Method and device for predicting scrap steel melting process based on VIS-NIR spectrum

Abstract

The invention provides a method and a device for predicting a waste steel melting process based on a VIS-NIR spectrum, and relates to the technical field of steelmaking. The method comprises the following steps: acquiring historical VIS-NIR spectral data in a molten pool in a converter steelmaking process of a historical heat to construct a calculation model; acquiring first VIS-NIR spectral data, scrap steel ratio and molten iron temperature of the to-be-predicted heat; second VIS-NIR spectral data after a preset time interval is obtained, the proportion coefficient of liquid phase components in the molten pool is obtained according to the calculation model, the scrap steel ratio, the molten iron temperature and the second VIS-NIR spectral data, and the prediction result of the scrap steel melting process in the molten pool is obtained according to the proportion coefficient of the liquid phase components in the molten pool. According to the method, the steel scrap melting process in the converter steelmaking process can be analyzed and predicted, and a brand-new method for monitoring steel scrap melting online in real time is provided for steelmaking production.

Description

Technical Field

[0001] The invention relates to the technical field of steelmaking, and in particular to a method and a device for predicting the melting process of scrap steel based on VIS-NIR spectrum. Background Art

[0002] Scrap steel is a key raw material for the modern steel industry and an important ferrous resource for energy conservation and environmental protection. Vigorously promoting the efficient use of scrap steel is not only in line with the strategic needs of my country's steel industry transformation and upgrading and low-carbon green development, but also an effective way to reduce my country's dependence on foreign iron ore and ensure the security of my country's ferrous resources. At present, converter high scrap steel ratio smelting is an important method for consuming a large amount of scrap steel. However, when the scrap steel ratio entering the furnace is increased, it is easy to cause problems such as difficult to control the composition of the steel and too low steel temperature, which seriously affects the efficient and stable operation of the converter. Therefore, the rapid melting of scrap steel and the prediction and monitoring of the melting process have become the application bottlenecks that the current converter high scrap steel ratio smelting technology urgently needs to break through.

[0003] At present, some scholars have conducted relevant research on the melting behavior of scrap steel, and established scrap steel melting models under different conditions based on the moving boundary layer theory and experimental data. However, existing reports mainly use rotating scrap steel bars for forced convection, and the conclusions drawn are difficult to accurately guide actual production. Summary of the invention

[0004] In order to solve the technical problem of how to predict and monitor the rapid melting and melting process of scrap steel, the embodiment of the present invention provides a method and device for predicting the melting process of scrap steel based on VIS-NIR spectroscopy. The technical solution is as follows:

[0005] On the one hand, a method for predicting the melting process of scrap steel based on VIS-NIR spectrum is provided, the method is implemented by a prediction device for the melting process of scrap steel based on VIS-NIR spectrum, and the method comprises:

[0006] S1. Obtain historical VIS-NIR spectral data in the molten pool during converter steelmaking in historical furnaces, and build a calculation model based on the historical VIS-NIR spectral data.

[0007] S2. Acquire the first VIS-NIR spectrum data, scrap steel ratio and molten iron temperature in the molten pool during the converter steelmaking process of the heat to be predicted.

[0008] S3. Acquire second VIS-NIR spectrum data after a preset time interval, and determine whether the second VIS-NIR spectrum data is smaller than the first VIS-NIR spectrum data.

[0009] If yes, execute step S4.

[0010] If not, the prediction ends.

[0011] S4. According to the calculation model, scrap steel ratio, molten iron temperature and the second VIS-NIR spectrum data, the proportion coefficient of the liquid phase component in the molten pool is obtained, and the melting process prediction result of the scrap steel in the molten pool is obtained according to the proportion coefficient of the liquid phase component in the molten pool.

[0012] Optionally, the step of obtaining historical VIS-NIR spectral data in the molten pool during converter steelmaking of historical heats in S1, and constructing a calculation model based on the historical VIS-NIR spectral data, includes:

[0013] The historical VIS-NIR spectral data in the molten pool during the converter steelmaking process of historical furnaces are continuously collected by installing a spectral acquisition probe inside the oxygen nozzle.

[0014] A calculation model is constructed based on the historical VIS-NIR spectral data, as well as the scrap steel ratio and molten iron temperature of the furnace corresponding to the historical VIS-NIR spectral data.

[0015] Optionally, S4 obtains a proportion coefficient of a liquid phase component in the molten pool according to the calculation model, the scrap steel ratio, the molten iron temperature, and the second VIS-NIR spectrum data, and obtains a prediction result of the melting process of the scrap steel in the molten pool according to the proportion coefficient of the liquid phase component in the molten pool, including:

[0016] S41. According to the calculation model, scrap steel ratio and molten iron temperature, the spectrometer measurement signal of the predicted end point of the solid-to-liquid phase transformation is obtained, and the spectrometer measurement signal of the start point of the solid-to-liquid phase transformation is calculated based on the predicted spectrometer measurement signal of the end point of the solid-to-liquid phase transformation.

[0017] S42. Calculate the proportion coefficient of the liquid phase component in the molten pool based on the predicted spectrometer measurement signal at the end point of the solid-to-liquid phase transformation, the spectrometer measurement signal at the start point of the solid-to-liquid phase transformation, the second VIS-NIR spectrum data and the relationship function.

[0018] S43. Obtain a prediction result of the melting process of the scrap steel in the molten pool according to the proportion coefficient of the liquid phase components in the molten pool.

[0019] Optionally, calculating the spectrometer measurement signal at the start time of the solid-to-liquid phase transformation according to the predicted spectrometer measurement signal at the end time of the solid-to-liquid phase transformation in S41 includes:

[0020] The spectrometer measurement signal at the end point of the historical solid-to-liquid phase transformation and the spectrometer measurement signal at the start point of the historical solid-to-liquid phase transformation are obtained, and the corresponding relationship between the spectrometer measurement signal at the end point of the solid-to-liquid phase transformation and the spectrometer measurement signal at the start point of the solid-to-liquid phase transformation is established.

[0021] According to the predicted spectrometer measurement signal at the end point of the transformation from the solid phase to the liquid phase and the corresponding relationship, the spectrometer measurement signal at the start point of the transformation from the solid phase to the liquid phase is calculated.

[0022] Optionally, the correspondence between the spectrometer measurement signal at the end point of the solid-to-liquid phase transformation and the spectrometer measurement signal at the start point of the solid-to-liquid phase transformation includes:

[0023] For the melting process on the molten pool surface, the ratio of the spectrometer measurement signal at the beginning of the solid-to-liquid phase transformation to the spectrometer measurement signal at the end of the solid-to-liquid phase transformation is between 1.05 and 1.15.

[0024] For the melting process inside the molten pool, the ratio of the spectrometer measurement signal at the beginning of the transformation from solid to liquid phase to the spectrometer measurement signal at the end of the transformation from solid to liquid phase is between 1.25 and 1.5.

[0025] Optionally, the relationship function in S42 is as shown in the following formula (1):

[0026] (1)

[0027] In the formula, It represents the proportion of liquid phase in the molten pool at any time. It indicates the proportion of liquid phase in the molten pool at the initial moment. The spectrometer measurement signal indicates the moment when the solid phase inside the molten pool begins to transform into the liquid phase. represents the spectrometer measurement signal at any time, The spectrometer measurement signal indicates the end point of the transformation from solid phase to liquid phase inside the molten pool.

[0028] Optionally, the method further comprises:

[0029] Acquire third VIS-NIR spectrum data after a preset time interval, and determine whether the third VIS-NIR spectrum data is smaller than the second VIS-NIR spectrum data.

[0030] If so, the proportion coefficient of the liquid phase component in the molten pool is obtained according to the calculation model, the scrap steel ratio and the molten iron temperature, and the prediction result of the scrap steel melting process in the molten pool is obtained according to the proportion coefficient of the liquid phase component in the molten pool.

[0031] If not, the calculation model is optimized according to the third VIS-NIR spectrum data, scrap steel ratio and molten iron temperature.

[0032] On the other hand, a prediction device for the melting process of scrap steel based on VIS-NIR spectroscopy is provided. The device is applied to a prediction method for the melting process of scrap steel based on VIS-NIR spectroscopy. The device comprises: a top-blown oxygen gun with an embedded spectral acquisition probe, an optical fiber, a spectrometer, a computer and a database.

[0033] The top-blown oxygen lance with an embedded spectral acquisition probe is used to collect historical VIS-NIR spectral data in the molten pool during the converter steelmaking process of historical furnaces, the first VIS-NIR spectral data in the molten pool during the converter steelmaking process of the furnace to be predicted, and the second VIS-NIR spectral data after a preset time interval.

[0034] The optical fiber is used to transmit the spectral data collected by the spectral acquisition probe to the spectrometer.

[0035] Spectrometer, used to convert optical signals into electrical signals and output them to a computer.

[0036] The computer is used to construct a calculation model according to the historical VIS-NIR spectrum data, and determine whether the second VIS-NIR spectrum data is smaller than the first VIS-NIR spectrum data.

[0037] If so, the proportion coefficient of the liquid phase component in the molten pool is obtained according to the calculation model, scrap steel ratio, molten iron temperature and the second VIS-NIR spectrum data, and the prediction result of the scrap steel melting process in the molten pool is obtained according to the proportion coefficient of the liquid phase component in the molten pool.

[0038] If not, the prediction ends.

[0039] Database, used for data storage.

[0040] Optionally, historical VIS-NIR spectral data in the molten pool during converter steelmaking of historical heats are obtained, and a calculation model is constructed based on the historical VIS-NIR spectral data, including:

[0041] The historical VIS-NIR spectral data in the molten pool during the converter steelmaking process of historical furnaces are continuously collected by installing a spectral acquisition probe inside the oxygen nozzle.

[0042] A calculation model is constructed based on the historical VIS-NIR spectral data, as well as the scrap steel ratio and molten iron temperature of the furnace corresponding to the historical VIS-NIR spectral data.

[0043] Optionally, a proportion coefficient of the liquid phase component in the molten pool is obtained according to the calculation model, the scrap steel ratio, the molten iron temperature and the second VIS-NIR spectrum data, and a prediction result of the melting process of the scrap steel in the molten pool is obtained according to the proportion coefficient of the liquid phase component in the molten pool, including:

[0044] S41. According to the calculation model, scrap steel ratio and molten iron temperature, the spectrometer measurement signal of the predicted end point of the solid-to-liquid phase transformation is obtained, and the spectrometer measurement signal of the start point of the solid-to-liquid phase transformation is calculated based on the predicted spectrometer measurement signal of the end point of the solid-to-liquid phase transformation.

[0045] S42. Calculate the proportion coefficient of the liquid phase component in the molten pool based on the predicted spectrometer measurement signal at the end point of the solid-to-liquid phase transformation, the spectrometer measurement signal at the start point of the solid-to-liquid phase transformation, the second VIS-NIR spectrum data and the relationship function.

[0046] S43. Obtain a prediction result of the melting process of the scrap steel in the molten pool according to the proportion coefficient of the liquid phase components in the molten pool.

[0047] Optionally, calculating the spectrometer measurement signal at the start time of the solid-to-liquid phase transformation according to the predicted spectrometer measurement signal at the end time of the solid-to-liquid phase transformation comprises:

[0048] The spectrometer measurement signal at the end point of the historical solid-to-liquid phase transformation and the spectrometer measurement signal at the start point of the historical solid-to-liquid phase transformation are obtained, and the corresponding relationship between the spectrometer measurement signal at the end point of the solid-to-liquid phase transformation and the spectrometer measurement signal at the start point of the solid-to-liquid phase transformation is established.

[0049] According to the predicted spectrometer measurement signal at the end point of the transformation from the solid phase to the liquid phase and the corresponding relationship, the spectrometer measurement signal at the start point of the transformation from the solid phase to the liquid phase is calculated.

[0050] Optionally, the correspondence between the spectrometer measurement signal at the end point of the solid-to-liquid phase transformation and the spectrometer measurement signal at the start point of the solid-to-liquid phase transformation includes:

[0051] For the melting process on the molten pool surface, the ratio of the spectrometer measurement signal at the beginning of the solid-to-liquid phase transformation to the spectrometer measurement signal at the end of the solid-to-liquid phase transformation is between 1.05 and 1.15.

[0052] For the melting process inside the molten pool, the ratio of the spectrometer measurement signal at the beginning of the transformation from solid to liquid phase to the spectrometer measurement signal at the end of the transformation from solid to liquid phase is between 1.25 and 1.5.

[0053] Optionally, the relationship function is as shown in the following formula (1):

[0054] (1)

[0055] In the formula, It represents the proportion of liquid phase in the molten pool at any time. It indicates the proportion of liquid phase in the molten pool at the initial moment. The spectrometer measurement signal indicates the moment when the solid phase inside the molten pool begins to transform into the liquid phase. represents the spectrometer measurement signal at any time, The spectrometer measurement signal indicates the end point of the transformation from solid phase to liquid phase inside the molten pool.

[0056] Optionally, the computer is further configured to:

[0057] Acquire third VIS-NIR spectrum data after a preset time interval, and determine whether the third VIS-NIR spectrum data is smaller than the second VIS-NIR spectrum data.

[0058] If so, the proportion coefficient of the liquid phase component in the molten pool is obtained according to the calculation model, the scrap steel ratio and the molten iron temperature, and the prediction result of the scrap steel melting process in the molten pool is obtained according to the proportion coefficient of the liquid phase component in the molten pool.

[0059] If not, the calculation model is optimized according to the third VIS-NIR spectrum data, scrap steel ratio and molten iron temperature.

[0060] On the other hand, a prediction device for the melting process of scrap steel based on VIS-NIR spectroscopy is provided, and the prediction device for the melting process of scrap steel based on VIS-NIR spectroscopy comprises: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above-mentioned prediction methods for the melting process of scrap steel based on VIS-NIR spectroscopy is implemented.

[0061] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned methods for predicting the scrap steel melting process based on VIS-NIR spectroscopy.

[0062] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0063] The present invention provides a new prediction method and device for online monitoring of scrap steel melting process based on VIS-NIR spectrum, which can be applied to all converters using top blowing oxygen supply and has a suitable capacity range of 30t to 400t.

[0064] The present invention realizes the whole process monitoring and prediction of the melting process of scrap steel in converter steelmaking based on the spectral analysis and detection of the fire point area, thereby optimizing the operation of the blowing process, improving the end point hit rate, and reducing the smelting consumption. After the present invention is applied, the prediction accuracy of scrap steel melting in the converter smelting process can be increased by 4-8%, the end point hit rate is increased by 3-5%, the end point oxygen is reduced by 10-30ppm, the steel material consumption is saved by 2-4kg / t, and the comprehensive economic benefit is greater than 2 yuan / t. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0066] Figure 1 It is a flow chart of a method for predicting scrap steel melting process based on VIS-NIR spectrum provided by an embodiment of the present invention;

[0067] Figure 2 It is a flow chart of a prediction method for online monitoring of scrap steel melting process based on VIS-NIR spectroscopy provided by an embodiment of the present invention;

[0068] Figure 3 It is a block diagram of a prediction device for scrap steel melting process based on VIS-NIR spectrum provided by an embodiment of the present invention;

[0069] Figure 4 It is a schematic diagram of the structure of a device for predicting the melting process of scrap steel based on VIS-NIR spectrum provided by an embodiment of the present invention;

[0070] In the figure, 1. Top-blown oxygen gun with embedded spectrum acquisition probe; 2. Optical fiber; 3. Spectrometer; 4. Computer; 5. Database. DETAILED DESCRIPTION

[0071] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0072] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0073] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0074] In the embodiments of the present invention, sometimes the subscripts such as W1 It may be written in non-subscript form such as W1. When the difference is not emphasized, the meaning is the same.

[0075] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0076] The embodiment of the present invention provides a method for predicting the melting process of scrap steel based on VIS-NIR spectrum, which can be implemented by a prediction device for predicting the melting process of scrap steel based on VIS-NIR spectrum, and the prediction device for predicting the melting process of scrap steel based on VIS-NIR spectrum can be a terminal or a server. Figure 1 , 2 The flowchart of the method for predicting the melting process of scrap steel based on VIS-NIR spectrum is shown. The processing flow of the method may include the following steps:

[0077] S1. Obtain historical VIS-NIR spectral data in the molten pool during converter steelmaking in historical furnaces, and build a calculation model based on the historical VIS-NIR spectral data.

[0078] Optionally, the above step S1 may include the following steps S11-S12:

[0079] S11. Continuously collect historical VIS-NIR spectral data in the molten pool during the converter steelmaking process of historical furnaces through a spectral acquisition probe installed inside the oxygen nozzle.

[0080] S12. Construct a calculation model based on the historical VIS-NIR spectral data, and the scrap steel ratio and molten iron temperature of the furnace corresponding to the historical VIS-NIR spectral data.

[0081] In a feasible implementation, a spectral acquisition probe is installed inside the oxygen nozzle, and the VIS-NIR (Visible-Near Infrared) spectrum in the molten pool of the converter steelmaking process is continuously collected through an optical path formed by the oxygen lance nozzle and the oxygen jet.

[0082] The signal measured by the spectrometer is composed of the luminescence spectrum signal of the sample itself, the environmental radiation signal and the radiation signal of the spectrometer itself, and the final spectral data is obtained through the spectrometer response function.

[0083] Specifically, the spectrometer is the core component of thermal emission spectrum measurement. When using it for thermal emission measurement, the contribution ratio of the sample and the instrument environment radiation in the acquired signal varies significantly due to differences in experimental conditions, so the corresponding measurement and calibration methods also differ.

[0084] Emissivity is an intrinsic property of matter and is defined as the amount of energy emitted by a surface as heat ( ) is equal to the energy of thermal emission from a black body surface at the same temperature ( ), that is:

[0085] (1)

[0086] In the formula, is the emissivity, is the wavelength, is the radiation energy (radiance), Theoretically, we only need to obtain the DN (Digital Number) values ​​corresponding to the sample and the blackbody radiation energy at the same temperature to obtain the thermal emissivity (same emissivity) of the sample, that is:

[0087] (2)

[0088] In the formula, and is the true DN value of the sample and blackbody excluding instrument and environmental radiation. However, in the actual measurement process, the radiation contribution from the spectrometer itself and the internal environment of the sample cavity cannot be ignored.

[0089] When performing thermal emission measurements, the spectrometer's measurement signal It consists of two parts: one is the radiation energy of the sample , and the other part is the energy from the spectrometer itself . For the energy radiated by the spectrometer, only the part modulated by the interferometer will affect the measurement result. The signal that has not been modulated by the interferometer appears as a constant in the measured interference pattern, and will not affect the final result after Fourier transform. The energy radiated by the spectrometer in the measurement signal mainly comes from the radiation of the detector itself, and the signal measured by the spectrometer is actually the difference between the radiation signal of the sample and the detector, that is:

[0090] (3)

[0091] In the formula, is the signal measured by the instrument, dimensionless; and are the energy and radiance of the sample and detector radiation, respectively; is the instrument response function. The energy from the sample It is usually composed of two parts. In addition to the radiation energy of the sample itself, the light radiated from the environment inside the sample cavity will also enter the detector after being reflected by the sample surface, including:

[0092] (4)

[0093] In the formula, is the emissivity, is the sample emissivity, is the energy (radiance) of blackbody radiation at a given temperature, is the reflectivity, is the sample reflectance, is the temperature, is the temperature of the sample, is the energy radiated from the internal environment of the sample chamber to the sample surface, is the ambient temperature inside the sample chamber. Equations (3) and (4) are widely used in the processing and analysis of thermal emission measurement data.

[0094] During the phase change process, the luminescence spectrum signal of the sample in the molten pool itself mainly comes from two parts. One is the thermal radiation spectrum signal on the surface of the molten pool, and the other is the thermal radiation spectrum inside the molten pool after being absorbed by the surface of the molten pool.

[0095] The calculation of the luminescence spectrum signal of the sample itself in the molten pool can be simplified to the following formula (5):

[0096] (5)

[0097] In the formula, , are the energies of the solid and liquid phase radiation on the sample surface, respectively; , are the energies of the solid and liquid phase radiation inside the sample, respectively; is the transmittance of the internal radiation energy through the molten pool surface, which can be approximated as:

[0098] (6)

[0099] In the formula, , are the transmittances of the energy radiated from the inside of the molten pool through the solid phase and liquid phase on the surface of the molten pool, respectively; , and They are the areas occupied by the solid and liquid phases on the molten pool surface and the total area of ​​the molten pool surface, respectively.

[0100] Since the spectral signal measured by the spectrometer mainly comes from the normal direction of the sample, and the radiation signals in other directions of the sample are difficult to be measured by the spectrometer, the proportion of the solid phase to the liquid phase in the molten pool can be simplified as the ratio of the cross-sectional areas of each system of the sample in this direction.

[0101] The transmittance of the radiation energy inside the sample through the sample surface can be estimated by the ratio of the solid and liquid phases on the molten pool surface combined with the transmittance of the energy radiated inside the molten pool through the solid and liquid phases on the molten pool surface (as shown in Equation 6). It can be approximated to zero. Substituting the simplified formula (6) into formula (5) yields the following general formula:

[0102] (7)

[0103] The ambient temperature of the spectrometer during the measurement process is generally constant, so the radiation energy of the spectrometer can be eliminated by the difference method. The impact of

[0104] (8)

[0105] If the surface and interior of the sample are regarded as a system, the radiation energy of the liquid or solid phase can be simplified as a function of the area occupied by the solid and liquid phases. Combining formula (1), we can get:

[0106] (9)

[0107] and,

[0108] (10)

[0109] In the formula, , and are the areas occupied by the solid and liquid phases inside the molten pool and the total area inside the molten pool, respectively. , are the emissivity of the molten pool surface and the solid phase inside, respectively.

[0110] To eliminate the spectrometer response function The influence of, let:

[0111] (11)

[0112] In the formula, The spectrometer measurement signal at any time of the transition from solid phase to liquid phase, It is the spectrometer measurement signal at the beginning of the transformation from solid phase to liquid phase during the melting process (on the surface of the molten pool or inside the molten pool). It is the spectrometer measurement signal at the end point of the transformation from solid phase to liquid phase during the melting process (on the surface of the molten pool or inside the molten pool).

[0113] Crystals have a definite spatial lattice structure. When heat is provided externally, the energy is first used to overcome the interaction forces between atoms or molecules, causing them to change from an ordered solid state to a disordered liquid state. During this transition, the system is in a "latent heat" state, that is, it absorbs heat but does not increase the average kinetic energy of the molecules, so the temperature does not rise. Until all the lattice structures are destroyed, that is, all the solids are converted into liquids, continued heating will cause the kinetic energy of the liquid particles to increase, thereby causing the temperature to rise, and vice versa. Therefore, during the melting or solidification process of the crystal, despite the coexistence of solid and liquid, the temperature of the crystal will remain at a fixed melting point until it is completely melted. Therefore, during the solid-liquid phase transition process, the effect of temperature changes on the radiation energy of the sample can be ignored. Then:

[0114] (12)

[0115] For the melting process, if the measured signal at the beginning of the transformation from solid phase to liquid phase is used as the reference value. For this special moment, , , then the signal measured by the instrument is:

[0116] (13)

[0117] For the melting process, the final moment of the transformation from solid phase to liquid phase is , , , then the signal measured by the instrument is:

[0118] (14)

[0119] During the melting process, due to the influence of the phase change "latent heat", the change in the molten pool temperature during the melting of scrap steel can be further ignored. Under the condition of changes, the environmental radiation at any two moments of the melting process can be approximately considered equal. Since the density of solid iron is greater than that of liquid iron, the liquid iron produced during the solid-liquid phase change will come to the surface of the molten pool, which means that liquid iron will only be generated inside the molten pool after the surface of the molten pool is completely converted into liquid phase. Therefore, in the early stage of the melting process, it can be considered that no phase change occurs inside the molten pool, that is, the radiation energy inside the molten pool is constant.

[0120] Then formula (11) can be simplified as:

[0121] (15)

[0122] In the formula, is the spectrometer measurement signal at the initial moment of transformation from solid phase to liquid phase on the molten pool surface. It is the spectrometer measurement signal at the end point of the transformation from solid phase to liquid phase on the surface of the molten pool. It is the spectrometer measurement signal at any time when the solid phase on the molten pool surface transforms into the liquid phase. is the proportion of solid phase on the molten pool surface at any time, It is the proportion of liquid phase on the molten pool surface at any time.

[0123] make , , and ignoring the influence of radiation inside the molten pool, we have:

[0124] (16)

[0125] Since the melting of metallic iron will continue to absorb heat, the temperature inside the molten pool will drop. Therefore, after the surface of the molten pool has melted, the inside of the molten pool will have a short heating process. During this process, the radiation energy on the surface of the molten pool can be considered to be constant, while the increase in the temperature inside the molten pool will cause the radiation energy from the inside of the molten pool to continue to increase until the inside of the molten pool begins to melt.

[0126] As for the melting process inside the molten pool, it can be considered that the radiation energy on the surface of the molten pool is constant, and the radiation energy of the furnace after reflection from the surface of the molten pool is also constant. If the beginning of the melting inside the molten pool is taken as the initial state, and the complete conversion of the metallic iron into the liquid phase is taken as the end state, then equation (11) can be simplified to:

[0127] (17)

[0128] In the formula, It is the spectrometer measurement signal at the initial moment of transformation from solid phase to liquid phase inside the molten pool. It is the spectrometer measurement signal at the end point of the transformation from solid phase to liquid phase inside the molten pool. It is the spectrometer measurement signal at any time when the solid phase inside the molten pool transforms into the liquid phase. is the proportion of the solid phase in the molten pool at any time, It is the proportion of liquid phase inside the molten pool at any time.

[0129] make , , and ignoring the influence of radiation inside the molten pool, we have:

[0130] (18)

[0131] In summary, the online measurement of the VIS-NIR spectrum in the molten pool at different times can calculate the proportion coefficient of the liquid phase system in the molten pool, that is, the melting process of scrap steel.

[0132] At present, in the traditional process of domestic converter smelting, scrap steel accounts for about 10% to 25%. Therefore, for the converter smelting process, the melting of scrap steel will only go through the internal melting stage. Due to the difference in the amount of scrap steel added, the VIS-NIR spectrum obtained by the initial measurement is not the initial state of the internal melting process, but the spectral characteristics corresponding to the amount of scrap steel added and the molten iron temperature. Therefore, for this process, and The value of is unknown and needs to be determined by and The relationship between the molten iron temperature and the scrap ratio is further obtained. In addition, in the actual production process, due to the difference in the amount of scrap added and the molten iron temperature, the ratio of each heat and There are some differences in the value of and The value of is corrected. That is:

[0133] (19)

[0134] In the formula, Indicates the molten iron temperature, Indicates scrap steel ratio.

[0135] The establishment of the calculation model needs to be based on the actual production situation. In the early stage of VIS-NIR spectrum measurement, the above calculation model is trained by continuously collecting VIS-NIR spectra in the molten pool. The specific operation process is as follows:

[0136] a) The experimental measurement results show that the luminescence intensity of the VIS-NIR spectrum of solid metal iron at the same temperature is significantly higher than that of liquid metal iron, and the increase in temperature will significantly increase the luminescence intensity of the VIS-NIR spectrum. Therefore, as the scrap steel in the molten pool melts, the luminescence intensity of the VIS-NIR spectrum will gradually decrease until the scrap steel melts. When the scrap steel is completely melted, the molten pool enters a rapid heating stage, during which the luminescence intensity of the VIS-NIR spectrum will gradually increase. The minimum value of the luminescence intensity of the VIS-NIR spectrum measured during this process is approximately equal to .

[0137] b) Through the collection The calculation model is trained by comparing the scrap steel ratio and molten iron temperature of the corresponding furnace, and the trained calculation model is used to predict the performance of furnaces with different scrap steel ratios and molten iron temperatures. and Value. Among them, and The ratio is between 1.25 and 1.5.

[0138] The present invention proposes a prediction method for online monitoring of scrap steel melting process based on VIS-NIR spectrum, and predicts the melting process of scrap steel in the furnace in real time by measuring and analyzing the VIS-NIR spectrum in the molten pool in actual production.

[0139] In order to predict the melting process of scrap steel in the molten pool, the collected VIS-NIR spectrum data needs to be processed. The specific operation logic is as follows: Steps S2-S4:

[0140] S2. Acquire the first VIS-NIR spectrum data, scrap steel ratio and molten iron temperature in the molten pool during the converter steelmaking process of the heat to be predicted.

[0141] In a feasible implementation manner, after the converter body is straightened, the VIS-NIR spectrum in the furnace is collected (3 consecutive times, each time interval is 1ms, and the average value of the three collected data is taken as the effective measurement value), and the molten iron temperature and scrap steel ratio of this furnace are loaded.

[0142] S3. Acquire second VIS-NIR spectrum data after a preset time interval, and determine whether the second VIS-NIR spectrum data is smaller than the first VIS-NIR spectrum data.

[0143] If yes, execute step S4.

[0144] If not, the prediction ends.

[0145] In a feasible implementation, after a time interval of 1s, the VIS-NIR spectrum in the furnace is collected again, and the magnitude relationship of the VIS-NIR spectrum intensity collected twice is compared. If the spectrum intensity value collected this time is less than the spectrum intensity value collected last time, the next step of calculation is entered. If the spectrum intensity value collected this time is greater than the spectrum intensity value collected last time, the calculation ends.

[0146] S4. According to the calculation model, scrap steel ratio, molten iron temperature and the second VIS-NIR spectrum data, the proportion coefficient of the liquid phase component in the molten pool is obtained, and the melting process prediction result of the scrap steel in the molten pool is obtained according to the proportion coefficient of the liquid phase component in the molten pool.

[0147] Optionally, the above step S4 may include the following steps S41-S43:

[0148] S41, according to the calculation model, scrap steel ratio and molten iron temperature, obtain the spectrometer measurement signal at the predicted end point of solid-to-liquid phase transformation , based on the spectrometer measurement signal at the predicted end point of the solid-to-liquid transition Calculate the spectrometer measurement signal at the beginning of the solid-to-liquid phase transition .

[0149] Optionally, the spectrometer measurement signal at the predicted end point of the solid-to-liquid phase transformation in S41 Calculate the spectrometer measurement signal at the beginning of the solid-to-liquid phase transition ,include:

[0150] S411, obtaining the spectrometer measurement signal at the end point of the historical solid-to-liquid phase transformation And the spectrometer measurement signal at the beginning of the historical solid-to-liquid phase transformation , construct the spectrometer measurement signal at the end point of the solid-to-liquid phase transition The spectrometer measurement signal at the beginning of the solid-to-liquid phase transition The corresponding relationship.

[0151] S412, based on the spectrometer measurement signal at the predicted end point of the solid-to-liquid phase transformation And the corresponding relationship, the spectrometer measurement signal at the beginning of the solid phase to liquid phase transformation is calculated .

[0152] S42, based on the spectrometer measurement signal at the predicted end point of the solid phase to liquid phase transformation , the spectrometer measurement signal at the beginning of the solid-liquid phase transition , the second VIS-NIR spectrum data and the relationship function are used to calculate the proportion coefficient of the liquid phase component in the molten pool.

[0153] Optionally, the relationship function in S42 is as shown in the following formula (20):

[0154] (20)

[0155] In the formula, It represents the proportion of liquid phase in the molten pool at any time. It indicates the proportion of liquid phase in the molten pool at the initial moment. The spectrometer measurement signal indicates the moment when the solid phase inside the molten pool begins to transform into the liquid phase. represents the spectrometer measurement signal at any time, The spectrometer measurement signal indicates the end point of the transformation from solid phase to liquid phase inside the molten pool.

[0156] In a feasible implementation, through the above calculation model, it can be calculated that and The value, combined with the spectral intensity value collected this time, can be used to calculate the proportion R of the liquid phase system in the molten pool, and further calculate the melting process of the scrap steel.

[0157] S43. Obtain a prediction result of the melting process of the scrap steel in the molten pool according to the proportion coefficient of the liquid phase components in the molten pool.

[0158] Optionally, the method further comprises:

[0159] Acquire third VIS-NIR spectrum data after a preset time interval, and determine whether the third VIS-NIR spectrum data is smaller than the second VIS-NIR spectrum data.

[0160] If so, the proportion coefficient of the liquid phase component in the molten pool is obtained according to the calculation model, the scrap steel ratio and the molten iron temperature, and the prediction result of the scrap steel melting process in the molten pool is obtained according to the proportion coefficient of the liquid phase component in the molten pool.

[0161] If not, the calculation model is optimized according to the third VIS-NIR spectrum data, scrap steel ratio and molten iron temperature.

[0162] In a feasible implementation, after a time interval of 1s, the VIS-NIR spectrum in the furnace is collected again, and the magnitude relationship of the VIS-NIR spectrum intensity collected twice is compared. If the spectrum intensity value collected this time is less than the spectrum intensity value collected last time, the melting process of the scrap steel is continued to be calculated. If the spectrum intensity value collected this time is greater than the spectrum intensity value collected last time, the loop is jumped out, and the spectrum intensity value collected this time is used as The value output is combined with the initial input molten iron temperature and scrap steel ratio of this furnace to re-optimize the calculation model.

[0163] Example 1, 100t steelmaking converter:

[0164] like Figure 2 As shown in the figure, firstly, the VIS-NIR spectrum in the molten pool during converter smelting is collected in situ to build a computational model. The relationship function between molten iron temperature and scrap steel ratio is used for subsequent calculations.

[0165] After the calculation model is built, the scrap ratio and molten iron temperature of this heat are loaded to predict the value, and calculated based on experimental data Value (select according to the actual situation on site ).

[0166] The VIS-NIR spectral data in the molten pool were continuously collected (with a time interval of 1 s) and combined with formula (20) to calculate the proportion coefficient of the liquid phase component in the molten pool. Furthermore, the melting process of the scrap steel in the molten pool was calculated by calculating the proportion coefficient of the liquid phase system inside the molten pool.

[0167] Furthermore, when the intensity of the collected VIS-NIR spectrum is less than the intensity of the previous VIS-NIR spectrum, it means that the scrap steel in the molten pool has been melted and has entered the rapid heating stage. Therefore, the intensity of the spectrum collected in this stage is approximately equal to the intensity of the current heat. value.

[0168] Furthermore, The value, molten iron temperature and scrap steel ratio are taken as new inputs into the model for calculation to further optimize the calculation accuracy of the model.

[0169] After the application of the present invention, the prediction accuracy of scrap steel melting in the converter smelting process can be improved by 4-6%, and as the number of smelting furnaces increases, the prediction accuracy of the method will be further improved. After the application of the present invention, the converter endpoint hit rate is increased by 3-4%, the endpoint oxygen is reduced by 10-25ppm, the steel material consumption is saved by 2-3.5kg / t, and the comprehensive economic benefit is greater than 1.5 yuan / t.

[0170] Example 2, 300t dephosphorization converter:

[0171] The VIS-NIR spectrum in the converter is collected by a top-blown oxygen gun (1) with an embedded spectrum collection probe, and the spectrum signal is transmitted to a spectrometer (3) through an optical fiber (2) for spectroscopic processing. The spectrometer (3) converts the optical signal into an electrical signal and outputs it to a computer (4). The computer (4) uses Figure 2 The data processing method shown in the figure calculates and analyzes the spectral signal and calculates the molten iron temperature, scrap steel ratio and Data such as values ​​are stored in a database (5) for training the computational model.

[0172] After the calculation model is built, the scrap ratio and molten iron temperature of this heat are loaded to predict the value, and calculated based on experimental data Value (select according to the actual situation on site ).

[0173] The VIS-NIR spectral data in the molten pool were continuously collected (with a time interval of 1 s) and combined with formula (20) to calculate the proportion coefficient of the liquid phase component in the molten pool. Furthermore, the melting process of the scrap steel in the molten pool was calculated by calculating the proportion coefficient of the liquid phase system inside the molten pool.

[0174] Furthermore, when the intensity of the collected VIS-NIR spectrum is less than the intensity of the previous VIS-NIR spectrum, it means that the scrap steel in the molten pool has been melted and has entered the rapid heating stage. Therefore, the intensity of the spectrum collected in this stage is approximately equal to the intensity of the current heat. value.

[0175] Furthermore, The value, molten iron temperature and scrap steel ratio are taken as new inputs into the model for calculation to further optimize the calculation accuracy of the model.

[0176] After the application of the present invention, the prediction accuracy of scrap steel melting in the converter smelting process can be improved by 5-8%, and as the number of smelting furnaces increases, the prediction accuracy of the method will be further improved. After the application of the present invention, the converter endpoint hit rate is increased by 4-5%, the endpoint oxygen is reduced by 15-30ppm, the steel material consumption is saved by 3-4kg / t, and the comprehensive economic benefit is greater than 2 yuan / t.

[0177] In the embodiment of the present invention, a new prediction method and device for online monitoring of scrap steel melting process based on VIS-NIR spectroscopy are provided, which can be applied to all converters using top blowing oxygen supply and have a suitable capacity range of 30t to 400t.

[0178] The present invention realizes the whole process monitoring and prediction of the melting process of scrap steel in converter steelmaking based on the spectral analysis and detection of the fire point area, thereby optimizing the operation of the blowing process, improving the end point hit rate, and reducing the smelting consumption. After the present invention is applied, the prediction accuracy of scrap steel melting in the converter smelting process can be increased by 4-8%, the end point hit rate is increased by 3-5%, the end point oxygen is reduced by 10-30ppm, the steel material consumption is saved by 2-4kg / t, and the comprehensive economic benefit is greater than 2 yuan / t.

[0179] Figure 3 The present invention is a block diagram of a device for predicting the melting process of scrap steel based on VIS-NIR spectrum according to an exemplary embodiment. The device is used in a method for predicting the melting process of scrap steel based on VIS-NIR spectrum. Figure 3 The device includes a top-blown oxygen gun with an embedded spectrum acquisition probe, an optical fiber, a spectrometer, a computer and a database.

[0180] The spectral acquisition probe is installed inside the oxygen nozzle, and is used to collect historical VIS-NIR spectral data in the molten pool during the converter steelmaking process of the previous furnace, the first VIS-NIR spectral data in the molten pool during the converter steelmaking process of the predicted furnace, and the second VIS-NIR spectral data after a preset time interval.

[0181] The optical fiber is used to transmit the spectral data collected by the spectral acquisition probe to the spectrometer.

[0182] Spectrometer, used to convert optical signals into electrical signals and output them to a computer.

[0183] The computer is used to construct a calculation model according to the historical VIS-NIR spectrum data, and determine whether the second VIS-NIR spectrum data is smaller than the first VIS-NIR spectrum data.

[0184] If so, the proportion coefficient of the liquid phase component in the molten pool is obtained according to the calculation model, scrap steel ratio, molten iron temperature and the second VIS-NIR spectrum data, and the prediction result of the scrap steel melting process in the molten pool is obtained according to the proportion coefficient of the liquid phase component in the molten pool.

[0185] If not, the prediction ends.

[0186] Database, used for data storage.

[0187] In the embodiment of the present invention, a new prediction method and device for online monitoring of scrap steel melting process based on VIS-NIR spectroscopy are provided, which can be applied to all converters using top blowing oxygen supply and have a suitable capacity range of 30t to 400t.

[0188] The present invention realizes the whole process monitoring and prediction of the melting process of scrap steel in converter steelmaking based on the spectral analysis and detection of the fire point area, thereby optimizing the operation of the blowing process, improving the end point hit rate, and reducing the smelting consumption. After the present invention is applied, the prediction accuracy of scrap steel melting in the converter smelting process can be increased by 4-8%, the end point hit rate is increased by 3-5%, the end point oxygen is reduced by 10-30ppm, the steel material consumption is saved by 2-4kg / t, and the comprehensive economic benefit is greater than 2 yuan / t.

[0189] Figure 4 is a schematic diagram of a structure of a prediction device for scrap steel melting process based on VIS-NIR spectrum provided by an embodiment of the present invention, such as Figure 4 As shown, the prediction device for scrap steel melting process based on VIS-NIR spectrum may include the above Figure 3 The device for predicting the melting progress of scrap steel based on VIS-NIR spectrum is shown. Optionally, the device for predicting the melting progress of scrap steel based on VIS-NIR spectrum 410 may include a first processor 2001 .

[0190] Optionally, the device 410 for predicting the melting progress of scrap steel based on VIS-NIR spectrum may further include a memory 2002 and a transceiver 2003 .

[0191] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0192] Combine the following Figure 4 The components of the prediction device 410 for the melting process of scrap steel based on VIS-NIR spectrum are specifically introduced as follows:

[0193] The first processor 2001 is the control center of the prediction device 410 for the melting process of scrap steel based on VIS-NIR spectrum, and can be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiment of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0194] Optionally, the first processor 2001 can perform various functions of the device 410 for predicting the scrap steel melting process based on VIS-NIR spectroscopy by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002 .

[0195] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 4 CPU0 and CPU1 are shown in FIG.

[0196] In a specific implementation, as an embodiment, the prediction device 410 for the scrap steel melting process based on VIS-NIR spectrum may also include multiple processors, such as Figure 4 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0197] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0198] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently, and may be accessed through the interface circuit ( Figure 4 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0199] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0200] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 4 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0201] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently, and communicate with the first processor 2001 through the interface circuit ( Figure 4 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0202] It should be noted that Figure 4 The structure of the prediction device 410 for scrap steel melting process based on VIS-NIR spectrum shown in the figure does not constitute a limitation on the router, and the actual knowledge structure recognition device may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0203] In addition, the technical effects of the device 410 for predicting the melting process of scrap steel based on VIS-NIR spectroscopy can refer to the technical effects of the method for predicting the melting process of scrap steel based on VIS-NIR spectroscopy described in the above method embodiment, which will not be repeated here.

[0204] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0205] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0206] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0207] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0208] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0209] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0210] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0211] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0212] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0213] 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 on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0214] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0215] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0216] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for predicting the melting process of scrap steel based on VIS-NIR spectroscopy, characterized in that: The method comprises: S1. Obtain historical VIS-NIR spectral data in the molten pool during converter steelmaking in historical heats, and construct a calculation model based on the historical VIS-NIR spectral data; S2, obtaining the first VIS-NIR spectrum data, scrap steel ratio and molten iron temperature in the molten pool during the converter steelmaking process of the heat to be predicted; S3, acquiring second VIS-NIR spectrum data after a preset time interval, and determining whether the second VIS-NIR spectrum data is smaller than the first VIS-NIR spectrum data; If yes, execute step S4; If not, the prediction ends; S4. Obtain the proportion coefficient of the liquid phase component in the molten pool according to the calculation model, the scrap steel ratio, the molten iron temperature and the second VIS-NIR spectrum data, and obtain the prediction result of the scrap steel melting process in the molten pool according to the proportion coefficient of the liquid phase component in the molten pool.

2. The method for predicting the melting process of scrap steel based on VIS-NIR spectrum according to claim 1, characterized in that: The step of obtaining historical VIS-NIR spectral data in the molten pool during converter steelmaking of historical heats in S1, and constructing a calculation model based on the historical VIS-NIR spectral data, includes: The spectrum acquisition probe installed inside the oxygen nozzle is used to continuously collect historical VIS-NIR spectrum data in the molten pool during the converter steelmaking process of historical furnaces. A calculation model is constructed based on the historical VIS-NIR spectral data, and the scrap steel ratio and molten iron temperature of the furnace corresponding to the historical VIS-NIR spectral data.

3. The method for predicting the melting process of scrap steel based on VIS-NIR spectrum according to claim 1, characterized in that: The step S4 of obtaining a proportion coefficient of a liquid phase component in the molten pool according to the calculation model, the scrap steel ratio, the molten iron temperature and the second VIS-NIR spectrum data, and obtaining a prediction result of the melting process of the scrap steel in the molten pool according to the proportion coefficient of the liquid phase component in the molten pool includes: S41, obtaining a predicted spectrometer measurement signal at the end point of the solid-to-liquid phase transformation according to the calculation model, the scrap steel ratio and the molten iron temperature, and calculating a spectrometer measurement signal at the start point of the solid-to-liquid phase transformation according to the predicted spectrometer measurement signal at the end point of the solid-to-liquid phase transformation; S42, calculating the proportion coefficient of the liquid phase component in the molten pool according to the spectrometer measurement signal at the predicted end point of the solid-to-liquid phase transformation, the spectrometer measurement signal at the start point of the solid-to-liquid phase transformation, the second VIS-NIR spectrum data and the relationship function; S43, obtaining a prediction result of the melting process of the scrap steel in the molten pool according to the proportion coefficient of the liquid phase components in the molten pool.

4. The method for predicting the melting progress of scrap steel based on VIS-NIR spectrum according to claim 3, characterized in that: The step of calculating the spectrometer measurement signal at the start time of the solid-to-liquid phase transformation according to the predicted spectrometer measurement signal at the end time of the solid-to-liquid phase transformation in S41 includes: Acquire the spectrometer measurement signal at the end point of the historical solid-to-liquid phase transformation and the spectrometer measurement signal at the start point of the historical solid-to-liquid phase transformation, and construct a corresponding relationship between the spectrometer measurement signal at the end point of the solid-to-liquid phase transformation and the spectrometer measurement signal at the start point of the solid-to-liquid phase transformation; The spectrometer measurement signal at the start time of the solid-to-liquid phase transformation is calculated based on the predicted spectrometer measurement signal at the end time of the solid-to-liquid phase transformation and the corresponding relationship.

5. The method for predicting the melting progress of scrap steel based on VIS-NIR spectrum according to claim 4, characterized in that: The correspondence between the spectrometer measurement signal at the end point of the solid-to-liquid phase transformation and the spectrometer measurement signal at the start point of the solid-to-liquid phase transformation includes: For the melting process of the molten pool surface, the ratio of the spectrometer measurement signal at the start of the solid-to-liquid phase transformation to the spectrometer measurement signal at the end of the solid-to-liquid phase transformation is between 1.05 and 1.15; For the melting process inside the molten pool, the ratio of the spectrometer measurement signal at the start of the solid-to-liquid phase transformation to the spectrometer measurement signal at the end of the solid-to-liquid phase transformation is between 1.25 and 1.

5.

6. The method for predicting scrap steel melting progress based on VIS-NIR spectrum according to claim 3, characterized in that: The relationship function in S42 is shown in the following formula (1): （1） In the formula, It represents the proportion of liquid phase in the molten pool at any time. It indicates the proportion of liquid phase in the molten pool at the initial moment. The spectrometer measurement signal indicates the moment when the solid phase inside the molten pool begins to transform into the liquid phase. represents the spectrometer measurement signal at any time, The spectrometer measurement signal indicates the end point of the transformation from solid phase to liquid phase inside the molten pool.

7. The method for predicting the melting progress of scrap steel based on VIS-NIR spectrum according to claim 1, characterized in that: The method further comprises: Acquire third VIS-NIR spectrum data after a preset time interval, and determine whether the third VIS-NIR spectrum data is less than the second VIS-NIR spectrum data; If yes, then the proportion coefficient of the liquid phase component in the molten pool is obtained according to the calculation model, the scrap steel ratio and the molten iron temperature, and the prediction result of the melting process of the scrap steel in the molten pool is obtained according to the proportion coefficient of the liquid phase component in the molten pool; If not, the calculation model is optimized according to the third VIS-NIR spectrum data, scrap steel ratio and molten iron temperature.

8. A prediction device for scrap steel melting process based on VIS-NIR spectrum, the prediction device for scrap steel melting process based on VIS-NIR spectrum is used to implement the prediction method for scrap steel melting process based on VIS-NIR spectrum as claimed in any one of claims 1 to 7, characterized in that: The device comprises: a top-blown oxygen gun with a spectrum acquisition probe embedded therein, an optical fiber, a spectrometer, a computer and a database; The top-blown oxygen lance with an embedded spectrum acquisition probe is used to collect historical VIS-NIR spectrum data in the molten pool during the converter steelmaking process of the historical heats, first VIS-NIR spectrum data in the molten pool during the converter steelmaking process of the predicted heat, and second VIS-NIR spectrum data after a preset time interval; The optical fiber is used to transmit the spectrum data collected by the spectrum collection probe to the spectrometer; The spectrometer is used to convert the optical signal into an electrical signal and output it to a computer; The computer is used to construct a calculation model according to the historical VIS-NIR spectrum data, and determine whether the second VIS-NIR spectrum data is smaller than the first VIS-NIR spectrum data; If yes, then the proportion coefficient of the liquid phase component in the molten pool is obtained according to the calculation model, the scrap steel ratio, the molten iron temperature and the second VIS-NIR spectrum data, and the prediction result of the melting process of the scrap steel in the molten pool is obtained according to the proportion coefficient of the liquid phase component in the molten pool; If not, the prediction ends; The database is used for data storage.

9. A prediction device for scrap steel melting process based on VIS-NIR spectrum, characterized in that: The prediction device for scrap steel melting process based on VIS-NIR spectrum includes: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 7.

Images