JP6003909B2 - Blast furnace air permeability prediction apparatus and blast furnace air permeability prediction method - Google Patents

Description

  The present invention relates to a blast furnace air permeability predicting apparatus and a blast furnace air permeability predicting method for predicting air permeability of a blast furnace for stable maintenance management of blast furnace operation.

In recent years, blast furnace operations have been carried out under severe conditions, including the implementation of pulverized coal injection, etc. in order to pursue rationalization of raw fuel costs. Under such circumstances, the stable maintenance of daily blast furnace operation, in particular, the stable maintenance of ventilation is important. Therefore, in order to ensure stable operation of the blast furnace, it is important to establish a breathability prediction technique. The air permeability of the blast furnace is evaluated by an index obtained by indexing the airflow resistance in the blast furnace, that is, the airflow resistance index (ΔP / V). This ventilation resistance index ΔP / V is calculated by the following formula (1). Here, BP is the blowing pressure [Pa], TP is the furnace top pressure [Pa], and BGV is the Bosch gas amount [m ³ (standard state) / min]. These values are measured by sensors installed in the blast furnace.

  Stabilizing the ventilation resistance index of the blast furnace is important from the viewpoint of improving productivity and reducing fuel consumption. Up to now, the blast furnace air permeability has been predicted by the following method.

  That is, in Patent Document 1, coke after being subjected to the impact test is classified by each of two types of sieves having different opening diameters, and an index calculated from an equation determined based on the passing mass ratio of each sieve. Describes a method for predicting air permeability in a blast furnace. Moreover, in the method of patent document 2, the filler particle diameter of a furnace lower part is estimated using the virtual fall amount of the ventilation pressure in the furnace lower part of a blast furnace during operation. Moreover, the method of patent document 2 uses the hypothetical | virtual fall amount and the hypothetical | virtual fall amount of the ventilation pressure in the furnace lower part in the stable operation of a blast furnace calculated | required beforehand, and the filler particle diameter of the furnace lower part at that time Is estimated. And the method of patent document 2 uses the ratio of the said filler particle diameter of the blast furnace in operation and the said filler particle diameter in the stable operation as a parameter | index of the operation stability of a blast furnace. In the method described in Patent Document 2, a virtual blowing pressure Pb ′ on the tuyere shaft obtained by using pressures in the vicinity of the furnace inner wall at two or more points belonging to the morning glory portion above the tuyere, and the above two points The pressure difference from the pressure measurement value Pmin at the highest position among the above pressures is set as a virtual drop amount. In the method described in Patent Document 2, the average packed particle size in the lower part of the furnace is obtained from this hypothetical decrease using the Ergun equation. Patent Document 3 describes a method for estimating the airflow resistance from the tuyere to the top of the furnace from the multiple regression equation obtained from actual machine operation specifications. In the method described in Patent Document 3, the amount of slag, the amount of Bosch gas, the amount of dust, O / C (the ratio of ore raw material to coke), CR (coke ratio), PCR (rough coal ratio), and charging The airflow resistance from the tuyere to the top of the furnace is estimated based on at least one factor among the raw material properties.

JP 2001-240881 A JP 2003-306708 A JP 2012-87375 A

  According to the methods described in Patent Documents 1 and 2, it is necessary to construct a prediction model that imitates the phenomenon in the blast furnace, but it is extremely difficult to accurately model all the phenomena in the blast furnace. A highly accurate prediction model cannot be constructed. Further, according to the method described in Patent Document 3, the relationship between each operating condition and the airflow resistance index is very complicated and non-linear. Therefore, it is possible to construct a sufficiently accurate prediction model with a simple linear regression equation. Can not. Therefore, according to the conventional blast furnace air permeability prediction method, it is difficult to accurately predict the blast furnace air flow resistance index.

  The present invention has been made to solve the above-described problems, and an object of the present invention is to provide a blast furnace air permeability predicting apparatus and a blast furnace air permeability predicting method capable of accurately predicting a ventilation resistance index of a blast furnace. .

  In order to solve the above-described problems and achieve the object, the blast furnace air permeability predicting apparatus according to the present invention includes past operating conditions of the blast furnace and information on the ventilation resistance index when the blast furnace is operated under the operating conditions. For each variable of the actual data, a data expansion unit that expands the data retroactively to the past of a plurality of steps and creates an actual data set, and a plurality of operating conditions in the actual data set with respect to the operating condition to be predicted Using the similarity calculation unit for calculating the similarity and information on the operation condition in the actual data set, a prediction formula of the ventilation resistance index representing the relationship between the operation condition of the blast furnace and the ventilation resistance index is created, and the similarity By solving the optimization problem using the evaluation function weighted by the similarity calculated by the degree calculation unit as an evaluation function for evaluating the prediction error of the prediction expression, the prediction expression A prediction formula creation unit for determining a parameter, and the ventilation when operating the blast furnace under the operation condition of the prediction target by inputting the operation condition of the prediction target into the prediction formula created by the prediction formula creation unit A breathability predicting unit for predicting a resistance index.

  The blast furnace air permeability predicting apparatus according to the present invention is characterized in that, in the above invention, the prediction formula creating unit solves the optimization problem with a physical characteristic to be predicted as a restriction target.

  In the blast furnace air permeability prediction device according to the present invention, in the above invention, the similarity calculation unit uses a product of the similarity to the operation condition of the prediction target, the actual data, and the temporal similarity of the prediction target as the similarity. It is characterized by calculating.

  In the blast furnace air permeability prediction apparatus according to the present invention, in the above invention, the operation conditions used by the data development unit, the similarity calculation unit, the prediction formula creation unit, and the air flow prediction unit are linear by principal component analysis. It is characterized by being transformed and dimensionally compressed.

  In order to solve the above-described problems and achieve the object, the blast furnace air permeability prediction method according to the present invention includes information on the past blast furnace operating conditions and the ventilation resistance index when the blast furnace is operated under the operating conditions. For each variable of the actual data, a data expansion step for developing the data retroactively to the past before a plurality of steps to create a historical data set, and a plurality of operating conditions in the actual data set with respect to the operating condition to be predicted Using the similarity calculation step for calculating the similarity and the information on the operation condition in the actual data set, a prediction formula of the ventilation resistance index representing the relationship between the operation condition of the blast furnace and the ventilation resistance index is created, and the similarity In order to solve the optimization problem, the evaluation function weighted by the similarity calculated in the degree calculation step is used as an evaluation function for evaluating the prediction error of the prediction formula. Thus, a prediction formula creation step for determining parameters of the prediction formula, and by inputting the operation conditions of the prediction target into the prediction formula generated in the prediction formula creation step, And a breathability prediction step of predicting a ventilation resistance index when the operation is performed.

  According to the blast furnace air permeability predicting apparatus and the blast furnace air permeability predicting method according to the present invention, the ventilation resistance index of the blast furnace can be predicted with high accuracy.

FIG. 1 is a block diagram showing a configuration of a blast furnace air permeability prediction system according to an embodiment of the present invention. FIG. 2 is a diagram illustrating an example of performance data stored in the performance database illustrated in FIG. 1. FIG. 3 is a flowchart showing the flow of the performance database expansion process according to the embodiment of the present invention. FIG. 4 is a flowchart showing a flow of blast furnace air permeability prediction processing according to an embodiment of the present invention. FIG. 5A is a diagram showing the relationship between the actual value of the ventilation resistance index and the predicted value of the ventilation resistance index predicted by using the conventional blast furnace air permeability prediction method. FIG. 5B is a diagram showing the relationship between the actual value of the ventilation resistance index and the predicted value of the ventilation resistance index predicted using the blast furnace air permeability prediction method of the present invention. FIG. 6A is a diagram showing the relationship between the actual value of the ventilation resistance index and the predicted value of the ventilation resistance index predicted by using the conventional blast furnace air permeability prediction method. FIG. 6B is a diagram showing the relationship between the actual value of the ventilation resistance index and the predicted value of the ventilation resistance index predicted by using the blast furnace air permeability prediction method of the present invention.

  Hereinafter, the configuration and operation of a blast furnace air permeability prediction system according to an embodiment of the present invention will be described with reference to the drawings.

[Configuration of Blast Furnace Breathability Prediction System]
First, with reference to FIG. 1 and FIG. 2, the structure of the blast furnace air permeability prediction system which is one embodiment of the present invention will be described. FIG. 1 is a block diagram showing a configuration of a blast furnace air permeability prediction system according to an embodiment of the present invention. FIG. 2 is a diagram illustrating an example of performance data stored in the performance database illustrated in FIG. 1.

  As shown in FIG. 1, a blast furnace air permeability prediction system 1 according to an embodiment of the present invention includes an input device 2, an output device 3, a performance database 4, and a blast furnace air permeability prediction device 5 as main components. Yes. The input device 2 includes an information input device such as a keyboard, a mouse pointer, and a numeric keypad, and is operated when an operator inputs various types of information to the blast furnace air permeability predicting device 5. The output device 3 is configured by an information output device such as a display device or a printing device, and outputs various processing information of the blast furnace air permeability predicting device 5.

As shown in FIG. 2, the performance database 4 includes the ventilation resistance index in the blast furnace process at a constant cycle of several minutes to several tens of minutes, and the blowing temperature, blowing moisture, pulverized coal injection amount, oxygen enrichment amount, etc. in the blast furnace. Stores operating condition results data. Specifically, the actual result database 4 is expressed by the actual value y ⁿ (where n = 1, 2,..., N) of the output variable and the following mathematical formula (2) at a constant cycle of several minutes to several tens of minutes. Stores the actual value of the input variable.

  In the present embodiment, the output variable is a ventilation resistance index, and the input variable is an operating variable of a blast furnace process that is physically and causally related to the ventilation resistance index, a blowing temperature, a blowing moisture, a pulverized coal injection amount, And operating conditions such as oxygen enrichment. The performance database 4 is configured such that old performance data is removed by a method such as a first-in first-out method so that a prediction model of blast furnace permeability can be constructed based on the latest performance data.

  Returning to FIG. The blast furnace air permeability predicting device 5 is constituted by an information processing device such as a workstation or a personal computer, and includes a CPU 10, a RAM 11, and a ROM 12 as main components. The CPU 10 controls the overall operation of the blast furnace air permeability predicting device 5. The CPU 10 functions as a data expansion unit 10a, a similarity calculation unit 10b, a prediction formula creation unit 10c, and a breathability prediction unit 10d by executing a blast furnace air permeability prediction program 12a stored in advance in the ROM 12. The functions of these units will be described later.

  In the blast furnace air permeability predicting system 1 having such a configuration, the blast furnace air permeability predicting device 5 predicts the ventilation resistance index in the blast furnace by executing the results database development process and the blast furnace air permeability predicting process described below. Hereinafter, with reference to the flowcharts shown in FIG. 3 and FIG. 4, the operation of the blast furnace air permeability prediction device 5 when executing the result database development process and the blast furnace air permeability prediction process will be described.

[Result database expansion processing]
First, with reference to the flowchart shown in FIG. 3, the operation of the blast furnace air permeability predicting device 5 when executing the performance database development process will be described.

  FIG. 3 is a flowchart showing the flow of the performance database expansion process according to the embodiment of the present invention. The flow chart shown in FIG. 3 shows the results of operating conditions such as the ventilation resistance index in the blast furnace process collected by an external computer at regular intervals, and the blowing temperature, blowing moisture, pulverized coal injection amount, and oxygen enrichment amount in the blast furnace. The data is stored in the results database 4 and starts when the contents of the results database 4 are updated by a method such as a first-in first-out method, and the results database expansion process proceeds to the process of step S1.

  In the process of step S1, the data development unit 10a includes output variables (ventilation resistance index) and input variables (blast temperature, blast moisture, pulverized coal injection amount, oxygen enrichment amount, etc.) stored in the performance database 4. Develop past performance data (operating conditions) into a form that can be used for air permeability prediction. Specifically, past performance data is stored in the performance database 4 as a matrix of N rows (L + 1) columns, as shown in the following formula (3).

Therefore, first, the data expansion unit 10a expands the past performance data before the (K-1) step side by side for each variable stored in the performance database 4, and the following equation (4) is obtained. A matrix of N rows and K (L + 1) columns as shown is generated. Note that the first column of the matrix shown in Equation (4) is an output variable y ⁿ (where n = 1, 2,..., N).

  Next, the data expansion unit 10a uses the second and subsequent columns of the matrix shown in Equation (4) as explanatory variables, and changes the symbols of the explanatory variables as shown in Equation (5) below. Hereinafter, the matrix shown in Equation (5) is referred to as an expanded actual data set.

  Note that the explanatory variables in the second and subsequent columns of the post-development performance data set may have been subjected to linear transformation and dimension compression in advance by principal component analysis. Specifically, when the actual value of the explanatory variable is expressed as in the following formula (6), first, the data expansion unit 10a uses the following formula (7) and the average value is 0. Standardize each explanatory variable so that the standard deviation is 1.

  The actual value of the explanatory variable after standardization is expressed as the following formula (8) or (9). Next, the data expansion unit 10a calculates a covariance matrix V of the matrix Z defined by the following formula (10), and calculates an eigenvalue of the covariance matrix V and an eigenvector corresponding thereto. The covariance matrix V has a plurality of non-negative eigenvalues and a plurality of eigenvectors corresponding to them.

Next, the data expansion unit 10a rearranges the eigenvectors in descending order of the corresponding eigenvalues. A matrix P = [w ₁ , w ₂ ,..., W _M ⁿ ] ^T (where M is a natural number equal to or less than K (L + 1) −1) obtained by extracting M eigenvectors from the corresponding eigenvalues in descending order. Represent. The matrix P is called a loading matrix. The data expansion unit 10a uses a result obtained by linearly converting the actual value z of the explanatory variable using the loading matrix P as shown in the following formula (11) as the explanatory variable of the expanded actual data set. Hereinafter, the post-expansion result data set to be used is represented as the following formula (12). Thereby, the process of step S1 is completed and a performance database expansion | deployment process is complete | finished.

[Blast furnace air permeability prediction processing]
Next, the operation of the blast furnace air permeability prediction device 5 when executing the blast furnace air permeability prediction processing will be described with reference to the flowchart shown in FIG.

  FIG. 4 is a flowchart showing a flow of blast furnace air permeability prediction processing according to an embodiment of the present invention. The flowchart shown in FIG. 4 starts at the timing when data of the operation condition to be predicted shown in the following formula (13) is input to the input device 2, and the blast furnace air permeability prediction process proceeds to the process of step S11.

  In the process of step S11, the data expansion unit 10a performs variable conversion on the data of the operation condition to be predicted input from the input device 2 in the same manner as the result database expansion process. Specifically, the data expansion unit 10a first expands past performance data before each step (K-1) for each input variable of the operation condition, and develops K ( L + 1) Generate a vector having -1 element.

  Hereinafter, the symbol of the vector variable shown in Expression (14) is changed as shown in Expression (15) below.

  Next, the data development unit 10a standardizes each variable of the vector shown in the formula (15) using the following formula (16), and uses the explanatory variables to be predicted after standardization shown in the following formula (17). Generate. Finally, the data expansion unit 10a linearly transforms the prediction target explanatory variable using the loading matrix P as shown in the following equation (18), and uses this as a request point (prediction target explanatory variable value). . Thereby, the process of step S11 is completed and a blast furnace air permeability prediction process progresses to the process of step S12.

In the process of step S12, the similarity calculation unit 10b calculates the similarity between the explanatory variable value to be predicted and the past explanatory variable value stored in the post-deployment result data set. Specifically, first, the similarity calculation unit 10b calculates the requirement points shown in Formula (18) and the explanatory variable values x ⁿ = [x ₁ ⁿ , x ₂ ⁿ _,. ⁿ ] For ^T , a distance Γ ⁿ from the required point shown in the following mathematical formula (19) is calculated. Note that the parameter λ _m in the equation (19) is a weighting factor for scaling input variables measured on different scales such as the blowing flow rate and the blowing moisture content.

Then, the similarity calculation unit 10b requests each explanatory variable value x ⁿ = [x ₁ ⁿ , x ₂ ⁿ ,..., X _M ⁿ ] ^T of the post-expansion actual data set using the following formula (20). The similarity W ^{n of the} point at the position of the distance Γ ⁿ calculated by the equation (19) is calculated from the point. Here, the parameter σ _Γ in the equation (20) is a standard deviation of the distance Γ ⁿ , and the parameter p is an adjustment parameter.

Note that, as shown in the following formula (21), the similarity W ⁿ is the similarity between the prediction target explanatory variable, the plurality of actual data stored in the expanded actual data set, and the prediction target explanatory variable. It may be a product of temporal similarity. Here, in Equation (21), the parameter λ is a forgetting factor and is an adjustment parameter having a value greater than 0 and less than 1. By inserting the forgetting element λ, the similarity of new performance data is increased, and the similarity of old performance data is decreased. Thereby, the process of step S12 is completed and a blast furnace air permeability prediction process progresses to the process of step S13.

In the processing of step S13, the prediction formula creation unit 10c uses the N pieces of actual data (actual values x ^{n of} explanatory variables) stored in the post-expansion actual data set and the similarity W ⁿ between the requested points. Thus, a local prediction model that emphasizes past performance data similar to the request point is created. Specifically, the prediction formula creation unit 10c creates a prediction model represented by the following mathematical formula (22).

Here, in Equation (22), θ = [b, a ₁ , a ₂ ,..., A _M ] ^T is a model parameter. The model parameter θ is an optimal value that minimizes the value of the evaluation function J, which is a weighted sum of squares of errors between the actual measurement value and the prediction value, which are calculated by the following equation (23) and weighted by the similarity W ^n. It can be calculated by solving the optimization problem.

Here, y ⁿ (where n = 1, 2,..., N) is the value of the output variable corresponding to the nth actual data, and diag (s) is the element of the vector s as the main diagonal element. Is a diagonal matrix. Create a local prediction model that better fits historical data that has a high degree of similarity, that is, close to the required point, by calculating model parameters that minimize the weighted sum of squares of the error between the predicted value and the measured value be able to.

When solving the optimization problem, the optimization problem may be solved by giving the following constraint conditions. Specifically, the constraint condition is expressed by the following equation (24) with respect to the range of the partial regression coefficient φ = [a ₁ , a ₂ ,..., A _M ] ^T of the input variable in the model parameter θ. May be provided. Here, the subscript bar represents the lower limit value, and the superscript bar represents the upper limit value.

  For the lower limit and upper limit, physical foresight information between input and output variables shall be given. Specifically, if the blowing temperature, which is one of the input variables, increases, the ventilation resistance index, which is an output variable, decreases. Therefore, for the model parameter corresponding to the air temperature, the lower limit value and the upper limit value are set to −∞ and 0, respectively. Also, if the blast moisture, which is one of the input variables, increases, the ventilation resistance index increases. Therefore, for the model parameters corresponding to the blast moisture, the lower limit value and the upper limit value are set to 0 and ∞, respectively. In this way, by adding constraints on the foresight information obtained from the physical model, it is possible to better fit the actual data close to the requested point and to have a local regression coefficient that matches the physical characteristics of the prediction target. A predictive model can be created. Thereby, the process in step S13 is completed, and the blast furnace air permeability prediction process proceeds to the process in step S14.

  In the process of step S14, the air permeability predicting unit 10d calculates the predicted value of the air permeability of the blast furnace by substituting the explanatory variable value of the required point into the prediction model created by the process of step S13. Thereby, the process of step S14 is completed and a series of blast furnace air permeability prediction processes are completed.

[Experimental example]
The experimental results of predicting the ventilation resistance index for a certain blast furnace process using the blast furnace air permeability prediction method of the present invention and the conventional blast furnace air permeability prediction method will be described. Here, the conventional blast furnace air permeability prediction method is a method for predicting air permeability by a simple linear regression equation as in the method described in Patent Document 3. In this experiment, operating conditions such as the blowing temperature, blowing moisture, pulverized coal injection amount, and oxygen enrichment amount were input variables, and the ventilation resistance index ΔP / V in the blast furnace was an output variable.

  The parameters used in the blast furnace air permeability prediction method of the present invention are as follows. The number L of input variables was 500, the number N of samples stored in the performance database was 80000, the number K of data expansion was 20, and the number M of explanatory variables dimensionally compressed by principal component analysis was 71. The value of the forgetting factor for calculating the similarity in time was 0.999. The record data stored in the record database was collected at a fixed period of 30 minutes.

  5A and 5B are diagrams showing the relationship between the actual value of the ventilation resistance index and the predicted value of the ventilation resistance index predicted by using the conventional blast furnace air permeability prediction method and the blast furnace air permeability prediction method of the present invention. . As shown in FIG. 5A, the RMSE (Root Mean Square Error) of the prediction error of the ventilation resistance index ΔP / V predicted using the conventional blast furnace air permeability prediction method was 0.637. On the other hand, as shown in FIG. 5B, the RMSE of the prediction error of the ventilation resistance index predicted by using the blast furnace air permeability prediction method of the present invention was 0.412. 6A and 6B are diagrams showing the relationship between the actual value of the ventilation resistance index and the predicted value of the ventilation resistance index predicted by using the conventional blast furnace air permeability prediction method and the blast furnace air permeability prediction method of the present invention. It is. As shown in FIG. 6B, the actual measurement value and the prediction value obtained by the blast furnace air permeability prediction method of the present invention are more consistent with the actual value and the prediction value obtained by the conventional blast furnace air permeability prediction method shown in FIG. 6A. It was confirmed that From this, it became clear that according to the blast furnace air permeability prediction method of the present invention, the air flow resistance index can be predicted with high accuracy.

  As is clear from the above description, according to the blast furnace air permeability prediction system 1 which is an embodiment of the present invention, the data development unit 10a has a plurality of variables for the performance data stored in the performance database 4. Data is developed back to the past before the step to create a performance data set. Further, the similarity calculation unit 10b calculates the similarity with respect to the operation condition to be predicted for a plurality of operation conditions stored in the result data set, and the prediction formula creation unit 10c is stored in the result data set. A prediction model that represents the relationship between the operation condition and the airflow resistance index is created using the information on the operation condition, and the prediction function predicts the evaluation function weighted by the similarity calculated by the similarity calculation unit 10b. The parameters of the prediction model are determined by solving the optimization problem as an evaluation function for evaluating the error. Then, the ventilation resistance index when the blast furnace is operated under the operation condition of the prediction target is obtained by inputting the operation condition of the prediction object into the prediction expression created by the prediction expression creation unit 10c. Predict. According to such a configuration, since the prediction model can be automatically adjusted based on the performance data stored in the performance database 4, the ventilation resistance index of the blast furnace can be predicted with high accuracy.

  In addition, according to the blast furnace air permeability prediction system 1 according to an embodiment of the present invention, the prediction formula creation unit 10c solves the optimization problem using the physical characteristics of the prediction target as a constraint, so that the prediction model is contrary to the physical phenomenon. Can be suppressed, and the prediction accuracy of the airflow resistance index can be further improved.

  Although the embodiment to which the invention made by the present inventor is applied has been described above, the present invention is not limited by the description and the drawings that form part of the disclosure of the present invention according to this embodiment. That is, other embodiments, examples, operational techniques, and the like made by those skilled in the art based on this embodiment are all included in the scope of the present invention.

1 Blast Furnace Breathability Prediction System 2 Input Device 3 Output Device 4 Results Database 5 Blast Furnace Breathability Prediction Device 10 CPU
10a Data development unit 10b Similarity calculation unit 10c Prediction formula creation unit 10d Breathability prediction unit 11 RAM
12 ROM
12a Blast furnace air permeability prediction program

Claims (5)

For each variable of the performance data including past blast furnace operating conditions and information on the airflow resistance index when the blast furnace was operated under the operating conditions, the data is expanded to the past several steps before the first column. a data development section for creating a track record data set as an output variable and the second or subsequent column as explanatory variable matrix,
For a plurality of operation conditions in the actual data set, a similarity calculation unit that calculates a similarity to the operation condition to be predicted; and
Using the information on the operating conditions in the performance data set, create a prediction formula of the ventilation resistance index that represents the relationship between the operating conditions of the blast furnace and the ventilation resistance index, and weight the similarity calculated by the similarity calculation unit A prediction formula creation unit that determines a parameter of the prediction formula by solving an optimization problem as an evaluation function that evaluates the prediction error of the prediction formula as
A breathability prediction unit that predicts a ventilation resistance index when operating a blast furnace under the operation condition of the prediction target by inputting the operation condition of the prediction target into the prediction formula created by the prediction formula creation unit; With
The data expansion unit standardizes each explanatory variable, obtains a covariance matrix of a matrix representing the actual value of the explanatory variable after the standardization, calculates an eigenvalue of the covariance matrix and an eigenvector corresponding thereto, and calculates the eigenvector. The actual value of the explanatory variable is linearly converted using the linearly converted explanatory variable as the explanatory variable of the actual data set.
Blast breathable predicting device comprising a call. The prediction equation creating unit-out solution to the optimization problem by adding the physical properties of the prediction target constraint condition,
The constraint condition includes providing a restriction based on a physical causal relationship determined in advance by a physical characteristic between the operation condition to be predicted and the ventilation resistance index in the operation condition to be predicted.
Blast breathable prediction apparatus according to claim 1, wherein the this.   The said similarity calculation part calculates the product of the similarity with respect to the operation condition of a prediction object, the performance data, and the temporal similarity of a prediction object as a similarity, The Claim 1 or 2 characterized by the above-mentioned. Blast furnace air permeability prediction device.   The operation conditions used for processing by the data development unit, the similarity calculation unit, the prediction formula creation unit, and the air permeability prediction unit are linearly transformed and dimension-compressed by principal component analysis. The blast furnace air permeability predicting apparatus according to any one of Items 1 to 3. For each variable of the performance data including past blast furnace operating conditions and information on the airflow resistance index when the blast furnace was operated under the operating conditions, the data is expanded to the past several steps before the first column. and data expansion step of creating a track record data set as an output variable and the second or subsequent column as explanatory variable matrix,
For a plurality of operation conditions in the actual data set, a similarity calculation step for calculating a similarity to the operation condition to be predicted; and
Using the information on the operating conditions in the performance data set, create a prediction formula for the ventilation resistance index representing the relationship between the operating conditions of the blast furnace and the ventilation resistance index, and weight the similarity calculated in the similarity calculation step A prediction formula creation step for determining a parameter of the prediction formula by solving an optimization problem as an evaluation function that evaluates the prediction error of the prediction formula as
Furnace air permeability prediction step of predicting a ventilation resistance index when operating a blast furnace under the operation conditions of the prediction target by inputting the operation conditions of the prediction target into the prediction formula created in the prediction formula creation step And including
The data expansion step includes:
Standardizing each explanatory variable;
Obtaining a covariance matrix of a matrix representing the actual value of the explanatory variable after the standardization;
Calculating eigenvalues of the covariance matrix and corresponding eigenvectors;
Linearly transforming the actual value of the explanatory variable using the eigenvector;
Using the linearly transformed explanatory variable as an explanatory variable of the actual data set.
Blast breathable prediction wherein a call.

Images