Method and device for controlling the combustion of a blast furnace hot blast stove

Abstract

The application discloses a kind of blast furnace hot blast stove combustion heat accumulation control method and device, comprising: monitoring the action of each valve of hot blast stove, when detecting the combustion start signal, start combustion control, set initial gas flow according to the historical combustion data of hot blast stove, and gas is transported to hot blast stove according to initial gas flow;Real-time combustion data of hot blast stove is collected using callback function and time control function, and real-time combustion data is calculated, to obtain periodic combustion data;According to the periodic combustion data, the waste gas temperature rising curve is fitted, the weight of each calculation factor is adjusted when calculating the waste gas temperature rising curve through the weight calculation model, until the waste gas temperature rising curve meets the preset hit rate, the waste gas temperature rising trend is calculated;According to waste gas temperature rising trend, obtain predicted combustion time, compare predicted combustion time and preset combustion time, and adjust the gas flow of current time.The application can improve the thermal efficiency of hot blast stove combustion, and then provide continuous and stable high-temperature hot blast.

Description

Technical Field

[0001] This invention relates to the field of blast furnace ironmaking, and more particularly to a method and apparatus for controlling combustion heat storage in blast furnace hot blast stoves. Background Technology

[0002] This section is intended to provide background or context for embodiments of the present invention. The description herein is not intended to imply that it is prior art simply because it is included in this section.

[0003] The blast furnace hot blast stove is an important heat exchange device in the blast furnace ironmaking process, providing a continuous and stable high-temperature blast (around 1200 degrees Celsius) to support the reduction reaction in the blast furnace ironmaking process. In order to provide a continuous and stable high-temperature blast, the hot blast stove needs to have good heat storage capacity and store a large amount of heat during the furnace firing process, so that it can provide heat for a long time to heat the cold blast during the blasting process.

[0004] To maintain production rhythm and ensure stable hot blast stove conditions, the combustion and air supply times are generally kept relatively stable. This necessitates a stable heat storage process in the hot blast stove. As a crucial indicator of heat storage capacity, exhaust gas temperature is required to remain stable during actual combustion, reaching the designated temperature within the set combustion time. Once the designated temperature is reached, if the blast furnace foreman does not require a furnace change, low-volume combustion must continue to maintain heat storage.

[0005] Due to the nature of the hot blast stove's operation, the air supply cannot be interrupted. Therefore, in the traditional two-burn-one-supplier operation mode, during the furnace replacement period of the first furnace (the one that starts burning first when two hot blast stoves are burning), only one of the three hot blast stoves is burning. At this time, the main gas flow is excessive, and the gas flow of the subsequent furnace needs to be increased. This results in inconsistent thermal efficiency in the hot blast stove during the heat storage process. The heat storage efficiency is high in the early stage of combustion, but in the later stage of combustion, due to the increase in exhaust gas temperature, the heat carried away is also higher, so the heat storage efficiency is lower towards the end of combustion. Summary of the Invention

[0006] This invention provides a method for controlling the combustion heat storage of a blast furnace hot blast stove, used to provide a continuous and stable high-temperature hot blast and improve the combustion thermal efficiency of the hot blast stove. The method includes:

[0007] Monitor the operation of each valve in the hot blast stove, and start combustion control when a combustion start signal is detected;

[0008] Acquire historical combustion data of the hot blast stove, set the initial gas flow rate based on the historical combustion data of the hot blast stove, and deliver gas to the hot blast stove according to the initial gas flow rate;

[0009] Real-time combustion data of the hot air furnace is collected using callback functions and time control functions, and periodic combustion data is calculated based on the real-time combustion data.

[0010] The exhaust gas temperature rise curve is fitted based on the periodic combustion data. The weight of each calculation factor is adjusted when fitting the exhaust gas temperature rise curve using a weight calculation model until the exhaust gas temperature rise curve meets the preset hit rate. The exhaust gas temperature rise trend is calculated based on the exhaust gas temperature rise curve. The weight calculation model is trained by a machine learning model using historical combustion data and is used to adjust the weight of each calculation factor when fitting the exhaust gas temperature rise curve.

[0011] Based on the trend of exhaust gas temperature rise, the predicted combustion time is obtained. The predicted combustion time is compared with the preset combustion time, and the gas flow rate at the current moment is adjusted according to the comparison results to maintain the exhaust gas temperature within the preset exhaust gas temperature range.

[0012] This invention also provides a combustion heat storage control device for a blast furnace hot blast stove, used to provide continuous and stable high-temperature hot blast and improve the combustion thermal efficiency of the hot blast stove. The device includes:

[0013] The monitoring module is used to monitor the operation of each valve in the hot blast stove. When a combustion start signal is detected, combustion control is initiated.

[0014] The flow rate determination module is used to acquire historical combustion data of the hot blast stove, set the initial gas flow rate based on the historical combustion data of the hot blast stove, and deliver gas to the hot blast stove according to the initial gas flow rate.

[0015] The calculation module is used to collect real-time combustion data of the hot blast stove using callback functions and time control functions, and calculate periodic combustion data based on the real-time combustion data;

[0016] The weight adjustment module is used to fit the exhaust gas temperature rise curve based on the periodic combustion data. It adjusts the weight of each calculation factor when fitting the exhaust gas temperature rise curve through the weight calculation model until the exhaust gas temperature rise curve meets the preset hit rate. It calculates the exhaust gas temperature rise trend based on the exhaust gas temperature rise curve. The weight calculation model is trained by the machine learning model using historical combustion data and is used to adjust the weight of each calculation factor when fitting the exhaust gas temperature rise curve.

[0017] The flow rate adjustment module is used to obtain the predicted combustion time based on the temperature rise trend of the exhaust gas, compare the predicted combustion time with the preset combustion time, and adjust the gas flow rate at the current moment according to the comparison result to maintain the exhaust gas temperature within the preset exhaust gas temperature range.

[0018] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described blast furnace hot blast stove combustion heat storage control method.

[0019] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described blast furnace hot blast stove combustion heat storage control method.

[0020] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described blast furnace hot blast stove combustion heat storage control method.

[0021] In this embodiment of the invention, the operation of each valve in the hot blast stove is monitored. When a combustion start signal is detected, combustion control is initiated. Historical combustion data of the hot blast stove is acquired, and an initial gas flow rate is set based on this data. Gas is then supplied to the hot blast stove according to the initial gas flow rate. Real-time combustion data of the hot blast stove is collected using callback and timing functions, and periodic combustion data is calculated based on this data. An exhaust gas temperature rise curve is fitted based on the periodic combustion data. The weights of each calculation factor are adjusted using a weighted calculation model until the exhaust gas temperature rise curve meets a preset hit rate. The exhaust gas temperature rise trend is calculated based on the exhaust gas temperature rise curve. The weighted calculation model is trained on a machine learning model using historical combustion data and is used to adjust the weights of each calculation factor when fitting the exhaust gas temperature rise curve. Based on the exhaust gas temperature rise trend, a predicted combustion time is obtained. The predicted combustion time is compared with a preset combustion time, and the gas flow rate at the current moment is adjusted based on the comparison result to maintain the exhaust gas temperature within a preset range. In this way, by calculating historical combustion data, collecting real-time combustion data, and using machine models to formulate corresponding gas flow strategies and continuously adjusting the gas flow, possible errors in manual calculations can be avoided, effectively improving the combustion thermal efficiency of the hot blast stove. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0023] Figure 1 This is a flowchart of the combustion heat storage control method for a blast furnace hot blast stove provided in an embodiment of the present invention;

[0024] Figure 2 This is an example diagram of the fitted exhaust gas temperature rise curve provided in an embodiment of the present invention;

[0025] Figure 3 This is an example diagram illustrating the calculation of the exhaust gas temperature rise trend after adjusting the weights, provided in an embodiment of the present invention.

[0026] Figure 4 This is an example diagram of the predicted exhaust gas temperature during the combustion time provided in an embodiment of the present invention;

[0027] Figure 5 This is a schematic diagram of the combustion heat storage control device for a blast furnace hot blast stove provided in an embodiment of the present invention;

[0028] Figure 6 This is a structural block diagram of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0030] In this document, the term "and / or" merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0031] In the description of this specification, the terms "comprising," "including," "having," and "containing" are open-ended terms, meaning that they include but are not limited to. The terms "an embodiment," "a specific embodiment," "some embodiments," and "for example," etc., refer to specific features, structures, or characteristics described in connection with that embodiment or example that are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. The order of steps involved in the various embodiments is used to illustrate the implementation of this application, and the order of steps is not limited and can be adjusted appropriately as needed.

[0032] The thermal efficiency of a hot blast stove is inconsistent throughout the heat storage process. It is high in the early stages of combustion, but decreases towards the end due to the increased exhaust gas temperature and the resulting heat loss. Furthermore, the ring gas pressure fluctuates significantly during furnace switching. To maintain high efficiency and stable ring pressure during the hot blast stove's heat storage process, it is necessary to divide the process into multiple combustion stages. Different gas volumes are used in different stages to ensure the exhaust gas temperature reaches the set temperature within the designated combustion time, thus meeting the blast requirements for the next stage of hot blast stove operation.

[0033] As the gas quality (i.e., the calorific value of the blast furnace gas produced by the blast furnace), ambient temperature, gas and air temperature after heat exchange, oxygen enrichment and other conditions are constantly changing, the working conditions of the hot blast stove are also changing. In order to stabilize heat storage and maximize the utilization of gas combustion, manual combustion and traditional model control methods are no longer applicable. A more intelligent furnace model is needed to participate in gas flow control, and more intelligent parameter adjustment is also needed to ensure the heat storage of the hot blast stove.

[0034] Based on this, embodiments of the present invention provide a method for controlling combustion heat storage in a blast furnace hot blast stove, such as... Figure 1 As shown, it includes:

[0035] Step 101: Monitor the operation of each valve in the hot blast stove. When a combustion start signal is detected, start combustion control.

[0036] Step 102: Obtain historical combustion data of the hot blast stove, set the initial gas flow rate based on the historical combustion data of the hot blast stove, and supply gas to the hot blast stove according to the initial gas flow rate;

[0037] Step 103: Collect real-time combustion data of the hot air furnace using callback functions and time control functions, and calculate periodic combustion data based on the real-time combustion data;

[0038] Step 104: Fit the exhaust gas temperature rise curve based on the periodic combustion data, and adjust the weight of each calculation factor when fitting the exhaust gas temperature rise curve using a weight calculation model until the exhaust gas temperature rise curve meets the preset hit rate. Calculate the exhaust gas temperature rise trend based on the exhaust gas temperature rise curve. The weight calculation model is trained from historical combustion data using a machine learning model and is used to adjust the weight of each calculation factor when fitting the exhaust gas temperature rise curve.

[0039] Step 105: Based on the trend of exhaust gas temperature rise, obtain the predicted combustion time, compare the predicted combustion time with the preset combustion time, and adjust the gas flow rate at the current moment according to the comparison result to maintain the exhaust gas temperature within the preset exhaust gas temperature range.

[0040] The heat storage in a hot blast stove comes entirely from the heat generated by the combustion of oxygen in the blast furnace gas and combustion air. The rate of heat storage depends on the calorific value and flow rate of the gas. Due to fluctuations in blast furnace production, the calorific value of the gas produced also fluctuates continuously. Furthermore, because the thermal efficiency of the hot blast stove varies throughout the entire heat storage process, more precise gas flow control is required to maximize heat storage efficiency. The blast furnace hot blast stove combustion heat storage control method proposed in this invention determines the gas flow rate and continuously adjusts it during combustion to achieve the most efficient combustion, effectively improving the hot blast stove's combustion thermal efficiency by more than 2%. In addition, due to the constantly changing furnace conditions, this invention uses a machine learning model to optimize parameters. Training and validation sets are generated from the combustion process, and the parameters are optimized through the machine learning model to eliminate the need for manual intervention.

[0041] In practice, after receiving the hot blast stove combustion signal, it is necessary to confirm the hardware status of the hot blast stove to ensure that it can operate normally. The relevant hardware status includes:

[0042] Branch gas shut-off valve: determines whether the gas flow valve is open.

[0043] Branch gas regulating valve: regulates the gas flow rate.

[0044] Branch gas flow rate setting value: The gas flow rate is adjusted by combining the gas flow rate feedback value and the PID system.

[0045] Branch gas flow rate opening feedback value: Combines the gas flow rate opening set value with the PID system to adjust the gas flow rate.

[0046] Branch air shut-off valve: determines whether the air flow valve is open.

[0047] Branch air regulating valve: Adjusts the air flow rate.

[0048] Branch pipe airflow opening setpoint: The airflow is adjusted by combining the airflow opening feedback value and the PID system.

[0049] Branch pipe airflow opening feedback value: Combines the airflow opening setpoint with the PID system to adjust the airflow.

[0050] In one embodiment, the valves of the hot blast stove include: a gas shut-off valve, an air shut-off valve, an exhaust gas shut-off valve, a nitrogen purging valve, and a pressurizing valve.

[0051] In one embodiment, setting the initial gas flow rate based on historical combustion data of the hot blast stove includes:

[0052] Based on historical combustion data, calculate the average gas flow rate during the first half of the furnace firing process, when thermal efficiency is highest.

[0053] The average gas flow rate in the first half of the process, where thermal efficiency is highest, is set as the initial gas flow rate.

[0054] In one embodiment, when the air supply duration or cold air flow rate in the previous round of combustion in the hot blast stove exceeds a preset standard, an air supply coefficient is added when calculating the initial gas flow rate for the current round of combustion.

[0055] If the air supply duration or cold air flow rate in the previous round of combustion in the hot blast stove is lower than the preset standard, the initial gas flow rate in the current round of combustion will be reduced.

[0056] In one embodiment, the combustion data includes exhaust gas temperature, gas flow rate, and air flow rate.

[0057] In practice, the hot blast stove combustion (heat storage) process can be divided into the following stages according to the time sequence: initial combustion period, exhaust gas temperature management period, preheater replacement period, final combustion period, and final combustion period. Generally speaking, the closer to the initial stage, the higher the combustion thermal efficiency; the closer to the final stage, the lower the combustion thermal efficiency. To achieve the most efficient combustion, different gas setting strategies need to be adopted for different combustion stages.

[0058] In one specific embodiment, during the initial combustion period, since there is no gas temperature rise curve yet, the initial basic gas flow rate is set according to the average actual blast furnace gas flow rate of the first half of the first six effective combustion processes, where thermal efficiency is highest. The initial gas flow rate is calculated using the following formula:

[0059]

[0060] Gas Ini Gas is the blast furnace gas flow rate, i.e., the initial gas flow rate. v The average gas flow rate during the first half of a previous effective combustion cycle is represented by SI; the air supply coefficient is represented by GI; and the gas calorific value coefficient is represented by GI.

[0061] If the previous air supply duration or cold air flow rate exceeded the standard, the current hot blast stove is in a state of insufficient air supply. During the initial combustion period, an air supply coefficient needs to be adjusted to heat up the hot blast stove as quickly as possible. Conversely, if the previous air supply duration and cold air flow rate were low, the required gas flow rate during the initial combustion period of this round of stove firing will be less.

[0062] The blast furnace gas burned in the hot blast stoves generally comes from the blast furnace gas produced by multiple blast furnaces in the plant. After entering the ring network, the blast furnace gas is used by the hot blast stoves. As the blast furnace conditions change, the calorific value of the blast furnace gas also changes. A higher calorific value requires a smaller gas flow rate, and vice versa.

[0063] In one specific embodiment, a callback function and a high-precision time control function are used to obtain periodic combustion data. The sampling time is 250ms, with four samples per second. The arithmetic average of the sampled exhaust gas temperature, gas flow rate, and air flow rate is calculated to obtain the arithmetic average of exhaust gas temperature, gas flow rate, and air flow rate per second. An arithmetic average is then calculated every ten seconds to obtain the arithmetic average of exhaust gas temperature, gas flow rate, and air flow rate every ten seconds.

[0064] Due to the large lag and slow time-varying characteristics of the hot blast stove control coefficient, a decision is made every minute after the initial combustion period and before the end of the combustion period, and the set gas flow rate is adjusted once according to the speed of furnace combustion.

[0065] The rate at which the exhaust gas temperature rises is mainly regulated by the gas flow rate during combustion. Before adjusting the gas flow rate, it is first determined whether the gas flow rate has reached the upper limit. If the gas regulating valve opening exceeds the upper limit for three consecutive adjustment cycles (e.g., the gas regulating valve opening is greater than 85%, which is considered to be exceeding the upper limit), then the gas shortage logic is entered, and the set gas flow rate is reduced to the actual gas flow rate.

[0066] If the gas flow rate is sufficient, during the waste gas temperature management period, based on the waste gas temperature rise curve of the previous period, a fitted waste gas temperature rise curve is obtained (see below). Figure 2 .

[0067] The first prediction cycle, the decision basis, is the exhaust gas temperature of the previous three minutes (18 points).

[0068] The second prediction cycle, the decision basis, is the exhaust gas temperature of the previous five minutes (30 points).

[0069] The third prediction cycle, the decision basis, is the exhaust gas temperature of the previous eight minutes (48 points).

[0070] In one embodiment, fitting an exhaust gas temperature rise curve based on periodic combustion data includes:

[0071] The exhaust gas temperature rise curves for the first, second, and third prediction cycles are fitted based on the periodic combustion data. The first prediction cycle is shorter than the second prediction cycle, and the second prediction cycle is shorter than the third prediction cycle.

[0072] Adjust the weights of the exhaust gas temperature rise curves for the first, second, and third prediction cycles to obtain the predicted temperature rise slope.

[0073] Based on the predicted temperature rise slope, the exhaust gas temperature rise curve is obtained.

[0074] In practice, adjusting the weights of the three prediction periods can yield different prediction biases. Generally, the medium prediction period is adopted, with the weight of the medium prediction period set as Wm, the weight of the short prediction period as Ws, and the weight of the long prediction period as Wl. The trend of exhaust gas temperature rise is shown below. Figure 3 The temperature rise trend of the exhaust gas is calculated using the following formula:

[0075] Gv=Gn×Wm+Gl×Wl+Gs×Ws

[0076] Wherein, Gv is the weighted temperature rise slope; Gl is the long-period predicted temperature rise slope; Gs is the short-period predicted temperature rise slope; and Gn is the medium-period predicted temperature rise slope.

[0077] In one specific embodiment, the current combustion time is set to 20 minutes, the total combustion time is set to 120 minutes, and the exhaust gas temperature is set to 350°C. Based on this temperature rise trend, the predicted exhaust gas temperature is:

[0078] Tp = Ts + Gv × (Dt - Ds)

[0079] Where Tp is the predicted exhaust gas temperature; Ts is the current exhaust gas temperature; Gv is the weighted temperature rise slope; Dt is the set combustion time; and Ds is the current combustion time.

[0080] See the example diagram showing the calculated exhaust gas temperature during the predicted combustion time. Figure 4 If the predicted remaining combustion time is within ±3 minutes, the current gas flow rate will not be adjusted; if the predicted combustion time is too fast, the gas flow rate will need to be reduced; if the predicted combustion time is too slow, the gas flow rate will need to be increased.

[0081] In practice, the gas flow adjustment strategy is determined based on the trend of exhaust gas temperature rise. To control the adjustment magnitude, a step-by-step gas flow adjustment is required. Given a predicted deviation in exhaust gas temperature, the greater the predicted temperature rise deviation, the more the gas flow should be reduced. Conversely, the smaller the predicted temperature rise deviation, the more the gas flow should be increased. During the exhaust gas temperature management period, the gas flow is continuously adjusted to bring the exhaust gas temperature to the set temperature within the set combustion time.

[0082] In one embodiment, the weight calculation model is trained according to the following steps:

[0083] Use historical combustion data of hot blast stoves as machine learning datasets;

[0084] Split the machine learning dataset into a training set and a test set;

[0085] Import the machine learning model, configure the parameters for the machine learning model, and train the machine learning model based on the training set.

[0086] The performance of the trained machine learning model is evaluated based on the test set, and the machine learning model that achieves the hit rate of the preset standard is used as the parameter to adjust the model.

[0087] In practical implementation, during the exhaust gas temperature management period, input parameters (current exhaust gas temperature, current gas setpoint, gas adjustment per minute for the first three minutes, current short-cycle weight, current medium-cycle weight, and current long-cycle weight) and output parameters (predicted exhaust gas temperature rise slope per minute calculated by the model, and predicted exhaust gas temperature after six minutes) are collected. Due to changes in furnace conditions, furnace age, and production environment, the short, medium, and long-cycle prediction weights need to be continuously adjusted to ensure the accuracy of the predicted temperature rise. Because this invention can automatically collect the furnace firing parameters and results for each furnace, training and validating the machine learning model and adjusting parameters is very convenient and efficient. This invention uses an auto-sklearn automatic machine learning model.

[0088] In one specific embodiment, apart from the exhaust gas temperature holding period, other gas setting rules need to be used during the furnace changeover stage and the end of combustion.

[0089] The blast furnace replacement phase: The three hot blast stoves generally operate in a two-burn, one-supplier combustion mode. During the middle of the combustion phase in the downstream stove, the upstream stove begins the replacement process. At this point, the three hot blast stoves switch to a one-burn, one-replace, one-supplier configuration. During the replacement phase, the upstream stove needs to be pressurized to facilitate blast supply, and the replacement time is 8 to 10 minutes. During this period, the number of hot blast stoves in combustion decreases from two to one, significantly reducing the gas demand. To balance the ring network pressure and reduce gas consumption during the later stages of low combustion efficiency, an additional gas consumption is added at the start of the replacement. During the replacement period, the predicted combustion time is reduced to accelerate combustion.

[0090] Late combustion stage: If the blast furnace foreman does not order a furnace change during the late combustion stage, the gas flow rate of the current lead furnace should be reduced for low-volume combustion, commonly known as furnace pulling. During furnace pulling, the exhaust gas temperature should be kept stable.

[0091] This invention also provides a combustion heat storage control device for a blast furnace hot blast stove, as described in the following embodiments. Since the principle by which this device solves the problem is similar to the combustion heat storage control method for a blast furnace hot blast stove, the implementation of this device can be referred to the implementation of the method, and repeated details will not be elaborated further.

[0092] Figure 5 This is a schematic diagram of the combustion heat storage control device for a blast furnace hot blast stove provided in an embodiment of the present invention, as shown below. Figure 5 As shown, the device includes:

[0093] The monitoring module 501 is used to monitor the operation of each valve in the hot blast stove. When a combustion start signal is detected, combustion control is initiated.

[0094] The flow determination module 502 is used to acquire historical combustion data of the hot blast stove, set the initial gas flow rate according to the historical combustion data of the hot blast stove, and deliver gas to the hot blast stove according to the initial gas flow rate.

[0095] The calculation module 503 is used to collect real-time combustion data of the hot air furnace using callback functions and time control functions, and calculate periodic combustion data based on the real-time combustion data;

[0096] The weight adjustment module 504 is used to fit the exhaust gas temperature rise curve based on the periodic combustion data, and adjust the weight of each calculation factor when fitting the exhaust gas temperature rise curve through the weight calculation model until the exhaust gas temperature rise curve meets the preset hit rate. The exhaust gas temperature rise trend is calculated based on the exhaust gas temperature rise curve. The weight calculation model is trained by the machine learning model using historical combustion data and is used to adjust the weight of each calculation factor when fitting the exhaust gas temperature rise curve.

[0097] The flow adjustment module 505 is used to obtain the predicted combustion time based on the temperature rise trend of the exhaust gas, compare the predicted combustion time with the preset combustion time, and adjust the gas flow rate at the current moment according to the comparison result to maintain the exhaust gas temperature within the preset exhaust gas temperature range.

[0098] In one embodiment, the valves of the hot blast stove include: a gas shut-off valve, an air shut-off valve, an exhaust gas shut-off valve, a nitrogen purging valve, and a pressurizing valve.

[0099] In one embodiment, the flow determination module 502 is specifically used for:

[0100] Based on historical combustion data, calculate the average gas flow rate during the first half of the furnace firing process, when thermal efficiency is highest.

[0101] The average gas flow rate in the first half of the process, where thermal efficiency is highest, is set as the initial gas flow rate.

[0102] In one embodiment, the flow determination module 502 is further configured to:

[0103] When the air supply duration or cold air flow rate in the previous round of combustion in the hot blast stove exceeds the preset standard, an air supply coefficient is added when calculating the initial gas flow rate for the current round of combustion.

[0104] If the air supply duration or cold air flow rate in the previous round of combustion in the hot blast stove is lower than the preset standard, the initial gas flow rate in the current round of combustion will be reduced.

[0105] In one embodiment, the combustion data includes exhaust gas temperature, gas flow rate, and air flow rate.

[0106] In one embodiment, the weight adjustment module 504 is specifically used for:

[0107] The exhaust gas temperature rise curves for the first, second, and third prediction cycles are fitted based on the periodic combustion data. The first prediction cycle is shorter than the second prediction cycle, and the second prediction cycle is shorter than the third prediction cycle.

[0108] Adjust the weights of the exhaust gas temperature rise curves for the first, second, and third prediction cycles to obtain the predicted temperature rise slope.

[0109] Based on the predicted temperature rise slope, the exhaust gas temperature rise curve is obtained.

[0110] In one embodiment, a model building module is further included, specifically for:

[0111] Use historical combustion data of hot blast stoves as machine learning datasets;

[0112] Split the machine learning dataset into a training set and a test set;

[0113] Import the machine learning model, configure the parameters for the machine learning model, and train the machine learning model based on the training set.

[0114] The performance of the trained machine learning model is evaluated based on the test set, and the machine learning model that achieves the hit rate of the preset standard is used as the parameter to adjust the model.

[0115] Based on the aforementioned inventive concept, such as Figure 6 As shown, the present invention also proposes a computer device 600, including a memory 610, a processor 620, and a computer program 630 stored in the memory 610 and executable on the processor 620. When the processor 620 executes the computer program 630, it implements the aforementioned blast furnace hot blast stove combustion heat storage control method.

[0116] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described blast furnace hot blast stove combustion heat storage control method.

[0117] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described blast furnace hot blast stove combustion heat storage control method.

[0118] In summary, in this embodiment of the invention, the operation of each valve in the hot blast stove is monitored, and combustion control begins upon detection of a combustion start signal. Historical combustion data of the hot blast stove is acquired, and an initial gas flow rate is set based on this data. Gas is then supplied to the hot blast stove according to the initial gas flow rate. Real-time combustion data of the hot blast stove is collected using callback and timing functions, and periodic combustion data is calculated based on this real-time data. Finally, a waste gas temperature rise curve is fitted using the periodic combustion data, and the fitting calculation is adjusted using a weighted calculation model. The weights of each calculation factor are assigned to the exhaust gas temperature rise curve until the curve meets a preset hit rate. The exhaust gas temperature rise trend is then calculated based on the curve. This weight calculation model is trained using historical combustion data on a machine learning model and is used to adjust the weights of each calculation factor when fitting the exhaust gas temperature rise curve. Based on the exhaust gas temperature rise trend, a predicted combustion time is obtained. This predicted combustion time is compared with a preset combustion time, and the gas flow rate is adjusted based on the comparison result to maintain the exhaust gas temperature within the preset range. In this way, by calculating historical combustion data, collecting real-time combustion data, and using a machine model to formulate a corresponding gas flow strategy and continuously adjust the gas flow rate, potential errors from manual calculations can be avoided, effectively improving the combustion thermal efficiency of the hot air furnace.

[0119] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0120] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0121] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0122] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0123] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for controlling combustion heat storage in a blast furnace hot blast stove, characterized in that, include: Monitor the operation of each valve in the hot blast stove, and start combustion control when a combustion start signal is detected; Acquire historical combustion data of the hot blast stove, set the initial gas flow rate based on the historical combustion data of the hot blast stove, and deliver gas to the hot blast stove according to the initial gas flow rate; Real-time combustion data of the hot air furnace is collected using callback functions and time control functions, and periodic combustion data is calculated based on the real-time combustion data. The exhaust gas temperature rise curve is fitted based on the periodic combustion data. The weight of each calculation factor is adjusted when fitting the exhaust gas temperature rise curve using a weight calculation model until the exhaust gas temperature rise curve meets the preset hit rate. The exhaust gas temperature rise trend is calculated based on the exhaust gas temperature rise curve. The weight calculation model is trained by a machine learning model using historical combustion data and is used to adjust the weight of each calculation factor when fitting the exhaust gas temperature rise curve. Based on the trend of exhaust gas temperature rise, the predicted combustion time is obtained. The predicted combustion time is compared with the preset combustion time, and the gas flow rate at the current moment is adjusted according to the comparison results to maintain the exhaust gas temperature within the preset exhaust gas temperature range.

2. The method as described in claim 1, characterized in that, The valves of the hot blast stove include: gas shut-off valve, air shut-off valve, waste gas shut-off valve, nitrogen purging valve, and pressurization valve.

3. The method as described in claim 1, characterized in that, The initial gas flow rate is set based on the historical combustion data of the hot blast stove, including: Based on historical combustion data, calculate the average gas flow rate during the first half of the furnace firing process, when thermal efficiency is highest. The average gas flow rate in the first half of the process, where thermal efficiency is highest, is set as the initial gas flow rate.

4. The method as described in claim 3, characterized in that, include: When the air supply duration or cold air flow rate in the previous round of combustion in the hot blast stove exceeds the preset standard, an air supply coefficient is added when calculating the initial gas flow rate for the current round of combustion. If the air supply duration or cold air flow rate in the previous round of combustion in the hot blast stove is lower than the preset standard, the initial gas flow rate in the current round of combustion will be reduced.

5. The method as described in claim 1, characterized in that, Combustion data includes exhaust gas temperature, gas flow rate, and air flow rate.

6. The method as described in claim 1, characterized in that, The exhaust gas temperature rise curve was fitted based on periodic combustion data, including: The exhaust gas temperature rise curves for the first, second, and third prediction cycles are fitted based on the periodic combustion data. The first prediction cycle is shorter than the second prediction cycle, and the second prediction cycle is shorter than the third prediction cycle. Adjust the weights of the exhaust gas temperature rise curves for the first, second, and third prediction cycles to obtain the predicted temperature rise slope. Based on the predicted temperature rise slope, the exhaust gas temperature rise curve is obtained.

7. The method as described in claim 1, characterized in that, It also includes training the weight calculation model according to the following steps: Use historical combustion data of hot blast stoves as machine learning datasets; Split the machine learning dataset into a training set and a test set; Import the machine learning model, configure the parameters for the machine learning model, and train the machine learning model based on the training set. The performance of the trained machine learning model is evaluated based on the test set, and the machine learning model that achieves the hit rate of the preset standard is used as the trained weight calculation model.

8. A combustion heat storage control device for a blast furnace hot blast stove, characterized in that, include: The monitoring module is used to monitor the operation of each valve in the hot blast stove. When a combustion start signal is detected, combustion control is initiated. The flow rate determination module is used to acquire historical combustion data of the hot blast stove, set the initial gas flow rate based on the historical combustion data of the hot blast stove, and deliver gas to the hot blast stove according to the initial gas flow rate. The calculation module is used to collect real-time combustion data of the hot air furnace using callback functions and time control functions, and calculate periodic combustion data based on the real-time combustion data; The weight adjustment module is used to fit the exhaust gas temperature rise curve based on the periodic combustion data. It adjusts the weight of each calculation factor when fitting the exhaust gas temperature rise curve through the weight calculation model until the exhaust gas temperature rise curve meets the preset hit rate. It calculates the exhaust gas temperature rise trend based on the exhaust gas temperature rise curve. The weight calculation model is trained by a machine learning model based on historical combustion data and is used to adjust the weight of each calculation factor when fitting the exhaust gas temperature rise curve. The flow rate adjustment module is used to obtain the predicted combustion time based on the temperature rise trend of the exhaust gas, compare the predicted combustion time with the preset combustion time, and adjust the gas flow rate at the current moment according to the comparison result to maintain the exhaust gas temperature within the preset exhaust gas temperature range.

9. The apparatus as claimed in claim 8, characterized in that, The valves of the hot blast stove include: gas shut-off valve, air shut-off valve, waste gas shut-off valve, nitrogen purging valve, and pressurization valve.

10. The apparatus as claimed in claim 8, characterized in that, The flow determination module is specifically used for: Based on historical combustion data, calculate the average gas flow rate during the first half of the furnace firing process, when thermal efficiency is highest. The average gas flow rate in the first half of the process, where thermal efficiency is highest, is set as the initial gas flow rate.

11. The apparatus as claimed in claim 10, characterized in that, The flow determination module is also used for: When the air supply duration or cold air flow rate in the previous round of combustion in the hot blast stove exceeds the preset standard, an air supply coefficient is added when calculating the initial gas flow rate for the current round of combustion. If the air supply duration or cold air flow rate in the previous round of combustion in the hot blast stove is lower than the preset standard, the initial gas flow rate in the current round of combustion will be reduced.

12. The apparatus as claimed in claim 8, characterized in that, Combustion data includes exhaust gas temperature, gas flow rate, and air flow rate.

13. The apparatus as claimed in claim 8, characterized in that, The weight adjustment module is specifically used for: The exhaust gas temperature rise curves for the first, second, and third prediction cycles are fitted based on the periodic combustion data. The first prediction cycle is shorter than the second prediction cycle, and the second prediction cycle is shorter than the third prediction cycle. Adjust the weights of the exhaust gas temperature rise curves for the first, second, and third prediction cycles to obtain the predicted temperature rise slope. Based on the predicted temperature rise slope, the exhaust gas temperature rise curve is obtained.

14. The apparatus as claimed in claim 8, characterized in that, It also includes a model building module, which is specifically used for: Use historical combustion data of hot blast stoves as machine learning datasets; Split the machine learning dataset into a training set and a test set; Import the machine learning model, configure the parameters for the machine learning model, and train the machine learning model based on the training set. The performance of the trained machine learning model is evaluated based on the test set, and the machine learning model that achieves the hit rate of the preset standard is used as the parameter to adjust the model.

15. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 7.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 7.

17. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 7.

Images