building the prediction model comprises a step of collecting sampling data of various chemical components with the sinter tumbler strength, a step of building a gray residual correction model and a support vector machine model to predict the tumbler strength aiming at the sampling data, and a step of carrying out combined prediction: confirming optimal weight coefficients of the gray residual correction model and the support vector machine model to form an optimal combined prediction model to predict the tumbler strength. By means of the method, the combined prediction of the gray residual correction model and the support vector machine model is finally achieved, prediction accuracy is high, and robustness and generalization is better.

Description

technical field [0001] The invention relates to a prediction method, in particular to a method for predicting the strength of a sintered ore drum. Background technique [0002] The stability of the chemical composition of sinter has increasingly become the key to the good operation of the whole pre-iron system. The existing inspection methods and equipment for the inspection of sintered ore in steel mills can no longer meet the needs of the production process, resulting in a long inspection cycle and a serious lag in inspection results. Especially when the product quality is abnormal, neither the sintering production can be adjusted in time nor the blast furnace production can be guided in time, and the investigation found that most domestic enterprises have similar problems. This situation has seriously disturbed the sintering production, and also caused considerable losses to the ironmaking production. [0003] Zhang Shu and Gao Weimin of Beijing University of Science an...

AI Technical Summary

Problems solved by technology

However, the shortcomings of neural network prediction are also fatal, such as the local minimum value of neural network, the topology needs to be tried and tested, and the generalization is poor, and the prediction accuracy cannot be taken into account.

Images