Blast furnace temperature grading diagnosis regulation and control method, device and equipment

Abstract

The invention relates to the technical field of blast furnace ironmaking furnace temperature control, and discloses a blast furnace temperature grading diagnosis regulation and control method, device and equipment, and the method comprises the following steps: obtaining current operation data of a blast furnace, and utilizing a furnace temperature trend prediction model to obtain predicted molten iron silicon content of the blast furnace; the current molten iron silicon content is obtained, and the furnace temperature trend is determined according to the predicted molten iron silicon content and the current molten iron silicon content; determining a furnace temperature change level according to the furnace temperature trend and a preset furnace temperature change grading table; acquiring current production data, and determining current furnace condition characterization of the blast furnace according to the current production data; and according to the furnace temperature change level and the current furnace condition characterization, the adjusting quantity of the preset adjusting and controlling parameters is determined through a furnace temperature adjusting and controlling model. According to the method, the accurate predicted furnace temperature is obtained by predicting the silicon content of the molten iron, the furnace temperature change trend and the furnace condition characterization are analyzed to determine the furnace temperature change reason, an effective regulation and control means is adopted, accurate regulation and control of the furnace temperature of the blast furnace are achieved, huge fluctuation of the furnace temperature is avoided, and long-term stable operation of the blast furnace is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of blast furnace ironmaking temperature control, and in particular to a blast furnace temperature classification diagnosis and control method, device and equipment. Background Art

[0002] Furnace temperature control is of great significance in blast furnace production. Its main purpose is to stabilize the furnace condition, reduce the phenomenon of suspended materials and nodules, facilitate the maintenance of furnace equipment, and extend the life of the blast furnace. When the temperature field in the furnace changes little, the soft melting zone is stable, which is easy to improve the utilization of coal gas; at the same time, the chemical reaction of the stable dripping zone and the furnace can improve the qualified rate of silicon and sulfur, reduce the silicon level, and reduce the heat dissipation of the furnace; in addition, the thermal balance of the lower part of the blast furnace is stable, the full delivery rate of wind temperature is improved, the potential of the hot blast furnace is fully utilized, and the coal powder injection rate is increased. Therefore, the establishment of a blast furnace temperature prediction and control system is the technical core of achieving complete closed-loop control of the blast furnace ironmaking process.

[0003] In the current blast furnace production, the furnace temperature is mainly controlled by the blast furnace operator according to the existing furnace conditions, which has a certain time lag. The control method of the furnace temperature also varies due to the difference in experience of the operators and lacks standardization. These situations cause the blast furnace temperature control to be driven by the blast furnace conditions and is in a passive state, which is not conducive to the long-term stable operation of the blast furnace. At the same time, the existing blast furnace temperature prediction and adjustment algorithm, from the commonly used furnace temperature to cool, stable, and hot angles, is limited by the rough judgment of the furnace temperature change, and the prediction of the furnace temperature has not been graded, resulting in the adjustment method not being detailed enough. Summary of the invention

[0004] In view of this, the present invention provides a blast furnace temperature graded diagnosis and control method, device and equipment to solve the problem that the blast furnace temperature cannot be accurately and efficiently predicted and controlled.

[0005] In a first aspect, the present invention provides a blast furnace temperature hierarchical diagnosis and control method, the method comprising:

[0006] Obtain the current operation data of the blast furnace, and use the furnace temperature trend prediction model to obtain the predicted molten iron silicon content of the blast furnace, which is used to characterize the furnace temperature;

[0007] Obtain the current silicon content of molten iron, and determine the furnace temperature trend based on the predicted silicon content of molten iron and the current silicon content of molten iron;

[0008] Determine the furnace temperature change level according to the furnace temperature trend and the preset furnace temperature change classification table;

[0009] Acquire current production data, and determine a current furnace condition representation of the blast furnace based on the current production data;

[0010] According to the furnace temperature change level and the current furnace condition characterization, the furnace temperature control model is used to determine the adjustment amount of the preset control parameters.

[0011] The blast furnace temperature graded diagnosis and control method provided by the present invention obtains accurate predicted furnace temperature by predicting the silicon content of molten iron, determines the cause of furnace temperature change by analyzing the furnace temperature change trend and furnace condition characterization, and adopts effective control measures to achieve precise control of the blast furnace temperature, avoid huge fluctuations in the furnace temperature, maintain the stability of the furnace temperature, and is conducive to the long-term stable operation of the blast furnace.

[0012] In an optional implementation, the training process of the furnace temperature trend prediction model includes:

[0013] Obtain the historical operation data of the blast furnace, and pre-process the historical operation data to obtain historical key operation data;

[0014] Conduct correlation analysis on historical key operating data to obtain the lag time of each historical key operating data affecting the silicon content of molten iron;

[0015] Based on the lag time of historical key operating data affecting the silicon content in molten iron and combined with the neural network model, a furnace temperature trend prediction model was obtained.

[0016] The blast furnace temperature graded diagnosis and control method provided by the present invention analyzes the lag time of the key operating data affecting the silicon content of molten iron, combines the neural network model to determine the furnace temperature trend prediction model, takes into account the lag time of the key operating data affecting the furnace temperature, and predicts the furnace temperature more accurately.

[0017] In an optional implementation, the historical operation data is preprocessed to obtain historical key operation data, including:

[0018] Filter the historical operation data to obtain effective operation data;

[0019] The historical direct reduction carbon amount and the historical furnace heat index are calculated based on the effective operation data. The effective operation data, the historical direct reduction carbon amount and the historical furnace heat index constitute the historical key operation data.

[0020] The blast furnace temperature graded diagnosis and control method provided by the present invention, in addition to the directly monitored operating data, also takes into account two key parameters, namely the direct reduced carbon amount and the furnace heat index, which have a greater impact on the furnace temperature, thereby expanding the data range of the key operating data, making the furnace temperature trend prediction model more accurate, and the final predicted furnace temperature closer to the actual situation.

[0021] In an optional implementation, determining the furnace temperature change level according to the furnace temperature trend and a preset furnace temperature change classification table includes:

[0022] Calculate the difference between the predicted silicon content in molten iron and the current silicon content in molten iron as the furnace temperature trend;

[0023] The silicon content difference is compared with the furnace temperature trend range corresponding to different change levels to determine the furnace temperature change level.

[0024] The blast furnace temperature classification diagnosis and control method provided by the present invention performs detailed classification of furnace temperature changes according to the predicted furnace temperature change trend, which is beneficial to guiding operators to adopt different control measures according to different levels of furnace temperature changes, reducing furnace temperature fluctuations and maintaining the stability of blast furnace production.

[0025] In an optional embodiment, determining the current furnace condition characterization of the blast furnace according to the current production data includes:

[0026] Obtain historical data of multiple production parameters and corresponding furnace condition representation;

[0027] Analyze the relationship between the values ​​of multiple production parameters and the corresponding furnace condition representation, and determine the relationship between the level range combination of each production parameter and the furnace condition representation;

[0028] Determine the current level range combination of each production parameter according to the level range to which the current value of each production parameter in the current production data belongs;

[0029] The current furnace condition characterization of the blast furnace is determined based on the relationship between the current level range combination, the level range combination of each production parameter and the furnace condition characterization.

[0030] The blast furnace temperature graded diagnosis and control method provided by the present invention determines the influence of each production parameter on the furnace condition by analyzing the corresponding furnace condition characteristics when different production parameters have different value combinations, so as to take effective control measures according to different furnace condition characteristics, and provide guidance for furnace temperature control in the blast furnace production process.

[0031] In an optional implementation, analyzing the relationship between the values ​​of multiple production parameters and the corresponding furnace condition representations, and determining the relationship between the level range combination of each production parameter and the furnace condition representation, further includes:

[0032] According to the furnace condition characterization, the level range combinations of various production parameters are divided into coal adding combination and coal reducing combination.

[0033] The blast furnace temperature graded diagnosis and control method provided by the present invention first divides the level range combination of each production parameter into a coal adding combination and a coal reducing combination, which is beneficial to provide a general direction for the operator before performing furnace temperature control and improves the furnace temperature control efficiency.

[0034] In an optional implementation, the training process of the furnace temperature control model includes:

[0035] Obtain historical furnace temperature change levels, historical furnace condition representations, and historical adjustment amounts of corresponding preset control parameters;

[0036] The historical furnace temperature change level and historical furnace condition representation at the same time are taken as input, and the historical adjustment amount of the preset control parameters corresponding to the same time is taken as output, and the furnace temperature control model is trained.

[0037] The blast furnace temperature classification diagnosis and control method provided by the present invention makes the furnace temperature classification prediction and control process closed-loop by determining the relationship between the furnace temperature change level, the furnace condition characterization and the preset adjustment parameter adjustment amount, so as to facilitate the adoption of effective control measures according to the furnace temperature prediction results and improve the furnace temperature control efficiency.

[0038] In a second aspect, the present invention provides a blast furnace temperature classification diagnosis and control device, the device comprising:

[0039] The furnace temperature prediction module is used to obtain the current operation data of the blast furnace and use the furnace temperature trend prediction model to obtain the predicted silicon content of the molten iron of the blast furnace. The silicon content of the molten iron is used to characterize the furnace temperature.

[0040] A furnace temperature trend determination module is used to obtain the current silicon content of the molten iron and determine the furnace temperature trend based on the predicted silicon content of the molten iron and the current silicon content of the molten iron;

[0041] A change level determination module is used to determine the furnace temperature change level according to the furnace temperature trend and a preset furnace temperature change classification table;

[0042] A furnace condition characterization determination module, used to obtain current production data and determine the current furnace condition characterization of the blast furnace based on the current production data;

[0043] The furnace temperature control module is used to determine the adjustment amount of the preset control parameters using the furnace temperature control model according to the furnace temperature change level and the current furnace condition characterization.

[0044] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0045] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to cause a computer to execute the method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 1 is a schematic flow chart of a blast furnace temperature classification diagnosis and control method according to an embodiment of the present invention;

[0048] Figure 2 It is a schematic flow chart of performing hierarchical diagnosis and adjustment of blast furnace temperature by using the blast furnace temperature hierarchical diagnosis and control method according to an embodiment of the present invention;

[0049] Figure 3 is a schematic flow chart of another blast furnace temperature classification diagnosis and control method according to an embodiment of the present invention;

[0050] Figure 4 It is an image of the activation function of the neural network model in the blast furnace temperature graded diagnosis and control method according to an embodiment of the present invention.

[0051] Figure 5 1 is a schematic diagram of the training process of the furnace temperature trend prediction model in the blast furnace temperature classification diagnosis and control method according to an embodiment of the present invention;

[0052] Figure 6 Schematic diagram of a furnace temperature prediction algorithm in a blast furnace temperature classification diagnosis and control method according to an embodiment of the present invention;

[0053] Figure 7 is a structural block diagram of a blast furnace temperature classification diagnosis and control device according to an embodiment of the present invention;

[0054] Figure 8 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0056] The embodiment of the present invention provides a blast furnace temperature graded diagnosis and control method, which predicts the furnace temperature in a graded manner and determines the adjustment amount of a preset control parameter according to the prediction result, so as to achieve the effect of accurately and efficiently predicting and controlling the blast furnace temperature.

[0057] According to an embodiment of the present invention, an embodiment of a blast furnace temperature graded diagnosis and control method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0058] In this embodiment, a blast furnace temperature classification diagnosis and control method is provided, which can be used in the above-mentioned computer system. Figure 1 is a flow chart of a blast furnace temperature classification diagnosis and control method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0059] Step S101, obtaining the current operation data of the blast furnace, and using the furnace temperature trend prediction model to obtain the predicted molten iron silicon content of the blast furnace, the molten iron silicon content is used to characterize the furnace temperature.

[0060] Specifically, the actual blast furnace operation data can be collected by connecting various sensors through PLC and stored in the database. The database contains hourly data for three consecutive months of operation, the number of operating parameters reaches 200-250, and the amount of single indicator data reaches 2000-2500, and the data that meets the upper and lower limits of single indicators are screened. Starting from the blast furnace's forward state, operating parameters, upper state, lower state, and raw fuel conditions, the main factors that affect or reflect the blast furnace's thermal state are selected as operating data based on expert experience. The operating data include but are not limited to: permeability index, blast pressure, material speed, wind temperature, moisture, coal injection amount, oxygen enrichment, ore-coke ratio, gas utilization rate, furnace top temperature, furnace throat temperature, furnace hearth temperature, slag ratio, ore, coke, and clinker rate.

[0061] The furnace temperature trend prediction model is a neural network model trained with a large amount of historical data, and can predict the predicted molten iron silicon content of the blast furnace based on the operation data. The molten iron silicon content is a chemical parameter that characterizes the furnace temperature and the quality of the molten iron. In this embodiment, the molten iron silicon content is used to characterize the furnace heat. The predicted molten iron silicon content can be the predicted value of the molten iron silicon content at the next sampling moment in the preset sampling period, which is only taken as an example, but is not limited to this.

[0062] Step S102, obtaining the current silicon content of the molten iron, and determining the furnace temperature trend according to the predicted silicon content of the molten iron and the current silicon content of the molten iron.

[0063] Specifically, the current silicon content of molten iron is obtained, and the furnace temperature trend is determined according to the relationship between the predicted silicon content of molten iron and the current silicon content of molten iron. The furnace temperature trend includes: furnace temperature increase, decrease, and the degree of increase or decrease.

[0064] Step S103, determining the furnace temperature change level according to the furnace temperature trend and a preset furnace temperature change classification table.

[0065] Specifically, the relationship between the furnace temperature trend and the furnace temperature change level is clearly defined in the preset furnace temperature change classification table, so the furnace temperature change level can be directly determined based on the furnace temperature trend.

[0066] In addition to referring to the furnace temperature trend, the furnace temperature change level can also be determined in combination with the value of actual production parameters. The actual production parameters are the basis for operators to adjust the furnace temperature during the blast furnace production process, including but not limited to: air volume, pressure difference, heat load, gas utilization rate, iron quantity difference, material speed, current furnace temperature, furnace temperature trend, and average silicon content of four consecutive packages of molten iron. The furnace temperature change is further refined into different degrees of change levels based on cooling, stability, and heating, and the number of levels is appropriate to adapt to the actual furnace conditions.

[0067] Step S104, obtaining current production data, and determining the current furnace condition characterization of the blast furnace according to the current production data.

[0068] Specifically, on the basis of the classification of furnace temperature change levels, different values ​​of actual production parameters are arranged and combined to determine the specific reasons for the furnace temperature change. The current production data of the actual production parameters are obtained, and the current production furnace condition characterization of the blast furnace is determined according to the current production data, for example: the air volume is 4500, the pressure difference is 181, the heat load value is 90, the gas utilization rate is 43%, the iron amount difference is 10, the material speed is 29, the current molten iron silicon content is 0.7, the average silicon content of four consecutive molten iron bags is 0.45, and the furnace temperature trend is 0.13. The current production furnace condition is characterized by: slag skin falling off and low utilization, which is only used as an example, but not limited to this.

[0069] Step S105, determining the adjustment amount of the preset control parameter by using the furnace temperature control model according to the furnace temperature change level and the current furnace condition characterization.

[0070] Specifically, the comprehensive consideration of the furnace temperature change level and the current furnace condition characterization can accurately analyze the cause of the furnace temperature change and accurately grasp the current furnace condition, and determine the adjustment amount of the preset control parameters through the furnace temperature control model. The preset control parameters include but are not limited to: coal injection amount, wind temperature, oxygen enrichment, and coke ratio. Figure 2 As shown, it is a flow chart of using the blast furnace temperature graded diagnosis and control method to perform graded diagnosis and adjustment on the blast furnace temperature. The graded diagnosis and adjustment process is carried out in a real-time cycle.

[0071] The blast furnace temperature graded diagnosis and control method provided in this embodiment obtains accurate predicted furnace temperature by predicting the silicon content in molten iron, determines the cause of furnace temperature change by analyzing the furnace temperature change trend and furnace condition characterization, and adopts effective control measures to achieve precise control of the blast furnace temperature, avoid huge fluctuations in the furnace temperature, maintain the stability of the furnace temperature, and is conducive to the long-term stable operation of the blast furnace.

[0072] In this embodiment, a blast furnace temperature classification diagnosis and control method is provided, which can be used in the above-mentioned computer system. Figure 3 is a flow chart of a blast furnace temperature classification diagnosis and control method according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0073] Step S201, obtaining the current operation data of the blast furnace, and using the furnace temperature trend prediction model to obtain the predicted molten iron silicon content of the blast furnace, the molten iron silicon content is used to characterize the furnace temperature.

[0074] Specifically, in the above step S201, the training process of the furnace temperature trend prediction model includes:

[0075] Step S2011, acquiring historical operation data of the blast furnace, and preprocessing the historical operation data to obtain historical key operation data.

[0076] In some optional implementations, the above step S2011 includes:

[0077] Step a1, screening the historical operation data to obtain effective operation data.

[0078] Specifically, the original historical operation data of the blast furnace can be obtained by sensors and other means. There may be invalid data with large errors in the original data, so it is necessary to screen the historical operation data and retain only the valid operation data. The original data can be preprocessed by correlation analysis (such as regression equation). According to the correlation analysis results (correlation coefficient), variables with high correlation are selected as valid operation data. The calculation formula of the correlation coefficient is:

[0079]

[0080] Among them, y represents the furnace temperature, x represents the operating parameters, and x i Indicates the value of the operating parameter, R xiy Represents x i Correlation coefficient with y. It should be noted that the operating parameters of the operating data can be selected according to actual conditions, including but not limited to: permeability index, blast pressure, material speed, wind temperature, moisture, coal injection amount, oxygen enrichment, ore-coke ratio, gas utilization rate, furnace top temperature, furnace throat temperature, furnace hearth temperature, slag ratio, ore, coke, and clinker rate.

[0081] Step a2, calculating the historical direct reduction carbon amount and the historical furnace heat index based on the effective operation data, the effective operation data, the historical direct reduction carbon amount and the historical furnace heat index constitute the historical key operation data.

[0082] Specifically, the corresponding direct reduction carbon content and furnace heat index are calculated based on the effective operation data, and the calculation formula is:

[0083]

[0084] Among them, Fe 还 represents the amount of iron in reduced iron, r d Indicates the direct reduction degree, C d Indicates the amount of directly reduced carbon.

[0085] T C =C1+C2-(C3+C4+C5+C6)

[0086] Among them, T C It represents the furnace heat index, C1 represents the sensible heat brought in by blast, C2 represents the heat of carbon combustion before the tuyere, C3 represents the heat absorption of humidity decomposition, C4 represents the heat absorption of carbon melting loss, C5 represents the heat loss of cooling system, and C6 represents the heat absorption of coal powder cracking.

[0087] The effective operation data and the corresponding historical direct reduction carbon content and historical furnace heat index together constitute the key operation data, which serve as the input of the furnace temperature trend prediction model.

[0088] The blast furnace temperature graded diagnosis and control method provided in this embodiment, in addition to the directly monitored operating data, also takes into account two key parameters that have a greater impact on the furnace temperature, namely the direct reduced carbon content and the furnace heat index, thereby expanding the data range of the key operating data, making the furnace temperature trend prediction model more accurate, and the final predicted furnace temperature closer to the actual situation.

[0089] Step S2012, performing correlation analysis on the historical key operating data to obtain the lag time of each historical key operating data affecting the silicon content of molten iron.

[0090] Specifically, the historical key operation data are analyzed by correlation analysis (regression equation) to obtain the lag time of the historical key operation data affecting the silicon content of molten iron, and the historical key operation data include: sintering ore composition, coke, coal powder, heat load, gas utilization rate, fuel ratio, material speed, wind temperature, air volume, blast moisture content, coal injection amount, ore-coke ratio, furnace heat index, furnace top gas composition, furnace top temperature, slag ratio, oxygen enrichment, which are only used as examples, but not limited to this. As shown in Table 1, the lag time of each historical key operation data affecting the silicon content of molten iron, wherein the lag time is based on one furnace of iron.

[0091] Table 1

[0092] parameter Lag time (minutes) parameter Lag time (minutes) Sintered ore composition (Fe) 520 Rheumatoid arthritis 120 Coke (ash) 520 Coal injection amount 280 Coal powder (C content) 300 Coke ratio 420 Heat load 160 Heat Index (TC) 60 <![CDATA[Coal gas utilization rate (η CO )]]> 100 Top gas composition (CO) 380 Fuel ratio 100 Furnace top temperature 380 Material speed (5 batches) 120 Coke ash 520 Wind temperature 40 Slag 520 Air volume 60 Oxygen enrichment 100

[0093] Step S2013, based on the lag time of the historical key operating data affecting the silicon content of the molten iron, combined with the neural network model, a furnace temperature trend prediction model is obtained.

[0094] Specifically, based on the lag time of historical key operating data affecting the silicon content of molten iron, a neural network model is constructed:

[0095] y=f(net)

[0096]

[0097] Among them, y represents the output signal of the neural network, net represents the constructed neural network, and f(x) represents the activation function of the neural network model, such as Figure 4 The figure shows an image of an activation function, which is only used as an example but is not limited to this.

[0098] like Figure 5 As shown, it is a training flow diagram of the furnace temperature trend prediction model. The historical key operation data is divided into a training set and a test set. The neural network model is classified and trained using the training set data. The trained neural network model is tested using the test set. Each time, the sample error in the test set and the prediction hit rate of the silicon content in the molten iron need to be calculated until the sample error output in the test set is within the preset range or converges, and the prediction hit rate of the silicon content in the molten iron meets the preset requirements, and the model training process is terminated. The preset range of the sample error can be 5%, which is only used as an example, but not limited to this. The predicted value of the furnace temperature at the next sampling moment will be obtained by using the trained neural network model to predict the furnace temperature. When it actually runs to the next moment, the actual value of the furnace temperature will be directly collected. The prediction hit rate of the silicon content in the molten iron is calculated based on the predicted value and the actual value of the furnace temperature to verify the prediction hit rate of the neural network model at this time. If the prediction hit rate does not meet the preset requirements, the latest key operation data and the historical key operation data need to be combined into a sample set to retrain the neural network model. Dynamically adjust the neural network model to ensure that the prediction hit rate of the neural network model always meets the preset requirements and maintain production stability.

[0099] like Figure 6 As shown, this is a schematic diagram of the furnace temperature prediction algorithm, where the node function value in the neural network model is:

[0100] z1=f(a1*w4+a2w2+a3+w3)

[0101] z2=f(a1*w4+a2w5+a3+w6)

[0102] The node error is expressed as:

[0103] E=f(Σa*wb)

[0104] Among them, a represents the activation vector column of each neuron (a1, a2, ..., a n ), w represents the weight coefficient vector column of each neuron (w1,w2,...,w n), b represents the bias vector column of the neuron (b1, b2, ..., b n ), z represents the output value vector column of the neuron (z1,z2,...,z n ).

[0105] Error output of the training sample at point p:

[0106]

[0107] Among them, E(k) represents the error function E at the kth step of learning, is the expected output of the jth output node of the network, y p,j (k) is the actual output of the jth output node of the network at the kth step; P is the number of training samples, and N is the number of nodes in the output layer of the neural network.

[0108] For example, at 12:00, the trained neural network model is used to predict the silicon content of molten iron at 13:00, and the predicted value of the silicon content of molten iron is obtained. When the blast furnace runs to 13:00, the actual value of the silicon content of molten iron in the blast furnace is collected, and the prediction hit rate of the silicon content of molten iron is calculated using the following formula:

[0109]

[0110] If the calculated forecast hit rate of the silicon content in molten iron meets the preset requirements (for example, the forecast hit rate of the silicon content in molten iron is not less than 95%, which is only used as an example, but not limited to this), there is no need to retrain the neural network model; if the calculated forecast hit rate of the silicon content in molten iron does not meet the requirements, the key operating data at 13:00 and before are used as the sample set, and the neural network model is retrained until the sample error output of the trained neural network model is within the preset range or converges, and the forecast hit rate of the silicon content in molten iron meets the preset requirements.

[0111] The blast furnace temperature graded diagnosis and control method provided by the present invention analyzes the lag time of the key operating data affecting the silicon content of molten iron, combines the neural network model to determine the furnace temperature trend prediction model, takes into account the lag time of the key operating data affecting the furnace temperature, and predicts the furnace temperature more accurately.

[0112] Step S202, obtain the current silicon content of molten iron, and determine the furnace temperature trend according to the predicted silicon content of molten iron and the current silicon content of molten iron. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0113] Step S203, determining the furnace temperature change level according to the furnace temperature trend and a preset furnace temperature change classification table.

[0114] Specifically, the above step S203 includes:

[0115] Step S2031, calculating the difference between the predicted silicon content in the molten iron and the current silicon content in the molten iron as the furnace temperature trend.

[0116] Specifically, the predicted silicon content of molten iron is subtracted from the current silicon content of molten iron to obtain the silicon content difference. Since the silicon content of molten iron can characterize the furnace temperature, the silicon content difference can be used to characterize the furnace temperature trend.

[0117] Step S2032, comparing the silicon content difference with the furnace temperature trend range corresponding to different change levels to determine the furnace temperature change level.

[0118] Specifically, according to the actual production situation, the corresponding relationship between the furnace temperature change level and the silicon content difference range is preset in advance. For example, when the furnace temperature change level is level one, the corresponding silicon content difference range is: S i -S i-1 ≥0.12; When the furnace temperature change level is level 2, the corresponding silicon content difference range is: 0.01≥S i -S i-1 ≥0.12; When the furnace temperature change level is level 3, the corresponding silicon content difference range is: -0.01≥S i -S i-1 ≥0.01; When the furnace temperature change level is level 4, the corresponding silicon content difference range is: -0.12≤S i -S i-1 ≤-0.01; When the furnace temperature change level is level 5, the corresponding silicon content difference range is: S i -S i-1 ≤-0.12. The number of furnace temperature change levels and the silicon content difference range corresponding to each level can be determined according to actual production conditions, which is only used as an example here, but is not limited to this.

[0119] In addition to determining the furnace temperature change level based on the silicon content difference, the furnace temperature change level can also be determined more accurately in combination with the value of the production parameter. Table 2 shows a classification table for determining the furnace temperature change level based on the production parameters and the silicon content difference.

[0120] Table 2

[0121]

[0122] The blast furnace temperature classification diagnosis and control method provided in this embodiment classifies the furnace temperature changes in detail according to the predicted furnace temperature change trend, which is beneficial to guide operators to adopt different control measures according to different levels of furnace temperature changes, reduce furnace temperature fluctuations, and maintain the stability of blast furnace production.

[0123] Step S204, obtaining current production data, and determining the current furnace condition characterization of the blast furnace according to the current production data.

[0124] Specifically, the above step S204 includes:

[0125] Step S2041, obtaining historical data of multiple production parameters and corresponding furnace condition representations.

[0126] Step S2042, analyzing the relationship between the values ​​of multiple production parameters and the corresponding furnace condition representations, and determining the relationship between the level range combination of each production parameter and the furnace condition representation.

[0127] In some optional embodiments, analyzing the relationship between the values ​​of multiple production parameters and the corresponding furnace condition representations, and determining the relationship between the level range combination of each production parameter and the furnace condition representation, further includes:

[0128] According to the furnace condition characterization, the level range combinations of various production parameters are divided into coal adding combination and coal reducing combination.

[0129] Specifically, the possible value ranges of each production parameter in Table 2 are arranged and combined to obtain the specific reasons for the furnace temperature change, so as to give the furnace condition characterization corresponding to each arrangement and combination, and further distinguish them according to the addition and reduction of coal, as shown in Table 3, which is the corresponding relationship between each arrangement and combination in the coal addition combination and the furnace condition characterization, and as shown in Table 4, which is the corresponding relationship between each arrangement and combination in the coal reduction combination and the furnace condition characterization.

[0130] Table 3

[0131] Serial number Permutations and combinations Furnace Condition Characterization 1 A2-B2-C1-D2-E2-F2-G1-H2-I1 The slag skin falls off and the utilization is low 2 A2-B1-C1-D3-E1-F3-G3-H5-I1 Slag skin falls off, utilization is low, furnace temperature drops 3 A2-B2-C2-D2-E3-F3-G1-H2-I1 Low utilization, less iron output, and rapid drop in furnace temperature 4 A2-B1-C1-D2-E3-F3-G3-H3-I1 Low utilization, less iron output, medium and decreasing furnace temperature 5 A2-B1-C2-D2-E1-F4-G3-H4-I2 Low utilization, fast material speed, high iron output, medium and decreasing furnace temperature 6 A2-B1-C1-D1-E2-F4-G3-H4-I2 The slag skin falls off, the material is fast, the furnace temperature is low and decreases 7 A2-B1-C2-D1-E2-F5-G2-H2-I1 The material speed is too fast, and the furnace temperature is rising 8 A2-B1-C2-D1-E2-F4-G3-H4-I1 Fast material speed, lower furnace temperature 9 A2-B2-C2-D1-E2-F3-G3-H4-I2 Furnace temperature medium, decreasing 10 A2-B1-C2-D1-E2-F3-G4-H5-I2 The furnace temperature is low and the drop is too large 11 A2-B2-C2-D1-E2-F5-G2-H4-I1 The material speed is too fast, the furnace temperature is above average and decreasing 12 A2-B1-C1-D1-E2-F3-G2-H4-I1 The slag skin falls off, the iron output is small, and the furnace temperature is medium and decreasing. 13 A2-B2-C2-D1-E2-F4-G2-H4-I1 Fast material speed, less iron output, medium and decreasing furnace temperature 14 A2-B2-C2-D1-E2-F4-G4-H5-I2 The material speed is fast and the furnace temperature drops too quickly 15 A2-B2-C2-D1-E2-F5-G4-H5-I2 The material speed is too fast, the furnace temperature is low and falling 16 A2-B1-C2-D1-E2-F5-G4-H3-I3 The material speed is too fast, and the furnace temperature is continuously low and decreasing. 17 A2-B1-C1-D1-E1-F3-G3-H5-I1 Slag skin falls off, more iron is discharged, and the furnace temperature drops 18 A2-B1-C1-D2-E1-F4-G3-H2-I1 Slag skin falls off, utilization is low, more iron is produced, material speed is fast, furnace temperature rises 19 A2-B2-C1-D1-E2-F3-G2-H4-I1 The slag skin falls off and the furnace temperature is medium and decreasing 20 A2-B2-C2-D1-E3-F3-G3-H2-I2 The amount of iron output is small, but the furnace temperature is low and rising 21 A2-B1-C2-D1-E2-F3-G4-H5-I2 The furnace temperature is low and greatly reduced 22 A2-B2-C1-D1-E2-F4-G3-H2-I2 The slag skin falls off, the material speed is fast, and the furnace temperature is medium and rising 23 A2-B2-C1-D1-E2-F4-G4-H5-I3 The slag skin falls off, the material speed is fast, the furnace temperature is continuously low and drops too fast 24 A2-B2-C2-D1-E2-F3-G3-H2-I3 The furnace temperature is continuously low and then increases 25 A2-B1-C2-D1-E2-F4-G3-H2-I2 Fast material speed, low and rising furnace temperature 26 A2-B1-C2-D1-E2-F4-G2-H2-I2 Fast material speed, medium and rising furnace temperature 27 A2-B1-C2-D1-E2-F4-G4-H4-I2 Fast material speed, low furnace temperature and decreasing 28 A2-B2-C2-D2-E1-F3-G4-H2-I3 Low utilization, high iron output, and continuous low furnace temperature 29 A2-B2-C2-D1-E1-F5-G4-H4-I3 The material speed is too fast, the iron output is too much, the furnace temperature is continuously low, and the temperature decreases. 30 A2-B1-C2-D1-E3-F3-G2-H4-I1 The iron output is small, the furnace temperature is medium and decreasing, but the high temperature continues 31 A2-B1-C2-D1-E2-F4-G3-H5-I1 The material speed is fast, the furnace temperature is medium and drops too fast 32 A2-B1-C2-D1-E1-F4-G2-H3-I2 More iron output, fast material speed, medium furnace temperature 33 A2-B1-C2-D1-E2-F5-G4-H5-I3 The material speed is too fast, the furnace temperature is continuously low and drops too fast 34 A2-B1-C2-D1-E2-F4-G4-H3-I3 Fast material speed and low furnace temperature

[0132] Table 4

[0133]

[0134] The blast furnace temperature graded diagnosis and control method provided in this embodiment first divides the level range combination of each production parameter into a coal addition combination and a coal reduction combination, which is beneficial for providing a general direction for the operator before performing furnace temperature control and improving the efficiency of furnace temperature control.

[0135] Step S2043, determining the current level range combination of each production parameter according to the level range to which the current value of each production parameter in the current production data belongs.

[0136] Step S2044, determining the current furnace condition characterization of the blast furnace according to the relationship between the current level range combination, the level range combination of each production parameter and the furnace condition characterization.

[0137] Specifically, according to the current value of each production parameter in the current production data, Table 3 and Table 4 are searched to determine the level range combination (the permutation and combination items in Table 3 and Table 4) to which the current production data belongs, and then the corresponding current furnace condition characterization is determined.

[0138] The blast furnace temperature graded diagnosis and control method provided in this embodiment determines the influence of each production parameter on the furnace condition by analyzing the corresponding furnace condition characteristics when different production parameters have different value combinations, so as to take effective control measures according to different furnace condition characteristics, and provide guidance for furnace temperature control in the blast furnace production process.

[0139] Step S205 , according to the furnace temperature change level and the current furnace condition characterization, the furnace temperature control model is used to determine the adjustment amount of the preset control parameter.

[0140] Specifically, the training process of the furnace temperature control model in the above step S205 includes:

[0141] Step S2051, obtaining historical furnace temperature change levels, historical furnace condition representations, and corresponding historical adjustment amounts of preset control parameters.

[0142] Specifically, the furnace temperature control model is trained using historical data. In this embodiment, the historical data includes: historical furnace temperature change levels, historical furnace condition characterizations, and corresponding historical adjustment amounts of preset control parameters. The historical adjustment amounts of preset control parameters are used to characterize the adjustment means and the adjustment range. There is no limit on the number of preset control parameters. The adjustment means include, but are not limited to: increasing or decreasing the amount of coal injection, increasing or decreasing the wind temperature, increasing or decreasing the amount of oxygen enrichment, adjusting the coke ratio, and other measures.

[0143] Step S2052, taking the historical furnace temperature change level and historical furnace condition representation at the same time as input, and taking the historical adjustment amount of the preset control parameter corresponding to the same time as output, to train and obtain a furnace temperature control model.

[0144] Specifically, the historical furnace temperature change level and historical furnace condition characterization at the same time are taken as input, and the historical adjustment amount of the preset control parameters corresponding to the same time is taken as output, and the furnace temperature control model is trained. The furnace temperature control model characterizes the adjustment amount of the preset control parameters corresponding to different furnace temperature change levels and furnace condition characterizations, as shown in Table 5.

[0145] Table 5

[0146]

[0147] When the permutations and combinations in Table 3 or Table 4 appear, the operator is promptly prompted to observe the furnace condition characterization. The operator determines whether to add or reduce coal based on the furnace condition characterization, and determines the furnace temperature change level based on the furnace temperature prediction results. According to the furnace condition characterization and the furnace temperature change level, the furnace temperature control model is used to determine the adjustment amount of the preset control parameters. When the change level falls within the range described in Table 2, the operation is adjusted according to the adjustment rules and measures described in Table 5 to cope with the furnace temperature change. Table 2 covers most of the situations in daily operations. From the perspective of data combinations, other combinations may appear, but from the perspective of production process characteristics, other situations other than Table 2 will basically not appear. Other situations are abnormal situations and require manual intervention once they occur.

[0148] The blast furnace temperature graded diagnosis and control method provided in this embodiment makes the furnace temperature graded prediction and control process closed-loop by determining the relationship between the furnace temperature change level, the furnace condition characterization and the preset adjustment parameter adjustment amount, so as to facilitate the adoption of effective control measures according to the furnace temperature prediction results and improve the furnace temperature control efficiency.

[0149] In this embodiment, a blast furnace temperature hierarchical diagnosis and control device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be repeated hereafter. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0150] This embodiment provides a blast furnace temperature classification diagnosis and control device, such as Figure 7 As shown, including:

[0151] The furnace temperature prediction module 701 is used to obtain the current operation data of the blast furnace and obtain the predicted silicon content of the molten iron of the blast furnace using the furnace temperature trend prediction model. The silicon content of the molten iron is used to characterize the furnace temperature.

[0152] The furnace temperature trend determination module 702 is used to obtain the current silicon content of the molten iron and determine the furnace temperature trend according to the predicted silicon content of the molten iron and the current silicon content of the molten iron.

[0153] The change level determination module 703 is used to determine the furnace temperature change level according to the furnace temperature trend and a preset furnace temperature change classification table.

[0154] The furnace condition characterization determination module 704 is used to obtain current production data and determine the current furnace condition characterization of the blast furnace according to the current production data.

[0155] The furnace temperature control module 705 is used to determine the adjustment amount of the preset control parameters using the furnace temperature control model according to the furnace temperature change level and the current furnace condition characterization.

[0156] In some optional implementations, the furnace temperature prediction module 701 includes:

[0157] The data preprocessing unit is used to obtain the historical operation data of the blast furnace and preprocess the historical operation data to obtain historical key operation data.

[0158] The correlation analysis unit is used to perform correlation analysis on historical key operating data to obtain the lag time of each historical key operating data affecting the silicon content of molten iron.

[0159] The furnace temperature prediction model training unit is used to obtain a furnace temperature trend prediction model based on the lag time of the historical key operating data affecting the silicon content of molten iron and the neural network model.

[0160] In some optional implementations, the data preprocessing unit includes:

[0161] The data screening subunit is used to screen the historical operation data to obtain effective operation data.

[0162] The key parameter calculation subunit is used to calculate the historical direct reduction carbon content and the historical furnace heat index based on the effective operation data. The effective operation data, the historical direct reduction carbon content and the historical furnace heat index constitute the historical key operation data.

[0163] In some optional implementations, the change level determination module 703 includes:

[0164] The furnace temperature trend calculation unit is used to calculate the silicon content difference between the predicted molten iron silicon content and the current molten iron silicon content as the furnace temperature trend.

[0165] The change level determination unit is used to compare the silicon content difference with the furnace temperature trend range corresponding to different change levels to determine the furnace temperature change level.

[0166] In some optional embodiments, the furnace condition characterization determination module 704 includes:

[0167] The historical production data acquisition unit is used to acquire historical data of multiple production parameters and corresponding furnace condition representations.

[0168] The furnace condition representation relationship determination unit is used to analyze the relationship between the values ​​of multiple production parameters and the corresponding furnace condition representations, and determine the relationship between the level range combination of each production parameter and the furnace condition representation.

[0169] The current production level range determination unit is used to determine the current level range combination of each production parameter according to the level range to which the current value of each production parameter in the current production data belongs.

[0170] The current furnace condition characterization determining unit is used to determine the current furnace condition characterization of the blast furnace according to the current level range combination, the relationship between the level range combination of each production parameter and the furnace condition characterization.

[0171] In some optional embodiments, the furnace temperature control module 705 includes:

[0172] The historical data acquisition unit is used to obtain historical furnace temperature change levels, historical furnace condition representations and corresponding historical adjustment amounts of preset control parameters.

[0173] The furnace temperature control model training unit is used to take the historical furnace temperature change level and historical furnace condition representation at the same time as input, and the historical adjustment amount of the preset control parameter corresponding to the same time as output, to train the furnace temperature control model.

[0174] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0175] The blast furnace temperature graded diagnosis and control device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0176] The embodiment of the present invention also provides a computer device having the above Figure 7 The blast furnace temperature grading diagnosis and control device shown.

[0177] See also Figure 8 , Figure 8 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 8 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8 A processor 10 is taken as an example.

[0178] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0179] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0180] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0181] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0182] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0183] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0184] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A blast furnace temperature classification diagnosis and control method, characterized in that: The method comprises: Acquire current operation data of the blast furnace, and use a furnace temperature trend prediction model to obtain a predicted molten iron silicon content of the blast furnace, wherein the molten iron silicon content is used to characterize the furnace temperature; Obtaining the current silicon content of the molten iron, and determining the furnace temperature trend according to the predicted silicon content of the molten iron and the current silicon content of the molten iron; Determine the furnace temperature change level according to the furnace temperature trend and a preset furnace temperature change classification table; Acquiring current production data, and determining a current furnace condition representation of the blast furnace according to the current production data; According to the furnace temperature change level and the current furnace condition characterization, the adjustment amount of the preset control parameter is determined using the furnace temperature control model.

2. The method according to claim 1, characterized in that: The training process of the furnace temperature trend prediction model includes: Acquire historical operation data of the blast furnace, and preprocess the historical operation data to obtain historical key operation data; Performing correlation analysis on the historical key operating data to obtain the lag time of each historical key operating data affecting the silicon content of molten iron; Based on the lag time of the historical key operating data affecting the silicon content in molten iron, combined with the neural network model, a furnace temperature trend prediction model is obtained.

3. The method according to claim 2, characterized in that The preprocessing of the historical operation data to obtain historical key operation data includes: Screening the historical operation data to obtain effective operation data; The historical direct reduction carbon amount and the historical furnace heat index are calculated according to the effective operation data, and the effective operation data, the historical direct reduction carbon amount and the historical furnace heat index constitute the historical key operation data.

4. The method according to claim 1, characterized in that Determining the furnace temperature change level according to the furnace temperature trend and a preset furnace temperature change classification table includes: Calculate the difference between the predicted silicon content of molten iron and the current silicon content of molten iron; The silicon content difference is compared with the furnace temperature trend range corresponding to different change levels to determine the furnace temperature change level.

5. The method according to claim 1, characterized in that Determining the current furnace condition characterization of the blast furnace according to the current production data includes: Obtain historical data of multiple production parameters and corresponding furnace condition representation; Analyze the relationship between the values ​​of multiple production parameters and the corresponding furnace condition representation, and determine the relationship between the level range combination of each production parameter and the furnace condition representation; Determine the current level range combination of each production parameter according to the level range to which the current value of each production parameter in the current production data belongs; The current furnace condition characterization of the blast furnace is determined according to the relationship between the current level range combination, the level range combination of each production parameter and the furnace condition characterization.

6. The method according to claim 5, characterized in that Analyze the relationship between the values ​​of multiple production parameters and the corresponding furnace condition characterization, determine the relationship between the level range combination of each production parameter and the furnace condition characterization, and also include: According to the furnace condition characterization, the level range combinations of various production parameters are divided into coal adding combination and coal reducing combination.

7. The method according to claim 1, characterized in that The training process of the furnace temperature control model includes: Obtain historical furnace temperature change levels, historical furnace condition representations, and historical adjustment amounts of corresponding preset control parameters; The historical furnace temperature change level and historical furnace condition representation at the same time are taken as input, and the historical adjustment amount of the preset control parameters corresponding to the same time is taken as output, and the furnace temperature control model is trained.

8. A blast furnace temperature classification diagnosis and control device, characterized in that: The device comprises: A furnace temperature prediction module is used to obtain the current operation data of the blast furnace and obtain the predicted silicon content of the molten iron of the blast furnace using the furnace temperature trend prediction model, wherein the silicon content of the molten iron is used to characterize the furnace temperature; A furnace temperature trend determination module, used to obtain the current silicon content of the molten iron, and determine the furnace temperature trend according to the predicted silicon content of the molten iron and the current silicon content of the molten iron; A change level determination module, used to determine the furnace temperature change level according to the furnace temperature trend and a preset furnace temperature change classification table; A furnace condition characterization determination module, used for acquiring current production data and determining the current furnace condition characterization of the blast furnace according to the current production data; The furnace temperature control module is used to determine the adjustment amount of the preset control parameter by using the furnace temperature control model according to the furnace temperature change level and the current furnace condition characterization.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images