Continuous casting slag carry-over intelligent forecasting system based on hierarchical real-time memory algorithm
A forecasting system and memory technology, applied in the field of artificial intelligence, can solve problems such as time lag, and achieve the effect of solving time lag, abundant selection time, and improving accuracy
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2019-09-13
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
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...
Examples
Embodiment Construction
[0045] The present invention will be further described below in conjunction with the examples, the purpose is only to better understand the contents of the present invention, therefore, the examples given do not limit the protection scope of the present invention.
[0046] see figure 1 , figure 2 , image 3 , a continuous casting slag intelligent prediction system based on hierarchical real-time memory algorithm, the system is based on bionic neural network, including variable input part, sequence prediction part, pouring state evaluation part, slag prediction part, among which:
[0047] Variable input part: According to the continuous casting process analysis, three main characteristic variables with regularity and follow-through are selected as input variables: ladle weight change rate, tundish weight change rate, and average casting speed change rate;
[0048] Sequence prediction part: First, the input is converted into a sparse discrete representation SDR form in a contin...