Continuous casting slag carry-over intelligent forecasting system based on hierarchical real-time memory algorithm

Abstract

The invention relates to a continuous casting slag carry-over intelligent forecasting system based on a hierarchical real-time memory algorithm, and belongs to the technical field of artificial intelligence. The continuous casting slag carry-over intelligent forecasting system based on the hierarchical real-time memory algorithm is constructed by simulating a neocortex neure structure and organization form, and comprises a variable input part, a sequence forecasting part, a casting state evaluating part and a slag carry-over forecasting part. According to the continuous casting slag carry-overintelligent forecasting system based on the hierarchical real-time memory algorithm, which is provided by the invention, based on a novel neural network, existing continuous casting production detection data is forecast, a slag carry-over forecasting mechanism is led out, feature information of data in the time dimension can be effectively captured, slag carry-over time is accurately and rapidlyforecast, a problem of time delay is solved and slag carry-over identification accuracy is improved.

Description

technical field [0001] The invention relates to an intelligent prediction system for continuous casting slag based on a hierarchical real-time memory algorithm, and belongs to the technical field of artificial intelligence. Background technique [0002] Continuous casting ladle slag detection technology is one of the important means to control the purity of molten steel and improve the quality of castings and the yield of molten steel by effectively identifying the state of molten steel in the later stage of ladle pouring. [0003] In recent years, many scholars have done a lot of research on ladle slag detection methods. In 2010, Tan Dapeng et al. realized the automatic monitoring of continuous casting slag through artificial neural network technology; in 2012, Li Pengfei et al. proposed a method based on wavelet decomposition, The automatic detection method of molten steel continuous casting slag combined with chaos analysis and RBF neural network realized the automatic id...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to improve the detection accuracy of traditional slag, solve the problems of time lag, introduce intelligent continuous casting slag forecasting method, and adopt a new type of bionic neural network, so that the continuous casting machine can pass through without modifying the structure. The supervised Hebbian-like association learning mechanism analyzes and predicts the existing continuous casting production inspection data, thereby providing an intelligent forecasting system for continuous casting slag based on hierarchical real-time memory algorithms

Images