Modeling method of sintering process carbon consumption adaptive weighted width echo state learning system

Abstract

The application provides a sintering process carbon consumption adaptive weighted width echo state learning system modeling method, relates to the field of sintering process production energy saving and consumption reduction of steel and iron, and the method comprises the following steps: based on sintering process mechanism analysis and data correlation analysis, process parameters directly affecting sintering carbon consumption are determined, the process parameters are as follows: BRP, BRP temperature, BTP, BTP temperature, wind box negative pressure, vertical combustion speed, trolley speed, material layer thickness, returned ore, coke powder ratio, FeT content, SiO2 content, CaO content and MgO content; then, a sintering carbon consumption intelligent prediction model is established by using an adaptive weighted width echo state learning system; finally, according to actual production data, the process parameters directly related to sintering carbon consumption are taken as input, and the sintering carbon consumption is taken as output, so that the dynamic prediction of the sintering carbon consumption is carried out. The sintering carbon consumption intelligent prediction method can realize the accurate dynamic prediction of the carbon consumption, improve the utilization rate of carbon, and further lay a foundation for realizing green manufacturing and intelligent manufacturing of the steel industry.

Description

Technical Field

[0001] The present invention relates to the field of energy conservation and consumption reduction in steel sintering process production, and in particular to a carbon consumption adaptive weighted width echo state learning system modeling method for a sintering process. Background Art

[0002] The sintering process is a crucial step in the iron and steel metallurgical process. The quality and yield of the sintered ore produced not only directly impact the output, quality, and energy consumption of the blast furnace ironmaking process, but are also crucial for achieving favorable economic and technical indicators and technological progress. Besides blast furnace ironmaking, this process is also the largest energy-consuming step in the iron and steel metallurgical process, accounting for approximately 10%-15% of the total energy consumption. Of this energy consumption, coke fuel accounts for approximately 80%, electricity for approximately 13.5%, gas for approximately 6%, and other sources for approximately 0.5%. Therefore, accurate dynamic prediction of sintering carbon consumption is necessary to improve energy efficiency, reduce pollution emissions, and achieve green manufacturing. This is a key issue in improving energy efficiency, reducing pollution emissions, and achieving green and intelligent manufacturing in the steel industry. Summary of the Invention

[0003] In order to solve the problems of serious pollution and low energy utilization in the sintering process, the present invention provides a modeling method of a carbon consumption adaptive weighted width echo state learning system in the sintering process, which mainly includes the following steps:

[0004] S1: Based on the sintering process mechanism analysis and data correlation analysis, the process parameters that directly affect the sintering carbon consumption are determined. The process parameters include: BRP, BRP temperature, BTP, BTP temperature, wind box negative pressure, vertical combustion speed, trolley speed, material layer thickness, return ore, coke powder ratio, FeT content, SiO2 content, CaO content and MgO content;

[0005] S2: Based on the adaptive weighted width echo state learning system, an intelligent prediction model for sintering carbon consumption is established and trained;

[0006] S3: Based on actual production data, with process parameters that directly affect sintering carbon consumption as input and sintering carbon consumption as output, dynamic prediction of sintering carbon consumption is performed using the trained sintering carbon consumption intelligent prediction model.

[0007] A storage device stores instructions and data for implementing the sintering process carbon consumption adaptive weighted width echo state learning system modeling method.

[0008] A sintering process carbon consumption adaptive weighted width echo state learning system modeling device includes: a processor and a storage device; the processor loads and executes instructions and data in the storage device to implement the sintering process carbon consumption adaptive weighted width echo state learning system modeling method.

[0009] The technical solution provided by the present invention has the following beneficial effects: based on sintering process mechanism analysis and data correlation analysis, the process parameters that directly affect sintering carbon consumption can be determined: BRP, BRP temperature, BTP, BTP temperature, bellows negative pressure, vertical combustion speed, trolley speed, material layer thickness, return ore, coke powder ratio, FeT content, SiO2 content, CaO content, and MgO content; based on an adaptive weighted width echo state learning system, an intelligent prediction model for sintering carbon consumption is established; based on actual production data, the process parameters that directly affect sintering carbon consumption are used as input and sintering carbon consumption is used as output, and the trained intelligent prediction model for sintering carbon consumption is used to dynamically predict sintering carbon consumption. This method can capture the dynamic characteristics of the sintering process in real time, achieve accurate dynamic prediction of sintering carbon consumption, and lay the foundation for achieving green manufacturing and intelligent manufacturing in the steel industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0011] Figure 1 This is a flow chart of a method for modeling a carbon consumption adaptive weighted width echo state learning system in a sintering process according to an embodiment of the present invention;

[0012] Figure 2 This is a principle block diagram of the intelligent prediction model for sintering carbon consumption in an embodiment of the present invention;

[0013] Figure 3 This is a comparison chart of the dynamic prediction results and actual values ​​of sintering carbon consumption in an embodiment of the present invention;

[0014] Figure 4 3. It is a prediction error result diagram of the dynamic prediction result of sintering carbon consumption in an embodiment of the present invention;

[0015] Figure 5 It is a schematic diagram of the operation of the hardware device in the embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, specific embodiments of the present invention are now described in detail with reference to the accompanying drawings.

[0017] Example 1

[0018] Please refer to Figure 1 , Figure 1This is a flow chart of a method for modeling a sintering process carbon consumption adaptive weighted width echo state learning system in an embodiment of the present invention. The specific steps are as follows:

[0019] S1: The sintering process is a production process characterized by complex chemical and physical changes. The main factor affecting sintering carbon consumption is the sintering thermal state. Based on sintering process mechanism analysis and data correlation analysis, the process parameters directly affecting sintering carbon consumption are determined. These process parameters include sinter ore yield and carbon consumption. Sinter ore yield is determined by the raw material parameters used in the sintering process, including coke powder ratio, SiO2 content, TFe content, MgO content, CaO content, and return ore. These raw material parameters determine the amount of sintered ore and coke produced during the sintering process. Carbon consumption is determined by the state parameters and operating parameters of the sintering process, which reflect the thermal state of the sintering process. Operating parameters include trolley speed and bed thickness. State parameters include BTP, BTP temperature, bellows negative pressure, vertical combustion velocity, BRP, and BRP temperature. BTP represents the sintering endpoint, and BRP represents the rising point.

[0020] Therefore, the process parameters include: BRP, BRP temperature, BTP, BTP temperature, wind box negative pressure, vertical combustion speed, trolley speed, material layer thickness, return ore, coke powder ratio, FeT content, SiO2 content, CaO content and MgO content; these process parameters serve as inputs of the sintering carbon consumption intelligent prediction model.

[0021] S2: Based on the adaptive weighted width echo state learning system, an intelligent prediction model for sintering carbon consumption is established; please refer to Figure 2 , Figure 2 This is a block diagram of the principle of the intelligent sintering carbon consumption prediction model used in this embodiment. The model includes a characteristic node layer and a reservoir layer, and its structure effectively reflects the dynamic characteristics of the sintering process. The proposed adaptive weighted width echo state learning system can capture the dynamic characteristics of the production process in real time, laying the foundation for establishing an accurate and effective intelligent sintering carbon consumption prediction model.

[0022] The process of establishing an intelligent prediction model for sintering carbon consumption is as follows:

[0023] S2.1: The training sample data set consists of process parameters that directly affect sintering carbon consumption and the corresponding sintering carbon consumption. , x t For the t training samples as the input of the sintering carbon consumption intelligent prediction model, Y t For the t Sintering carbon consumption, NIndicates the total number of samples in the training sample dataset; input dataset ;Will X Randomly mapped to n In terms of group characteristics, i Mapping features Denoted as:

[0024]

[0025] in, is the activation function; is the weight vector; is the bias vector; n Indicates the number of feature mappings, whose value is a positive integer greater than or equal to 1; input data set X go through n The feature map is transformed into:

[0026]

[0027] S2.2: To capture the dynamic characteristics of the system, F The reservoir state update equation is expressed as follows after being transferred to the reservoir through nonlinear transformation:

[0028]

[0029] in, ( ) is the hyperbolic tangent function, W in and W back Learning stochastic generation via echo state networks.

[0030] S2.3: The output of the reservoir layer is combined with all the outputs of the feature node layer:

[0031]

[0032] S2.4: Assume that the weights in the output layer are recorded as W When , we can consider the following optimization problem to find its solution

[0033]

[0034] in, is a diagonal matrix associated with each input sample and, represents the trade-off parameter. At the same time,

[0035]

[0036] in, is a weighted finite element, diag() represents a diagonal matrix, , represents the residual probability density function, Indicates the t The residuals of the samples.

[0037] Based on kernel density estimation, the residual probability density function is expressed as:

[0038]

[0039]

[0040] in, Indicates the width of the estimation window, represents the kernel function. In this embodiment, the kernel function is selected as a Gaussian function.

[0041] S2.5: This embodiment uses a pseudo-inverse algorithm to solve the weights in the output layer, and obtains:

[0042]

[0043] in, I is the identity matrix.

[0044] S2.6: When obtained W When , the model training process is completed and no fine-tuning is required. The sintering carbon consumption intelligent prediction model is formed, and the predicted value of the sintering carbon consumption intelligent prediction model is recorded as :

[0045]

[0046] S2.7: When the sintering carbon consumption intelligent prediction model network is trained, the output is used as feedback for residual calculation to improve the accuracy of the sintering carbon consumption intelligent prediction model:

[0047]

[0048] in, represents the residual matrix, Indicates the t The residual of the sample, t =1,2,..., N .

[0049] Input the process parameter samples in the test data set in step S2 into the sintering carbon consumption intelligent prediction model to obtain the predicted value of sintering carbon consumption, and compare the predicted value of sintering carbon consumption with the sample value of sintering carbon consumption corresponding to the sintering parameter sample to obtain the following: Figure 3 The results shown by Figure 3 It can be seen that the predicted value of sintering carbon consumption is very close to the sample value. The sample value is the actual value of sintering carbon consumption corresponding to the actual production process. Figure 3The prediction error between the sintering carbon consumption prediction value and the sample value is as follows: Figure 4 As shown by Figure 3 and Figure 4 It can be seen that the prediction error of the dynamic prediction of sintering carbon consumption is kg / t, most of the prediction results are within Therefore, the sintering carbon consumption intelligent prediction model can accurately perform dynamic prediction of sintering carbon consumption, meet the production requirements of the actual sintering process, and promote green manufacturing and intelligent manufacturing of the sintering process.

[0050] S3: Based on the actual production data of sintering carbon consumption, the process parameters that directly affect sintering carbon consumption (BRP, BRP temperature, BTP, BTP temperature, bellows negative pressure, vertical combustion speed, trolley speed, material layer thickness, return ore, coke powder ratio, FeT content, SiO2 content, CaO content and MgO content) are used as input, and sintering carbon consumption is used as output. The sintering carbon consumption is dynamically predicted using the sintering carbon consumption intelligent prediction model.

[0051] Example 2

[0052] A sintering process carbon consumption adaptive weighted width echo state learning system modeling device 501, such as Figure 5 As shown, it includes: a processor 502 and a storage device 503; the processor 502 loads and executes the instructions and data in the storage device 503 to implement the sintering process carbon consumption adaptive weighted width echo state learning system modeling method.

[0053] Example 3

[0054] A storage device stores instructions and data for implementing the sintering process carbon consumption adaptive weighted width echo state learning system modeling method.

[0055] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A modeling method for a sintering process carbon consumption adaptive weighted width echo state learning system, characterized by: Including the following step: S1: Based on the sintering process mechanism analysis and data correlation analysis, the process parameters that directly affect the sintering carbon consumption are determined. The process parameters include: BRP, BRP temperature, BTP, BTP temperature, wind box negative pressure, vertical combustion speed, trolley speed, material layer thickness, return ore, coke powder ratio, FeT content, SiO2 content, CaO content and MgO content; S2: establishing and training a sintering carbon consumption intelligent prediction model based on an adaptive weighted width echo state learning system; the sintering carbon consumption intelligent prediction model includes a characteristic node layer and a reservoir; The process of establishing an intelligent prediction model for sintering carbon consumption is as follows: S2.1: The training sample data set consisting of process parameters that directly affect sintering carbon consumption and the corresponding sintering carbon consumption is {(x t ,Y t ),t=1,2,...,N},x t is the tth training sample, which is used as the input of the sintering carbon consumption intelligent prediction model. t is the t-th sintering carbon consumption, N represents the total number of samples in the training sample data set; input data set Randomly map X to n sets of features, the feature F of the i-th mapping i Denoted as: in, is the activation function; is the weight vector; is the bias vector; n represents the number of feature mappings; After the input data set X is transformed by n feature maps, we get: F=[F1,F2,…,F n ] Where F represents the mapping feature vector output by the feature node layer; S2.2: To capture the dynamic characteristics of the adaptive weighted width echo state learning system, F is transferred to the reservoir through a nonlinear transformation, and the reservoir state update equation is expressed as: in, is the hyperbolic tangent function, W in and W back Randomly generated through echo state network learning; E(n) represents the reservoir state of the nth feature map, F(n) represents the feature of the nth map, and E(n-1) represents the reservoir state of the n-1th feature map; S2.3: The output of the reservoir layer is combined with all the outputs of the feature node layer: A=[F|E] Among them, E represents the output of the reservoir layer; F represents the output of the feature node layer, that is, the mapping feature vector; S2.4: Solve the optimization problem of the system: arg min:||θ(AW-Y)|| 2 +λ||W|| 2 Where θ is the diagonal matrix associated with each input sample, λ represents the trade-off parameter, W is the weight in the output layer, and Y represents the sintering carbon consumption; S2.5: When W is obtained, the adaptive weighted width echo state learning system training is completed, forming a sintering carbon consumption intelligent prediction model: in, Indicates the predicted value of the sintering carbon consumption intelligent prediction model; S3: Based on actual production data, with process parameters that directly affect sintering carbon consumption as input and sintering carbon consumption as output, dynamic prediction of sintering carbon consumption is performed using the trained sintering carbon consumption intelligent prediction model.

2. The method for modeling a sintering process carbon consumption adaptive weighted width echo state learning system according to claim 1, characterized in that: In step S1, according to the analysis of the sintering process mechanism, the process parameters affecting the sintering carbon consumption include two aspects: sintered ore output and carbon consumption; the sintered ore output is determined by the raw material parameters in the sintering process, and the raw material parameters include coke powder ratio, SiO2 content, TFe content, MgO content, CaO content and return ore; the carbon consumption includes the state parameters and operating parameters in the sintering process, and the operating parameters include trolley speed and material layer thickness, and the state parameters include: BTP, BTP temperature, wind box negative pressure, vertical combustion speed, BRP and BRP temperature, wherein BTP represents the sintering end point and BRP represents the rising point.

3. The method for modeling a sintering process carbon consumption adaptive weighted width echo state learning system according to claim 1, characterized in that: In step S2.4, the diagonal matrix θ associated with each input sample is calculated as: θ=diag(ω t ),t=1,2,…,N Among them, ω t is a weighted finite element, diag() represents a diagonal matrix, and N represents the total number of samples in the training sample data set.

4. The method for modeling a sintering process carbon consumption adaptive weighted width echo state learning system according to claim 3, characterized in that: Weighted finite element ω t The calculation formula is: oh t =g(r t ) Among them, g() represents the residual probability density function, r t represents the residual of the t-th sample.

5. The method for modeling a sintering process carbon consumption adaptive weighted width echo state learning system according to claim 4, characterized in that: The residual probability density function is: in, represents the width of the estimation window, x represents the input data, and Ker(·) represents the kernel function.

6. The method for modeling a sintering process carbon consumption adaptive weighted width echo state learning system according to claim 1, characterized in that: Use the pseudo-inverse algorithm to solve the parameters in the optimization problem of step S2.4 and obtain: W=(λI+A T i 2 A) -1 A T i 2 Y Where I is the identity matrix.

7. The method for modeling a sintering process carbon consumption adaptive weighted width echo state learning system according to claim 1, characterized in that: In step S2, when the sintering carbon consumption intelligent prediction model is trained, the model output is used as feedback for residual calculation to improve the accuracy of the sintering carbon consumption intelligent prediction model: R=Y-AW Where R=[r1,r2,…,r N ] T represents the residual matrix, r t represents the residual of the t-th sample, t=1,2,...,N.

8. A storage device, characterized in that: The storage device stores instructions and data for implementing the sintering process carbon consumption adaptive weighted width echo state learning system modeling method according to any one of claims 1 to 7.

9. A modeling device for a sintering process carbon consumption adaptive weighted width echo state learning system, characterized by: include: Processor and storage device; the processor loads and executes instructions and data in the storage device to implement the sintering process carbon consumption adaptive weighted width echo state learning system modeling method described in any one of claims 1 to 7.

Images