Coal injection control method, system and device for blast furnace

Abstract

The invention discloses a coal injection control method, system and device for a blast furnace, and relates to the technical field of blast furnace coal injection control. According to the technical scheme, the tuyere image set composed of the infrared images of the blast-furnace tuyere in different operation states is obtained, and the preset image classification model is trained according to the tuyere image set, so that the image classification model identifies the operation states of the blast-furnace tuyere corresponding to the different infrared images; the current infrared image of the blast furnace tuyere is input into the image classification model to obtain the current operation state of the blast furnace tuyere, and due to the fact that the operation state at least comprises a normal combustion state, a raw material descending state, a coal gun deflection state, a coal gun burning loss state and a coal gun coal interruption state, corresponding control actions are executed on a coal gun of the blast furnace according to the current operation state. According to the control method, each abnormal state of the tuyere of the blast furnace can be accurately controlled, and the coal injection control reliability of the blast furnace is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of blast furnace coal injection control, and in particular to a blast furnace coal injection control method, system and device. Background Art

[0002] During the operation of a blast furnace, pulverized coal is sprayed into the furnace for combustion. Various abnormal conditions may occur during the combustion process. Existing monitoring methods are mostly implemented through manual visual observation, which cannot accurately identify the type of abnormal condition, resulting in deficiencies in abnormal condition handling strategies.

[0003] Therefore, how to improve the reliability of blast furnace coal injection control is a technical problem that needs to be solved urgently. Summary of the invention

[0004] The invention provides a blast furnace coal injection control method, system and device, which improve the reliability of blast furnace coal injection control.

[0005] The embodiment of the present invention provides the following solution:

[0006] In a first aspect, an embodiment of the present invention provides a method for controlling coal injection of a blast furnace, the method comprising:

[0007] Acquire a tuyere image set of a blast furnace tuyere, wherein the tuyere image set is a set of infrared images of the blast furnace tuyere in different operating states;

[0008] A preset image classification model is trained according to the tuyere image set, so that the image classification model can identify the operating status of the blast furnace tuyere corresponding to different infrared images, wherein the operating status at least includes a normal combustion state, a raw material descending state, a coal gun deflection state, a coal gun burnout state, and a coal gun broken coal state;

[0009] Input the current infrared image of the blast furnace tuyere into the image classification model to obtain the current operating status of the blast furnace tuyere;

[0010] According to the current operating state, corresponding control actions are performed on the coal gun of the blast furnace, wherein the control actions at least include normal coal injection, stopping coal injection and pipeline dredging.

[0011] In an optional embodiment, the current operating state is a raw material descending state; and the corresponding control action is performed on the coal gun of the blast furnace according to the current operating state, including:

[0012] When it is determined that the current operating state is the raw material descending state, the coal gun is controlled to stop spraying coal, and the operating state of the blast furnace tuyere is continuously monitored;

[0013] When the current operating state of the blast furnace tuyere is a normal combustion state, the coal gun is controlled to return to normal coal injection.

[0014] In an optional embodiment, the current operating state is a coal gun deflection state or a coal gun burnout state; and the corresponding control action is performed on the coal gun of the blast furnace according to the current operating state, including:

[0015] When it is determined that the current operating state is a coal gun deflection state, the deflection level of the coal gun is determined according to the tuyere image of the coal gun deflection state;

[0016] When the deflection level is less than the preset first level threshold, the coal gun is controlled according to the deflection level to perform normal coal injection with a corresponding deflection level coal injection amount;

[0017] When the deflection level is greater than or equal to the first level threshold, the coal gun is controlled to stop coal injection;

[0018] When it is determined that the current operating state is a coal gun burnout state, the coal gun burnout level is determined according to the tuyere image of the coal gun burnout state;

[0019] When the burnout level is less than the preset second level threshold, the coal gun is controlled according to the burnout level to perform normal coal injection with a corresponding coal injection amount of the burnout level;

[0020] When the burning level is greater than or equal to the second level threshold, the coal gun is controlled to stop coal injection.

[0021] In an optional embodiment, the current operating state is a coal gun out-of-coal state; performing corresponding control actions on the coal gun of the blast furnace according to the current operating state includes:

[0022] When the current operation state is determined to be a coal gun off state, the coal gun is controlled to stop coal injection;

[0023] When the coal gun stops spraying coal, the gas valve for clearing the pipeline of the coal gun is controlled to open to clear the blockage in the coal gun;

[0024] After the coal gun completes pipeline unblocking, control the coal gun to resume normal coal injection.

[0025] In an optional embodiment, training a preset image classification model according to the vent image set includes:

[0026] Classify the operating status according to the image features of each infrared image in the tuyere image set to obtain multiple infrared images of each operating status;

[0027] Dividing the multiple infrared images of each operating state into a training set and a test set of each operating state according to a preset ratio;

[0028] The image classification model is trained based on the training set for each operating state;

[0029] When the image classification model is trained, input the test set to the trained image classification model;

[0030] When the test results meet the preset conditions, it is determined that the image classification model has completed training.

[0031] In an optional embodiment, the operating state is classified according to the image features of each infrared image in the tuyere image set to obtain multiple infrared images of each operating state, including:

[0032] Determine the coal burning area of ​​each infrared image and the coal gun projection located in the coal burning area according to the image features represented by each infrared image;

[0033] When the brightness of the coal burning area is greater than a preset brightness threshold, and the coal gun end represented by the coal gun projection is located at the center of the coal burning area, and the coal gun end contains coal injection features, the infrared image is determined to be in a normal combustion state;

[0034] When the brightness of the coal burning area is less than or equal to the brightness threshold, the infrared image is determined to be in the raw material falling state;

[0035] When the brightness of the coal burning area is greater than the brightness threshold, and the coal gun end represented by the coal gun projection is not located at the center of the coal burning area, it is determined that the infrared image is in a coal gun tilt state;

[0036] When there is a gap in the coal gun projection, it is determined that the infrared image is in the coal gun burnout state;

[0037] When the end of the coal gun does not contain coal injection features, it is determined that the infrared image is in a coal gun broken state.

[0038] In a second aspect, an embodiment of the present invention further provides a coal injection control system for a blast furnace, the system comprising:

[0039] Infrared thermal imager, used to obtain infrared images of blast furnace tuyere under different operating conditions;

[0040] Host computer, the input end of the host computer is connected to the output end of the infrared thermal imager,

[0041] The host computer is used to store multiple infrared images as a set of tuyere images of blast furnace tuyere;

[0042] and training a preset image classification model according to the tuyere image set, so that the image classification model can identify the operating status of the blast furnace tuyere corresponding to different infrared images, wherein the operating status at least includes a normal combustion state, a raw material descending state, a coal gun deflection state, a coal gun burnout state, and a coal gun broken coal state;

[0043] The current infrared image of the blast furnace tuyere is input into the image classification model to obtain the current operating status of the blast furnace tuyere;

[0044] Controller, the input end of the controller is connected to the output end of the host computer;

[0045] The controller is used to execute corresponding control actions on the coal gun of the blast furnace according to the current operating state, wherein the control actions at least include normal coal injection, stopping coal injection and pipeline dredging.

[0046] In a third aspect, an embodiment of the present invention further provides a coal injection control device for a blast furnace, the device comprising:

[0047] An acquisition module is used to acquire a set of tuyere images of a blast furnace tuyere, wherein the set of tuyere images is a set of infrared images of the blast furnace tuyere in different operating states;

[0048] A training module is used to train a preset image classification model according to a set of tuyere images, so that the image classification model can identify the operating status of the blast furnace tuyere corresponding to different infrared images, wherein the operating status at least includes a normal combustion state, a raw material descending state, a coal gun deflection state, a coal gun burnout state, and a coal gun broken coal state;

[0049] An acquisition module is used to input the current infrared image of the blast furnace tuyere into the image classification model to obtain the current operating state of the blast furnace tuyere;

[0050] The control module is used to perform corresponding control actions on the coal gun of the blast furnace according to the current operating state, wherein the control actions at least include normal coal injection, stopping coal injection and pipeline dredging.

[0051] In a fourth aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory is coupled to the processor and stores instructions, and when the instructions are executed by the processor, the electronic device executes the steps of any one of the methods in the first aspect.

[0052] In a fifth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0053] Compared with the prior art, the coal injection control method, system and device of a blast furnace of the present invention have the following advantages:

[0054] The technical solution of the present invention obtains a tuyere image set consisting of infrared images of the blast furnace tuyere in different operating states, and trains a preset image classification model according to the tuyere image set, so that the image classification model can recognize the operating states of the blast furnace tuyere corresponding to different infrared images; the current infrared image of the blast furnace tuyere is input into the image classification model to obtain the current operating state of the blast furnace tuyere. Since the operating state at least includes normal combustion state, raw material descending state, coal gun deflection state, coal gun burnout state and coal gun broken coal state, the coal gun of the blast furnace is subjected to corresponding control actions according to the current operating state, so that the coal gun corresponds to accurately execute normal coal injection, stop coal injection and pipeline dredging. The control method reduces the misjudgment of observation by the human eye, so that each abnormal state of the blast furnace tuyere can be accurately controlled, thereby improving the reliability of blast furnace coal injection control. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 A flow chart of a coal injection control method for a blast furnace provided by an embodiment of the present invention;

[0057] Figure 2-1 An infrared image of a normal combustion state provided by an embodiment of the present invention;

[0058] Figure 2-2 An infrared image of the raw material descent state provided by an embodiment of the present invention;

[0059] Figure 2-3 An infrared image of the deflection state of a coal gun provided by an embodiment of the present invention;

[0060] Figure 2-4 An infrared image of the burnout state of a coal gun provided in an embodiment of the present invention;

[0061] Figure 2-5 An infrared image of a coal gun broken coal state provided by an embodiment of the present invention;

[0062] Figure 3 A flowchart for implementing training and application of the image classification model provided by an embodiment of the present invention;

[0063] Figure 4 A schematic structural diagram of a coal injection control device for a blast furnace provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0064] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention belong to the scope of protection of the embodiments of the present invention.

[0065] See also Figure 1 , Figure 1 The flowchart of a blast furnace coal injection control method provided by an embodiment of the present invention can be applied to the control terminal of the blast furnace to implement the operation control of the blast furnace. The control terminal can be a PLC (Programmable Logic Controller) or other equipment capable of running the method, which is not specifically limited here. The control method includes:

[0066] S11. Acquire a tuyere image set of a blast furnace tuyere, wherein the tuyere image set is a set of infrared images of the blast furnace tuyere under different operating conditions.

[0067] Specifically, the infrared image can be acquired based on an infrared thermal imager or a CCD (Charge coupled Device) camera. Taking the infrared thermal imager as an example, it can be set up outside the blast furnace tuyere and the infrared image of the blast furnace tuyere can be acquired based on a preset period when the blast furnace is in operation. Since the tuyere peephole area of ​​the blast furnace tuyere is small, but the temperature of the tuyere whirlpool area is high, the infrared thermal imager should have a narrow field of view, and the imaging area is about 3.14×10 -4 m 2 , the temperature measurement range of the infrared thermal imager is 0 to 2400°C. The acquired infrared images include images of the blast furnace tuyere in different operating states. All infrared images can be classified, and a preset number of infrared images in various operating states can be selected and combined into a tuyere image set. Of course, it is also possible to record the video data of the blast furnace tuyere based on a CCD camera, decompose the video data into image frames of the working state of the tuyere area, and combine all the image frames into a tuyere image set. After obtaining the tuyere image set, step S12 is entered.

[0068] S12. Train a preset image classification model based on the tuyere image set so that the image classification model can identify the operating status of the blast furnace tuyere corresponding to different infrared images, wherein the operating status at least includes a normal combustion state, a raw material descending state, a coal gun deflection state, a coal gun burnout state, and a coal gun broken coal state.

[0069] Specifically, the image classification model can be selected according to actual needs. The CNN (Convolutional Neural Network) model can be selected as the image classification model, and the vent image set is divided into a training set and a test set. Each infrared image in the training set is marked with a corresponding operating state. The image classification model identifies the features of the corresponding operating state of each infrared image during the training process, so that it can implement image classification of the operating state. After the training is completed, the image classification model is tested with the test set to determine the accuracy of its classification after training. When the accuracy rate is greater than 90%, it means that the image classification model can be implemented and applied, and it is determined that the image classification model has completed training.

[0070] Exemplarily, training a preset image classification model based on a tuyere image set includes:

[0071] In the first step, the operating status is classified according to the image features of each infrared image in the tuyere image set to obtain multiple infrared images of each operating status. The image features represent the characteristics of the operating status. The infrared images can be marked based on the characteristics of different operating states of the blast furnace tuyere, which is convenient for subsequent training and testing.

[0072] The coal burning area of ​​each infrared image and the coal gun projection within the coal burning area can be determined based on the image features represented by each infrared image. The infrared image is taken at the tuyere of the blast furnace. Since the coal gun is located outside the tuyere of the blast furnace, the coal gun will be photographed at the same time when the infrared image is taken. Since the pulverized coal has a high brightness during combustion, it will be projected onto the coal gun to form a coal gun projection. Based on the above features, the coal burning area and coal gun projection can be determined in each infrared image. The following will generate how to implement markings for different operating states based on the above features.

[0073] See also Figure 2-1 , Figure 2-1 Schematic diagram of infrared image in normal combustion state. When the brightness of the coal burning area is greater than the preset brightness threshold, and the end of the coal gun represented by the coal gun projection is located at the center of the coal burning area, the end of the coal gun needs to spray coal powder into the blast furnace, and the end of the coal gun contains coal spraying characteristics, it means that the coal powder is in a normal combustion state, the coal gun is accurately positioned, and normal coal spraying can be implemented, and the infrared image is determined to be in a normal combustion state. The coal spraying characteristics can be determined based on the grayscale characteristics in the end of the coal gun. The coal powder sprayed from the coal gun will affect the projection of the coal powder combustion light on the coal gun. Therefore, the grayscale of the central area of ​​the coal gun end will be different from other areas of the coal gun projection. Based on this distinguishing feature, it can be determined whether the end of the coal gun contains coal spraying characteristics.

[0074] See also Figure 2-2 , Figure 2-2Schematic diagram of infrared image of raw material falling state When the brightness of the coal burning area is less than or equal to the brightness threshold, the infrared image is determined to be in the raw material falling state. Blast furnace slag is generally composed of gangue in ore, ash and solvent in fuel. When the blast furnace slag changes from solid to liquid in the furnace, it drips continuously through the coke column and enters the furnace. Once the slag located in the edge area of ​​the blast furnace drips to the tuyere, due to the high cooling intensity at the front end of the tuyere, the slag changes from liquid to solid slag skin again at the front end of the tuyere. This phenomenon is called "raw material falling". At this time, if coal is continuously sprayed, it will cause coal powder to continuously enter the solid slag skin, which will eventually make it difficult for the tuyere to enter the air, affecting the normal production of the blast furnace. Therefore, when the brightness of the coal burning area is less than or equal to the brightness threshold, it means that the injected coal powder has entered the solid slag skin state, and the operation state of this infrared image is determined to be the raw material falling state.

[0075] See also Figure 2-3 , Figure 2-3 The figure is a schematic diagram of an infrared image of a coal gun tilted state. When the brightness of the coal combustion area is greater than the brightness threshold, and the coal gun end represented by the coal gun projection is not located at the center of the coal combustion area, the infrared image is determined to be in a coal gun tilted state. After the coal gun is tilted, coal injection can be carried out normally, but the coal injection direction is not ideal, which may cause incomplete combustion of coal powder. The coal gun projection on the infrared image is different from the coal gun projection position in the normal combustion state. Therefore, when the coal gun end is not located at the center of the coal combustion area, the infrared image is determined to be in a coal gun tilted state.

[0076] See also Figure 2-4 , Figure 2-4 The figure is a schematic diagram of an infrared image of a coal gun burnout state. When there is a gap in the coal gun projection, the infrared image is determined to be in a coal gun burnout state. The coal gun burnout state is the state after the coal powder ablates the coal gun. The projection contour can be extracted based on the characteristics of the coal gun projection. When the projection contour is smooth, it means that there is no gap in the coal gun projection and the coal gun has not been ablated. On the contrary, if there is a gap in the coal gun projection, it means that there is ablation in part of the coal gun, and the infrared image is determined to be in a coal gun burnout state.

[0077] See also Figure 2-5 , Figure 2-5 The infrared image schematic diagram of the coal gun broken coal state. When the coal gun end does not contain the coal injection feature, the infrared image is determined to be in the coal gun broken coal state. The coal gun broken coal state is caused by impurities in the coal powder blocking the coal injection hole of the coal gun, resulting in the inability to implement coal injection normally, that is, the infrared image does not have the grayscale feature of the position where the coal powder is sprayed, and the infrared image is determined to be in the coal gun broken coal state.

[0078] Based on the image features of the infrared image under each operating state, state marking can be implemented. The marking process can be implemented by a computer or manually, and there is no specific limitation here. After completing the state marking, proceed to the next step.

[0079] The second step is to divide the multiple infrared images of each operating state into a training set and a test set for each operating state according to a preset ratio. The preset ratio can be set based on actual needs, such as 7:3 or 8:2, or different preset ratios can be set based on different operating states. When the difficulty of identifying the operating state is relatively small, the preset ratio is set to 8:2, for example, the raw material falling state and the coal gun deflection state can be set to this ratio; when the difficulty of identifying the operating state is relatively large and it is easy to cause confusion in identification, the training set and test set of the operating state are set to 7:3, so as to facilitate the subsequent accurate training.

[0080] The third step is to train the image classification model based on the training set of each operating state. The training set of each operating state can be fed to the image classification model, and the image classification model performs feature recognition.

[0081] The fourth step is to input the test set into the trained image classification model after the image classification model has been trained. The purpose of this step is to test the training results of the image classification model. The test set can be used to determine whether the image classification model can accurately identify the image features of each operating state.

[0082] Step 5: When the test results meet the preset conditions, it means that the image classification model can accurately identify the image features of each operating state, and it is determined that the image classification model has completed training. The preset conditions can be set based on actual needs, for example, the preset condition is set to a test accuracy of more than 90%. After the image classification model completes training, step S13 is entered.

[0083] S13, inputting the current infrared image of the blast furnace tuyere into the image classification model to obtain the current operating status of the blast furnace tuyere.

[0084] Specifically, this step is the application process of the image classification model. The blast furnace tuyere can be photographed in real time during the operation of the blast furnace to obtain the current infrared image, which is input into the image classification model. The image classification model determines the current operating state of the blast furnace tuyere based on the image features of the current infrared image. The current operating state is any one of the normal combustion state, the raw material falling state, the coal gun deflection state, the coal gun burnout state and the coal gun broken coal state. After determining the current operating state of the blast furnace tuyere, step S14 is entered.

[0085] S14. Execute corresponding control actions on the coal gun of the blast furnace according to the current operating state, wherein the control actions at least include normal coal injection, stopping coal injection and pipeline dredging.

[0086] Specifically, the current operating state characterizes the combustion state and coal injection state of the blast furnace tuyere. Based on the current operating state, it can be determined whether the combustion and coal injection are normal, as well as the specific types of abnormalities, and then the corresponding control strategy can be implemented. Normal coal injection is to continue to inject coal powder into the blast furnace to ensure the normal operation of the blast furnace; stopping coal injection can be to stop coal injection and carry out maintenance, or to suspend coal injection; pipeline dredging is to clean impurities in the coal injection pipeline to ensure the smooth implementation of normal coal injection. This control method uses an infrared thermal imager to observe the working status of the tuyere area, integrates artificial intelligence and automatic control technology to form a closed loop, which can reduce the misjudgment rate of existing technologies through human eyes and improve the production efficiency and automation rate of ironmaking.

[0087] The following will specifically describe how to implement corresponding control actions under different current operating states.

[0088] When it is determined that the current operating state is the raw material falling state, it means that the coal powder is constantly entering the solid slag skin. If the coal injection continues, it will cause difficulty in air intake at the tuyere. Then the coal gun is controlled to stop coal injection and the operating state of the blast furnace tuyere is continued to be monitored. When the current operating state of the blast furnace tuyere is the normal combustion state, the coal gun is controlled to resume normal coal injection. This control strategy can ensure that when the raw material falls at the blast furnace tuyere, the coal gun is controlled to stop coal injection in time, and resume coal injection in time after the raw material falling state subsides.

[0089] When it is determined that the current operating state is a coal gun deflection state, it means that there is a deviation in the coal injection direction, but coal injection can still be implemented, and the deflection level of the coal gun is determined according to the tuyere image of the coal gun deflection state. When the deflection level is less than the preset first level threshold, it means that coal injection can continue, and the coal gun is controlled according to the deflection level to perform normal coal injection with the corresponding deflection level coal injection amount; when the deflection level is greater than or equal to the first level threshold, it means that the deflection degree of the coal gun is more serious. In order to prevent the coal injection abnormality from further expanding, the coal gun is controlled to stop coal injection.

[0090] Similarly, when it is determined that the current operating state is a coal gun burnout state, the burnout level of the coal gun is determined based on the tuyere image of the coal gun burnout state; when the burnout level is less than the preset second-level threshold, the coal gun is controlled to perform normal coal injection at a corresponding coal injection amount according to the burnout level; when the burnout level is greater than or equal to the second-level threshold, the coal gun is controlled to stop coal injection. When the coal gun is controlled to stop coal injection, an alarm signal can also be output to remind on-site inspection personnel to inspect and repair the coal gun. The alarm signal can be an audible and visual alarm signal, which can remind on-site personnel. It should be noted that the first-level threshold and the second-level threshold can be freely set based on the usage requirements of the actual scenario, and are not specifically limited here.

[0091] When it is determined that the current operating state is the coal gun off-coal state, the coal gun is controlled to stop spraying coal; when the coal gun stops spraying coal, the gas valve for unblocking the coal gun pipeline is controlled to open to clear the blockage in the coal gun; after the coal gun completes pipeline unblocking, the coal gun is controlled to resume normal coal spraying. The coal gun includes two input pipelines, specifically a coal powder input pipeline and a compressed gas input pipeline, which are respectively controlled by corresponding solenoid valves. When it is determined that the current operating state is the coal gun off-coal state, the solenoid valve of the coal powder input pipeline is first controlled to operate to stop the coal gun from spraying coal; then the solenoid valve of the compressed gas input pipeline is controlled to operate to unblock the coal gun pipeline with compressed gas. When the pressure relief pressure or the length of time of the compressed gas reaches the preset threshold, it means that the pipeline of the coal gun is unblocked, and the coal gun is controlled to resume normal coal spraying.

[0092] The following embodiment of the present invention takes the recognition and control of the raw material descending state as an example to explain the blast furnace coal injection control method as a whole. Figure 3 , Figure 3 Flowchart for training and applying image classification models. The steps are:

[0093] S301. An infrared thermal imager is used to collect images of the blast furnace tuyere to obtain multiple infrared images of the raw material descent state.

[0094] S302: labeling multiple infrared images.

[0095] S303 , dividing the plurality of infrared images into a training data set and a test data set at a preset ratio of 8:2.

[0096] S304: Train and test the image classification model based on the training data set and the test data set.

[0097] S305: When the recognition accuracy of the image classification model reaches greater than 90%, the image classification model is deployed online to the host computer.

[0098] S306, monitoring is performed by using an infrared thermal imager at the blast furnace tuyere to sense the current infrared image of the blast furnace tuyere, and data is transmitted via the TCP / IP protocol to output the current infrared image to a host computer.

[0099] S307: The host computer analyzes the current infrared image based on the deployed image classification model, and outputs instructions for corresponding execution actions based on the OPC protocol.

[0100] S308. Execute control actions of the coal gun based on the instructions of the host computer, the control actions including normal coal injection and stopping coal injection.

[0101] Based on the same technical concept as the control method, an embodiment of the present invention further provides a coal injection control system for a blast furnace, the system comprising an infrared thermal imager, a host computer and a controller.

[0102] The infrared thermal imager is used to obtain infrared images of the blast furnace tuyere under different operating conditions.

[0103] The input end of the host computer is connected to the output end of the infrared thermal imager, and the host computer is used to store multiple infrared images as a set of tuyere images of the blast furnace tuyere; and train a preset image classification model according to the tuyere image set, so that the image classification model can identify the operating state of the blast furnace tuyere corresponding to different infrared images, wherein the operating state at least includes normal combustion state, raw material falling state, coal gun deflection state, coal gun burnout state and coal gun broken state; and input the current infrared image of the blast furnace tuyere into the image classification model to obtain the current operating state of the blast furnace tuyere. The host computer can be an industrial computer, which integrates kepserver software for communication with the controller. The data transmission volume between the industrial computer and the infrared thermal imager is large, and the required industrial computer should have high performance requirements, with a CPU main frequency of not less than 4GHz, a memory of not less than 32G, a hard disk capacity of not less than 1T, and a network card bandwidth of not less than 1Gbps.

[0104] The input end of the controller is connected to the output end of the host computer; the controller is used to perform corresponding control actions on the coal gun of the blast furnace according to the current operating state, wherein the control actions at least include normal coal injection, stop coal injection and pipeline dredging. The controller can use PLC, which should have an OPC communication interface, through which it communicates with the kepserver software. The control action can be generated by the host computer and transmitted to the controller through binary for execution. For example, normal coal injection and stop coal injection are set to switch values ​​0 or 1. When the controller outputs 0, the coal gun is controlled to spray coal normally, and when the controller outputs 1, the coal gun is controlled to stop spraying coal.

[0105] Based on the same technical concept as the control method, the embodiment of the present invention also provides a blast furnace coal injection control device, please refer to Figure 4 , Figure 4 The control device includes:

[0106] An acquisition module 401 is used to acquire a set of tuyere images of a blast furnace tuyere, wherein the set of tuyere images is a set of infrared images of the blast furnace tuyere in different operating states;

[0107] The training module 402 is used to train a preset image classification model according to the tuyere image set, so that the image classification model can identify the operating status of the blast furnace tuyere corresponding to different infrared images, wherein the operating status at least includes a normal combustion state, a raw material descending state, a coal gun deflection state, a coal gun burnout state, and a coal gun broken coal state;

[0108] An acquisition module 403 is used to input the current infrared image of the blast furnace tuyere into the image classification model to obtain the current operating state of the blast furnace tuyere;

[0109] The control module 404 is used to perform corresponding control actions on the coal gun of the blast furnace according to the current operating state, wherein the control actions at least include normal coal injection, stopping coal injection and pipeline dredging.

[0110] In an optional embodiment, the current operating state is a raw material descending state; the control module includes:

[0111] The first determination submodule is used to control the coal gun to stop coal injection when determining that the current operating state is the raw material descending state, and continue to monitor the operating state of the blast furnace tuyere;

[0112] The first control submodule is used to control the coal gun to return to normal coal injection when the current operating state of the blast furnace tuyere is a normal combustion state.

[0113] In an optional embodiment, the current operating state is a coal gun deflection state or a coal gun burnout state; the control module further includes:

[0114] The second determination submodule is used to determine the deflection level of the coal gun according to the tuyere image of the deflection state of the coal gun when the current operating state is determined to be the deflection state of the coal gun;

[0115] The second control submodule is used to control the coal gun to perform normal coal injection with a corresponding coal injection amount of the skew level according to the skew level when the skew level is less than a preset first level threshold;

[0116] The third control submodule is used to control the coal gun to stop coal injection when the deflection level is greater than or equal to the first level threshold;

[0117] The third determination submodule is used to determine the burnout level of the coal gun according to the tuyere image of the burnout state of the coal gun when the current operation state is determined to be the burnout state of the coal gun;

[0118] The fourth control submodule is used to control the coal gun to perform normal coal injection with a corresponding coal injection amount according to the burn-down level when the burn-down level is less than the preset second level threshold value;

[0119] The fifth control submodule is used to control the coal gun to stop coal injection when the burnout level is greater than or equal to the second level threshold.

[0120] In an optional embodiment, the current operating state is a coal gun coal-free state; the control module further includes:

[0121] The fourth determination submodule is used to control the coal gun to stop coal injection when determining that the current operating state is a coal gun coal-off state;

[0122] The sixth control submodule is used to control the opening of the gas valve for clearing the pipeline of the coal gun when the coal gun stops spraying coal, so as to clear the blockage in the coal gun;

[0123] The seventh control submodule is used to control the coal gun to return to normal coal injection after the coal gun completes pipeline dredging.

[0124] In an optional embodiment, the training module includes:

[0125] A processing and obtaining submodule is used to classify the operating state according to the image features of each infrared image in the tuyere image set, so as to obtain multiple infrared images of each operating state;

[0126] A division acquisition submodule is used to divide the multiple infrared images of each operating state into a training set and a test set of each operating state according to a preset ratio;

[0127] A training submodule, used for training the image classification model according to the training set of each operating state;

[0128] An input submodule, used for inputting a test set into the trained image classification model when the image classification model has completed training;

[0129] The fifth determination submodule is used to determine whether the image classification model has completed training when the test result meets a preset condition.

[0130] In an optional embodiment, the processing obtaining submodule includes:

[0131] A first determination unit is used to determine the coal burning area of ​​each infrared image and the coal gun projection located in the coal burning area according to the image features represented by each infrared image;

[0132] The second determination unit is used to determine that the infrared image is in a normal combustion state when the brightness of the coal combustion area is greater than a preset brightness threshold, the coal gun end represented by the coal gun projection is located at the center of the coal combustion area, and the coal gun end contains coal injection features;

[0133] The third determination unit is used to determine that the infrared image is in a raw material falling state when the brightness of the coal burning area is less than or equal to the brightness threshold;

[0134] A fourth determination unit is used to determine that the infrared image is in a coal gun tilted state when the brightness of the coal combustion area is greater than a brightness threshold and the coal gun end represented by the coal gun projection is not located at the center of the coal combustion area;

[0135] A fifth determination unit, configured to determine that the infrared image is in a coal gun burnout state when there is a gap in the coal gun projection;

[0136] The sixth determination unit is used to determine that the infrared image is in a coal lance broken coal state when the end of the coal lance does not contain the coal injection feature.

[0137] Based on the same technical concept as the control method, an embodiment of the present invention also provides an electronic device, including a processor and a memory, wherein the memory is coupled to the processor and stores instructions, and when the instructions are executed by the processor, the electronic device executes the steps of any one of the control methods.

[0138] Based on the same technical concept as the control method, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of any one of the control methods are implemented.

[0139] The technical solution provided in the embodiments of the present invention has at least the following technical effects or advantages:

[0140] By acquiring a tuyere image set consisting of infrared images of the blast furnace tuyere in different operating states, a preset image classification model is trained according to the tuyere image set, so that the image classification model can recognize the operating states of the blast furnace tuyere corresponding to different infrared images; the current infrared image of the blast furnace tuyere is input into the image classification model, so as to obtain the current operating state of the blast furnace tuyere. Since the operating state at least includes the normal combustion state, the raw material descending state, the coal gun deflection state, the coal gun burnout state and the coal gun broken coal state, the corresponding control action is performed on the coal gun of the blast furnace according to the current operating state, so that the coal gun can accurately perform normal coal injection, stop coal injection and pipeline unblocking. The control method reduces the misjudgment of observation by the human naked eye, so that each abnormal state of the blast furnace tuyere can be accurately controlled, thereby improving the reliability of blast furnace coal injection control.

[0141] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented 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.

[0142] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (modules, systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0143] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0144] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0145] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0146] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for controlling coal injection of a blast furnace, characterized in that: The method comprises: Acquire a tuyere image set of a blast furnace tuyere, wherein the tuyere image set is a set of infrared images of the blast furnace tuyere in different operating states; A preset image classification model is trained according to the tuyere image set, so that the image classification model can identify the operating state of the blast furnace tuyere corresponding to different infrared images, wherein the operating state at least includes a normal combustion state, a raw material descending state, a coal gun deflection state, a coal gun burnout state, and a coal gun broken coal state; Inputting the current infrared image of the blast furnace tuyere into the image classification model to obtain the current operating state of the blast furnace tuyere; According to the current operating state, corresponding control actions are performed on the coal gun of the blast furnace, wherein the control actions at least include normal coal injection, stopping coal injection and pipeline dredging.

2. The method for controlling coal injection of a blast furnace according to claim 1, characterized in that: The current operating state is a raw material descending state; and the corresponding control action is performed on the coal gun of the blast furnace according to the current operating state, including: When it is determined that the current operating state is a raw material descending state, the coal gun is controlled to stop coal injection, and the operating state of the blast furnace tuyere is continuously monitored; When the current operating state of the blast furnace tuyere is the normal combustion state, the coal gun is controlled to return to normal coal injection.

3. The coal injection control method for a blast furnace according to claim 1, characterized in that: The current operating state is a coal gun deflection state or a coal gun burnout state; and the corresponding control action is performed on the coal gun of the blast furnace according to the current operating state, including: When it is determined that the current operating state is a coal gun deflection state, determining the deflection level of the coal gun according to the tuyere image of the coal gun deflection state; When the deflection level is less than a preset first level threshold, the coal gun is controlled according to the deflection level to perform normal coal injection with a coal injection amount corresponding to the deflection level; When the deflection level is greater than or equal to the first level threshold, controlling the coal gun to stop coal injection; When it is determined that the current operating state is a coal gun burnout state, determining the burnout level of the coal gun according to the tuyere image of the coal gun burnout state; When the burnout level is less than a preset second level threshold, the coal gun is controlled to perform normal coal injection at a corresponding coal injection amount of the burnout level according to the burnout level; When the burnout level is greater than or equal to the second level threshold, the coal gun is controlled to stop coal injection.

4. The coal injection control method for a blast furnace according to claim 1, characterized in that: The current operating state is a coal gun out-of-coal state; and the corresponding control action is performed on the coal gun of the blast furnace according to the current operating state, including: When determining that the current operating state is a coal gun coal-off state, controlling the coal gun to stop coal injection; When the coal gun stops spraying coal, the gas valve for clearing the pipeline of the coal gun is controlled to open to clear the blockage in the coal gun; After the coal gun completes pipeline dredging, the coal gun is controlled to resume normal coal injection.

5. The coal injection control method for a blast furnace according to claim 1, characterized in that: The step of training a preset image classification model according to the tuyere image set includes: Classifying the operating state according to the image features of each infrared image in the tuyere image set to obtain multiple infrared images of each operating state; Dividing the multiple infrared images of each operating state into a training set and a test set of each operating state according to a preset ratio; Training the image classification model according to the training set of each operating state; When the image classification model has completed training, inputting the test set into the trained image classification model; When the test result meets a preset condition, it is determined that the image classification model has completed training.

6. The method for controlling coal injection of a blast furnace according to claim 5, characterized in that: The classifying process of the operating state according to the image features of each infrared image in the tuyere image set to obtain a plurality of infrared images of each operating state includes: Determine the coal burning area of ​​each infrared image and the coal gun projection located in the coal burning area according to the image features represented by each infrared image; When the brightness of the coal combustion area is greater than a preset brightness threshold, and the coal gun end represented by the coal gun projection is located at the center of the coal combustion area, and the coal gun end contains coal injection features, it is determined that the infrared image is in a normal combustion state; When the brightness of the coal burning area is less than or equal to the brightness threshold, determining that the infrared image is in a raw material falling state; When the brightness of the coal burning area is greater than the brightness threshold, and the coal gun end represented by the coal gun projection is not located at the center of the coal burning area, determining that the infrared image is in a coal gun tilted state; When there is a gap in the coal gun projection, it is determined that the infrared image is in a coal gun burnout state; When the end of the coal gun does not contain the coal injection feature, it is determined that the infrared image is in the coal gun broken coal state.

7. A coal injection control system for a blast furnace, characterized in that: The system comprises: Infrared thermal imager, used to obtain infrared images of blast furnace tuyere under different operating conditions; A host computer, the input end of which is connected to the output end of the infrared thermal imager, The host computer is used to store the multiple infrared images as a set of tuyere images of the blast furnace tuyere; and training a preset image classification model according to the tuyere image set, so that the image classification model can identify the operating status of the blast furnace tuyere corresponding to different infrared images, wherein the operating status at least includes a normal combustion state, a raw material descending state, a coal gun deflection state, a coal gun burnout state, and a coal gun broken coal state; and inputting the current infrared image of the blast furnace tuyere into the image classification model to obtain the current operating state of the blast furnace tuyere; A controller, wherein an input end of the controller is connected to an output end of the host computer; The controller is used to perform corresponding control actions on the coal gun of the blast furnace according to the current operating state, wherein the control actions at least include normal coal injection, stopping coal injection and pipeline dredging.

8. A coal injection control device for a blast furnace, characterized in that: The device comprises: An acquisition module, used for acquiring a tuyere image set of a blast furnace tuyere, wherein the tuyere image set is a set of infrared images of the blast furnace tuyere in different operating states; A training module is used to train a preset image classification model according to the tuyere image set, so that the image classification model can identify the operating state of the blast furnace tuyere corresponding to different infrared images, wherein the operating state at least includes a normal combustion state, a raw material descending state, a coal gun deflection state, a coal gun burnout state, and a coal gun broken coal state; An acquisition module, used for inputting the current infrared image of the blast furnace tuyere into the image classification model to obtain the current operating state of the blast furnace tuyere; The control module is used to perform corresponding control actions on the coal gun of the blast furnace according to the current operating state, wherein the control actions at least include normal coal injection, stopping coal injection and pipeline dredging.

9. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein the memory is coupled to the processor and stores instructions, and when the instructions are executed by the processor, the electronic device executes the steps of the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 6 are implemented.

Images