Converter steelmaking temperature measurement and carbon determination method, system, device, equipment, medium and product

Abstract

The present invention provides a method, system, device, equipment, medium and product for measuring the temperature and determining the carbon content in converter steelmaking. The method includes: acquiring an initial spectral image sequence corresponding to the converter mouth; sliding a preset sliding window on the initial spectral image sequence at a preset period to obtain M spectral images collected through the sliding window, forming a candidate spectral image sequence, where M is an integer greater than or equal to 1; extracting a target image area in each spectral image in the candidate spectral image sequence, using the target image area as a target spectral image, and forming a target spectral image sequence; determining the temperature of the converter molten steel and the carbon content of the converter at the current moment based on the target spectral image sequence and a preset spectral change distribution. The present invention is used to solve the defects of high cost and low accuracy in detecting the temperature of converter molten steel and the carbon content of the converter in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of converter steelmaking, and particularly to a method, system, device, equipment, medium and product for measuring temperature and determining carbon content in converter steelmaking. Background Art

[0002] During the process of converter steelmaking, the temperature and carbon content of the molten steel in the converter have an important impact on the quality of the produced steel. In order to make the temperature and carbon content of the converter molten steel meet the expected targets, it is necessary to measure the temperature and carbon content of the converter molten steel in real time to guide the staff to make adjustments according to the actual situation.

[0003] Currently, steel mills mainly rely on the combination of a flue gas analysis system and the sublance method to measure the temperature and carbon content of the converter molten steel in real time. Among them, the flue gas analysis system calculates the temperature and carbon content in the converter by analyzing the flue gas in the converter during the steelmaking process, and the sublance method inserts a sublance into the molten steel to detect the temperature and carbon content. However, both of these methods have certain deficiencies. The flue gas analysis system has high costs and low accuracy, while the damage rate of the sublance in the sublance method is extremely high, and the sublance needs to be frequently replaced. Moreover, it can only measure the temperature and carbon content at a certain moment and cannot achieve real-time monitoring. Summary of the Invention

[0004] The present invention provides a method, system, device, equipment, medium and product for measuring temperature and determining carbon content in converter steelmaking, aiming to solve the defects of high costs and low accuracy in detecting the temperature and carbon content of converter molten steel in the prior art, and realizing accurate and real-time detection of the temperature and carbon content of converter molten steel.

[0005] The present invention provides a method for measuring temperature and determining carbon content in converter steelmaking, including:

[0006] Obtaining an initial spectral image sequence corresponding to the converter furnace mouth;

[0007] Sliding a preset sliding window over the initial spectral image sequence at a preset period to obtain M spectral images collected through the sliding window, forming a candidate spectral image sequence, where M is an integer greater than or equal to 1;

[0008] Extracting the target image region in each spectral image in the candidate spectral image sequence, using the target image region as a target spectral image, and forming a target spectral image sequence;

[0009] Based on the target spectral image sequence and a preset spectral change distribution, determining the temperature and carbon content of the converter molten steel in the converter at the current moment.

[0010] A method for measuring temperature and determining carbon content in converter steelmaking according to the present invention, based on the target spectral image sequence and the preset spectral change distribution, determining the temperature of the converter molten steel and the carbon content of the converter at the current moment, includes:

[0011] Based on the spectral change distribution, determining the predicted temperature of the converter molten steel and the predicted carbon content of the converter corresponding to the Mth spectral image;

[0012] Taking the predicted temperature of the converter molten steel as the temperature of the converter molten steel and the predicted carbon content of the converter as the carbon content of the converter.

[0013] A method for measuring temperature and determining carbon content in converter steelmaking according to the present invention, extracting the target image area in each spectral image of the candidate spectral image sequence and taking the target image area as the target spectral image, includes:

[0014] Performing the following processing procedures on each spectral image in the candidate spectral image sequence:

[0015] Performing gray-scale processing on the spectral image to obtain a gray-scale image;

[0016] Performing convolution processing on the gray-scale image using a preset convolution kernel to obtain a target gray-scale image;

[0017] Calculating the target value of each pixel point in the target gray-scale image using a preset formula;

[0018] Extracting the target image area in the spectral image of the pixel point corresponding to the maximum target value among the target values;

[0019] Taking the target image area as the target spectral image.

[0020] A method for measuring temperature and determining carbon content in converter steelmaking according to the present invention, the initial spectral image sequence includes: the current spectral image corresponding to the current moment;

[0021] Sliding a preset sliding window on the initial spectral image sequence according to a preset period to obtain M spectral images collected through the sliding window, forming a candidate spectral image sequence, includes:

[0022] Sliding the sliding window on the initial spectral image sequence according to the preset period to obtain the M spectral images including the current spectral image collected through the sliding window;

[0023] Judging the size relationship between M and a preset value;

[0024] When M is less than or equal to the preset value, forming the candidate spectral image sequence based on the M spectral images;

[0025] When M is greater than the preset value, move the sliding window according to the preset period to make M equal to the preset value, and form the candidate spectral image sequence based on M spectral images in the slid sliding window.

[0026] According to a method for measuring temperature and determining carbon content in converter steelmaking provided by the present invention, the step of when M is greater than the preset value, moving the sliding window according to the preset period to make M equal to the preset value, and forming the candidate spectral image sequence based on M spectral images in the slid sliding window includes:

[0027] When M is greater than the preset value, filter out the spectral image first collected by the sliding window in the current candidate spectral image sequence by moving the sliding window to make M equal to the preset value, and form the candidate spectral image sequence based on the remaining M spectral images after filtering.

[0028] The present invention also provides a system for measuring temperature and determining carbon content in converter steelmaking, including: a photographing device and an industrial control computer, and the photographing device is communicatively connected to the industrial control computer;

[0029] The photographing device is configured to photograph at least one spectral image corresponding to the converter furnace mouth, form an initial spectral image sequence, and send the initial spectral image sequence to the industrial control computer;

[0030] The industrial control computer is configured to obtain the initial spectral image sequence corresponding to the converter furnace mouth; slide a preset sliding window on the initial spectral image sequence according to a preset period to obtain M spectral images collected by the sliding window, and form a candidate spectral image sequence, where M is an integer greater than or equal to 1; extract the target image area in each spectral image in the candidate spectral image sequence, use the target image area as the target spectral image, and form a target spectral image sequence; determine the temperature of the converter molten steel and the carbon content in the converter at the current moment based on the target spectral image sequence and the preset spectral change distribution.

[0031] The present invention also provides a device for measuring temperature and determining carbon content in converter steelmaking, including:

[0032] An acquisition module configured to acquire an initial spectral image sequence corresponding to the converter furnace mouth;

[0033] A first formation module configured to slide a preset sliding window on the initial spectral image sequence according to a preset period to obtain M spectral images collected by the sliding window, and form a candidate spectral image sequence, where M is an integer greater than or equal to 1;

[0034] A second forming module, configured to extract a target image region from each spectral image in the candidate spectral image sequence, use the target image region as a target spectral image, and form a target spectral image sequence;

[0035] A determination module, configured to determine the temperature of molten steel in the converter and the carbon content in the converter at the current moment based on the target spectral image sequence and a preset spectral change distribution.

[0036] The present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the converter steelmaking temperature measurement and carbon determination method as described in any one of the above are implemented.

[0037] The present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the converter steelmaking temperature measurement and carbon determination method as described in any one of the above are implemented.

[0038] The converter steelmaking temperature measurement and carbon determination method, system, device, equipment, medium and product provided by the present invention obtain an initial spectral image sequence corresponding to the converter mouth; according to a preset period, slide a preset sliding window on the initial spectral image sequence to obtain M spectral images collected through the sliding window, and form a candidate spectral image sequence. The present invention obtains the candidate spectral image sequence obtained through the sliding window based on the preset period, ensuring the timeliness of the detection of the temperature of molten steel in the converter and the carbon content in the converter, and improving the detection efficiency; furthermore, extract the target image region from each spectral image in the candidate spectral image sequence, use the target image region as a target spectral image, and form a target spectral image sequence; based on the target spectral image sequence and a preset spectral change distribution, determine the temperature of molten steel in the converter and the carbon content in the converter at the current moment. The present invention can realize the real-time detection of the temperature of molten steel in the converter and the carbon content in the converter based on the preset period, and based on the preset spectral change distribution, can effectively ensure the accuracy of the temperature of molten steel in the converter and the carbon content in the converter, and the entire analysis process is fast, accurate, and low-cost, effectively improving the user experience. Description of the Drawings

[0039] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 is one of the flowcharts of the converter steelmaking temperature measurement and carbon determination method provided by the present invention;

[0041] Figure 2 It is the second schematic flow diagram of the method for measuring temperature and determining carbon content in converter steelmaking provided by the present invention;

[0042] Figure 3 It is the third schematic flow diagram of the method for measuring temperature and determining carbon content in converter steelmaking provided by the present invention;

[0043] Figure 4 It is the fourth schematic flow diagram of the method for measuring temperature and determining carbon content in converter steelmaking provided by the present invention;

[0044] Figure 5 It is the schematic structural diagram of the device for measuring temperature and determining carbon content in converter steelmaking provided by the present invention;

[0045] Figure 6 It is the schematic structural diagram of the system for measuring temperature and determining carbon content in converter steelmaking provided by the present invention;

[0046] Figure 7 It is the schematic structural diagram of the electronic device provided by the present invention. Detailed implementation manners

[0047] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without making creative efforts based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0048] The following combines Figures 1-4 to describe the method for measuring temperature and determining carbon content in converter steelmaking of the present invention.

[0049] The embodiment of the present invention provides a method for measuring temperature and determining carbon content in converter steelmaking. This method can be applied to intelligent terminals, such as mobile phones, computers, tablets, etc., and can also be applied in servers. Hereinafter, taking the application of this method in a server as an example for illustration, it should be noted that it is only for illustration and is not used to limit the protection scope of the present invention. Some other descriptions in the embodiments of the present invention are also for illustration and are not used to limit the protection scope of the present invention, and will not be described one by one hereinafter.

[0050] As an emerging technical means, flame spectrometry calculates the temperature of molten steel in a converter and the carbon content in the converter by measuring the spectrum of the flame at the furnace mouth. It not only has a relatively low cost but also high accuracy. During the steelmaking process, due to the ongoing reactions in the furnace, the material composition continuously changes, thus altering the spectrum of the furnace mouth flame. By analyzing the spectrum, the material composition in the furnace can be deduced inversely, enabling the calculation of the temperature of molten steel in the converter and the carbon content in the converter. Calculating the temperature of molten steel in the converter and the carbon content in the converter using the spectrum of the furnace mouth flame at a single moment has limited accuracy. However, the change of the furnace mouth flame spectrum has a certain pattern during steelmaking. Therefore, by using the sequence of flame spectra within a continuous time period to calculate the temperature of molten steel in the converter and the carbon content in the converter, and reasonably utilizing the pattern of spectral change over time, the calculation accuracy can be greatly improved.

[0051] However, if a continuous spectral sequence is used to calculate the temperature of molten steel in the converter and the carbon content in the converter, a relatively long waiting time is required during the acquisition process to collect enough spectral sequences to calculate the accurate temperature of molten steel in the converter and the carbon content in the converter, which is difficult to meet the requirements of real-time monitoring. Therefore, the present invention utilizes a sliding window and spectral change distribution to calculate the temperature of molten steel in the converter and the carbon content in the converter in real time.

[0052] The specific implementation of the method for measuring temperature and determining carbon in converter steelmaking of the present invention is as Figure 1 shown:

[0053] Step 101, obtain an initial spectral image sequence corresponding to the furnace mouth of the converter.

[0054] Specifically, use a photographing device to photograph at least one continuous spectral image corresponding to the furnace mouth of the converter to form an initial spectral image sequence corresponding to the current moment. Among them, the photographing device includes: a spectral camera.

[0055] Certainly, it is also possible to obtain at least one continuous spectral image sent by the photographing device to form an initial spectral image sequence corresponding to the current moment.

[0056] Specifically, since the furnace mouth flame changes regularly over time, obtaining continuous spectral images can effectively utilize the pattern of spectral change over time, thereby improving the accuracy of calculating the temperature of molten steel in the converter and the carbon content in the converter.

[0057] Step 102, slide a preset sliding window on the initial spectral image sequence at a preset period to obtain M spectral images collected through the sliding window, forming a candidate spectral image sequence.

[0058] Among them, M is an integer greater than or equal to 1.

[0059] In a specific embodiment, the initial spectral image sequence includes: the current spectral image corresponding to the current moment. The generation method of the candidate spectral image sequence is specifically as Figure 2As shown:

[0060] Step 201, slide the sliding window on the initial spectral image sequence according to a preset period to obtain M spectral images including the current spectral image collected through the sliding window.

[0061] Specifically, the present invention needs to maintain a candidate spectral image sequence with a length of a preset value. By sliding the preset sliding window, the newly obtained spectral image each time, that is, the current spectral image, is added to the candidate spectral image sequence.

[0062] Step 202, determine the size relationship between M and the preset value.

[0063] Specifically, when M is less than or equal to the preset value, execute Step 203; when M is greater than the preset value, execute Step 204.

[0064] Step 203, form a candidate spectral image sequence based on the M spectral images.

[0065] Step 204, move the sliding window according to a preset period to make M equal to the preset value, and form a candidate spectral image sequence based on the M spectral images in the slid sliding window.

[0066] Specifically, the user can set the preset period by himself according to the actual situation. For example, one second, one minute, one hour, etc. The user can also set the preset value by himself according to the actual situation. For example, 20, 50, 80, etc. Of course, the sliding window can be moved in real time.

[0067] In a specific embodiment, when M is greater than the preset value, by moving the sliding window, the spectral image collected by the sliding window first in the current candidate spectral image sequence is filtered out to make M equal to the preset value, and a candidate spectral image sequence is formed based on the remaining M spectral images after filtering.

[0068] Specifically, in order to adapt to the spectral change distribution, it is necessary to unify the length of the candidate spectral image sequence. Taking the preset value equal to N as an example for illustration, specifically as Figure 3 shown. Specifically, each time the sliding window slides, one current spectral image is collected, so that the candidate spectral image sequence includes the current spectral image. In order to maintain the length of the candidate spectral image as N, when M is greater than N, that is, M = N + 1; then the spectral image with the earliest time in the candidate spectral image sequence with a length of N + 1 is filtered out, thereby forming a new candidate spectral image sequence with a length of N. Thus, the main operations of the sliding window method are completed, and a candidate spectral image sequence with a length of N can be maintained at each moment for calculating the temperature of the converter molten steel and the carbon content of the converter.

[0069] Among them, in Figure 3Among them, time t+2 represents the current moment, time t+1 represents the previous moment, and time t represents the previous moment corresponding to the previous moment.

[0070] Among them, spectrum t+2 represents the current spectral image, spectrum t+1 represents the spectral image corresponding to the previous moment, and so on. Spectrum t-N+3 represents the spectral image with the earliest time in the current candidate spectral image sequence, spectrum t-N+2 represents the spectral image with the earliest time in the previous candidate spectral image sequence, and spectrum t-N+1 represents the spectral image with the earliest time in the previous candidate spectral image sequence corresponding to the previous candidate spectral image sequence.

[0071] Step 103: Extract the target image region in each spectral image in the candidate spectral image sequence, use the target image region as the target spectral image, and form a target spectral image sequence.

[0072] Specifically, during the steelmaking process, sometimes a large amount of black smoke will emerge from the furnace mouth, blocking the flame and causing the spectrum collected in the black smoke area to change. Therefore, it is necessary to process the spectral image and extract the region not interfered by soot as the target image region to ensure the accuracy of the spectrum.

[0073] In a specific embodiment, the specific implementation of extracting the target image region in any spectral image is as Figure 4 shown:

[0074] Step 401: Perform grayscale processing on the spectral image to obtain a grayscale image.

[0075] Specifically, the grayscale image is represented by a two-dimensional matrix I. Let the size of matrix I be H×W. Among them, the light intensity value at the i-th row and j-th column in the grayscale image is represented by I i,j where 0≤I i,j ≤255, and I i,j is an integer.

[0076] Step 402: Perform convolution processing on the grayscale image using a preset convolution kernel to obtain a target grayscale image.

[0077] Specifically, determine the size of the convolution kernel, and the size of the convolution kernel can be adjusted according to actual needs.

[0078] Among them, the size of the preset convolution kernel is K×K, and the element at the i-th row and j-th column of the convolution kernel is K i,j and K i,j =1;

[0079] Specifically, perform a convolution operation on the grayscale image based on a preset convolution kernel. The boundary padding of the convolution is P, the filled elements are 0, and the stride is S. After the convolution process, a target grayscale image is obtained. The target grayscale image is represented by a two-dimensional matrix I', where the size of the matrix I' is H'×W'.

[0080] Among them,

[0081] Step 403: Calculate the target value of each pixel point in the target grayscale image using a preset formula.

[0082] Specifically, the preset formula is shown in Formula (1):

[0083]

[0084] Among them, the target value is the target light intensity value, and I’ i,j is the target light intensity value.

[0085] Step 404: Extract the target image area in the spectral image corresponding to the pixel point with the maximum target value among the target values.

[0086] Specifically, determine the target light intensity value of each pixel point in the matrix I', determine the maximum target light intensity value from all pixel points, and use the area in the spectral image corresponding to the pixel point with the maximum target light intensity value as the target image area.

[0087] Specifically, each element of the matrix I' represents the sum of the light intensity values of a certain area of the matrix I. Therefore, the position corresponding to the maximum target light intensity value of the matrix I' can reflect the position of the brightest area of the matrix I. If the position of the maximum target light intensity value of the matrix I' is in the l-th row and the k-th column, then the upper-left corner element of the brightest area of the matrix I is in the (l×S + 1 - S)-th row and the (k×S + 1 - S)-th column, and the lower-right corner element is in the (l×S + K - S)-th row and the (k×S + K - S)-th column.

[0088] Among them, the brightest area is the area not disturbed by soot.

[0089] Obtain a target spectral image by extracting the target image area in any spectral image, and obtain a sequence of target spectral images.

[0090] Step 104: Based on the sequence of target spectral images and the preset spectral change distribution, determine the temperature of the molten steel in the converter and the carbon content in the converter at the current moment.

[0091] In a specific embodiment, the spectral change distribution is obtained by analyzing S samples of the sequence of target spectral images, where S is an integer greater than 1.

[0092] Specifically, the target spectral image sequence sample is also a target spectral image sequence sample with a length of N. Furthermore, through the analysis of a large number of target spectral image sequence samples with a length of N, the spectral change distribution is obtained.

[0093] Specifically, the principal component analysis method can be used to analyze the target spectral image sequence sample with a length of N to obtain the spectral change distribution. Among them, the spectral change distribution can be represented by a curve.

[0094] Specifically, in the actual application scenario, only within a very short time at the beginning of steelmaking, M is less than N. Therefore, during the entire time corresponding to the steelmaking process, except for the very short time at the beginning when M is less than or equal to N, M is greater than N at other times. And the molten steel temperature and carbon content in the converter during the very short time at the beginning of steelmaking will not affect the present invention. Therefore, by using the target spectral image sequence sample with a length of N for training, an accurate spectral change distribution can be obtained.

[0095] In a specific embodiment, based on the spectral change distribution, the predicted molten steel temperature and predicted carbon content in the converter corresponding to the Mth spectral image are determined; the predicted molten steel temperature is used as the molten steel temperature, and the predicted carbon content in the converter is used as the carbon content in the converter.

[0096] Specifically, based on the spectral change distribution, the molten steel temperature and carbon content in the converter of each spectral image in the target spectral image sequence can be determined. Furthermore, in the present invention, the molten steel temperature and carbon content in the converter of the last spectral image in the target spectral image sequence are used as the molten steel temperature and carbon content in the converter corresponding to the current moment.

[0097] The present invention can determine the molten steel temperature and carbon content in the converter in real time by setting a preset period, which can provide stable basic data for subsequent analysis of the molten steel temperature and carbon content in the converter. And through real-time monitoring, the accuracy of the molten steel temperature and carbon content in the converter is ensured, effectively improving the user experience.

[0098] The method, system, device, equipment, medium and product for measuring temperature and determining carbon content in converter steelmaking provided by the present invention obtain an initial spectral image sequence corresponding to the converter mouth; according to a preset period, slide a preset sliding window on the initial spectral image sequence to obtain M spectral images collected through the sliding window, forming a candidate spectral image sequence. The present invention obtains the candidate spectral image sequence obtained through the sliding window based on the preset period, ensuring the timeliness of the detection of the converter molten steel temperature and the converter carbon content, and improving the detection efficiency; furthermore, extract the target image area in each spectral image in the candidate spectral image sequence, use the target image area as the target spectral image, and form a target spectral image sequence; based on the target spectral image sequence and the preset spectral change distribution, determine the converter molten steel temperature and the converter carbon content in the converter at the current moment. The present invention can realize the real-time detection of the converter molten steel temperature and the converter carbon content in the converter based on the preset period, and based on the preset spectral change distribution, can effectively ensure the accuracy of the converter molten steel temperature and the converter carbon content, and the whole analysis process is fast, accurate and low-cost, effectively improving the user experience.

[0099] The converter steelmaking temperature measuring and carbon determining device provided by the present invention will be described below. The converter steelmaking temperature measuring and carbon determining device described below can be mutually corresponding and referred to the converter steelmaking temperature measuring and carbon determining method described above, and the repeated parts will not be described again. Specifically, as Figure 5 shown, the device includes:

[0100] An acquisition module 501, configured to acquire an initial spectral image sequence corresponding to the converter mouth;

[0101] A first generation module 502, configured to slide a preset sliding window on the initial spectral image sequence according to a preset period to obtain M spectral images collected through the sliding window, forming a candidate spectral image sequence, where M is an integer greater than or equal to 1;

[0102] A second generation module 503, configured to extract the target image area in each spectral image in the candidate spectral image sequence, use the target image area as the target spectral image, and form a target spectral image sequence;

[0103] A determination module 504, configured to determine the converter molten steel temperature and the converter carbon content in the converter at the current moment based on the target spectral image sequence and the preset spectral change distribution.

[0104] In a specific embodiment, the determination module 504 is specifically configured to determine the predicted converter molten steel temperature and the predicted converter carbon content corresponding to the Mth spectral image based on the spectral change distribution; use the predicted converter molten steel temperature as the converter molten steel temperature and the predicted converter carbon content as the converter carbon content.

[0105] In a specific embodiment, the second generation module 503 includes: an extraction module, which is used to perform the following processing procedures on each spectral image in the candidate spectral image sequence:

[0106] Perform grayscale processing on the spectral image to obtain a grayscale image; perform convolution processing on the grayscale image using a preset convolution kernel to obtain a target grayscale image; calculate the target value of each pixel point in the target grayscale image using a preset formula; extract the target image area in the spectral image corresponding to the pixel point with the maximum target value among the target values; and use the target image area as the target spectral image.

[0107] In a specific embodiment, the initial spectral image sequence includes: the current spectral image corresponding to the current moment; the first generation module 502, which is specifically used to slide a sliding window on the initial spectral image sequence according to a preset period to obtain M spectral images including the current spectral image collected through the sliding window; determine the size relationship between M and a preset value; when M is less than or equal to the preset value, form a candidate spectral image sequence based on the M spectral images; when M is greater than the preset value, move the sliding window according to the preset period to make M equal to the preset value, and form a candidate spectral image sequence based on the M spectral images in the slid sliding window.

[0108] In a specific embodiment, the first generation module 502 is specifically used to, when M is greater than the preset value, filter out the spectral image that was first collected by the sliding window in the current candidate spectral image sequence by moving the sliding window to make M equal to the preset value, and form a candidate spectral image sequence based on the remaining M spectral images after filtering.

[0109] The embodiment of the present invention also provides a temperature measurement and carbon determination system for converter steelmaking. The temperature measurement and carbon determination system for converter steelmaking described below can be mutually referred to with the temperature measurement and carbon determination method for converter steelmaking described above. Repeated parts will not be elaborated. Specifically, as Figure 6 shown, the system includes: a photographing device 601 and an industrial control computer 602, and the photographing device 601 and the industrial control computer 602 are communicatively connected;

[0110] The photographing device 601 is used to photograph at least one spectral image corresponding to the converter mouth to form an initial spectral image sequence, and send the initial spectral image sequence to the industrial control computer 602;

[0111] An industrial control computer 602 is used to obtain an initial spectral image sequence corresponding to the converter mouth; at a preset period, slide a preset sliding window on the initial spectral image sequence to obtain M spectral images collected through the sliding window, forming a candidate spectral image sequence, where M is an integer greater than or equal to 1; extract the target image region in each spectral image in the candidate spectral image sequence, use the target image region as the target spectral image, and form a target spectral image sequence; based on the target spectral image sequence and the preset spectral change distribution, determine the temperature of the molten steel in the converter and the carbon content in the converter at the current moment.

[0112] Figure 7 An example of the physical structure diagram of an electronic device is shown as Figure 7 shown. The electronic device may include: a processor 701, a communication interface 702, a memory 703, and a communication bus 704. Among them, the processor 701, the communication interface 702, and the memory 703 complete communication with each other through the communication bus 704. The processor 701 can call the logical instructions in the memory 703 to execute the method for measuring temperature and determining carbon in converter steelmaking, and the method includes: obtaining an initial spectral image sequence corresponding to the converter mouth; at a preset period, slide a preset sliding window on the initial spectral image sequence to obtain M spectral images collected through the sliding window, forming a candidate spectral image sequence, where M is an integer greater than or equal to 1; extract the target image region in each spectral image in the candidate spectral image sequence, use the target image region as the target spectral image, and form a target spectral image sequence; based on the target spectral image sequence and the preset spectral change distribution, determine the temperature of the molten steel in the converter and the carbon content in the converter at the current moment.

[0113] In addition, when the logical instructions in the above-mentioned memory 703 can be implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical disks, etc., which can store program codes.

[0114] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the converter steelmaking temperature measurement and carbon content determination method provided by each of the above methods. The method includes: acquiring an initial spectral image sequence corresponding to the converter mouth; sliding a pre-set sliding window on the initial spectral image sequence at a pre-set period to obtain M spectral images collected through the sliding window, forming a candidate spectral image sequence, where M is an integer greater than or equal to 1; extracting a target image area in each spectral image in the candidate spectral image sequence, taking the target image area as a target spectral image, and forming a target spectral image sequence; and determining the temperature of the converter molten steel and the carbon content in the converter at the current moment based on the target spectral image sequence and a pre-set spectral change distribution.

[0115] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is configured to execute the converter steelmaking temperature measurement and carbon content determination method provided by each of the above. The method includes: acquiring an initial spectral image sequence corresponding to the converter mouth; sliding a pre-set sliding window on the initial spectral image sequence at a pre-set period to obtain M spectral images collected through the sliding window, forming a candidate spectral image sequence, where M is an integer greater than or equal to 1; extracting a target image area in each spectral image in the candidate spectral image sequence, taking the target image area as a target spectral image, and forming a target spectral image sequence; and determining the temperature of the converter molten steel and the carbon content in the converter at the current moment based on the target spectral image sequence and a pre-set spectral change distribution.

[0116] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative efforts.

[0117] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for measuring temperature and determining carbon content in converter steelmaking, characterized in that, Including: Obtaining an initial spectral image sequence corresponding to the converter mouth; Sliding a preset sliding window on the initial spectral image sequence according to a preset period to obtain M spectral images collected through the sliding window, forming a candidate spectral image sequence, where M is an integer greater than or equal to 1; Extracting a target image region in each spectral image in the candidate spectral image sequence, taking the target image region as a target spectral image, and forming a target spectral image sequence; Based on the target spectral image sequence and a preset spectral change distribution, determining the temperature of the molten steel in the converter and the carbon content in the converter at the current moment.

2. The method for measuring temperature and determining carbon content in converter steelmaking according to claim 1, wherein, The determining the temperature of the molten steel in the converter and the carbon content in the converter at the current moment based on the target spectral image sequence and the preset spectral change distribution includes: Based on the spectral change distribution, determining a predicted temperature of the molten steel in the converter and a predicted carbon content in the converter corresponding to the Mth spectral image; Taking the predicted temperature of the molten steel in the converter as the temperature of the molten steel in the converter, and taking the predicted carbon content in the converter as the carbon content in the converter.

3. The method for measuring temperature and determining carbon content in converter steelmaking according to claim 1, characterized in that, The extracting a target image region in each spectral image in the candidate spectral image sequence and taking the target image region as a target spectral image includes: Performing the following processing procedure on each spectral image in the candidate spectral image sequence: Performing gray processing on the spectral image to obtain a gray image; Performing convolution processing on the gray image using a preset convolution kernel to obtain a target gray image; Calculating a target value of each pixel point in the target gray image using a preset formula; Extracting the target image region in the spectral image of the pixel point corresponding to the maximum target value among the target values; Taking the target image region as the target spectral image.

4. The method for measuring temperature and determining carbon content in converter steelmaking according to any one of claims 1-3, characterized in that, The initial spectral image sequence includes: a current spectral image corresponding to the current moment; The sliding the preset sliding window on the initial spectral image sequence according to a preset period to obtain M spectral images collected through the sliding window and forming a candidate spectral image sequence includes: Sliding the sliding window on the initial spectral image sequence according to the preset period to obtain the M spectral images including the current spectral image collected through the sliding window; Judging the size relationship between M and a preset value; When M is less than or equal to the preset value, forming the candidate spectral image sequence based on the M spectral images; When M is greater than the preset value, moving the sliding window according to the preset period to make M equal to the preset value, and forming the candidate spectral image sequence based on the M spectral images in the slid sliding window.

5. The method for measuring temperature and determining carbon content in converter steelmaking according to claim 4, characterized in that, The when M is greater than the preset value, moving the sliding window according to the preset period to make M equal to the preset value, and forming the candidate spectral image sequence based on the M spectral images in the slid sliding window includes: When the M is greater than the preset value, by moving the sliding window, filter out the spectral image that is first collected by the sliding window in the current candidate spectral image sequence, make the M equal to the preset value, and form the candidate spectral image sequence based on the remaining M spectral images after filtering.

6. A converter steelmaking temperature and carbon content measuring system, characterized in that, Comprising: A photographing device and an industrial control computer, where the photographing device and the industrial control computer are communicatively connected; The photographing device is configured to photograph at least one spectral image corresponding to the converter mouth, form an initial spectral image sequence, and send the initial spectral image sequence to the industrial control computer; The industrial control computer is configured to obtain the initial spectral image sequence corresponding to the converter mouth; at a preset period, slide a preset sliding window on the initial spectral image sequence to obtain M spectral images collected by the sliding window, form a candidate spectral image sequence, where M is an integer greater than or equal to 1; extract the target image area in each spectral image in the candidate spectral image sequence, use the target image area as the target spectral image, and form a target spectral image sequence; Based on the target spectral image sequence and the preset spectral change distribution, determine the temperature of the molten steel and the carbon content in the converter at the current moment.

7. A temperature and carbon content measuring device for converter steelmaking, characterized in that, Comprising: An acquisition module, configured to acquire the initial spectral image sequence corresponding to the converter mouth; A first formation module, configured to slide a preset sliding window on the initial spectral image sequence at a preset period to obtain M spectral images collected by the sliding window, and form a candidate spectral image sequence, where M is an integer greater than or equal to 1; A second formation module, configured to extract the target image area in each spectral image in the candidate spectral image sequence, use the target image area as the target spectral image, and form a target spectral image sequence; A determination module, configured to determine the temperature of the molten steel and the carbon content in the converter at the current moment based on the target spectral image sequence and the preset spectral change distribution.

8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the converter steelmaking temperature measurement and carbon determination method according to any one of claims 1 to 5.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the converter steelmaking temperature measurement and carbon determination method according to any one of claims 1 to 5.

10. A computer program product, the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, and when the program instructions are executed by a computer, it implements the steps of the converter steelmaking temperature measurement and carbon determination method according to any one of claims 1 to 5.

Images