A method and device for dynamic prediction of carbon content after converter blowing
A dynamic prediction, converter post-blowing technology, applied in neural learning methods, manufacturing converters, steel manufacturing processes, etc., to achieve the effect of improving the end point hit rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 example
[0059] Carbon content is one of the important parameters of converter end point control, and the real-time prediction of carbon content in converter blowing process is the key to end point control. However, the control model based on the sub-lance cannot realize the dynamic prediction of the carbon content in the post-blowing stage, and the carbon integral model cannot realize real-time prediction due to the delay of furnace gas data. Aiming at this problem, this embodiment provides a dynamic prediction method of carbon content after converter blowing, and establishes a real-time dynamic prediction model of carbon content in the later stage of converter blowing based on case reasoning CBR and long short-term memory network LSTM.
[0060] The method for dynamically predicting the content of carbon after converter blowing in this embodiment can be realized by electronic equipment, and the electronic equipment can be a terminal or a server. The execution flow of this method is as...
no. 2 example
[0117] This embodiment provides a device for dynamic prediction of carbon content after converter blowing, which device includes the following modules:
[0118] The similar case retrieval module is used to use the current converter production process as a new case, and the historical converter production process as a historical case, according to the process parameters of the main blowing stage of the new case, and based on the case reasoning algorithm, to retrieve the difference between the historical case and the new case The similarity between the similar cases that meet the preset requirements and the process parameters of the post-blowing stage of the similar cases;
[0119] The model training module is used to train the preset carbon content prediction model by using the post-blowing process parameters of the similar cases retrieved by the similar case retrieval module; wherein, the carbon content prediction model is a long short-term memory network model , the input of ...
no. 3 example
[0123] This embodiment provides an electronic device, which includes a processor and a memory; at least one instruction is stored in the memory, and the instruction is loaded and executed by the processor, so as to implement the method of the first embodiment.
[0124] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) and one or more memories, wherein at least one instruction is stored in the memory, so The above instruction is loaded by the processor and executes the above method.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More