A method and system for real-time evaluation and optimization of the baking state of a refining furnace

Abstract

The application discloses a kind of real-time evaluation and optimization methods of refining furnace in-furnace baking state, comprising the following steps: in the state of stopping furnace and when baking, three-dimensional point cloud in furnace, refractory surface microscale image, radiation image are collected, and the three-dimensional size information in furnace, refractory gap expansion information and refractory surface temperature information are calculated, obtain multiple baking state distribution;According to multiple baking state distribution, the correlation between baking curve and multiple baking state distribution is analyzed and determined;According to the correlation, the baking effect of the refining furnace is evaluated;If baking effect reaches the expected target, the present baking process is completed;If it does not reach the expected target, optimize the baking curve, continue baking operation until the baking effect reaches the expected target.The application also discloses a kind of real-time evaluation and optimization system of refining furnace in-furnace baking state.The application constructs refining furnace baking state real-time online monitoring and evaluation system, improves baking efficiency and fine management level.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of production detection of steelmaking refining furnace, and particularly relates to a real-time evaluation and optimization method and system for an in-furnace baking state of a refining furnace. BACKGROUND

[0002] The steelmaking refining process is a necessary means to improve the quality of steel products, increase the added value and competitiveness, and the number of refining furnaces in a service life of a primary furnace is an important index for evaluating the service life of a refining furnace, improving production efficiency and reducing production cost. Due to the influence of high-temperature molten steel erosion on the refractory bricks in the refining furnace, the service life of the refractory bricks is limited, and the refractory bricks need to be replaced and baked in each service life cycle, which is an important process for the refining furnace to proceed to the next service life cycle.

[0003] How to improve the number of service life of the refining furnace in a primary furnace is an important problem in the equipment maintenance of the refining process. At present, the baking process generally uses the baking curve proposed by expert experience to bake the refining furnace after replacing the refractory material. The baking state in the furnace reaches what state, and there is no evaluation index to evaluate the baking process in real time. Only the number of refining furnaces after the end of the service life of the primary furnace can be evaluated, and different steel grades need to be explored to reduce the baking time as much as possible under the condition of optimizing the baking state of the refining furnace to save fuel consumption and improve the service operation rate of the refining furnace. SUMMARY

[0004] In view of the deficiencies in the prior art, the purpose of the present application is to provide a real-time evaluation and optimization method and system for an in-furnace baking state of a refining furnace.

[0005] In order to achieve the above-mentioned purpose, the technical scheme provided by an embodiment of the present application is as follows:

[0006] A real-time evaluation and optimization method for an in-furnace baking state of a refining furnace, comprising the following steps:

[0007] S1: collecting the three-dimensional point cloud in the furnace, the micro-scale image of the surface of the refractory material, and the radiation image of the surface of the refractory material before baking in the state of stopping the furnace after replacing the refractory material in the refining furnace, and calculating the three-dimensional size information in the furnace, the gap expansion information of the refractory material, and the surface temperature information of the refractory material;

[0008] S2: then starting baking according to the baking curve, the baking process including multiple baking stages, collecting the three-dimensional point cloud in the furnace, the micro-scale image of the surface of the refractory material, and the radiation image of the surface of the refractory material at the end of each baking stage, and calculating the corresponding three-dimensional size information in the furnace, the gap expansion information of the refractory material, and the surface temperature information of the refractory material to obtain multiple baking state distributions during baking;

[0009] S3: Analyzing and determining the correlation between the baking curve and the plurality of baking state distributions according to the plurality of baking state distributions obtained in step S2;

[0010] S4: Evaluating the baking effect of the refining furnace according to the correlation obtained in step S3, if the baking effect reaches the expected target, the baking process is completed; if the baking effect does not reach the expected target, the baking curve is optimized, and the baking operation is continued until the baking effect reaches the expected target.

[0011] As a further improvement of the present application, the three-dimensional size information in the furnace is obtained by the three-dimensional reconstruction model.

[0012] As a further improvement of the present application, the refractory material gap expansion information is obtained by a deep learning algorithm.

[0013] As a further improvement of the present application, the refractory material surface temperature information is obtained by a blackbody furnace calibration algorithm.

[0014] As a further improvement of the present application, the baking state distribution is constructed by three parameters of the three-dimensional size information in the furnace, the refractory material gap expansion information, and the refractory material surface temperature information, and the calculation formula is as follows:

[0015]

[0016] Wherein, H ki is the baking state distribution of the i-th baking stage of the k steel refining furnace; σ k is the three-dimensional size weight value of the k steel refining furnace; ρ k is the refractory material gap expansion weight value of the k steel refining furnace; is the refractory material surface temperature weight value of the k steel refining furnace; D i (Δx i , Δy i , Δz i ) is the three-dimensional size change value of the refining furnace; E i (Δε i ) is the expansion volume of the refractory material gap of the refining furnace; T i (Δt i ) is the change value of the refractory material surface temperature of the refining furnace.

[0017] As a further improvement of the present application, the parameter weight values of the baking state distributions of the same steel of the same refining furnace are the same, and the parameter weight values of the baking state distributions of different steels of the same refining furnace are different.

[0018] As a further improvement of the present application, the baking effect grade of the refining furnace is evaluated by combining expert experience and big data analysis.

[0019] As a further improvement of the present application, the baking curve is a curve of atmosphere temperature versus baking time.

[0020] A real-time evaluation and optimization system for baking state in a refining furnace, characterized in that it is applied to the method, comprising:

[0021] A baking state detection unit for collecting three-dimensional point clouds in the furnace, micro-scale images of the refractory material surface, and radiation images of the refractory material surface at different baking stages before and during baking of the refining furnace;

[0022] A control unit for controlling the height and circumferential position of the top lance and baking control according to the feedback unit after optimization of the baking curve;

[0023] A fixing and communication unit for fixing the baking state detection unit to the top lance and transmitting the collected three-dimensional point clouds in the furnace, micro-scale images of the refractory material surface, and radiation images of the refractory material surface to the main server;

[0024] A main server for receiving three-dimensional point clouds in the furnace, micro-scale images of the refractory material surface, and radiation images of the refractory material surface at different baking stages before and during baking of the refining furnace, and calculating three-dimensional size information in the furnace, refractory material gap expansion information, and refractory material surface temperature information, respectively, calculating the baking state at different baking stages, and obtaining real-time evaluation and optimization results of the baking state;

[0025] A feedback unit for issuing an instruction to optimize the baking curve to the control unit according to the real-time evaluation and optimization results of the baking state of the main server.

[0026] As a further improvement of the present application, the baking state detection unit comprises:

[0027] A three-dimensional point cloud collection module for collecting three-dimensional point clouds in the furnace of the refining furnace;

[0028] A micro-scale image collection module for collecting micro-scale images of the refractory material surface of the refining furnace;

[0029] A surface radiation image collection module for collecting radiation images of the refractory material surface of the refining furnace;

[0030] A cooling module for cooling the three-dimensional point cloud collection module, the micro-scale image collection module, and the surface radiation image collection module.

[0031] The present application has the following advantages:

[0032] (1) The present application constructs a real-time online monitoring and evaluation system for the baking state at the end of the baking curve of the refining furnace, to monitor and feedback the baking state distribution in the furnace at each baking stage of the baking curve in real time, while greatly reducing the complexity of monitoring the baking process of the refining furnace, and providing good support for improving the baking efficiency of the refining furnace and increasing the number of furnaces in the first furnace campaign.

[0033] (2) The refining furnace baking curve optimization method and system proposed in the present application can evaluate the baking state of different refining furnace steel grades in real time, and construct a baking state grade based on real-time evaluation, so as to timely adjust the baking curve and realize the condition of reducing the baking time as much as possible under the optimal baking state of the refining furnace, thereby promoting the extensive operation mode of the refining furnace baking process to a fine and intelligent mode, improving the fine management level of the refining furnace, reducing energy consumption, and achieving energy saving and consumption reduction.

[0034] (3) The baking curve optimization method and system based on real-time evaluation results proposed in the present application have strong operability, high integration and high intelligence, and have important application value. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0036] Figure 1 The flowchart of the method of the preferred embodiment of the present application is shown in Figure 1.

[0037] Figure 2 The specific flowchart of the method of the preferred embodiment of the present application is shown in Figure 2.

[0038] Figure 3 The principle block diagram of the system of the preferred embodiment of the present application is shown in Figure 3. DETAILED DESCRIPTION

[0039] In order to make the person skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0040] Please refer to Figure 1The embodiment of the application discloses a real-time evaluation and optimization method for a refining furnace in-furnace baking state, comprising the following steps:

[0041] S1: collecting the three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface, and the radiation image of the refractory material surface before baking in the furnace in the shutdown state after replacing the refractory material of the refining furnace, and calculating the three-dimensional size information in the furnace, the refractory material gap expansion information, and the refractory material surface temperature information;

[0042] S2: then, starting baking according to the baking curve, the baking process comprising multiple baking stages, collecting the three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface, and the radiation image of the refractory material surface in each baking stage, and calculating the corresponding three-dimensional size information in the furnace, the refractory material gap expansion information, and the refractory material surface temperature information to obtain multiple baking state distributions during baking;

[0043] S3: analyzing and determining the correlation between the baking curve and the multiple baking state distributions according to the multiple baking state distributions obtained in step S2;

[0044] S4: evaluating the baking effect of the refining furnace according to the correlation obtained in step S3, if the baking effect reaches the expected target, the baking process is completed; if the baking effect does not reach the expected target, the baking curve is optimized, and the baking operation is continued until the baking effect reaches the expected target.

[0045] Preferably, the three-dimensional size information in the furnace is obtained through a three-dimensional reconstruction model.

[0046] Preferably, the refractory material gap expansion information is obtained through a deep learning algorithm.

[0047] Preferably, the refractory material surface temperature information is obtained through a blackbody furnace calibration algorithm.

[0048] In the embodiment, the baking state distribution is constructed by three parameters of the three-dimensional size information in the furnace, the refractory material gap expansion information, and the refractory material surface temperature information, and the calculation formula is as follows:

[0049]

[0050] wherein, H ki is the baking state distribution of the i-th baking stage of the k steel refining furnace; σ k is the three-dimensional size weight value of the k steel refining furnace; ρ k is the refractory material gap expansion weight value of the k steel refining furnace; is the refractory material surface temperature weight value of the k steel refining furnace; D i (Δx i , Δy i , Δz i) is the three-dimensional size change value of the refining furnace; E i (Δε i ) is the gap expansion volume of the refractory material of the refining furnace; T i (Δt i ) is the surface temperature change value of the refractory material of the refining furnace.

[0051] In order to better monitor and evaluate the furnace heating state of the same steel grade and different steel grades of the refining furnace, preferably the parameter weight values of the furnace heating state distribution of the same steel grade of the same refining furnace are the same, and the parameter weight values of the furnace heating state distribution of different steel grades of the same refining furnace are different.

[0052] In order to better evaluate whether the current furnace heating process meets the refining requirements of the steel grade, preferably the furnace heating effect grade of the refining furnace is evaluated by combining expert experience and big data analysis.

[0053] Preferably, the furnace heating curve is a relationship curve of atmosphere temperature and heating time, which can facilitate subsequent optimization of the furnace heating curve.

[0054] In order to better illustrate the refining furnace in-furnace heating state real-time evaluation and optimization method of the present application, the method of the present application is further described below in combination with specific embodiments. Please refer to Figure 1 、 Figure 2 , the specific work flow is:

[0055] Firstly, in the shutdown state after the replacement of the refractory material of the refining furnace, the three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface, and the radiation image of the refractory material surface are collected two hours before the refining furnace is prepared for heating, the three-dimensional size information in the furnace is obtained through the three-dimensional reconstruction model, the gap expansion information of the refractory material is obtained through the deep learning algorithm, and the surface temperature information of the refractory material is obtained through the blackbody furnace calibration algorithm.

[0056] Then, according to the oven curve, the oven is started, the oven curve is a relationship curve of baking time and atmosphere temperature, the abscissa is the baking time, the ordinate is the atmosphere temperature, the oven process includes multiple oven stages, such as i oven stages, i is a positive integer greater than or equal to 3, each oven stage has a corresponding atmosphere temperature and baking time. In this embodiment, i is 5, so the oven process includes five oven stages, namely the first oven stage, the second oven stage, the third oven stage, the fourth oven stage and the fifth oven stage. After the first oven stage is completed, the three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface and the radiation image of the refractory material surface in the first oven stage are collected; after the second oven stage is completed, the three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface and the radiation image of the refractory material surface in the second oven stage are collected; after the third oven stage is completed, the three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface and the radiation image of the refractory material surface in the third oven stage are collected; after the fourth oven stage is completed, the three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface and the radiation image of the refractory material surface in the fourth oven stage are collected; after the fifth oven stage is completed, the three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface and the radiation image of the refractory material surface in the fifth oven stage are collected. The three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface and the radiation image of the refractory material surface of each oven stage are obtained by three-dimensional reconstruction model, deep learning algorithm and blackbody furnace calibration algorithm to obtain the three-dimensional size information in the furnace, the refractory material gap expansion information and the refractory material surface temperature information of each oven stage.

[0057] The three-dimensional size change value of the refining furnace, the volume of the gap expansion of the refractory material of the refining furnace and the temperature change value of the surface of the refractory material of the refining furnace in the first oven stage are the values obtained by comparing the three-dimensional size information in the furnace, the gap expansion information of the refractory material and the surface temperature information of the refractory material obtained in the first oven stage with the three-dimensional size information in the furnace, the gap expansion information of the refractory material and the surface temperature information of the refractory material obtained before the oven, and the values are substituted into the calculation formula of the oven state distribution, so that the oven state distribution of the first oven stage is obtained, which is set as the first oven state distribution. In this way, the second oven state distribution, the third oven state distribution, the fourth oven state distribution and the fifth oven state distribution can be obtained.

[0058] Then, according to the first oven state distribution, the second oven state distribution, the third oven state distribution, the fourth oven state distribution and the fifth oven state distribution, the correlation between the oven curve and the first oven state distribution, the second oven state distribution, the third oven state distribution, the fourth oven state distribution and the fifth oven state distribution is analyzed and determined. The correlation refers to the value of the oven state distribution corresponding to each oven stage in the oven curve.

[0059] Finally, according to the obtained correlation relationship, the baking effect of the refining furnace is evaluated, if the baking effect reaches the expected target, the baking process is completed; if the baking effect does not reach the expected target, the baking curve is optimized, and the baking operation is continued until the baking effect reaches the expected target. There is a best baking state distribution corresponding to the baking curve in advance, which can be determined by experts, and whether the baking state distribution of each baking stage meets the range of the best baking state distribution is judged based on this. When the baking state specified by the baking curve is completed, the baking state distribution of each baking stage is judged, if it is within the range of the best baking state distribution value ± 5%, it is considered to meet the baking requirement; otherwise, the baking curve is optimized and adjusted, and the baking at a certain atmosphere temperature for a certain baking time is carried out again, a new baking state distribution is obtained and judged until it is within the range of the best baking state distribution value ± 5%, and the refining furnace baking is completed.

[0060] The embodiment of the application also discloses a real-time evaluation and optimization system for the baking state in the refining furnace, which is applied to the method of the above embodiment and comprises:

[0061] A baking state detection unit 1 is used to collect the three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface and the radiation image of the refractory material surface at different baking stages before and during the baking of the refining furnace;

[0062] A control unit 2 is used to control the height and circumferential position of the top gun and carry out baking control according to the baking curve optimized by the feedback unit 5;

[0063] A fixing and communication unit 3 is used to fix the baking state detection unit 1 to the top gun and transmit the collected three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface and the radiation image of the refractory material surface to the main server 4;

[0064] A main server 4 is used to receive the three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface and the radiation image of the refractory material surface at different baking stages before and during the baking of the refining furnace, and calculate the three-dimensional size information in the furnace, the refractory material gap expansion information and the refractory material surface temperature information respectively, calculate the baking state at different baking stages, and obtain the real-time evaluation and optimization result of the baking state;

[0065] A feedback unit 5 sends an instruction of optimizing the baking curve to the control unit 2 according to the real-time evaluation and optimization result of the baking state of the main server 4.

[0066] Since the furnace state detection unit 1 is installed on the top lance, the position of the furnace state detection unit 1 on the top lance can be adjusted after the control unit 2 adjusts the position of the top lance, so that the three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface and the radiation image of the refractory material surface at different stages before and during the heating of the refining furnace can be accurately collected, and the monitoring accuracy is improved.

[0067] Further, the furnace state detection unit 1 comprises: a three-dimensional point cloud collection module 101 for collecting the three-dimensional point cloud in the furnace of the refining furnace; a micro-scale image collection module 102 for collecting the micro-scale image of the refractory material surface of the refining furnace; a surface radiation image collection module 103 for collecting the radiation image of the refractory material surface of the refining furnace; and a cooling module 104 for cooling the three-dimensional point cloud collection module 101, the micro-scale image collection module 102 and the surface radiation image collection module 103. Specifically, the three-dimensional point cloud collection module 101 collects the three-dimensional point cloud in the furnace by using a 3D camera in cooperation with an active light source. The micro-scale image collection module 102 collects the micro-scale image of the refractory material surface by using a 3D camera in cooperation with a large-target far-focus lens. The surface radiation image collection module 103 collects the radiation image of the refractory material surface in the infrared wave band.

[0068] It is apparent for those skilled in the art that the present application is not limited to the details of the above-described exemplary embodiments, but can be implemented in other concrete forms without departing from the spirit or essential characteristics of the present application. Therefore, the embodiments should be considered in all aspects as illustrative and not restrictive, and the scope of the present application is defined by the appended claims rather than the above description, and it is intended to encompass all changes falling within the meaning and range of equivalents of the elements of the claims. Any reference signs in the claims should not be considered as limiting the claims involved.

[0069] In addition, it should be understood that, although the present specification is described in terms of embodiments, not every embodiment contains only one independent technical solution, and the description of the specification is only for the sake of clarity, and those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can be combined appropriately to form other embodiments that those skilled in the art can understand.

Claims

1. A method for real-time evaluation and optimization of the in-furnace baking state of a refining furnace, characterized by, The method comprises the following steps: S1: collecting the three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface, and the radiation image of the refractory material surface before the furnace is heated, and calculating the three-dimensional size information in the furnace, the gap expansion information of the refractory material, and the surface temperature information of the refractory material after the refractory material in the refining furnace is replaced and the furnace is stopped; S2: then, the furnace is heated according to the heating curve, and the heating process comprises multiple heating stages; the three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface, and the radiation image of the refractory material surface are collected after each heating stage, and the corresponding three-dimensional size information in the furnace, the gap expansion information of the refractory material, and the surface temperature information of the refractory material are calculated, so as to obtain the distribution of multiple heating states during the heating process; S3: according to the distribution of multiple heating states obtained in step S2, the correlation between the heating curve and the distribution of multiple heating states is analyzed and determined; S4: according to the correlation obtained in step S3, the heating effect of the refining furnace is evaluated; if the heating effect reaches the expected target, the heating process is completed; if the heating effect does not reach the expected target, the heating curve is optimized, and the heating operation is continued until the heating effect reaches the expected target.

2. A method for real-time evaluation and optimization of the in-furnace heating-up state of a refining furnace according to claim 1, characterized in that, The three-dimensional size information in the furnace is obtained through the three-dimensional reconstruction model.

3. The method for real-time evaluation and optimization of the baking state in a refining furnace according to claim 1, characterized in that: The gap expansion information of the refractory material is obtained through the deep learning algorithm.

4. The method for real-time evaluation and optimization of the baking state in a refining furnace according to claim 1, characterized in that: The surface temperature information of the refractory material is obtained through the blackbody furnace calibration algorithm.

5. The method of claim 1, wherein the method is characterized by: The heating state distribution is constructed by the three parameters of the three-dimensional size information in the furnace, the gap expansion information of the refractory material, and the surface temperature information of the refractory material, and the calculation formula is as follows: wherein H ki is the heating-up state distribution of the i-th heating-up stage of the k-steel refining furnace; σ k is the three-dimensional size weight value of the k-steel refining furnace; ρ k is the refractory material gap expansion weight value of the k-steel refining furnace; is the refractory material surface temperature weight value of the k-steel refining furnace; D i (Δx i , Δy i , Δz i ) is the three-dimensional size change value of the refining furnace; E i (Δε i ) is the volume of the refractory material gap expansion of the refining furnace; T i (Δt i ) is the change value of the refractory material surface temperature of the refining furnace.

6. The method of claim 5, wherein the method is characterized by: The parameter weight values of the heating state distribution of the same refining furnace and the same steel grade are the same, and the parameter weight values of the heating state distribution of the same refining furnace and different steel grades are different.

7. The method of claim 1, wherein the method is characterized by: The heating effect grade of the refining furnace is evaluated by combining expert experience and big data analysis.

8. The method of claim 1, wherein the method is characterized by: The heating curve is the relationship curve between the atmosphere temperature and the heating time.

9. A real-time evaluation and optimization system for the in-furnace baking state of a refining furnace, characterized by The method is applied to any one of claims 1-8, comprising: a heating state detection unit for collecting the three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface, and the radiation image of the refractory material surface before and during the heating process of the refining furnace; a control unit for controlling the height and circumferential position of the top lance, and controlling the heating according to the optimized heating curve of the feedback unit; a fixing and communication unit for fixing the heating state detection unit to the top lance, and transmitting the collected three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface, and the radiation image of the refractory material surface to the main server; a main server for receiving the three-dimensional point cloud in the furnace, the micro-scale image of the refractory material surface, and the radiation image of the refractory material surface before and during the heating process of the refining furnace, and calculating the three-dimensional size information in the furnace, the gap expansion information of the refractory material, and the surface temperature information of the refractory material, respectively, calculating the heating state of different heating stages, and obtaining the real-time evaluation and optimization results of the heating state; a feedback unit for issuing an instruction to optimize the heating curve to the control unit according to the real-time evaluation and optimization results of the heating state of the main server.

10. The real-time evaluation and optimization system for the in-furnace baking state of a refining furnace according to claim 9, characterized in that, The heating state detection unit comprises: a three-dimensional point cloud collection module for collecting the three-dimensional point cloud in the furnace of the refining furnace. A refractory micro-scale image acquisition module is configured to acquire a micro-scale image of a surface of the refractory of the furnace; A surface radiation image acquisition module is configured to acquire a surface radiation image of the refractory of the furnace; A cooling module is configured to cool the three-dimensional point cloud acquisition module, the refractory micro-scale image acquisition module, and the surface radiation image acquisition module.

Images