Low-temperature impact test method and system for steel smelting

Abstract

The invention discloses a low-temperature impact test method and system for steel smelting, and relates to the technical field of steel detection, and the method comprises the steps: arranging a hollow isolation layer which is used for isolating to-be-tested steel from being in direct contact with a cooling medium of a low-temperature cooling device; isolating the to-be-tested steel by using a hollow isolating layer, and performing low-temperature cooling on the to-be-tested steel by using a low-temperature cooling device based on the hollow isolating layer; when the temperature sensor detects that the real-time cooling temperature of the to-be-tested steel reaches a preset temperature, an impact assembly is started, and the impact assembly impacts the cooled to-be-tested steel according to an impact execution case; obtaining an impact test data set, and evaluating the to-be-tested steel according to the impact test data set to obtain a first steel test evaluation index. The technical problem of inaccurate test caused by non-uniform cooling in the prior art is solved, and the technical effect of improving the accuracy, reliability and consistency of steel low-temperature performance evaluation is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of steel material detection, and in particular to a low-temperature impact testing method and system for steel material smelting. Background Art

[0002] With the rapid development of industrial technology and the increasing demand for engineering applications, the performance evaluation of steel in low-temperature environments has become an important research direction in the field of materials science. Indicators such as the toughness and impact resistance of steel under low-temperature conditions directly determine its reliability and safety in extreme environments (such as polar engineering, deep-sea equipment, aerospace, etc.). However, with the diversification of steel application scenarios and increasingly stringent performance requirements, traditional low-temperature impact testing lacks an effective testing method and cannot solve the problem of inaccurate testing caused by uneven cooling in existing technologies. Summary of the invention

[0003] The present application provides a low-temperature impact test method and system for steel smelting, which is used to solve the technical problem of inaccurate testing caused by uneven cooling in the prior art.

[0004] In view of the above problems, the present application provides a low-temperature impact testing method and system for steel smelting.

[0005] In a first aspect of the present application, a low temperature impact test method for steel smelting is provided, the method comprising: A hollow isolation layer is provided, wherein the hollow isolation layer is used to isolate the steel to be tested from direct contact with the cooling medium of the low-temperature cooling device; the steel to be tested is isolated by the hollow isolation layer, and the low-temperature cooling device is used to low-temperature cool the steel to be tested based on the hollow isolation layer; when the temperature sensor detects that the real-time cooling temperature of the steel to be tested reaches a preset temperature, the impact component is started, and the impact component impacts the cooled steel to be tested according to an impact execution use case; an impact test data set is obtained, and the steel to be tested is evaluated according to the impact test data set to obtain a first steel test evaluation index.

[0006] The second aspect of the present application provides a low temperature impact testing system for steel smelting, the system comprising: An isolation layer setting module is used to set a hollow isolation layer, wherein the hollow isolation layer is used to isolate the steel to be tested from direct contact with the cooling medium of the low-temperature cooling device; a low-temperature cooling module is used to use the hollow isolation layer to isolate the steel to be tested, and use the low-temperature cooling device to low-temperature cool the steel to be tested based on the hollow isolation layer; an impact module is used to start the impact component when the temperature sensor detects that the real-time cooling temperature of the steel to be tested reaches a preset temperature, and the impact component impacts the cooled steel to be tested according to the impact execution use case; an evaluation module is used to obtain an impact test data set, evaluate the steel to be tested according to the impact test data set, and obtain a first steel test evaluation index.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application sets a hollow isolation layer, wherein the hollow isolation layer is used to isolate the steel to be tested from direct contact with the cooling medium of the low-temperature cooling device; the hollow isolation layer is used to isolate the steel to be tested, and the low-temperature cooling device is used to low-temperature cool the steel to be tested based on the hollow isolation layer; when the temperature sensor detects that the real-time cooling temperature of the steel to be tested reaches a preset temperature, the impact component is started, and the impact component impacts the cooled steel to be tested according to the impact execution use case; an impact test data set is obtained, and the steel to be tested is evaluated according to the impact test data set to obtain a first steel test evaluation index. The present invention solves the technical problem of inaccurate testing caused by uneven cooling in the prior art, and achieves uniform cooling by setting a hollow isolation layer, accurately performs impact testing in combination with an impact component, and analyzes defect change data using a steel performance evaluation model, thereby achieving the technical effect of improving the accuracy, reliability and consistency of steel low-temperature performance evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] 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.

[0009] Figure 1 A schematic flow chart of a low temperature impact test method for steel smelting provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a low-temperature impact testing system for steel smelting provided in an embodiment of the present application.

[0010] Explanation of the reference numerals: isolation layer setting module 11 , low temperature cooling module 12 , impact module 13 , evaluation module 14 . DETAILED DESCRIPTION

[0011] The present application provides a low-temperature impact test method and system for steel smelting, aiming to solve the technical problem of inaccurate testing caused by uneven cooling in the prior art. By setting a hollow isolation layer to achieve uniform cooling, combining an impact component to accurately perform impact testing, and using a steel performance evaluation model to analyze defect change data, the application achieves the technical effect of improving the accuracy, reliability and consistency of low-temperature performance evaluation of steel.

[0012] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0013] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0014] Embodiment 1, as Figure 1 As shown, the present application provides a low temperature impact test method for steel smelting, the method comprising: Step S100: providing a hollow isolation layer, wherein the hollow isolation layer is used to isolate the steel material to be tested from direct contact with the cooling medium of the low-temperature cooling device.

[0015] In the embodiment of the present application, when conducting a low-temperature impact test of steel smelting, a hollow isolation layer (such as a porous ceramic fiber composite structure) is provided to physically isolate the steel to be tested from the cooling medium of the low-temperature cooling device (such as liquid nitrogen) to avoid instantaneous thermal stress concentration caused by direct contact. The isolation layer achieves uniform diffusion of cold energy through its porous structure (porosity 30%-50%), which not only blocks direct contact between the cooling medium and the steel, but also smoothly transfers the cold energy to the surface of the steel through radiation and convection, thereby eliminating the microscopic cracks or deformation problems caused by local overcooling or sudden changes in temperature gradients in traditional direct cooling methods, and improving the accuracy and reliability of the test results.

[0016] Furthermore, the method provided in the application embodiment also includes: The hollow isolation layer is a single-layer structure, and the single-layer structure is a porous ceramic fiber composite structure, which is used to evenly diffuse the coldness of the cooling medium to the surface of the steel to be tested.

[0017] In the embodiment of the present application, in the steel low temperature impact test, the hollow isolation layer can be a single-layer structure made of a porous ceramic fiber composite structure. The isolation layer uses its porous characteristics (porosity 30%-50%) to evenly diffuse the cold energy of the low temperature cooling device (such as liquid nitrogen) to the surface of the steel to be tested by radiation and convection, avoiding the instantaneous thermal stress concentration caused by direct contact between the cooling medium and the steel.

[0018] Furthermore, in the method provided in the embodiment of the application, the hollow isolation layer is a double-layer structure, and further comprises: An outer conductive shell, the outer conductive shell is used to conduct the cold energy of the cooling medium; a porous ceramic fiber composite structure, the porous ceramic fiber composite structure is used to evenly diffuse the cold energy conducted by the outer conductive shell to the surface of the steel to be tested.

[0019] In an embodiment of the present application, in the low-temperature impact test of steel, the hollow isolation layer can also be a double-layer structure. The double-layer hollow isolation layer includes an outer conductive shell and a porous ceramic fiber composite structure. The outer conductive shell is made of a high thermal conductivity material (such as an aluminum alloy or a copper alloy) and is directly in contact with a cooling medium (such as liquid nitrogen) to quickly absorb and conduct cold. For example, when liquid nitrogen is injected into the cooling cavity, the outer conductive shell quickly transfers the cold to the inside of the isolation layer through its high thermal conductivity. The porous ceramic fiber composite structure has a porous characteristic, and the porosity is controlled at 30%-50%. Through the gas / solid heat conduction channel in the pores, the cold conducted by the outer conductive shell is evenly diffused to the surface of the steel to be tested by radiation and convection, avoiding local overcooling or sudden changes in temperature gradients, and ensuring uniform temperature distribution on the steel surface.

[0020] Furthermore, the method provided in the application embodiment also includes: The low-temperature cooling device includes a plurality of cooling medium boxes and a switching valve group, wherein the cooling medium of the plurality of cooling medium boxes respectively stores liquid nitrogen, dry ice or ethanol mixture, and normal temperature buffer solution; the switching valve group switches and selects the cooling medium of the plurality of cooling medium boxes according to the switching valve group, and the low-temperature cooling device performs low-temperature cooling according to the selected cooling medium.

[0021] In an embodiment of the present application, the cryogenic cooling device includes a plurality of cooling medium boxes and a switching valve group. The plurality of cooling medium boxes store different cooling media, including liquid nitrogen, dry ice or ethanol mixture, and normal temperature buffer. Liquid nitrogen is used to achieve ultra-low temperature cooling (such as -196°C), dry ice or ethanol mixture is used for medium and low temperature cooling (such as -78°C), and normal temperature buffer is used for temperature buffering and transition. The switching valve group is composed of high-precision solenoid valves, which can automatically switch the cooling medium according to the test requirements. For example, in the initial stage, the switching valve group selects the normal temperature buffer for pre-cooling to avoid thermal stress of the steel due to the sudden drop in temperature; when the temperature of the steel drops to 0°C, the switching valve group closes the normal temperature buffer channel and opens the dry ice or ethanol mixture channel to achieve medium and low temperature cooling; when the temperature further drops to -78°C, the switching valve group closes the dry ice or ethanol mixture channel and opens the liquid nitrogen channel to achieve ultra-low temperature cooling. Through the intelligent switching of the switching valve group, the cryogenic cooling device can perform step-by-step cooling according to the selected cooling medium, ensure a smooth transition of the cooling process, and avoid sudden temperature changes, thereby meeting the requirements for cooling rate and temperature range in different test stages.

[0022] Step S200: using the hollow isolation layer to isolate the steel material to be tested, and using the low-temperature cooling device to perform low-temperature cooling on the steel material to be tested based on the hollow isolation layer.

[0023] In an embodiment of the present application, the steel to be tested is isolated by a hollow isolation layer, and indirect cooling is performed in combination with a cryogenic cooling device. Specifically, multiple step temperature thresholds are first configured based on a preset temperature, and these thresholds decrease in sequence until the target cooling temperature is reached. When the temperature sensor detects that the real-time cooling temperature of the steel reaches a certain step temperature threshold, a transient window is generated, and transient cooling is performed within the window at the current step temperature threshold until the variance of the continuous real-time cooling temperature is less than the preset variance, ensuring that the surface temperature of the steel is evenly distributed. Subsequently, the cryogenic cooling device switches the cooling medium (such as liquid nitrogen, dry ice or ethanol mixture) by switching the valve group, and performs the next step of cryogenic cooling on the steel based on the hollow isolation layer. The hollow isolation layer evenly diffuses the cold to the surface of the steel through its outer conductive shell and porous ceramic fiber composite structure, avoiding local overcooling or sudden changes in temperature gradient. Through this stepped cooling and indirect cooling method, the cooling rate of the steel is accurately controlled at 2-10°C / min, avoiding the instantaneous thermal stress concentration caused by direct contact with the cooling medium, thereby ensuring the accuracy and repeatability of the low-temperature impact test.

[0024] Furthermore, in the method provided in the embodiment of the application, the low-temperature cooling device is used to low-temperature cool the steel to be tested based on the hollow isolation layer, and further includes: Based on multiple step temperature thresholds configured with the preset temperature, the multiple step temperature thresholds decrease in sequence until the preset temperature is met; when the temperature sensor detects that the real-time cooling temperature of the steel to be tested reaches each step temperature threshold, a transient window is generated, and transient cooling is performed with the current step temperature threshold according to the transient window until the variance of the continuous real-time cooling temperature is less than the preset variance, and the low-temperature cooling device is used to perform the next step low-temperature cooling on the steel to be tested based on the hollow isolation layer.

[0025] In the embodiment of the present application, multiple step temperature thresholds are configured based on a preset temperature, and the multiple step temperature thresholds decrease in sequence until the preset temperature is met. Specifically, firstly, a target cooling temperature (such as -196°C) is preset according to the test requirements, and multiple step temperature thresholds (such as 0°C, -78°C, -196°C) are configured that decrease in sequence.

[0026] When the pre-deployed temperature sensor detects that the real-time cooling temperature of the steel to be tested reaches each step temperature threshold, a transient window is generated. Within the transient window, the cryogenic cooling device selects the cooling medium (such as normal temperature buffer, dry ice mixture or liquid nitrogen) corresponding to the current step temperature threshold by switching the valve group, and indirectly cools the steel based on the hollow insulation layer. The hollow insulation layer evenly diffuses the cold to the surface of the steel through its outer conductive shell and porous ceramic fiber composite structure to avoid local overcooling or sudden changes in temperature gradient. The temperature data of multiple temperature measuring points on the surface of the steel are collected in real time, and the average value is calculated. The square of the deviation of the temperature of each temperature measuring point from the average value is further calculated, and the average value of these square deviations, that is, the variance, is obtained. The variance is continuously monitored until the variance of the continuous real-time cooling temperature is less than the preset variance to ensure uniform temperature distribution on the steel surface.

[0027] When the variance of the continuous real-time cooling temperature of the steel at the current step temperature threshold is less than the preset variance, the low-temperature cooling device switches to the cooling medium corresponding to the next step temperature threshold by switching the valve group, and repeats the above transient cooling process. For example, when the steel temperature drops from 0°C to -78°C, a transient window is generated again, and transient cooling is performed within the window with -78°C as the threshold until the temperature stability meets the requirements. Finally, the steel temperature gradually decreases to the preset target temperature (such as -196°C), completing the entire cooling process.

[0028] Step S300: When the temperature sensor detects that the real-time cooling temperature of the steel to be tested reaches a preset temperature, the impact component is started, and the impact component impacts the cooled steel to be tested according to the impact execution use case.

[0029] In an embodiment of the present application, when the temperature sensor detects that the real-time cooling temperature of the steel to be tested reaches the preset temperature, the impact component is automatically started, and the impact component performs an impact test on the cooled steel to be tested according to a preset impact execution case. Specifically, firstly, the preset impact execution case is loaded from the database, including key parameters such as impact energy, impact speed, and impact angle, to ensure that the test process complies with the standard specifications, and then the impact hammer is calibrated to ensure that its position, angle, and energy output accuracy meet the test requirements. At the same time, the steel to be tested is accurately fixed at the impact test position through a mechanical arm or a positioning device to avoid distortion of the test results due to position deviation. Subsequently, the impact component impacts the cooled steel to be tested according to the loaded impact execution case, for example, the impact hammer vertically hits the steel surface with a preset impact energy (such as 300J) and speed (such as 5m / s) to simulate the impact load under actual working conditions.

[0030] During the impact process, high-speed cameras and sensors are used to collect data such as the impact energy, surface defect data, and defect change rate of the steel in real time.

[0031] Furthermore, in the method provided in the embodiment of the application, the impact assembly impacts the cooled steel to be tested according to the impact execution case, and further includes: According to the multiple step temperature thresholds, multiple groups of shock execution use cases are set, wherein each step temperature threshold corresponds to a group of shock execution use cases; multiple steels to be tested from the same batch are obtained, and the multiple steels to be tested from the same batch are respectively shock-treated according to the corresponding group of shock execution use cases at each step temperature threshold to obtain a shock test data set for each step temperature threshold, and so on, to obtain multiple groups of shock test data sets corresponding to the multiple step temperature thresholds.

[0032] In an embodiment of the present application, first, according to multiple step temperature thresholds (such as -20°C, -50°C, -100°C, -196°C), multiple groups of impact execution use cases are set using preset test standards. Each group of use cases includes parameters such as impact energy (such as 150J, 300J), impact speed (such as 3m / s, 5m / s) and impact angle (such as 90° vertical impact). These parameters are loaded through standardized templates in the database. Each execution use case in the obtained multiple groups of impact execution use cases corresponds to a step temperature threshold.

[0033] Subsequently, multiple steel samples to be tested are selected from the same production batch and cryogenically cooled, and the temperature of the steel is monitored in real time by a temperature sensor (such as a thermocouple or an infrared thermometer). When the temperature of the steel reaches the preset step temperature threshold, the cooling is stopped. At this time, at each step temperature threshold, the steel is impact tested according to the impact execution case of the corresponding group. For example, at -100°C, an impact tester (such as a pendulum impact tester) is used to vertically impact the steel with an impact energy of 300J and a speed of 5m / s. During the impact process, the deformation and crack propagation process of the steel are recorded in real time by a high-speed camera (such as a Phantom high-speed camera) and a strain sensor. In each impact test, continuous images of steel surface changes are automatically collected and stored. Among them, the steel surface change images are obtained by detection using a high-resolution microscope or a laser scanner.

[0034] Finally, the test data under each step temperature threshold are organized into a structured data set to obtain multiple groups of impact test data sets corresponding to multiple step temperature thresholds.

[0035] Step S400: Acquire an impact test data set, and evaluate the steel to be tested according to the impact test data set to obtain a first steel test evaluation index.

[0036] In the embodiment of the present application, the defect feature convolution is performed on the impact test data set by calling the pre-trained steel performance evaluation model to extract the surface defect data and the defect change rate. Then, a comprehensive evaluation is performed in combination with the preset temperature stored in the cryogenic cooling device, the impact execution case of the impact component, the surface defect data and the defect change rate to generate the first steel test evaluation index.

[0037] Furthermore, in the method provided in the embodiment of the application, the steel to be tested is evaluated according to the impact test data set to obtain a first steel test evaluation index, and further includes: A steel performance evaluation model is constructed, wherein the steel performance evaluation model is obtained by performing machine learning training on cooling temperature samples, impact energy samples, surface defect data samples, defect change rate samples, and labels characterizing the size of steel performance; the steel performance evaluation model is called to perform defect feature convolution on the impact test data set to obtain surface defect data and defect change rate; an evaluation is performed based on the preset temperature stored in the low-temperature cooling device, the impact execution case of the impact component, and the surface defect data and the defect change rate to obtain a first steel test evaluation index.

[0038] In the embodiment of the present application, a steel performance evaluation model is first constructed. Specifically, cooling temperature samples, impact energy samples, surface defect data samples, defect change rate samples, and labels characterizing the size of steel performance are first obtained from a preset database, and the corresponding steel surface change image samples are extracted at the same time. When constructing the model, a hybrid architecture of a convolutional neural network (CNN) and a long short-term memory network (LSTM) is adopted. The CNN branch specifically processes steel surface change image samples, and extracts local features of cracks, such as edges, bifurcation structures, etc. through multi-layer convolution and pooling operations; the LSTM branch processes the time series data of the defect change rate to capture the dynamic fluctuations and timing correlation of the crack propagation speed. The features of the two branches are fused through a fully connected layer, and combined with scalar parameters such as cooling temperature and impact energy, and finally mapped to steel performance labels. During the training process, the cross entropy loss function and Adam optimizer are used for parameter optimization, and the model weights are continuously adjusted through the back propagation algorithm until the model reaches the preset convergence requirements.

[0039] In the model calling stage, the impact test data set is input into the trained steel performance evaluation model. The input data includes the steel surface change image. The steel performance evaluation model first performs a convolution operation on the steel surface image through the CNN branch to extract the geometric features of the crack, such as length and number of forks, and generate surface defect data; at the same time, the LSTM branch analyzes the time series of the defect change rate and outputs the dynamic characteristics of the crack propagation speed. Through this process, the surface defect data and defect change rate are obtained.

[0040] Next, the steel performance evaluation model is used to evaluate the preset temperature stored in the cryogenic cooling device, the impact execution case of the impact component, the surface defect data and the defect change rate to obtain the corresponding steel performance label. Finally, the steel performance label output by the steel performance evaluation model is used as the first steel test evaluation indicator.

[0041] Furthermore, in the method provided in the embodiment of the application, the impact assembly impacts the cooled steel to be tested according to the impact execution case, and further includes: The impact component is started, and the impact component impacts the cooled steel to be tested according to the secondary impact execution use case to obtain a secondary impact test data set; transfer learning is performed on the steel performance evaluation model according to the secondary impact test data set, and a second steel test evaluation index is output according to the steel performance evaluation model after transfer learning, and the first steel test evaluation index is updated based on the second steel test evaluation index.

[0042] In the embodiment of the present application, the impact assembly is started again, and the steel to be tested after cooling is impacted according to the secondary impact execution case (preset impact parameters, such as energy 60J, angle 90°, and number of times 2) to impact the steel to be tested treated by the low-temperature cooling device. During the impact process, the secondary impact test data set is collected in real time by high-speed cameras and sensors.

[0043] Next, transfer learning is performed on the steel performance evaluation model. When performing transfer learning, sample data under secondary impact test conditions is obtained from the preset database, and the obtained samples are input into the steel performance evaluation model to fine-tune the model. Specifically, the first few convolutional layers of the CNN branch are frozen to retain its ability to extract surface defect features (such as crack length and bifurcation density). Then, the LSTM branch and the fully connected layer are fine-tuned to adapt them to the timing characteristics of the sample data (such as the dynamic changes in the crack propagation rate). During the training process, the label data in the sample data is used as a supervisory signal, and the model parameters are updated through the back-propagation algorithm and the Adam optimizer until the model converges on the sample data.

[0044] After the transfer learning is completed, the updated steel performance evaluation model is called to evaluate the secondary impact test data set, that is, the secondary impact test data set is input into the updated steel performance evaluation model for evaluation to obtain the second steel test evaluation index.

[0045] Finally, the first steel test evaluation index is updated according to the second steel test evaluation index, that is, the average of the second steel test evaluation index and the first steel test evaluation index is calculated. For example, when the second steel test evaluation index is 2.2 and the first steel test evaluation index is 1.8, their average is calculated and the first steel test evaluation index is updated to 2.0.

[0046] Furthermore, in the method provided in the embodiment of the application, after the impact assembly impacts the cooled steel to be tested according to the impact execution case, it also includes: After the impact component impacts the cooled steel to be tested according to the impact execution case, the low-temperature cooling device is used to perform secondary low-temperature cooling on the steel to be tested based on the hollow isolation layer, and surface defect change data of the steel to be tested after the secondary low-temperature cooling is collected; a third steel test evaluation index is obtained based on the surface defect change data of the secondary low-temperature cooling; and the first steel test evaluation index is updated based on the third steel test evaluation index.

[0047] In the embodiment of the present application, after the impact assembly impacts the cooled steel to be tested according to the impact execution case, a low-temperature cooling device is used to perform secondary low-temperature cooling on the steel to be tested based on the hollow isolation layer. During the secondary low-temperature cooling process, the changes in the surface defects of the steel, including crack length, bifurcation density, etc., are monitored in real time through high-precision sensors and image acquisition equipment to form surface defect change data of the secondary low-temperature cooling.

[0048] Next, based on the surface defect change data of secondary cryogenic cooling, the steel performance evaluation model is called for analysis. The model extracts the geometric features of the crack (such as crack length and bifurcation density) through the CNN branch, analyzes the dynamic features of the crack propagation speed (such as the change of crack propagation rate over time) through the LSTM branch, and outputs the third steel test evaluation index in combination with the fully connected layer.

[0049] Finally, the first steel test evaluation index is updated based on the third steel test evaluation index. Specifically, the adjustment is made according to the preset weights of the third steel test evaluation index and the first steel test evaluation index. For example, the weight of the third steel test evaluation index is 0.3, and the weight of the first steel test evaluation index is 0.7. When the third steel test evaluation index is 2.5 and the first steel test evaluation index is 2.0, 2.15 is obtained by multiplying 2.5 by 0.3 and adding 2.0 by 0.7, which is the updated value of the first steel test evaluation index.

[0050] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects: The present application sets a hollow isolation layer, wherein the hollow isolation layer is used to isolate the steel to be tested from direct contact with the cooling medium of the low-temperature cooling device; the hollow isolation layer is used to isolate the steel to be tested, and the low-temperature cooling device is used to low-temperature cool the steel to be tested based on the hollow isolation layer; when the temperature sensor detects that the real-time cooling temperature of the steel to be tested reaches a preset temperature, the impact component is started, and the impact component impacts the cooled steel to be tested according to the impact execution use case; an impact test data set is obtained, and the steel to be tested is evaluated according to the impact test data set to obtain a first steel test evaluation index. The present invention solves the technical problem of inaccurate testing caused by uneven cooling in the prior art, and achieves uniform cooling by setting a hollow isolation layer, accurately performs impact testing in combination with an impact component, and analyzes defect change data using a steel performance evaluation model, thereby achieving the technical effect of improving the accuracy, reliability and consistency of steel low-temperature performance evaluation.

[0051] Embodiment 2, based on the same inventive concept as the low temperature impact test method for steel smelting in the above embodiment, Figure 2As shown, the present application provides a low temperature impact test system for steel smelting, and the system and method embodiments in the present application are based on the same inventive concept. The system includes: An isolation layer setting module 11 is used to set a hollow isolation layer, wherein the hollow isolation layer is used to isolate the steel to be tested from direct contact with the cooling medium of the low-temperature cooling device; a low-temperature cooling module 12 is used to use the hollow isolation layer to isolate the steel to be tested, and use the low-temperature cooling device to low-temperature cool the steel to be tested based on the hollow isolation layer; an impact module 13 is used to start the impact component when the temperature sensor detects that the real-time cooling temperature of the steel to be tested reaches a preset temperature, and the impact component impacts the cooled steel to be tested according to the impact execution use case; an evaluation module 14 is used to obtain an impact test data set, evaluate the steel to be tested according to the impact test data set, and obtain a first steel test evaluation index.

[0052] Furthermore, the system is also used to implement the following functions: The hollow isolation layer is a single-layer structure, and the single-layer structure is a porous ceramic fiber composite structure, which is used to evenly diffuse the coldness of the cooling medium to the surface of the steel to be tested.

[0053] Furthermore, the system is also used to implement the following functions: The hollow isolation layer is a double-layer structure, comprising: An outer conductive shell, the outer conductive shell is used to conduct the cold energy of the cooling medium; a porous ceramic fiber composite structure, the porous ceramic fiber composite structure is used to evenly diffuse the cold energy conducted by the outer conductive shell to the surface of the steel to be tested.

[0054] Furthermore, the system is also used to implement the following functions: The low-temperature cooling device includes a plurality of cooling medium boxes and a switching valve group, wherein the cooling medium of the plurality of cooling medium boxes respectively stores liquid nitrogen, dry ice or ethanol mixture, and normal temperature buffer solution; the switching valve group switches and selects the cooling medium of the plurality of cooling medium boxes according to the switching valve group, and the low-temperature cooling device performs low-temperature cooling according to the selected cooling medium.

[0055] Furthermore, the system is also used to implement the following functions: Based on multiple step temperature thresholds configured with the preset temperature, the multiple step temperature thresholds decrease in sequence until the preset temperature is met; when the temperature sensor detects that the real-time cooling temperature of the steel to be tested reaches each step temperature threshold, a transient window is generated, and transient cooling is performed with the current step temperature threshold according to the transient window until the variance of the continuous real-time cooling temperature is less than the preset variance, and the low-temperature cooling device is used to perform the next step low-temperature cooling on the steel to be tested based on the hollow isolation layer.

[0056] Furthermore, the system is also used to implement the following functions: According to the multiple step temperature thresholds, multiple groups of shock execution use cases are set, wherein each step temperature threshold corresponds to a group of shock execution use cases; multiple steels to be tested from the same batch are obtained, and the multiple steels to be tested from the same batch are respectively shock-treated according to the corresponding group of shock execution use cases at each step temperature threshold to obtain a shock test data set for each step temperature threshold, and so on, to obtain multiple groups of shock test data sets corresponding to the multiple step temperature thresholds.

[0057] Furthermore, the system is also used to implement the following functions: A steel performance evaluation model is constructed, wherein the steel performance evaluation model is obtained by performing machine learning training on cooling temperature samples, impact energy samples, surface defect data samples, defect change rate samples, and labels characterizing the size of steel performance; the steel performance evaluation model is called to perform defect feature convolution on the impact test data set to obtain surface defect data and defect change rate; an evaluation is performed based on the preset temperature stored in the low-temperature cooling device, the impact execution case of the impact component, and the surface defect data and the defect change rate to obtain a first steel test evaluation index.

[0058] Furthermore, the system is also used to implement the following functions: The impact component is started, and the impact component impacts the cooled steel to be tested according to the secondary impact execution use case to obtain a secondary impact test data set; transfer learning is performed on the steel performance evaluation model according to the secondary impact test data set, and a second steel test evaluation index is output according to the steel performance evaluation model after transfer learning, and the first steel test evaluation index is updated based on the second steel test evaluation index.

[0059] Furthermore, the system is also used to implement the following functions: After the impact component impacts the cooled steel to be tested according to the impact execution case, the low-temperature cooling device is used to perform secondary low-temperature cooling on the steel to be tested based on the hollow isolation layer, and surface defect change data of the steel to be tested after the secondary low-temperature cooling is collected; a third steel test evaluation index is obtained based on the surface defect change data of the secondary low-temperature cooling; and the first steel test evaluation index is updated based on the third steel test evaluation index.

[0060] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0061] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0062] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A low temperature impact test method for steel smelting, characterized in that: The method comprises: A hollow isolation layer is provided, wherein the hollow isolation layer is used to isolate the steel material to be tested from direct contact with the cooling medium of the low-temperature cooling device; The steel material to be tested is isolated by the hollow isolation layer, and the low-temperature cooling device is used to low-temperature cool the steel material to be tested based on the hollow isolation layer; When the temperature sensor detects that the real-time cooling temperature of the steel to be tested reaches a preset temperature, the impact component is started, and the impact component impacts the cooled steel to be tested according to the impact execution case; An impact test data set is obtained, and the steel to be tested is evaluated according to the impact test data set to obtain a first steel test evaluation index.

2. The method according to claim 1, characterized in that The hollow isolation layer is a single-layer structure, and the single-layer structure is a porous ceramic fiber composite structure, which is used to evenly diffuse the coldness of the cooling medium to the surface of the steel to be tested.

3. The method according to claim 1, characterized in that The hollow isolation layer is a double-layer structure, comprising: An outer conductive shell, the outer conductive shell is used to conduct cold energy of the cooling medium; A porous ceramic fiber composite structure is used to evenly diffuse the cold energy conducted by the outer conduction shell to the surface of the steel to be tested.

4. The method according to claim 1, characterized in that The cryogenic cooling device comprises a plurality of cooling medium boxes and a switching valve group, wherein the cooling medium of the plurality of cooling medium boxes is respectively stored liquid nitrogen, dry ice or ethanol mixture, and normal temperature buffer solution; A switching valve group is provided to switch and select the cooling medium of the plurality of cooling medium boxes according to the switching valve group, and the low-temperature cooling device performs low-temperature cooling according to the selected cooling medium.

5. The method according to claim 1, characterized in that The low-temperature cooling device is used to low-temperature cool the steel to be tested based on the hollow isolation layer, and the method includes: A plurality of step temperature thresholds configured based on the preset temperature, wherein the plurality of step temperature thresholds decrease in sequence until the preset temperature is met; When the temperature sensor detects that the real-time cooling temperature of the steel to be tested reaches each step temperature threshold, a transient window is generated, and transient cooling is performed at the current step temperature threshold according to the transient window until the variance of the continuous real-time cooling temperature is less than the preset variance. The low-temperature cooling device is used to perform the next step low-temperature cooling on the steel to be tested based on the hollow isolation layer.

6. The method according to claim 5, characterized in that The impact assembly impacts the cooled steel material to be tested according to the impact execution case, and the method further includes: According to the multiple step temperature thresholds, multiple groups of impact execution use cases are set, wherein each step temperature threshold corresponds to a group of impact execution use cases; Obtain multiple steel materials to be tested from the same batch, and perform shocks on the multiple steel materials to be tested from the same batch according to the corresponding group of shock execution use cases at each step temperature threshold, to obtain a shock test data set for each step temperature threshold, and so on, to obtain multiple groups of shock test data sets corresponding to the multiple step temperature thresholds.

7. The method according to claim 1, characterized in that The steel to be tested is evaluated according to the impact test data set to obtain a first steel test evaluation index, the method comprising: Constructing a steel performance evaluation model, wherein the steel performance evaluation model is obtained by machine learning training on cooling temperature samples, impact energy samples, surface defect data samples, defect change rate samples, and labels representing the size of steel performance; Calling the steel performance evaluation model to perform defect feature convolution on the impact test data set to obtain surface defect data and defect change rate; An evaluation is performed based on the preset temperature stored in the cryogenic cooling device, the impact execution case of the impact assembly, and the surface defect data and the defect change rate to obtain a first steel test evaluation index.

8. The method according to claim 7, characterized in that The impact assembly impacts the cooled steel material to be tested according to the impact execution case, and the method further includes: Starting an impact component, wherein the impact component impacts the cooled steel material to be tested according to a secondary impact execution case, and obtaining a secondary impact test data set; The steel performance evaluation model is subjected to transfer learning according to the secondary impact test data set, a second steel test evaluation index is output according to the steel performance evaluation model after transfer learning, and the first steel test evaluation index is updated based on the second steel test evaluation index.

9. The method according to claim 7, characterized in that After the impact assembly impacts the cooled steel material to be tested according to the impact execution case, the method further includes: After the impact component impacts the cooled steel to be tested according to the impact execution case, the low-temperature cooling device is used to perform secondary low-temperature cooling on the steel to be tested based on the hollow isolation layer, and surface defect change data of the steel to be tested after the secondary low-temperature cooling is collected; According to the surface defect change data of the secondary cryogenic cooling, the third steel material test evaluation index is obtained; The first steel material test and evaluation index is updated based on the third steel material test and evaluation index.

10. Low temperature impact test system for steel smelting, characterized in that: The system comprises: An isolation layer setting module, used for setting a hollow isolation layer, wherein the hollow isolation layer is used to isolate the steel material to be tested from direct contact with the cooling medium of the low-temperature cooling device; A low-temperature cooling module, used to isolate the steel material to be tested by using the hollow isolation layer, and to perform low-temperature cooling on the steel material to be tested based on the hollow isolation layer by using the low-temperature cooling device; An impact module, used for starting an impact component when the temperature sensor detects that the real-time cooling temperature of the steel to be tested reaches a preset temperature, and the impact component impacts the cooled steel to be tested according to an impact execution case; The evaluation module is used to obtain an impact test data set, evaluate the steel to be tested according to the impact test data set, and obtain a first steel test evaluation index.

Images