Method for predicting the furnace temperature state of a blast furnace
A prediction method and blast furnace technology, which is applied in the field of blast furnace smelting, can solve the problems of prediction deviation, little consideration, complex operating conditions of blast furnace, etc., and achieve the effect of reducing deviation
Inactive Publication Date: 2021-03-09
WISDRI ENG & RES INC LTD
View PDF1 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, due to the large number of blast furnace tuyeres, it is difficult to conduct comprehensive observations at the same time even when tuyere cameras are installed. Therefore, this condition is rarely considered in various studies, and important information is lost.
Moreover, the operating conditions of blast furnaces are complex, and changes in production and operating conditions will affect the accuracy of model analysis
[0004] At present, the furnace temperature prediction method is mainly based on the mathematical model prediction of the operating data, but the operating conditions of the blast furnace are complex, and various conditions change with the production conditions. deviation
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment
[0027] Such as figure 1 As shown, the present invention discloses a specific embodiment of a method for predicting the furnace temperature state of a blast furnace, the method comprising the following steps:
[0028] Step S1: select the parameters characterizing the furnace temperature;
[0029] Step S2: Extract image feature information representing the thermal state of the blast furnace tuyere from the image data of the blast furnace tuyere;
[0030] Step S3: selecting blast furnace parameters, said blast furnace parameters including blast furnace operating parameters and state parameters;
[0031] Step S4: Establish a neural network model, the neural network model takes the image feature information representing the thermal state of the tuyere of the blast furnace, the blast furnace parameters selected in step S3 as input, and takes the furnace temperature parameter selected in step S1 as output; training Obtaining the image feature information representing the thermal st...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for predicting the furnace temperature state of a blast furnace. The method comprises the following steps: selecting characterization furnace temperature parameters; extracting image feature information representing the thermal state of a blast-furnace tuyere from blast-furnace tuyere image data; selecting blast furnace parameters; establishing a neural network model by taking the image feature information representing the thermal state of the blast-furnace tuyere and the selected blast-furnace parameters as input and the representation furnace temperature parameters as output; training to obtain the image feature information and the correlation coefficient of the selected blast furnace parameters to the characterization furnace temperature parameter at each lag time point; and acquiring current blast-furnace tuyere image data and selected blast-furnace parameter data, inputting the current blast-furnace tuyere image data and the selected blast-furnaceparameter data into the trained neural network model, and outputting the characterization furnace temperature parameter data of each lag time point to realize furnace temperature prediction. Observable tuyere image information is added for furnace temperature prediction, and a timely and reliable furnace temperature state prediction method is provided for an operator.
Description
technical field [0001] The invention relates to the field of blast furnace smelting, in particular to a method for predicting the furnace temperature state of a blast furnace. Background technique [0002] Furnace temperature is an important state parameter in the blast furnace production process. If the furnace temperature is too high, it will increase the coke ratio, increase the cost of the blast furnace, and reduce the life of the blast furnace. If the furnace temperature is too low, it will lead to insufficient heat in the furnace and reduce the production of pig iron. It may even cause operational accidents such as furnace cooling. In addition, the blast furnace is a system with a large lag. If the adjustment measures are taken after the furnace temperature has changed significantly, it is difficult to avoid the fluctuation of the furnace temperature. Therefore, the prediction of furnace temperature is of great significance to blast furnace operation. [0003] The bl...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06N3/08G06N3/02C21B5/00
CPCG06Q10/04G06N3/084G06N3/02C21B5/00C21B2300/04
Inventor 李鹏
Owner WISDRI ENG & RES INC LTD