Intelligent waste steel sorting treatment system and method based on machine vision

Abstract

The invention discloses an intelligent waste steel sorting treatment system and method based on machine vision, and relates to the technical field of waste steel sorting. Historical use data, including historical service data and historical environment data, of waste steel is collected, and fatigue damage prediction of the waste steel is conducted based on the historical service data; the method comprises the steps of carrying out scrap steel creep damage prediction based on historical environment data, collecting scrap steel surface damage data, carrying out scrap steel internal damage extension prediction based on scrap steel fatigue damage, scrap steel creep damage and scrap steel surface damage, obtaining downstream use scene data, simulating scrap steel damage evolution based on the downstream use scene data, and predicting the residual service life of scrap steel. According to the method, the degeneration degree of the waste steel under different stress levels and environments is quantified, the evolution trend of internal damage of the waste steel is accurately predicted, and therefore the accuracy of waste steel sorting is improved.

Description

Technical Field

[0001] This invention relates to the field of scrap steel sorting technology, and in particular to an intelligent scrap steel sorting and processing system and method based on machine vision. Background Technology

[0002] With the rapid development of the steel industry, scrap steel, as a green and renewable resource that can be infinitely recycled, occupies an important position in the fields of steel smelting and metal processing. Existing scrap steel recycling technologies usually focus on the chemical composition analysis and simple surface quality inspection of scrap steel. However, judging solely based on the current chemical composition and surface morphology can easily overlook the mechanical loads and environmental erosion that scrap steel has endured during its historical service. It cannot reflect the degree of mechanical property degradation of the material after long-term use, resulting in an inability to accurately assess the changes in the internal microstructure of scrap steel. Simple surface quality inspection cannot detect the microcracks that have started inside and the trend of damage propagation, making it very easy to miss scrap steel with serious internal hidden dangers.

[0003] Therefore, existing technologies cannot quantify internal damage and remaining service life through damage mechanisms such as fatigue and creep, which are closely related to service history and future usage conditions. As a result, the assessment results are difficult to meet the requirements of high performance and precise reuse in scrap steel sorting.

[0004] To address the aforementioned problems, this invention provides an intelligent scrap steel sorting and processing system and method based on machine vision. Summary of the Invention

[0005] In view of this, the present invention provides an intelligent scrap steel sorting system and method based on machine vision. The present invention quantifies the degree of degradation of scrap steel under different stress levels and environments, accurately predicts the evolution trend of internal damage in scrap steel, thereby improving the accuracy of scrap steel sorting.

[0006] To achieve the above objectives, the present invention provides the following technical solution: In a first aspect, the present invention provides an intelligent scrap steel sorting and processing method based on machine vision, comprising the following specific steps: Step 1: Collect historical usage data of scrap steel, including historical service data and historical environmental data. Based on the historical service data, predict the fatigue damage of scrap steel, and based on the historical environmental data, predict the creep damage of scrap steel. Step 2: Collect surface damage data of scrap steel, and predict the internal damage propagation of scrap steel based on scrap steel fatigue damage, scrap steel creep damage and scrap steel surface damage; Step 3: Obtain downstream usage scenario data, simulate the damage evolution of scrap steel based on the downstream usage scenario data, and predict the remaining service life of scrap steel; Step 4: Assess whether the scrap steel meets the reuse standards based on its remaining service life.

[0007] Preferably, step one includes the following specific steps: Step 11: Collect historical usage data of scrap steel, including historical service data and historical environmental data. The historical service data includes stress amplitude, number of load cycles and load frequency. The historical environmental data includes temperature, stress level and exposure duration. Step 12: Calculate the predicted fatigue damage value of scrap steel using the fatigue damage prediction calculation formula imported from historical service data. The fatigue damage prediction calculation formula is as follows: ,in, Indicates the number of stress levels. This represents the actual number of cycles at the i-th stress level. This represents the number of failure cycles at the i-th stress level. This can be obtained through stress-life curves, which can be represented as: ,in, Indicates the stress amplitude. Indicates the fatigue strength coefficient. Indicates the fatigue strength index; Step 13: Calculate the predicted creep damage value of scrap steel using the creep damage prediction calculation formula imported from historical environmental data. The creep damage prediction calculation formula is as follows: ,in, Indicates the number of operating conditions (temperature and stress). This represents the exposure duration under the j-th operating condition. This represents the failure duration under the j-th operating condition. The parameters can be obtained using the Larson-Miller parameter method, which can be expressed as: ,in, Indicates the Larson-Miller parameters. Indicates temperature. This represents a material constant, typically with a value of 20.

[0008] Preferably, step two includes the following specific steps: Step 21: Collect surface damage data of scrap steel, including crack length, crack depth, corrosion pit depth and surface roughness; Step 22: Obtain the crack length influence value based on the ratio of crack length to the critical crack length value; obtain the crack depth influence value based on the ratio of crack depth to the critical crack depth value; obtain the corrosion pit depth influence value based on the ratio of corrosion pit depth to the critical corrosion pit depth value; obtain the surface roughness influence value based on the ratio of surface roughness to the critical surface roughness value; and obtain the surface damage value by weighted summation of the crack length influence value, crack depth influence value, corrosion pit depth influence value, and surface roughness influence value. Step 23: Obtain the damage coupling effect value based on the product of the surface damage value, the predicted fatigue damage value of scrap steel, and the predicted creep damage value of scrap steel. Obtain the initial internal damage value of scrap steel based on the weighted sum of the surface damage value, the predicted fatigue damage value of scrap steel, the predicted creep damage value of scrap steel, and the damage coupling effect value.

[0009] Preferably, step three includes the following specific steps: Step 31: Obtain downstream usage scenario data, which includes scenario temperature, humidity, corrosive medium concentration, scenario cyclic load stress amplitude, and scenario cyclic frequency. Step 32: Obtain the scene temperature severity value based on the ratio of scene temperature to safe scene temperature; obtain the humidity severity value based on the ratio of humidity to safe humidity; obtain the corrosion medium concentration severity value based on the ratio of corrosion medium concentration to safe corrosion medium concentration; obtain the downstream application scene severity value by weighted summation of the scene temperature severity value, humidity severity value, and corrosion medium concentration severity value. Step 33: Obtain the surface damage propagation increment based on the surface damage propagation formula, wherein the surface damage propagation formula is: ,in, Indicates the incremental expansion of surface damage. Indicates the surface damage value. This represents the standardized damage propagation time step. The effective stress is represented by a standardized formula, which is obtained through the effective stress calculation formula: , Indicates effective stress. This indicates that stress is applied to the scene. This indicates the initial damage value inside the scrap steel. Represents the surface damage reference coefficient. Indicates the stress sensitivity index. Indicates the surface damage sensitivity index; Step 34: Obtain the fatigue damage propagation increment based on the fatigue damage propagation formula, wherein the fatigue damage propagation formula is: ,in, Indicates the increment of fatigue damage propagation. This represents the fatigue damage baseline coefficient. Indicates the fatigue stress index. This represents the standardized cyclic load stress amplitude. Indicates the cycle frequency. Indicates the time step of damage propagation; Step 35: Obtain the creep damage propagation increment based on the creep damage propagation formula, wherein the creep damage propagation formula is: ,in, Indicates the increment of creep damage propagation. Indicates the creep damage baseline coefficient. Indicates activation energy. Indicates the creep stress index. For Arrhenius's formula, Represents the ideal gas constant. Indicates the scene temperature. This represents the continuous static stress in standardized downstream application scenarios; Step 36: Obtain the internal damage expansion value of scrap steel by weighted summation of surface damage expansion increment, fatigue damage expansion increment and creep damage expansion increment; obtain the comprehensive internal damage increment of scrap steel by multiplying the internal damage expansion value of scrap steel, the severity value of downstream use scenario and the use scenario conversion coefficient. Step 37: Obtain the actual internal damage value of the scrap steel based on the sum of the initial internal damage value and the comprehensive increase of internal damage in the scrap steel; Step 38: Calculate the remaining service life of the scrap steel by importing the actual internal damage value into the remaining service life calculation formula. The remaining service life calculation formula is as follows: ,in, Indicates the design life. This indicates the actual internal damage value of the scrap steel. This represents the attenuation factor of internal damage on service life.

[0010] Preferably, step four includes the following specific steps: The remaining service life of the scrap steel is compared with the preset service life. If the remaining service life of the scrap steel is greater than or equal to the preset service life, the scrap steel is judged to meet the reuse standard. If the remaining service life of the scrap steel is less than the preset service life, the scrap steel is judged not to meet the reuse standard.

[0011] Secondly, the present invention provides an intelligent scrap steel sorting and processing system based on machine vision, comprising: The fatigue damage prediction module is used to collect historical service data of scrap steel and predict fatigue damage of scrap steel based on the historical service data. The creep damage prediction module is used to collect historical environmental data of scrap steel and predict creep damage of scrap steel based on the historical environmental data. The internal damage prediction module is used to collect surface damage data of scrap steel and make extended predictions of internal damage of scrap steel based on scrap steel fatigue damage, scrap steel creep damage and scrap steel surface damage. The remaining service life prediction module is used to acquire downstream usage scenario data, simulate the damage evolution of scrap steel based on the downstream usage scenario data, and predict the remaining service life of scrap steel. The scrap steel sorting module is used to assess whether scrap steel meets reuse standards based on its remaining service life.

[0012] Thirdly, the present invention provides a storage medium comprising stored instructions, wherein, when the instructions are executed, the device containing the storage medium is controlled to perform the intelligent scrap steel sorting method based on machine vision as described above.

[0013] Fourthly, the present invention provides an electronic device, including a memory and one or more instructions, wherein one or more instructions are stored in the memory and configured to be executed by one or more processors as described above for intelligent sorting of scrap steel based on machine vision.

[0014] The beneficial effects of this invention are as follows: This invention collects historical usage data of scrap steel, including historical service data and historical environmental data; predicts fatigue damage of scrap steel based on historical service data; predicts creep damage of scrap steel based on historical environmental data; collects surface damage data of scrap steel; predicts the expansion of internal damage of scrap steel based on fatigue damage, creep damage, and surface damage; obtains downstream usage scenario data; simulates the evolution of scrap steel damage based on downstream usage scenario data; predicts the remaining service life of scrap steel; and assesses whether scrap steel meets reuse standards based on the remaining service life of scrap steel. This invention quantifies the degree of degradation of scrap steel under different stress levels and environments, accurately predicts the evolution trend of internal damage in scrap steel, thereby improving the accuracy of scrap steel sorting. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A schematic diagram of the intelligent scrap steel sorting and processing method based on machine vision provided in an embodiment of the present invention; Figure 2 A schematic diagram of the intelligent scrap steel sorting and processing method based on machine vision provided in an embodiment of the present invention; Figure 3A schematic diagram of the intelligent scrap steel sorting and processing method based on machine vision provided in an embodiment of the present invention; Figure 4 A schematic diagram of the intelligent scrap steel sorting and processing system based on machine vision provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of an electronic device structure provided in an embodiment of the present invention. Detailed Implementation

[0017] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0018] In this invention, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, or apparatus. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element.

[0019] Please see Figure 1 This invention provides a machine vision-based intelligent scrap steel sorting and processing method, including the following specific steps: Step 1: Collect historical usage data of scrap steel, including historical service data and historical environmental data. Based on the historical service data, predict the fatigue damage of scrap steel, and based on the historical environmental data, predict the creep damage of scrap steel. Please see Figure 2 In this embodiment, step one includes the following specific steps: Step 11: Collect historical usage data of scrap steel, including historical service data and historical environmental data. Historical service data includes stress amplitude, load cycle count, and load frequency. Stress amplitude can be obtained by installing strain gauges on the scrap steel bearing structure and monitoring the peak and trough values ​​of the cyclic load in real time. The value is obtained by calculating half of the difference between the peak stress and the trough stress. The load cycle count is obtained by statistically analyzing the stress-time curve. The load frequency is obtained by analyzing the period (time interval between two adjacent peaks) of the stress-time curve. Historical environmental data includes temperature, stress level, and exposure duration. Temperature is obtained by temperature sensors. Stress level is obtained by measuring the constant or changing stress borne by the scrap steel using stress sensors. Exposure duration is obtained by time recording equipment to record the duration of the scrap steel under specific historical conditions. Step 12: Based on historical service data, import the fatigue damage prediction calculation formula to calculate the predicted fatigue damage value of the scrap steel. The fatigue damage prediction calculation formula is as follows: ,in, Indicates the number of stress levels. This represents the actual number of cycles at the i-th stress level. This represents the number of failure cycles at the i-th stress level. This can be obtained through stress-life curves, which reflect the number of cycles required for a specific material to undergo fatigue fracture under a set stress amplitude. A stress-life curve can be represented as: ,in, This represents the stress amplitude, i.e., the magnitude of stress change during cyclic loading, reflecting the severity of the cyclic loading. The fatigue strength coefficient, which has the same dimensions as the stress amplitude, reflects the material's ability to resist fatigue. The fatigue strength index reflects the material's sensitivity to fatigue. and All are material constants, obtained through fatigue test fitting. The fatigue damage prediction value of scrap steel can predict the density and distribution of fatigue microcracks inside the scrap steel. Step 13: Based on historical environmental data, import the creep damage prediction calculation formula to calculate the predicted value of creep damage in scrap steel. The creep damage prediction calculation formula is as follows: ,in, Indicates the number of operating conditions (temperature and stress). This represents the exposure duration under the j-th operating condition. This represents the failure duration under the j-th operating condition. The time to fracture can be obtained using the Larson-Miller parameter method, which reflects the fracture time under specified operating conditions (temperature and stress). The Larson-Miller parameter method can be expressed as: ,in, This represents the Larson-Miller parameter. For a specific material, the relationship between the Larson-Miller parameter and stress can be obtained by looking up a table. When referring to temperature, it should be noted that the temperature unit is converted to Kelvin during calculations. This represents a material constant, typically taken as 20, reflecting the material's creep sensitivity. In engineering calculations, the normalization operations for temperature and failure duration are usually omitted, i.e., ... and It is considered a scaling factor, therefore, in the formula calculation and All values ​​are dimensionless. The predicted value of creep damage in scrap steel can predict creep cavities and microcracks inside the scrap steel.

[0020] Step 2: Collect surface damage data of scrap steel, and predict the internal damage propagation of scrap steel based on scrap steel fatigue damage, scrap steel creep damage and scrap steel surface damage; In this embodiment, step two includes the following specific steps: Step 21: Collect surface damage data of scrap steel. The surface damage data of scrap steel includes crack length, crack depth, corrosion pit depth and surface roughness. Use a high-resolution camera to collect surface images of scrap steel. After image enhancement, use edge detection to segment cracks, extract crack skeleton, calculate pixel length to obtain crack length, acquire 3D scan data of scrap steel, obtain crack depth based on point cloud height data, fit the uncorroded area as a reference surface, calculate the height difference between each point in the corroded area and the reference surface to obtain corrosion pit depth, use spline fitting to separate the waviness and roughness components of the profile, calculate the arithmetic mean deviation of the profile to obtain surface roughness. The depth of corrosion pit reduces the effective cross section and increases stress concentration. The deeper the corrosion pit, the greater the damage to scrap steel. Surface roughness affects crack initiation. The higher the roughness, the greater the damage to scrap steel. Step 22: Obtain the crack length influence value based on the ratio of crack length to the critical crack length value; obtain the crack depth influence value based on the ratio of crack depth to the critical crack depth value; obtain the corrosion pit depth influence value based on the ratio of corrosion pit depth to the critical corrosion pit depth value; obtain the surface roughness influence value based on the ratio of surface roughness to the critical surface roughness value; obtain the surface damage value by weighted summation of the crack length influence value, crack depth influence value, corrosion pit depth influence value, and surface roughness influence value. The critical crack length and critical crack depth values ​​are obtained through fracture mechanics analysis. The critical corrosion pit depth value is determined based on the corrosion rate and the material's remaining strength requirements. For example, a corrosion pit depth exceeding 10% of the material thickness is considered critical. The critical surface roughness value is determined based on fatigue strength. For example, a surface roughness exceeding 6.3 μm is considered critical. Step 23: Obtain the damage coupling effect value based on the product of the surface damage value, the predicted fatigue damage value of scrap steel, and the predicted creep damage value of scrap steel. Obtain the initial internal damage value of scrap steel based on the weighted sum of the surface damage value, the predicted fatigue damage value of scrap steel, the predicted creep damage value of scrap steel, and the damage coupling effect value.

[0021] Step 3: Obtain downstream usage scenario data, simulate the damage evolution of scrap steel based on the downstream usage scenario data, and predict the remaining service life of scrap steel; Please see Figure 3 In this embodiment, step three includes the following specific steps: Step 31: Obtain downstream usage scenario data. Downstream usage scenario data includes scenario temperature, humidity, corrosive medium concentration, scenario cyclic load stress amplitude, and scenario cyclic frequency. The corrosive medium concentration is monitored online by an electrochemical sensor. The scenario cyclic load stress amplitude is the difference between the peak stress and the valley stress of the cyclic load, reflecting the severity of the cyclic load. The load fluctuation of the downstream usage scenario is monitored in real time by strain gauges or directly obtained from the design load. The scenario cyclic frequency is the number of cycles per unit time, reflecting the frequency of the cyclic load. The load frequency of the downstream usage scenario is monitored by a vibration sensor. Step 32: Obtain the scene temperature severity value based on the ratio of scene temperature to safe scene temperature; obtain the humidity severity value based on the ratio of humidity to safe humidity; obtain the corrosion medium concentration severity value based on the ratio of corrosion medium concentration to safe corrosion medium concentration; obtain the downstream application scene severity value by weighted summation of the scene temperature severity value, humidity severity value, and corrosion medium concentration severity value; test the damage evolution rate at different temperatures and take the upper limit of temperature that does not accelerate damage as the safe scene temperature; test the corrosion rate at different humidity levels and take the upper limit of humidity that does not accelerate corrosion as the safe humidity; test the corrosion rate at different concentrations and take the upper limit of concentration that does not accelerate corrosion as the safe corrosion medium concentration. Step 33: Obtain the surface damage propagation increment based on the surface damage propagation formula, which is: ,in, Indicates the incremental expansion of surface damage. Indicates the surface damage value. This represents the standardized damage propagation time step, obtained by dividing the damage propagation time step by a reference duration. The reference duration is selected based on the downstream application scenario, and the unit can be seconds, hours, or days. The standardized effective stress is obtained by dividing the effective stress by the material's yield strength. Effective stress is the actual stress after internal damage correction following the application of external stress, reflecting the reduction in load-bearing area due to internal damage. The material's yield strength is the critical stress at which plastic deformation occurs, obtained through tensile testing. The effective stress is calculated using the effective stress calculation formula: , Indicates effective stress. This indicates the stress applied in the scenario, that is, the actual load stress that the scrap steel bears in the downstream application scenario. This indicates the initial damage value inside the scrap steel. This represents the surface damage reference coefficient, reflecting the basic propagation rate of the material under unit effective stress and unit initial damage. This represents the stress sensitivity index, reflecting the degree of nonlinear influence of stress on damage propagation. This represents the surface damage sensitivity index, reflecting the self-accelerating effect of initial damage on further propagation. , and All of these are surface damage constants, calibrated through surface damage experiments, for example, by fitting the evolution rate under known stress and initial surface damage values. Step 34: Obtain the fatigue damage propagation increment based on the fatigue damage propagation formula, which is: ,in, Indicates the increment of fatigue damage propagation. This represents the fatigue damage baseline factor, reflecting the fundamental fatigue damage generated by the material per load cycle under a unit stress amplitude. The fatigue stress index represents the degree of nonlinearity in the effect of stress amplitude on fatigue damage. and These are all fatigue damage constants, calibrated through fatigue tests, for example, by fitting the damage accumulation rate under known stress amplitude and number of cycles. The standardized cyclic load stress amplitude is obtained by the ratio of the cyclic load stress amplitude to the material's yield strength. Indicates the cycle frequency. Indicates the time step of damage propagation; Step 35: Obtain the creep damage propagation increment based on the creep damage propagation formula, which is: ,in, Indicates the increment of creep damage propagation. This represents the creep damage baseline coefficient, reflecting the basic creep damage rate of a material under unit temperature and unit stress. The activation energy represents the effect of temperature on creep, and its unit is J / mol. The creep stress index represents the degree of nonlinearity in the effect of stress on the creep rate. , and These are all creep damage constants, calibrated through creep tests, such as obtaining them by fitting creep rates under different temperatures and stresses. The Arrhenius equation describes the thermal activation process. This represents the ideal gas constant, typically 8.314 J / (mol·K). This represents the scene temperature. It should be noted that the scene temperature unit is converted to Kelvin during calculation. The sustained static stress in the standardized downstream application scenario is obtained by the ratio of the sustained static stress in the downstream application scenario to the material yield strength. The sustained static stress in the downstream application scenario can be obtained by the ratio of the static load to the load-bearing cross-sectional area. Step 36: Obtain the internal damage expansion value of scrap steel by weighted summation of surface damage expansion increment, fatigue damage expansion increment and creep damage expansion increment. Obtain the comprehensive internal damage increment of scrap steel by multiplying the internal damage expansion value of scrap steel, the severity value of downstream use scenario and the use scenario conversion coefficient. The use scenario conversion coefficient is obtained by damage increment experiment. Prefabricate material samples with the same damage level and conduct fatigue / creep experiments under different severity values ​​of use scenarios. Record the damage increment, fit the curve, and the slope is the use scenario conversion coefficient. Step 37: Obtain the actual internal damage value of the scrap steel based on the sum of the initial internal damage value and the comprehensive increase of internal damage in the scrap steel; Step 38: Calculate the remaining service life of the scrap steel by importing the actual internal damage value into the remaining service life calculation formula. The remaining service life calculation formula is as follows: ,in, Indicates the design life. This indicates the actual internal damage value of the scrap steel. The attenuation factor of internal damage on service life is obtained through accelerated life testing. Material samples with different damage levels are prefabricated and fatigue / creep tests are conducted under the same working conditions. The actual failure life is recorded, and the slope of the fitted curve is the attenuation factor of internal damage on service life.

[0022] All weights in this embodiment are obtained using the coefficient of variation method. The steps are as follows: calculate the mean and standard deviation of each indicator, then divide the standard deviation of each indicator by its mean to obtain the coefficient of variation of that indicator, which represents the degree of dispersion of the indicator data. Then, add the coefficients of variation of each indicator together, and finally calculate the proportion of each coefficient of variation to the total to obtain the weight of each indicator.

[0023] Step 4: Assess whether the scrap steel meets the reuse standards based on its remaining service life.

[0024] In this embodiment, step four includes the following specific steps: The remaining service life of the scrap steel is compared with the preset service life. If the remaining service life of the scrap steel is greater than or equal to the preset service life, the scrap steel is judged to meet the reuse standard. If the remaining service life of the scrap steel is less than the preset service life, the scrap steel is judged not to meet the reuse standard.

[0025] Please see Figure 4 This invention also provides a machine vision-based intelligent scrap steel sorting and processing system, including: The fatigue damage prediction module is used to collect historical service data of scrap steel and predict fatigue damage of scrap steel based on the historical service data. The creep damage prediction module is used to collect historical environmental data of scrap steel and predict creep damage of scrap steel based on the historical environmental data. The internal damage prediction module is used to collect surface damage data of scrap steel and make extended predictions of internal damage of scrap steel based on scrap steel fatigue damage, scrap steel creep damage and scrap steel surface damage. The remaining service life prediction module is used to acquire downstream usage scenario data, simulate the damage evolution of scrap steel based on the downstream usage scenario data, and predict the remaining service life of scrap steel. The scrap steel sorting module is used to assess whether scrap steel meets reuse standards based on its remaining service life.

[0026] This invention also provides a storage medium that includes stored instructions, wherein when the instructions are executed, the device containing the storage medium is controlled to perform the machine vision-based intelligent scrap steel sorting and processing method described above.

[0027] Please see Figure 5 The present invention also provides an electronic device, specifically including a memory and one or more instructions, wherein one or more instructions are stored in the memory and configured to be executed by one or more processors as described above, using the intelligent scrap steel sorting method based on machine vision.

[0028] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple. For relevant parts, refer to the description of the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0029] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0030] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art. The general principles defined in this invention may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A machine vision-based intelligent scrap steel sorting and processing method, characterized in that, The specific steps include the following: Step 1: Collect historical usage data of scrap steel, including historical service data and historical environmental data. Based on the historical service data, predict the fatigue damage of scrap steel, and based on the historical environmental data, predict the creep damage of scrap steel. Step 2: Collect surface damage data of scrap steel, and predict the internal damage propagation of scrap steel based on scrap steel fatigue damage, scrap steel creep damage and scrap steel surface damage; Step 3: Obtain downstream usage scenario data, simulate the damage evolution of scrap steel based on the downstream usage scenario data, and predict the remaining service life of scrap steel; Step 4: Assess whether the scrap steel meets the reuse standards based on its remaining service life.

2. The intelligent scrap steel sorting and processing method based on machine vision according to claim 1, characterized in that, Step one includes the following specific steps: Step 11: Collect historical usage data of scrap steel, including historical service data and historical environmental data. The historical service data includes stress amplitude, number of load cycles and load frequency. The historical environmental data includes temperature, stress level and exposure duration. Step 12: Calculate the predicted fatigue damage value of scrap steel using the fatigue damage prediction calculation formula imported from historical service data. The fatigue damage prediction calculation formula is as follows: ,in, Indicates the number of stress levels. This represents the actual number of cycles at the i-th stress level. This represents the number of failure cycles at the i-th stress level; Step 13: Calculate the predicted creep damage value of scrap steel using the creep damage prediction calculation formula imported from historical environmental data. The creep damage prediction calculation formula is as follows: ,in, Indicates the number of operating conditions. This represents the exposure duration under the j-th operating condition. This represents the failure duration under the j-th operating condition.

3. The intelligent scrap steel sorting and processing method based on machine vision according to claim 2, characterized in that, Step two includes the following specific steps: Step 21: Collect surface damage data of scrap steel, including crack length, crack depth, corrosion pit depth and surface roughness; Step 22: Obtain the crack length influence value based on the ratio of crack length to the critical crack length value; obtain the crack depth influence value based on the ratio of crack depth to the critical crack depth value; obtain the corrosion pit depth influence value based on the ratio of corrosion pit depth to the critical corrosion pit depth value; obtain the surface roughness influence value based on the ratio of surface roughness to the critical surface roughness value; and obtain the surface damage value by weighted summation of the crack length influence value, crack depth influence value, corrosion pit depth influence value, and surface roughness influence value. Step 23: Obtain the damage coupling effect value based on the product of the surface damage value, the predicted fatigue damage value of scrap steel, and the predicted creep damage value of scrap steel. Obtain the initial internal damage value of scrap steel based on the weighted sum of the surface damage value, the predicted fatigue damage value of scrap steel, the predicted creep damage value of scrap steel, and the damage coupling effect value.

4. The intelligent scrap steel sorting and processing method based on machine vision according to claim 3, characterized in that, Step three includes the following specific steps: Step 31: Obtain downstream usage scenario data, which includes scenario temperature, humidity, corrosive medium concentration, scenario cyclic load stress amplitude, and scenario cyclic frequency. Step 32: Obtain the scene temperature severity value based on the ratio of scene temperature to safe scene temperature; obtain the humidity severity value based on the ratio of humidity to safe humidity; obtain the corrosion medium concentration severity value based on the ratio of corrosion medium concentration to safe corrosion medium concentration; obtain the downstream application scene severity value by weighted summation of the scene temperature severity value, humidity severity value, and corrosion medium concentration severity value. Step 33: Obtain the surface damage propagation increment based on the surface damage propagation formula, wherein the surface damage propagation formula is: ,in, Indicates the incremental expansion of surface damage. Indicates the surface damage value. This represents the standardized damage propagation time step. The effective stress is represented by a standardized formula, which is obtained through the effective stress calculation formula: , Indicates effective stress. This indicates that stress is applied to the scene. This indicates the initial damage value inside the scrap steel. Represents the surface damage reference coefficient. Indicates the stress sensitivity index. This indicates the surface damage sensitivity index.

5. The intelligent scrap steel sorting and processing method based on machine vision according to claim 4, characterized in that, Step three also includes the following specific steps: Step 34: Obtain the fatigue damage propagation increment based on the fatigue damage propagation formula, wherein the fatigue damage propagation formula is: ,in, Indicates the increment of fatigue damage propagation. This represents the fatigue damage baseline coefficient. Indicates the fatigue stress index. This represents the standardized cyclic load stress amplitude. Indicates the cycle frequency. Indicates the time step of damage propagation; Step 35: Obtain the creep damage propagation increment based on the creep damage propagation formula, wherein the creep damage propagation formula is: ,in, Indicates the increment of creep damage propagation. Indicates the creep damage baseline coefficient. Indicates activation energy. Indicates the creep stress index. Represents the ideal gas constant. Indicates the scene temperature. This represents the continuous static stress in standardized downstream application scenarios; Step 36: Obtain the internal damage expansion value of scrap steel by weighted summation of surface damage expansion increment, fatigue damage expansion increment and creep damage expansion increment; obtain the comprehensive internal damage increment of scrap steel by multiplying the internal damage expansion value of scrap steel, the severity value of downstream use scenario and the use scenario conversion coefficient. Step 37: Obtain the actual internal damage value of the scrap steel based on the sum of the initial internal damage value and the comprehensive increase of internal damage in the scrap steel; Step 38: Calculate the remaining service life of the scrap steel by importing the actual internal damage value into the remaining service life calculation formula. The remaining service life calculation formula is as follows: ,in, Indicates the design life. This indicates the actual internal damage value of the scrap steel. This represents the attenuation factor of internal damage on service life.

6. The intelligent scrap steel sorting and processing method based on machine vision according to claim 5, characterized in that, Step four includes the following specific steps: The remaining service life of the scrap steel is compared with the preset service life. If the remaining service life of the scrap steel is greater than or equal to the preset service life, the scrap steel is judged to meet the reuse standard. If the remaining service life of the scrap steel is less than the preset service life, the scrap steel is judged not to meet the reuse standard.

7. A machine vision-based intelligent scrap steel sorting and processing system, used to implement the machine vision-based intelligent scrap steel sorting and processing method as described in any one of claims 1-6, characterized in that, include: The fatigue damage prediction module is used to collect historical service data of scrap steel and predict fatigue damage of scrap steel based on the historical service data. The creep damage prediction module is used to collect historical environmental data of scrap steel and predict creep damage of scrap steel based on the historical environmental data. The internal damage prediction module is used to collect surface damage data of scrap steel and make extended predictions of internal damage of scrap steel based on scrap steel fatigue damage, scrap steel creep damage and scrap steel surface damage. The remaining service life prediction module is used to acquire downstream usage scenario data, simulate the damage evolution of scrap steel based on the downstream usage scenario data, and predict the remaining service life of scrap steel. The scrap steel sorting module is used to assess whether scrap steel meets reuse standards based on its remaining service life.

8. A storage medium, characterized in that, The storage medium includes stored instructions, wherein, when the instructions are executed, the device containing the storage medium is controlled to perform the intelligent scrap steel sorting method based on machine vision as described in any one of claims 1-6.

9. An electronic device, characterized in that, It includes a memory and one or more instructions, wherein one or more instructions are stored in the memory and configured to be executed by one or more processors as described in any one of claims 1-6.

Images