Blast furnace temperature targeted adjusting method and system based on big data platform

Abstract

The invention relates to the technical field of blast furnace ironmaking, and discloses a blast furnace temperature targeted adjusting method and system based on a big data platform, and the method comprises the following steps: obtaining multiple groups of historical data in a blast furnace; training a preset neural network model by using the plurality of groups of historical data to obtain a furnace temperature prediction model; acquiring real-time measurement data of a plurality of preset parts of the blast furnace, and utilizing the furnace temperature prediction model to obtain a furnace temperature prediction value of each preset part; and the coal injection amount of each tuyere is adjusted according to the furnace temperature predicted value of each preset part, and targeted adjustment of the furnace temperature is achieved. According to the method, detailed historical data is acquired and analyzed, the furnace temperature prediction model is trained based on the historical data to realize furnace temperature prediction of each preset part of the cooling wall of the blast furnace, targeted adjustment of the furnace temperature is realized according to the prediction result, and the functions of revealing internal temperature distribution of the blast furnace, furnace temperature prediction and closed-loop adjustment are simply and efficiently realized.

Description

Technical Field

[0001] The present invention relates to the technical field of blast furnace ironmaking, and in particular to a blast furnace temperature targeted regulation method and system based on a big data platform. Background Art

[0002] Blast furnace ironmaking is an upstream process of steel manufacturing and an important part of the entire steel industry. Therefore, if we want to achieve high production, low consumption and extend the life of the blast furnace, it is essential to maintain the stable and smooth operation of the blast furnace for a long time. The blast furnace temperature is an important indicator to judge whether the blast furnace is running smoothly. In addition to the overall temperature of the blast furnace, the uniformity of the temperature inside the blast furnace will also have a significant impact on the stable and smooth production of the blast furnace. At the same time, for super-large blast furnaces, when the iron mouth is unevenly distributed, the unevenness of the hearth during iron tapping will cause significant deviations in the temperature of each iron mouth.

[0003] During the blast furnace smelting process, the injected coal powder burns in the furnace and releases heat. Therefore, the amount of coal injection can also correct the fluctuation of furnace temperature to a certain extent. The coal powder injection system mainly transports coal powder into the blast furnace through the coal injection branch pipe. On the one hand, since the coal injection branch pipe is not equipped with flow metering equipment, it is impossible to monitor the branch pipe flow in real time, which leads to the inability to guarantee the flow of coal powder in each branch pipe, resulting in uneven coal powder injection in the blast furnace. On the other hand, the uneven distribution of coal gas flow inside the blast furnace and the uneven iron tapping at the iron mouth will cause the furnace temperature distribution to be chaotic, which will eventually affect the stable and smooth operation of the blast furnace. At this time, if the flow of the branch pipe is controlled, the distribution of coal gas flow can be appropriately adjusted to uniform the furnace temperature. At the same time, the stable and uniform furnace temperature distribution also provides a basis for high coal ratio injection, so how to achieve accurate control of the coal injection amount of each branch pipe is particularly important. In the actual production process, the circumferential distribution of the furnace temperature inside the blast furnace is uneven due to various reasons. The existing technology cannot realize the disclosure of the circumferential distribution of the temperature inside the blast furnace, and it is also impossible to realize the closed-loop processing of furnace temperature prediction and intelligent regulation. Summary of the invention

[0004] In view of this, the present invention provides a blast furnace temperature targeted regulation method and system based on a big data platform to solve the problem that the internal temperature distribution of the blast furnace cannot be revealed and the furnace temperature prediction and closed-loop regulation cannot be achieved.

[0005] In a first aspect, the present invention provides a method for targeted regulation of blast furnace temperature based on a big data platform, the method comprising:

[0006] Acquire multiple groups of historical data in the blast furnace, including: average cooling wall temperature at multiple preset temperature measurement points, average tuyere area at multiple preset tuyere positions, average tuyere water inlet and outlet at multiple preset tuyere positions, average tuyere coal injection amount at multiple preset tuyere positions, and molten iron temperature at multiple iron ports;

[0007] Use multiple sets of historical data to train the preset neural network model to obtain a furnace temperature prediction model;

[0008] Obtain real-time measurement data of multiple preset locations of the blast furnace, and use the furnace temperature prediction model to obtain the furnace temperature prediction value of each preset location. The real-time measurement data include: cooling wall temperature, tuyere area, tuyere water inlet and outlet, and tuyere coal injection amount;

[0009] The coal injection amount of each tuyere is adjusted according to the predicted value of the furnace temperature at each preset position to achieve targeted adjustment of the furnace temperature.

[0010] The targeted regulation method for blast furnace temperature based on a big data platform provided by the present invention acquires and analyzes detailed historical data, trains a furnace temperature prediction model based on the historical data to predict the furnace temperature of each preset position of the blast furnace cooling wall, and implements targeted regulation of the furnace temperature according to the prediction results, thereby simply and efficiently realizing the functions of revealing the internal temperature distribution of the blast furnace, furnace temperature prediction and closed-loop regulation.

[0011] In an optional implementation, multiple groups of historical data in a blast furnace are obtained, including:

[0012] The blast furnace is divided into multiple areas according to the iron mouth position, each area contains a target iron mouth, and the cooling wall temperature measurement points and tuyere positions in each area are determined;

[0013] Respectively obtain the cooling wall temperature of multiple preset temperature measurement points in each area, the tuyere area of ​​multiple preset tuyere positions, the tuyere water inlet and outlet volume of multiple preset tuyere positions, the tuyere coal injection volume of multiple preset tuyere positions, and the molten iron temperature of multiple iron holes;

[0014] The average cooling wall temperature of the preset temperature measuring points in each area is calculated, and the average tuyere area, average tuyere water inlet and outlet, and average tuyere coal injection amount of the preset tuyere positions in each area are calculated.

[0015] In an optional implementation, a preset neural network model is trained using multiple sets of historical data to obtain a furnace temperature prediction model, including:

[0016] Multiple sets of historical data from each region are divided into training sets and validation sets;

[0017] The average temperature of each layer of cooling wall, the average area of ​​tuyere, the average water inlet and outlet of tuyere, and the average coal injection amount of tuyere in the training set are used as the input of the preset neural network model, and the molten iron temperature of the target iron mouth is used as the output of the preset neural network model to train and obtain the training model of the corresponding area;

[0018] The average cooling wall temperature of each layer, the average tuyere area, the average water inlet and outlet volume, and the average coal injection volume of the tuyere in the validation set are used as input to validate the training model of the corresponding area and obtain the training model error of the corresponding area.

[0019] If the training model error is greater than the preset error threshold, the parameters of the training model are optimized according to the training model error until the training model error is no greater than the preset error threshold, and the furnace temperature prediction model of the corresponding area is obtained.

[0020] The targeted regulation method of blast furnace temperature based on a big data platform provided by the present invention divides the blast furnace into multiple areas according to the iron mouth position, measures the historical data of each area respectively, and uses the historical data of each area to train the furnace temperature prediction model of the corresponding area, thereby avoiding the difference in the furnace temperature prediction model caused by different molten iron temperatures at different iron mouths, and improving the precision and accuracy of the furnace temperature prediction model.

[0021] In an optional implementation, real-time measurement data of multiple preset locations of a blast furnace are obtained, and a furnace temperature prediction model is used to obtain a furnace temperature prediction value of each preset location, including:

[0022] The temperature sensors at the preset cooling wall temperature measuring points are used to collect the temperatures of multiple cooling walls, the water volume sensors at the tuyere positions are used to collect the water volume in and out of the tuyere at the tuyere positions, and the flow sensors at the tuyere positions are used to collect the coal injection volume at the tuyere positions;

[0023] According to the area where each preset part is located, select the furnace temperature prediction model of the corresponding area;

[0024] According to the cooling wall temperature, tuyere area, tuyere water inlet and outlet, and tuyere coal injection amount of each preset position, the furnace temperature prediction model of the corresponding area is used to determine the furnace temperature prediction value of each preset position.

[0025] The targeted regulation method of blast furnace temperature based on a big data platform provided by the present invention obtains real-time measurement data of each preset position, selects a furnace temperature prediction model according to the area where each preset position is located, and predicts the furnace temperature of each preset position more accurately, which is conducive to accurately grasping the temperature distribution of each preset position of the blast furnace.

[0026] In an optional implementation, adjusting the coal injection amount of each tuyere according to the predicted value of the furnace temperature of each preset position includes:

[0027] Obtain the current coal injection amount of each tuyere and the current furnace temperature prediction value of each preset position, and calculate the average value, maximum value and minimum value of the current furnace temperature prediction value of each preset position;

[0028] Calculate the target coal injection amount of each tuyere according to the average value, maximum value, minimum value of the current furnace temperature prediction value of each preset position and the current coal injection amount of the tuyere;

[0029] Calculate the difference between the current coal injection amount of each tuyere and the target coal injection amount of each tuyere, and adjust the coal injection amount of each tuyere according to the difference.

[0030] The targeted blast furnace temperature regulation method based on a big data platform provided by the present invention analyzes the predicted value of the furnace temperature at each preset position, adjusts the coal injection amount of each tuyere, reduces the temperature difference of the furnace temperature at each preset position in the blast furnace, and evens out the furnace temperature to ensure stable and smooth operation of the blast furnace.

[0031] In an optional embodiment, the preset locations are distributed circumferentially in multiple layers in the blast furnace.

[0032] The targeted regulation method for blast furnace temperature based on a big data platform provided by the present invention has multiple layers of circumferential distribution at each preset position, and multiple cooling wall temperature measuring points are arranged on each layer, so as to reveal the circumferential distribution of the blast furnace temperature and accurately grasp the temperature conditions of each preset position in the blast furnace.

[0033] In an optional implementation, adjusting the coal injection amount of each tuyere according to the difference includes:

[0034] The current coal injection amount of the corresponding tuyere is collected by using the flow meter at each preset position;

[0035] Determine the setting value of the flow meter according to the difference and the current coal injection amount of the corresponding tuyere;

[0036] If the set value of the flow meter is greater than the preset flow threshold, the coal injection amount of the corresponding tuyere is adjusted according to the set value of the flow meter;

[0037] If the set value of the flow meter is not greater than the preset flow threshold, the set value of the flow meter is set to the preset flow threshold to adjust the coal injection amount of the corresponding tuyere.

[0038] The targeted regulation method for blast furnace temperature based on a big data platform provided by the present invention utilizes a flow meter to obtain the coal injection amount of each tuyere, thereby realizing real-time monitoring of the coal injection amount of each tuyere, which is beneficial to regulating the coal injection amount of each tuyere according to the furnace temperature of each preset position, so as to improve the uneven temperature distribution inside the blast furnace and ensure the stable and smooth operation of the blast furnace.

[0039] In a second aspect, the present invention provides a blast furnace temperature targeted regulation system based on a big data platform, the system comprising:

[0040] A historical data acquisition module is used to acquire multiple groups of historical data in the blast furnace, the historical data including: the average cooling wall temperature of multiple preset temperature measurement points, the average tuyere area of ​​multiple preset tuyere positions, the average tuyere water inlet and outlet volume of multiple preset tuyere positions, the average tuyere coal injection volume of multiple preset tuyere positions, and the molten iron temperature of multiple iron holes;

[0041] A model training module is used to train a preset neural network model using multiple sets of historical data to obtain a furnace temperature prediction model;

[0042] The furnace temperature prediction module is used to obtain real-time measurement data of multiple preset parts of the blast furnace, and use the furnace temperature prediction model to obtain the furnace temperature prediction value of each preset part. The real-time measurement data includes: cooling wall temperature, tuyere area, tuyere water inlet and outlet, and tuyere coal injection amount;

[0043] The furnace temperature adjustment module is used to adjust the coal injection amount of each tuyere according to the predicted value of the furnace temperature at each preset position, so as to achieve targeted adjustment of the furnace temperature.

[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 It is a schematic diagram of a process of a blast furnace temperature targeted regulation method based on a big data platform according to an embodiment of the present invention;

[0048] Figure 2 It is a schematic diagram of regional division in a blast furnace temperature targeted regulation method based on a big data platform according to an embodiment of the present invention;

[0049] Figure 3 is a schematic diagram of a BP neural network model in a blast furnace temperature targeted regulation method based on a big data platform according to an embodiment of the present invention;

[0050] Figure 4 is a flow chart of another method for targeted regulation of blast furnace temperature based on a big data platform according to an embodiment of the present invention;

[0051] Figure 5It is a schematic diagram of the circumferential distribution of each preset part in the blast furnace temperature targeted regulation method based on a big data platform according to an embodiment of the present invention;

[0052] Figure 6 is a structural block diagram of a blast furnace temperature targeted regulation system based on a big data platform according to an embodiment of the present invention;

[0053] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] 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.

[0055] The embodiment of the present invention provides a method and system for targeted regulation of blast furnace temperature based on a big data platform, which constructs a furnace temperature prediction model through historical data to predict and control the furnace temperature, so as to achieve the effect of revealing the internal temperature distribution of the blast furnace, furnace temperature prediction and closed-loop regulation.

[0056] According to an embodiment of the present invention, an embodiment of a blast furnace temperature targeted regulation method based on a big data platform 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 may be executed in an order different from that shown here.

[0057] In this embodiment, a blast furnace temperature targeted adjustment method based on a big data platform is provided, which can be used in the above-mentioned computer system. Figure 1 is a flow chart of a blast furnace temperature targeted regulation method based on a big data platform according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0058] Step S101, obtaining multiple groups of historical data in the blast furnace, the historical data including: the average cooling wall temperature of multiple preset temperature measuring points, the average tuyere area of ​​multiple preset tuyere positions, the average tuyere water inlet and outlet volume of multiple preset tuyere positions, the average tuyere coal injection volume of multiple preset tuyere positions, and the molten iron temperature of multiple iron ports.

[0059] Specifically, temperature sensors are installed at multiple locations on the cooling wall of the blast furnace. The blast furnace has multiple layers of cooling walls, and each layer of cooling walls has multiple cooling walls. Each cooling wall corresponds to a temperature sensor, but the number of cooling wall blocks on each layer of cooling walls may be different. No matter how many cooling walls each layer of cooling walls is divided into, they need to be classified and processed according to their positions. The temperature data of each temperature sensor is collected by a programmable logic controller (PLC) as the cooling wall temperature and uploaded to the big data platform. The average temperature of the cooling wall at multiple preset temperature measurement points can be calculated in the big data platform. The blast furnace contains multiple tuyere, and the area of ​​each tuyere is automatically calculated by the background according to the production situation; the water inlet and outlet of the tuyere and the amount of coal injection at the tuyere are detected by the corresponding flow sensor, and then uploaded to the big data platform through the PLC, and the average water inlet and outlet and the average coal injection at the tuyere are calculated in the big data platform; there may be multiple iron holes distributed around the blast furnace, and the molten iron samples of each iron hole can be taken for inspection when the iron is tapped, and the molten iron temperature of the target iron hole can be detected and uploaded to the big data platform through the PLC, just as an example, but not limited to this. As the host computer of the PLC, the big data platform can process the acquired historical data.

[0060] The historical data of the blast furnace obtained is the data value of the blast furnace every hour. When selecting data, the abnormal state of the blast furnace should be avoided as much as possible. No less than 200 groups of historical data before the current time point should be selected to meet the requirements of data analysis.

[0061] In some optional embodiments, the preset locations are distributed circumferentially in multiple layers in the blast furnace.

[0062] Specifically, in order to ensure that the furnace temperature in the blast furnace is evenly distributed in the circumferential direction, it is necessary to obtain data from various circumferential locations and analyze and process them. Therefore, each preset location is distributed in multiple layers in the blast furnace, such as Figure 2 As shown in the figure, it is a schematic diagram of the circumferential distribution of each preset position, where the outermost 1-40 represents 40 air outlets, ①- 14 temperature measuring points on the cooling wall are shown, and Ⅰ, Ⅱ, and Ⅲ represent three areas divided according to the position of the iron mouth, which is only used as an example but not limited to this.

[0063] The targeted regulation method of blast furnace temperature based on a big data platform provided in this embodiment has multiple layers of circumferential distribution at each preset position, and multiple cooling wall temperature measuring points are arranged on each layer, so as to reveal the circumferential distribution of blast furnace temperature and accurately grasp the temperature conditions of each preset position in the blast furnace.

[0064] Step S102, using the multiple groups of historical data to train a preset neural network model to obtain a furnace temperature prediction model.

[0065] Specifically, in 1986, Rumellhart and Hinton jointly proposed a hierarchical feedforward artificial neural network consisting of an input layer, a hidden layer, and an output layer: the BP neural network model. The main steps of the BP neural network model are forward propagation calculation and error back propagation, in which the forward propagation calculation process uses the output of the neurons in the input layer as the input signal of the neurons in the next layer, and outputs it to the next layer after the weighted and nonlinear activation function calculation of the weights and biases between the layers, until the output layer generates the final output result. The error back propagation process is to calculate the error of the output layer and transfer the error back between the layers, continuously adjust the connection weights and biases between the neurons in each layer, and optimize the accuracy of the network output results until the error calculated by the network reaches the given target value or reaches the predetermined number of iterations. The BP neural network model is widely used in many fields such as optimization calculation, function approximation, image processing, and numerical prediction.

[0066] The structure of BP neural network consists of three parts: input layer, hidden layer and output layer. The input layer accepts external input data, the hidden layer is responsible for processing the input signal and converting it into a higher-level feature expression, and the task of the output layer is to map the result of the hidden layer to the final output result. In each layer, the nodes are linked by connections with specific weights, and each node processes input data and calculates output independently. The data transmission between each layer only depends on the weights and biases between adjacent layers, and does not require additional input signals or state information. Many studies have shown that BP neural network with a single hidden layer can approximate any nonlinear function. At the same time, it has a simpler structure, lower computational complexity, and is easier to control in the training process. The advantages of parameter estimation and generalization ability are also easier to master, making it more able to meet the needs of calculation.

[0067] In this embodiment, the BP neural network model is used as the preset neural network model, the average temperature of each layer of cooling wall, the average area of ​​the tuyere, the average water inlet and outlet of the tuyere, and the average coal injection amount of the tuyere are used as the input of the preset neural network model, and the molten iron temperature of the corresponding iron mouth is used as the output to construct a BP neural network model including multiple input layers, an output layer and a hidden layer, such as Figure 3 The number of input layers is the sum of the data of cooling wall temperature, tuyere area, tuyere water inlet and outlet, and tuyere coal injection amount at multiple preset temperature measurement points in the historical data. The preset neural network model is trained using multiple sets of historical data to determine the parameters of the neural network model and obtain the furnace temperature prediction model.

[0068] Step S103, obtaining real-time measurement data of multiple preset positions of the blast furnace, and using the furnace temperature prediction model, taking the real-time measurement data as the model input to obtain the furnace temperature prediction value of each preset position, the real-time measurement data includes: cooling wall temperature, tuyere area, tuyere water inlet and outlet, tuyere coal injection amount.

[0069] Specifically, the tuyere position can be used as a preset position, and the cooling wall temperature of the corresponding preset position can be determined according to the preset temperature measurement point at each preset position, and the tuyere area, tuyere water inlet and outlet, and tuyere coal injection amount of the corresponding preset position can be determined according to the tuyere position at each preset position. The real-time measurement data is used as the input of the furnace temperature prediction model of the corresponding area, and the furnace temperature prediction model is used to predict the furnace temperature prediction value of each preset position.

[0070] Step S104, adjusting the coal injection amount of each tuyere according to the furnace temperature prediction value of each preset position, so as to achieve targeted adjustment of the furnace temperature.

[0071] Specifically, during the blast furnace smelting process, the injected pulverized coal burns in the furnace to release heat, so the amount of coal injected will affect the furnace temperature. According to the predicted furnace temperature of each preset position and the difference between the predicted furnace temperatures, the set value of the coal injection amount of each tuyere is determined, and the coal injection amount of each tuyere is set and controlled through PLC to achieve targeted injection of pulverized coal and targeted control of furnace temperature.

[0072] The targeted regulation method for blast furnace temperature based on a big data platform provided in this embodiment obtains and analyzes detailed historical data, trains a furnace temperature prediction model based on historical data to predict the furnace temperature of each preset position of the blast furnace cooling wall, and implements targeted regulation of the furnace temperature according to the prediction results, thus simply and efficiently realizing the functions of revealing the internal temperature distribution of the blast furnace, furnace temperature prediction and closed-loop regulation.

[0073] In this embodiment, a blast furnace temperature targeted adjustment method based on a big data platform is provided, which can be used in the above-mentioned computer system. Figure 4 is a flow chart of a blast furnace temperature targeted regulation method based on a big data platform according to an embodiment of the present invention. Figure 4 As shown, the process includes the following steps:

[0074] Step S201, obtain multiple groups of historical data in the blast furnace, the historical data include: the average cooling wall temperature of multiple preset temperature measuring points, the average tuyere area of ​​multiple preset tuyere positions, the average tuyere water inlet and outlet volume of multiple preset tuyere positions, the average tuyere coal injection volume of multiple preset tuyere positions, and the molten iron temperature of multiple iron ports.

[0075] Specifically, the above step S201 includes:

[0076] Step S2011, dividing the blast furnace into multiple areas according to the iron mouth position, each area contains a target iron mouth, and determining the cooling wall temperature measurement points and tuyere positions in each area.

[0077] Specifically, Figure 2 As shown, a blast furnace has 3 iron mouths, 16 layers of cooling walls, 14 preset temperature measuring points and 40 tuyere in the circumferential direction. It should be noted that the number of preset temperature measuring points of each layer of cooling wall is not necessarily the same. In this embodiment, 14 preset temperature measuring points are used as an example for illustration, but it is not limited to this. The blast furnace is decomposed into three vertical regions Ⅰ, Ⅱ and Ⅲ according to the angular center line between each two iron mouths as the boundary, and the cooling wall temperature, tuyere area, tuyere water inlet and outlet, tuyere coal injection amount and the molten iron temperature of the corresponding iron mouth in each region are classified as a group. Taking region Ⅰ as an example, the corresponding parameters are the cooling wall temperature of sections ④, ⑤, ⑥ and ⑦, the tuyere area of ​​1 to 13, the water inlet and outlet of 1 to 13 tuyere, the coal injection amount of 1 to 13 tuyere and the molten iron temperature of 1# iron mouth.

[0078] Step S2012, respectively obtain the cooling wall temperature of multiple preset temperature measuring points in each area, the tuyere area of ​​multiple preset tuyere positions, the tuyere water inlet and outlet volume of multiple preset tuyere positions, the tuyere coal injection volume of multiple preset tuyere positions, and the molten iron temperature of multiple iron holes.

[0079] Specifically, for Figure 2 The circumferential distribution diagram of a blast furnace shown in the figure measures the cooling wall temperature at 14 preset temperature measurement points, the area of ​​40 tuyere ports, the water inlet and outlet volumes of 40 tuyere ports, and the molten iron temperature at the target iron ports in the three areas.

[0080] For all the original data, abnormal data such as null values ​​and singular values ​​should be screened out, that is, when abnormal data appears at a certain time point, all data at that moment should be deleted. The original data includes: the cooling wall temperature of multiple preset temperature measurement points in each area, the tuyere area of ​​multiple preset tuyere positions, the tuyere water inlet and outlet volume of multiple preset tuyere positions, the tuyere coal injection volume of multiple preset tuyere positions, and the molten iron temperature of multiple iron mouths. The original data can also be standardized to scale each feature to a mean of 0 and a standard deviation of 1, which helps to eliminate the differences between the features to meet the subsequent training requirements of the neural network model.

[0081] Step S2013, calculating the average cooling wall temperature of the preset temperature measuring points in each area, calculating the average tuyere area, average tuyere water inlet and outlet, and average tuyere coal injection amount of the preset tuyere positions in each area.

[0082] Specifically, since each layer of the cooling wall has 14 temperature measuring points, for area I, a set of historical data includes the average values ​​of 16 cooling wall temperatures, the average values ​​of the areas of tuyere No. 1 to 13, the average values ​​of the water inlet and outlet of tuyere No. 1 to 13, the average values ​​of the coal injection amount of tuyere No. 1 to 13, and the molten iron temperature of the 1# iron mouth. The dimension of a set of historical data is 20.

[0083] Step S202, using multiple groups of historical data to train a preset neural network model to obtain a furnace temperature prediction model.

[0084] Specifically, the above step S202 includes:

[0085] Step S2021, divide the multiple groups of historical data of each region into a training set and a validation set respectively.

[0086] Specifically, for the three regions Ⅰ, Ⅱ, and Ⅲ, model training needs to be performed separately. Similarly, taking region Ⅰ as an example, the dimension of a set of historical data is 20, and 200 sets of historical data are obtained according to the method described in step S201, and the 200 sets of historical data are divided into training sets and validation sets according to a preset ratio, for example, 90% as training sets and 10% as validation sets, which is equivalent to 180 sets of historical data as training sets and 20 sets of data as validation sets, which is only an example, but not limited to this.

[0087] Step S2022, taking the average temperature of each layer of cooling wall, the average area of ​​tuyere, the average water inlet and outlet of tuyere, and the average coal injection amount of tuyere in the training set as the input of the preset neural network model, and the molten iron temperature of the target iron mouth as the output of the preset neural network model, training is performed to obtain the training model of the corresponding area.

[0088] Specifically, the average temperature of each layer of cooling wall, the average area of ​​tuyere, the average water inlet and outlet of tuyere, and the average coal injection amount of tuyere in the training set are used as the input of the preset neural network model. The number of input layers is the sum of the data of the average temperature of each layer of cooling wall, the average area of ​​tuyere, the average water inlet and outlet of tuyere, and the average coal injection amount of tuyere. For area No. Ⅰ, the number of input layers is 19, and the molten iron temperature of the target iron mouth is used as the output of the preset neural network model. For area No. Ⅰ, the number of output layers is 1.

[0089] The number of nodes in the input layer is set to n, the number of nodes in the hidden layer is set to l, and the number of nodes in the output layer is set to m. The weight from the input layer to the hidden layer is set to ω ij , the weight from the hidden layer to the output layer is set to ω jk ; The bias from the input layer to the hidden layer is set to a j , the bias from the hidden layer to the output layer is set to b k .

[0090] The Sigmoid function is selected as the activation function of the hidden layer, as follows:

[0091]

[0092] Then the hidden layer H j The input value of can be calculated as:

[0093]

[0094] Output layer O k The output value (prediction value) can be calculated by the following formula:

[0095]

[0096] Finally, the error is calculated by the error calculation function:

[0097]

[0098] In the above formula, Y k is the expected output value; i=1, 2…n; j=1, 2…l; k=1, 2…m.

[0099] Step S2023, taking the average cooling wall temperature of each layer, the average tuyere area, the average tuyere water inlet and outlet, and the average tuyere coal injection amount in the verification set as input, verifies the training model of the corresponding area, and obtains the training model error of the corresponding area.

[0100] Specifically, multiple groups of historical data in the verification set of each area are used to verify the prediction accuracy of the training model of the corresponding area, and the training model of the corresponding area is used to predict the molten iron temperature of the corresponding iron mouth. The molten iron temperature is compared with the actually measured molten iron temperature, and the prediction error is determined as the training model error.

[0101] Step S2024, if the training model error is greater than the preset error threshold, the parameters of the training model are optimized according to the training model error until the training model error is no greater than the preset error threshold, and the furnace temperature prediction model of the corresponding area is obtained.

[0102] Specifically, if the training model error exceeds the expected value during the model training process, the weights and biases are repeatedly optimized until the training model error is no greater than the expected value, and each region uses its own multiple sets of historical data to perform model training respectively to obtain the furnace temperature prediction model of the corresponding region. The preset error threshold can be 5%, which is only used as an example, but is not limited to this.

[0103] The targeted adjustment method of blast furnace temperature based on a big data platform provided in this embodiment divides the blast furnace into multiple areas according to the iron mouth position, measures the historical data of each area respectively, and uses the historical data of each area to train the furnace temperature prediction model of the corresponding area, thereby avoiding the difference in furnace temperature prediction model caused by different molten iron temperatures at different iron mouths, and improving the precision and accuracy of the furnace temperature prediction model.

[0104] Step S203, obtain multiple real-time measurement data of the blast furnace, and use the furnace temperature prediction model to obtain the furnace temperature prediction value of each preset position. The real-time measurement data include: cooling wall temperature, tuyere area, tuyere water inlet and outlet, and tuyere coal injection amount.

[0105] Specifically, the above step S203 includes:

[0106] Step S2031, using the temperature sensors at each preset cooling wall temperature measuring point to collect multiple cooling wall temperatures, using the water volume sensors at each tuyere position to collect the tuyere water inlet and outlet volume at each tuyere position, and using the flow sensors at each tuyere position to collect the tuyere coal injection volume at each tuyere position.

[0107] Specifically, corresponding temperature sensors are set at each preset cooling wall temperature measurement point to obtain the temperature of each cooling wall, and the water volume sensors at each tuyere position are used to collect the water volume in and out of the tuyere at each tuyere position, and the flow sensors at each tuyere position are used to collect the coal injection volume at each tuyere position. The real-time measurement data is uploaded to the big data platform through PLC. In this embodiment, each preset position is each tuyere position, so as to predict the furnace temperature in the longitudinal area of ​​each tuyere position, so as to achieve the purpose of revealing the circumferential distribution of the temperature in the furnace, which is only used as an example, but not limited to this.

[0108] Step S2032, selecting a furnace temperature prediction model for a corresponding area according to the area where each preset part is located.

[0109] Specifically, Figure 3 As shown, taking No. 1 and No. 40 tuyere as examples, the prediction of the molten iron temperature in the vertical direction of No. 1 tuyere is based on the furnace temperature prediction model of area I; the prediction of the molten iron temperature in the vertical direction of No. 40 tuyere is based on the furnace temperature prediction model of area III.

[0110] Step S2033, according to the cooling wall temperature, tuyere area, tuyere water inlet and outlet, and tuyere coal injection amount of each preset position, the furnace temperature prediction model of the corresponding area is used to determine the furnace temperature prediction value of each preset position.

[0111] Specifically, Figure 3As shown in the figure, for tuyere No. 1, the input data of the furnace temperature prediction model of its No. I area are the tuyere area, water inlet and outlet, coal injection amount of tuyere No. 1, the average temperature of the 16-layer cooling wall in the fourth section, and the data dimension is 19; for tuyere No. 40, the input data of the furnace temperature prediction model of its No. III area are the tuyere area, water inlet and outlet, coal injection amount of tuyere No. 40, the average temperature of the 16-layer cooling wall in the fourth section, and the data dimension is 19. According to the above process, the furnace temperature prediction values ​​of the 40 tuyere positions can be determined, as shown in the following figure: Figure 5 The circumferential distribution of the furnace temperature inside the blast furnace shown is only for example, but not limited to this.

[0112] The targeted regulation method of blast furnace temperature based on a big data platform provided in this embodiment obtains real-time measurement data of each preset position, selects a furnace temperature prediction model according to the area where each preset position is located, and predicts the furnace temperature of each preset position more accurately, which is conducive to accurately grasping the temperature distribution of each preset position of the blast furnace.

[0113] Step S204, adjusting the coal injection amount of each tuyere according to the furnace temperature prediction value of each preset position, so as to achieve targeted adjustment of the furnace temperature.

[0114] The targeted regulation method for blast furnace temperature based on a big data platform provided in this embodiment obtains and analyzes detailed historical data, trains a furnace temperature prediction model based on historical data to predict the furnace temperature of each preset position of the blast furnace cooling wall, and implements targeted regulation of the furnace temperature according to the prediction results, thus simply and efficiently realizing the functions of revealing the internal temperature distribution of the blast furnace, furnace temperature prediction and closed-loop regulation.

[0115] Specifically, the above step S204 includes:

[0116] Step S2041, obtaining the current coal injection amount of each tuyere and the current furnace temperature prediction value of each preset position, and calculating the average value, maximum value and minimum value of the current furnace temperature prediction value of each preset position.

[0117] Specifically, coal is injected through a coal injection branch pipe at each tuyere position, and a flow meter is installed on each coal injection branch pipe to obtain the current coal injection amount of each tuyere in real time. According to the current furnace temperature prediction value of each preset position, the average value, maximum value and minimum value of the current furnace temperature prediction value of each preset position are calculated.

[0118] Step S2042, calculating the target coal injection amount of each tuyere according to the average value, maximum value, minimum value of the current furnace temperature prediction value of each preset position and the current coal injection amount of the tuyere.

[0119] Specifically, according to the average value of the current furnace temperature prediction value of each preset position, the current furnace temperature prediction values ​​of all preset positions are classified, and the current furnace temperature prediction values ​​greater than the average value and less than the average value are sorted by size respectively. The calculation formula for the target coal injection amount of each tuyere is:

[0120]

[0121] Among them, M ci is the flow value of each coal injection branch pipe before modification, i = 1, 2, ..., 40; α is the adjustment coefficient, and its value determines the adjustment range of coal injection amount; T max and T min They are the maximum and minimum values ​​of the temperature in the previous furnace temperature prediction value. The above flow setting cycle is consistent with the collection cycle of temperature and other data, and ultimately the circumferential prediction and regulation of the blast furnace temperature can be achieved.

[0122] Step S2043, calculating the difference between the current coal injection amount of each tuyere and the target coal injection amount of each tuyere, and adjusting the coal injection amount of each tuyere according to the difference.

[0123] In some optional implementations, the process of adjusting the coal injection amount of each tuyere according to the difference in the above step S2043 includes:

[0124] Step a1, using the flow meter at each preset position to collect the current coal injection amount of the corresponding tuyere.

[0125] Specifically, a flow meter is installed at each preset position to collect the current coal injection amount of the corresponding air outlet.

[0126] Step a2, determining the setting value of the flow meter according to the difference and the current coal injection amount of the corresponding tuyere.

[0127] Specifically, the set value of the flow meter is determined according to the difference between the current coal injection amount of each air outlet and the target coal injection amount of each air outlet, and the current coal injection amount of the corresponding air outlet. The set value of the flow meter has a corresponding relationship with the coal injection amount of the air outlet. This technology is a mature existing technology and will not be repeated here.

[0128] Step a3: if the set value of the flow meter is greater than the preset flow threshold, the coal injection amount of the corresponding tuyere is adjusted according to the set value of the flow meter.

[0129] Step a4: if the set value of the flow meter is not greater than the preset flow threshold, the set value of the flow meter is set to the preset flow threshold to adjust the coal injection amount of the corresponding tuyere.

[0130] Specifically, the flow meter can automatically adjust the valve opening according to the set value to achieve the adjustment and control of the coal injection amount at the tuyere. In actual situations, the opening of each branch valve needs to be controlled between 50% and 100%. If the opening is too small, the resistance is large and valve failure may occur easily.

[0131] The targeted blast furnace temperature regulation method based on the big data platform provided in this embodiment uses a flow meter to obtain the coal injection amount of each tuyere, realizes real-time monitoring of the coal injection amount of each tuyere, and adjusts the coal injection amount of each tuyere by analyzing the predicted value of the furnace temperature at each preset position, thereby reducing the temperature difference of the furnace temperature at each preset position in the blast furnace, which is beneficial to adjust the coal injection amount of each tuyere according to the furnace temperature of each preset position, so as to improve the uneven temperature distribution inside the blast furnace and ensure the stable and smooth operation of the blast furnace.

[0132] In this embodiment, a blast furnace temperature targeted regulation system based on a big data platform 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 implement a combination of software and / or hardware of a predetermined function. Although the system 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 conceived.

[0133] This embodiment provides a blast furnace temperature targeted regulation system based on a big data platform. Figure 6 As shown, including:

[0134] The historical data acquisition module 601 is used to obtain multiple groups of historical data in the blast furnace, and the historical data include: the average cooling wall temperature of multiple preset temperature measuring points, the average tuyere area of ​​multiple preset tuyere positions, the average tuyere water inlet and outlet volume of multiple preset tuyere positions, the average tuyere coal injection volume of multiple preset tuyere positions, and the molten iron temperature of multiple iron mouths.

[0135] The model training module 602 is used to train a preset neural network model using the multiple groups of historical data to obtain a furnace temperature prediction model.

[0136] The furnace temperature prediction module 603 is used to obtain real-time measurement data of multiple preset positions of the blast furnace, and use the furnace temperature prediction model to obtain the furnace temperature prediction value of each preset position. The real-time measurement data includes: cooling wall temperature, tuyere area, tuyere water inlet and outlet, and tuyere coal injection amount.

[0137] The furnace temperature adjustment module 604 is used to adjust the coal injection amount of each tuyere according to the furnace temperature prediction value of each preset position, so as to achieve targeted adjustment of the furnace temperature.

[0138] In some optional implementations, the historical data acquisition module 601 includes:

[0139] The area division unit is used to divide the blast furnace into multiple areas according to the iron mouth position, each area contains a target iron mouth, and determines the cooling wall temperature measurement points and tuyere positions in each area.

[0140] The data acquisition unit is used to respectively obtain the cooling wall temperature of multiple preset temperature measuring points in each area, the tuyere area of ​​multiple preset tuyere positions, the tuyere water inlet and outlet volume of multiple preset tuyere positions, the tuyere coal injection volume of multiple preset tuyere positions, and the molten iron temperature of multiple iron holes.

[0141] The data calculation unit is used to calculate the average cooling wall temperature of the preset temperature measuring points contained in each area, and calculate the average tuyere area, average tuyere water inlet and outlet, and average tuyere coal injection amount of the preset tuyere positions contained in each area.

[0142] In some optional implementations, the model training module 602 includes:

[0143] The data division unit is used to divide multiple groups of historical data of each region into training sets and verification sets.

[0144] The model training unit is used to use the average temperature of each layer of cooling wall, the average area of ​​the tuyere, the average water inlet and outlet of the tuyere, and the average coal injection amount of the tuyere in the training set as the input of the preset neural network model, and the molten iron temperature of the target iron mouth as the output of the preset neural network model, and train to obtain the training model of the corresponding area.

[0145] The model verification unit is used to take the average temperature of each layer of cooling wall, the average area of ​​the tuyere, the average water inlet and outlet of the tuyere, and the average coal injection amount of the tuyere in the verification set as input to verify the training model of the corresponding area and obtain the training model error of the corresponding area.

[0146] The model optimization unit is used to optimize the parameters of the training model according to the training model error if the training model error is greater than the preset error threshold, until the training model error is no greater than the preset error threshold, thereby obtaining the furnace temperature prediction model of the corresponding area.

[0147] In some optional implementations, the furnace temperature prediction module 603 includes:

[0148] The data measurement unit is used to collect multiple cooling wall temperatures using temperature sensors at each preset cooling wall temperature measuring point, collect the tuyere water inlet and outlet water volume at each tuyere position using water volume sensors at each tuyere position, and collect the tuyere coal injection volume at each tuyere position using flow sensors at each tuyere position.

[0149] The model selection unit is used to select the furnace temperature prediction model of the corresponding area according to the area where each preset part is located.

[0150] The temperature prediction unit is used to determine the furnace temperature prediction value of each preset position according to the cooling wall temperature, tuyere area, tuyere water inlet and outlet, and tuyere coal injection amount of each preset position using the furnace temperature prediction model of the corresponding area.

[0151] In some optional embodiments, the furnace temperature adjustment module 604 includes:

[0152] The prediction value analysis unit is used to obtain the current coal injection amount of each tuyere and the current furnace temperature prediction value of each preset position, and calculate the average value, maximum value and minimum value of the current furnace temperature prediction value of each preset position.

[0153] The target coal injection amount calculation unit is used to calculate the target coal injection amount of each tuyere according to the average value, maximum value, minimum value of the current furnace temperature prediction value of each preset position and the current coal injection amount of the tuyere.

[0154] The coal injection amount adjustment unit is used to calculate the difference between the current coal injection amount of each air outlet and the target coal injection amount of each air outlet, and adjust the coal injection amount of each air outlet according to the difference.

[0155] In some optional embodiments, the coal injection amount adjustment unit includes:

[0156] The current coal injection amount collection subunit is used to collect the current coal injection amount of the corresponding air outlet using the flow meter at each preset position.

[0157] The flow meter set value calculation subunit is used to determine the set value of the flow meter according to the difference and the current coal injection amount of the corresponding air outlet.

[0158] The first flow setting subunit is used to adjust the corresponding tuyere coal injection amount according to the set value of the flow meter if the set value of the flow meter is greater than a preset flow threshold.

[0159] The second flow setting subunit is used to set the set value of the flow meter to the preset flow threshold if the set value of the flow meter is not greater than the preset flow threshold, so as to adjust the coal injection amount of the corresponding tuyere.

[0160] 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.

[0161] The blast furnace temperature targeted regulation system based on the big data platform in this embodiment is presented in the form of functional units, where the units refer to ASIC (Application Specific Integrated Circuit) circuits, processors and memories that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0162] The embodiment of the present invention also provides a computer device having the above Figure 6 The blast furnace temperature targeted control system based on the big data platform is shown.

[0163] See also Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7 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 7 A processor 10 is taken as an example.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0169] 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.

[0170] 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 targeted regulation method based on a big data platform, characterized in that: The method comprises: Acquire multiple groups of historical data in the blast furnace, including: average cooling wall temperature at multiple preset temperature measurement points, average tuyere area at multiple preset tuyere positions, average tuyere water inlet and outlet at multiple preset tuyere positions, average tuyere coal injection amount at multiple preset tuyere positions, and molten iron temperature at multiple iron ports; Using the multiple groups of historical data to train a preset neural network model to obtain a furnace temperature prediction model; Acquire real-time measurement data of multiple preset positions of the blast furnace, and use the furnace temperature prediction model to obtain the furnace temperature prediction value of each preset position, wherein the real-time measurement data includes: cooling wall temperature, tuyere area, tuyere water inlet and outlet, and tuyere coal injection amount; The coal injection amount of each tuyere is adjusted according to the predicted value of the furnace temperature at each preset position to achieve targeted adjustment of the furnace temperature.

2. The method according to claim 1, characterized in that Get multiple sets of historical data from the blast furnace, including: The blast furnace is divided into multiple areas according to the iron mouth position, each area contains a target iron mouth, and the cooling wall temperature measurement points and tuyere positions in each area are determined; Respectively obtain the cooling wall temperature of multiple preset temperature measurement points in each area, the tuyere area of ​​multiple preset tuyere positions, the tuyere water inlet and outlet volume of multiple preset tuyere positions, the tuyere coal injection volume of multiple preset tuyere positions, and the molten iron temperature of multiple iron holes; The average cooling wall temperature of the preset temperature measuring points in each area is calculated, and the average tuyere area, average tuyere water inlet and outlet, and average tuyere coal injection amount of the preset tuyere positions in each area are calculated.

3. The method according to claim 2, characterized in that The preset neural network model is trained using the multiple sets of historical data to obtain a furnace temperature prediction model, including: Dividing the multiple groups of historical data of each region into a training set and a validation set respectively; The average temperature of each layer of cooling wall, the average area of ​​tuyere, the average water inlet and outlet of tuyere, and the average coal injection amount of tuyere in the training set are used as the input of the preset neural network model, and the molten iron temperature of the target iron mouth is used as the output of the preset neural network model to train and obtain the training model of the corresponding area; The average cooling wall temperature of each layer, the average tuyere area, the average water inlet and outlet volume, and the average coal injection volume of the tuyere in the validation set are used as input to validate the training model of the corresponding area and obtain the training model error of the corresponding area. If the training model error is greater than the preset error threshold, the parameters of the training model are optimized according to the training model error until the training model error is no greater than the preset error threshold, thereby obtaining a furnace temperature prediction model for the corresponding area.

4. The method according to claim 3, characterized in that Acquire real-time measurement data of multiple preset positions of the blast furnace, and use the furnace temperature prediction model to obtain the furnace temperature prediction value of each preset position, including: The temperature sensors at the preset cooling wall temperature measuring points are used to collect the temperatures of multiple cooling walls, the water volume sensors at the tuyere positions are used to collect the water volume in and out of the tuyere at the tuyere positions, and the flow sensors at the tuyere positions are used to collect the coal injection volume at the tuyere positions; According to the area where each preset part is located, select the furnace temperature prediction model of the corresponding area; According to the cooling wall temperature, tuyere area, tuyere water inlet and outlet, and tuyere coal injection amount of each preset position, the furnace temperature prediction model of the corresponding area is used to determine the furnace temperature prediction value of each preset position.

5. The method according to claim 1, characterized in that The coal injection amount of each tuyere is adjusted according to the predicted value of the furnace temperature of each preset position, including: Obtain the current coal injection amount of each tuyere and the current furnace temperature prediction value of each preset position, and calculate the average value, maximum value and minimum value of the current furnace temperature prediction value of each preset position; Calculate the target coal injection amount of each tuyere according to the average value, maximum value, minimum value of the current furnace temperature prediction value of each preset position and the current coal injection amount of the tuyere; The difference between the current coal injection amount of each tuyere and the target coal injection amount of each tuyere is calculated, and the coal injection amount of each tuyere is adjusted according to the difference.

6. The method according to claim 1, characterized in that The preset positions are distributed in multiple layers in the blast furnace.

7. The method according to claim 5, characterized in that Adjusting the coal injection amount of each tuyere according to the difference includes: The current coal injection amount of the corresponding tuyere is collected by using the flow meter at each preset position; Determine the setting value of the flow meter according to the difference and the current coal injection amount of the corresponding tuyere; If the set value of the flow meter is greater than the preset flow threshold, the coal injection amount of the corresponding tuyere is adjusted according to the set value of the flow meter; If the set value of the flow meter is not greater than the preset flow threshold, the set value of the flow meter is set to the preset flow threshold to adjust the coal injection amount of the corresponding tuyere.

8. A blast furnace temperature targeted regulation system based on a big data platform, characterized in that: The system comprises: A historical data acquisition module is used to acquire multiple groups of historical data in the blast furnace, the historical data including: the average cooling wall temperature of multiple preset temperature measurement points, the average tuyere area of ​​multiple preset tuyere positions, the average tuyere water inlet and outlet volume of multiple preset tuyere positions, the average tuyere coal injection volume of multiple preset tuyere positions, and the molten iron temperature of multiple iron holes; A model training module, used to train a preset neural network model using the multiple sets of historical data to obtain a furnace temperature prediction model; A furnace temperature prediction module is used to obtain real-time measurement data of multiple preset positions of the blast furnace, and obtain the furnace temperature prediction value of each preset position by using the furnace temperature prediction model, wherein the real-time measurement data includes: cooling wall temperature, tuyere area, tuyere water inlet and outlet, and tuyere coal injection amount; The furnace temperature adjustment module is used to adjust the coal injection amount of each tuyere according to the furnace temperature prediction value of each preset position, so as to achieve targeted adjustment of the furnace temperature.

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