Magnesium oxide production evaluation method and system based on machine vision

Abstract

The invention discloses a magnesium oxide production evaluation method and system based on machine vision, and relates to the technical field of magnesium oxide production evaluation, and the method comprises the steps: collecting a silicon steel image, analyzing the coating fluctuation condition and coating missing condition, analyzing the coating condition of a magnesium oxide coating, collecting factory environment data, and analyzing the severe environment condition. The initial damage risk is analyzed based on the coating condition of the magnesium oxide coating and the severe environment condition, the factory environment erosion evolution process is simulated, the pore distribution condition is predicted, and the comprehensive anti-oxidation condition is analyzed based on the oxygen entering condition and the anti-oxidation condition. According to the method, the initial coating condition of the silicon steel and the severe environment condition serve as input variables, and the distribution condition of air holes is predicted by simulating the erosion evolution process of the factory environment, so that the potential failure risk of the silicon steel is warned in advance, and the anti-oxidation capability of the magnesium oxide coating on the silicon steel is judged to reach the standard. And the accuracy and timeliness of magnesium oxide production evaluation are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of magnesium oxide production evaluation, in particular to a magnesium oxide production evaluation method and system based on machine vision. BACKGROUND

[0002] Silicon steel, especially grain-oriented silicon steel, is a key soft magnetic material for manufacturing core components such as transformers and large motors. In its production process, in order to form a good glass film bottom layer in the high-temperature annealing process and ultimately obtain good insulation performance and oxidation resistance, a layer of magnesium oxide coating is usually applied on the surface of silicon steel strip. The quality of the magnesium oxide coating, such as uniformity, compactness and ultimate oxidation resistance, directly determines the final quality and service life of the silicon steel product. Therefore, accurate and efficient detection and evaluation of the coating quality and oxidation resistance of the magnesium oxide coating are crucial technical links in the production of silicon steel.

[0003] The existing technology for magnesium oxide coating quality control usually has limitations such as isolated and one-sided detection means, lagging and static risk judgment, and insufficient evaluation of oxidation resistance. Traditional quality control mostly relies on offline sampling detection of coating appearance quality and independent monitoring of environmental parameters. These data lack effective correlation analysis, and cannot systematically evaluate the comprehensive performance of the coating in a real and dynamic factory environment. At the same time, the magnesium oxide coating quality evaluation process is static and cannot simulate the performance evolution process of the coating over time under specific environmental conditions. The judgment of the oxidation resistance of the coating fails to analyze the micro-mechanism of oxygen intrusion and its dynamic coupling relationship with environmental factors, resulting in inaccurate judgment results.

[0004] To solve the above problems, the present application provides a magnesium oxide production evaluation method and system based on machine vision. SUMMARY

[0005] In view of the shortcomings of the prior art, the present application provides a magnesium oxide production evaluation method and system based on machine vision. The present application takes the initial coating condition of silicon steel and the harsh environment condition as input variables, predicts the distribution of pores by simulating the erosion evolution process of the factory environment, and thus early warns of the potential failure risk of silicon steel, improving the accuracy and timeliness of magnesium oxide production evaluation.

[0006] To achieve the above purpose, the present application provides a magnesium oxide production evaluation method based on machine vision, comprising the following specific steps: Step 1, collect silicon steel images, analyze coating fluctuation and coating missing conditions, and analyze the magnesium oxide coating application condition based on the coating fluctuation and coating missing conditions; Step 2, collect factory environment data, and analyze the harsh environment condition; Step 3, based on the magnesium oxide coating application and the analysis of the initial damage risk of the harsh environment, simulate the evolution process of the factory environment erosion, and predict the pore distribution; Step 4, based on the pore distribution and the oxygen concentration in the factory environment, analyze the oxygen entry, based on the unit area oxidation weight gain, analyze the antioxidant capacity, and based on the oxygen entry and the antioxidant capacity, analyze the comprehensive antioxidant capacity; Step 5, based on the comprehensive antioxidant capacity, determine whether the antioxidant capacity of the magnesium oxide coating applied on the silicon steel meets the standard.

[0007] Preferably, the step 1 comprises the following specific steps: Collecting the silicon steel image using an industrial camera and preprocessing the silicon steel image; Based on the ratio of the gray scale standard deviation to the gray scale mean of all pixels in the coating area, the coating fluctuation evaluation value is obtained; Based on the ratio of the total number of pixels in the coating leakage area to the total number of pixels in the silicon steel image, the coating leakage rate evaluation value is obtained; Based on the weighted sum of the coating fluctuation evaluation value and the coating leakage rate evaluation value, the magnesium oxide coating application abnormality evaluation value is obtained.

[0008] Preferably, the step 2 comprises the following specific steps: Collecting factory environment data, including suspended particulate matter concentration, temperature, humidity and wind speed; Based on the ratio of the suspended particulate matter concentration to the safe particulate matter concentration threshold, the pollution abnormality evaluation value is obtained; Based on the absolute value of the difference between the temperature and the safe temperature threshold divided by the safe temperature threshold, the temperature abnormality evaluation value is obtained; Based on the absolute value of the difference between the humidity and the safe humidity threshold divided by the safe humidity threshold, the humidity abnormality evaluation value is obtained; Based on the ratio of the wind speed to the safe wind speed threshold, the wind speed abnormality evaluation value is obtained; Based on the weighted sum of the pollution abnormality evaluation value, the temperature abnormality evaluation value, the humidity abnormality evaluation value and the wind speed abnormality evaluation value, the environmental severity evaluation value is obtained.

[0009] Preferably, the step 3 comprises the following specific steps: Based on the weighted sum of the magnesium oxide coating application abnormality evaluation value and the environmental severity evaluation value, the initial comprehensive damage risk evaluation value of the coating is obtained; The gray scale value of each pixel of the silicon steel image is converted into a thickness value, the silicon steel coating thickness distribution map is obtained, the mapping relationship between the thickness influence and the damage risk weight is established, and the risk weight function is defined, which is expressed as: , wherein, is a scaling constant for adjusting the sensitivity of the weight function, for the coating thickness, for the target coating thickness, for the fixed constant, the embodiment is set to 0.001, for preventing the denominator from being zero, the silicon steel coating thickness distribution map of each thickness value into the risk weight function obtain a risk weight value, and obtain a risk weight map of the silicon steel coating based on the risk weight value , the risk weight map is obtained in the following manner: , normalize the sum of the risk weight map, and distribute the initial damage risk assessment value to each pixel of the silicon steel coating thickness distribution map point by point according to the normalized weight, and the calculation formula of the distribution is: , wherein, is the initial damage risk assessment value distributed to the position (i, j), is the initial comprehensive damage risk assessment value of the coating, is the sum of all risk weight values of the risk weight map, is the risk weight value at the position (i, j), and an initial damage risk state map of the silicon steel coating is output;‌ preset a prediction duration, obtain a damage increment acting on each pixel point based on the product of the environmental severity assessment value, the environmental damage conversion coefficient and the prediction duration, superimpose the damage increment on the initial damage risk assessment value of each pixel, and obtain a superimposed damage risk assessment value; compare the superimposed damage risk assessment value with a preset coating peeling critical damage value, if the superimposed damage risk assessment value exceeds the preset coating peeling critical damage value, mark the corresponding pixel point as a pore; execute a pore merging rule, remove noise pores with small areas, update the pore distribution, merge to generate a new pore region list, and output a pore distribution prediction map, wherein the pore merging rule is an 8-neighborhood rule.

[0010] Preferably, the step 4 comprises the following specific steps: use an oxygen concentration measuring instrument to obtain the oxygen concentration of the factory, and obtain pore data based on the pore distribution prediction map, the pore data including the number of pores and the area of the pores; obtain the oxygen entry rate based on the pore data and the oxygen concentration of the factory environment, and the calculation formula of the oxygen entry rate is: , wherein, is the effective diffusion coefficient, is the number of pores, is the area of the nth pore, is the oxygen concentration of the factory environment, is the average thickness of the coating; obtain an oxygen entry abnormality assessment value based on the ratio of the oxygen entry rate to the preset oxygen entry rate threshold value; Collecting the silicon steel sample to perform the simulation annealing operation, obtaining the unit area oxidation weight gain, and analyzing the anti-oxidation abnormality evaluation value based on the ratio of the preset unit area oxidation weight gain threshold value and the unit area oxidation weight gain; The comprehensive anti-oxidation abnormality evaluation value is obtained by weighted summation based on the oxygen entry abnormality evaluation value and the anti-oxidation abnormality evaluation value.

[0011] Preferably, the step 5 comprises the following specific steps: The anti-oxidation ability of the magnesium oxide coating coated on the silicon steel is judged to be up to standard or not based on the comparison result of the comprehensive anti-oxidation abnormality evaluation value and the preset comprehensive anti-oxidation abnormality threshold value, if the comprehensive anti-oxidation abnormality evaluation value is less than the preset comprehensive anti-oxidation abnormality threshold value, it is judged that the anti-oxidation ability of the magnesium oxide coating coated on the silicon steel is up to standard, if the comprehensive anti-oxidation abnormality evaluation value is greater than or equal to the preset comprehensive anti-oxidation abnormality threshold value, it is judged that the anti-oxidation ability of the magnesium oxide coating coated on the silicon steel is not up to standard.

[0012] The application also provides a magnesium oxide production evaluation system based on machine vision, comprising: The coating coating analysis module is used for collecting the silicon steel image, analyzing the coating fluctuation and the coating missing situation, and analyzing the magnesium oxide coating coating situation based on the coating fluctuation and the coating missing situation; The environment analysis module is used for collecting the factory environment data and analyzing the environment situation; The pore distribution prediction module is used for analyzing the initial damage risk based on the magnesium oxide coating coating situation and the environment situation, simulating the factory environment erosion evolution process, and predicting the pore distribution situation; The oxygen entry analysis module is used for analyzing the oxygen entry situation based on the pore distribution situation and the factory environment oxygen concentration, analyzing the anti-oxidation situation based on the unit area oxidation weight gain, and analyzing the comprehensive anti-oxidation situation based on the oxygen entry situation and the anti-oxidation situation; The production up-to-standard judgment module is used for judging whether the anti-oxidation ability of the magnesium oxide coating coated on the silicon steel is up to standard based on the comprehensive anti-oxidation situation.

[0013] The application also provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-mentioned magnesium oxide production evaluation method based on machine vision by calling the computer program stored in the memory.

[0014] The application also provides a computer readable storage medium storing instructions, when the instructions run on the computer, the computer executes the above-mentioned magnesium oxide production evaluation method based on machine vision.

[0015] Compared with the prior art, the beneficial effects of the present application are that the present application collects silicon steel images, analyzes coating fluctuation and coating missing conditions, analyzes magnesium oxide coating coating conditions based on the coating fluctuation and coating missing conditions, collects factory environment data, analyzes the environment harshness, analyzes the initial damage risk based on the magnesium oxide coating coating conditions and the environment harshness, simulates the factory environment erosion evolution process, predicts the pore distribution, analyzes the oxygen entry based on the pore distribution and the factory environment oxygen concentration, analyzes the oxidation resistance based on the unit area oxidation weight gain, analyzes the comprehensive oxidation resistance based on the oxygen entry and the oxidation resistance, judges whether the oxidation resistance of the magnesium oxide coating coated on the silicon steel meets the standard based on the comprehensive oxidation resistance, the present application takes the initial coating condition of the silicon steel and the environment harshness as the input variables, predicts the pore distribution by simulating the erosion evolution process of the factory environment, thereby early warning the potential failure risk of the silicon steel, and improves the accuracy and timeliness of the magnesium oxide production evaluation. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0017] Figure 1 The present application is a flowchart of the magnesium oxide production evaluation method based on machine vision. Figure 2 The present application is a flowchart of step 1 of the magnesium oxide production evaluation method based on machine vision. Figure 3 The present application is a flowchart of step 3 of the magnesium oxide production evaluation method based on machine vision. Figure 4 The present application is a schematic diagram of the overall framework of the magnesium oxide production evaluation system based on machine vision. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art belong to the scope of protection of the present application.

[0019] Please refer to Figure 1 The present application provides a magnesium oxide production evaluation method based on machine vision, which includes the following specific steps: Step 1, collect silicon steel image, analyze coating fluctuation and coating missing situation, and analyze magnesium oxide coating coating situation based on coating fluctuation and coating missing situation; Please refer to Figure 2 In this embodiment, step 1 includes the following specific steps: An industrial camera is used to collect the silicon steel image and pre-process the silicon steel image; In the specific implementation of this embodiment, the image pre-processing process includes cropping, grayscale, noise reduction, contrast enhancement, etc., wherein the cropping removes the edges and background of the silicon steel image and retains the coating area to be analyzed; The coating fluctuation evaluation value is obtained based on the ratio of the gray scale standard deviation to the gray scale mean value of all pixels in the coating area; The coating missing rate evaluation value is obtained based on the ratio of the total number of pixels in the coating missing area to the total number of pixels in the silicon steel image; In the specific implementation of this embodiment, the Otsu algorithm can be used to automatically find the best threshold value, and the pixels with a gray value higher than the threshold value are considered as the coating area, and the pixels with a gray value lower than the threshold value are considered as the missing coating area. A binary image is generated, where white represents the coating area and black represents the missing coating area. The binary image is subjected to an opening operation to remove small noise points, i.e., coating areas that are mistakenly identified as missing coating areas. The gray scale mean value and standard deviation of all pixels in the coating area are calculated. The mean value reflects the average thickness of the coating, and the larger the standard deviation, the greater the coating thickness fluctuation, indicating problems such as uneven thickness, stripes, or spots; The magnesium oxide coating coating abnormality evaluation value is obtained by weighted summation based on the coating fluctuation evaluation value and the coating missing rate evaluation value.

[0020] Step 2, collect factory environment data and analyze the harsh environment; In this embodiment, step 2 includes the following specific steps: Collect factory environment data, including suspended particulate matter concentration, temperature, humidity, and wind speed; In the specific implementation of this embodiment, the suspended particulate matter concentration is collected by an optical particle counter to reflect the cleanliness of the factory environment; The magnesium oxide release coating applied to the surface of the steel plate is crucial to the magnetic properties of the final product. However, this coating is in a very fragile state after application and before final high-temperature annealing, and is easily affected by environmental factors, such as dust, fibers, and other particles in the air falling on the uncured wet coating, which can form protrusions. After solidification, these particles may fall off, leaving pinholes or pits, and damaging the continuity of the coating; When the humidity is too high, magnesium oxide will react with water vapor in the air to form magnesium hydroxide, which has a loose structure, resulting in poor adhesion of the coating, which is easy to fall off and powder during subsequent winding and transportation. Excessive moisture in the coating reacts with the steel base at high temperatures to form an abnormal oxide layer, affecting the magnetic properties. After winding, the wet coating will cause the steel strip to adhere between the layers, which cannot be separated during annealing, resulting in waste products. When the humidity is too low, the coating surface will rapidly shrink to form tensile stress, causing micro-cracks in the coating and damaging its integrity. Dust from electrostatic adsorption can embed into the coating, forming contamination points; When the temperature is too high, the solvent in the coating slurry volatilizes too quickly, causing the coating surface to rapidly form a skin, and the internal solvent cannot escape, resulting in orange peel phenomenon or bubbles; If there is strong and uneven airflow, it will cause uneven solvent volatilization on the wet coating surface, resulting in stripes or uneven thickness. Turbulent airflow can also bring external contaminants into the clean coating area; The pollution abnormality evaluation value is obtained based on the ratio of the concentration of suspended particulate matter to the safety particulate matter concentration threshold. In the specific implementation of the present embodiment, when the concentration of particles greater than or equal to 0.5 μm is less than 250,000 / m 3 , the sticking defect rate can be controlled to be below 0.05%. Therefore, the safety particulate matter concentration threshold can be set to 250,000 / m 3 . The temperature abnormality evaluation value is obtained based on the absolute value of the difference between the temperature and the safety temperature threshold divided by the safety temperature threshold. In the present embodiment, the safety temperature threshold can be set to 26°C. The humidity abnormality evaluation value is obtained based on the absolute value of the difference between the humidity and the safety humidity threshold divided by the safety humidity threshold. In the present embodiment, the safety humidity threshold can be set to 40% RH. The wind speed abnormality evaluation value is obtained based on the ratio of the wind speed to the safety wind speed threshold. In the present embodiment, the safety wind speed threshold can be set to 0.35 m / s. The environmental harshness evaluation value is obtained by weighted summation of the pollution abnormality evaluation value, the temperature abnormality evaluation value, the humidity abnormality evaluation value, and the wind speed abnormality evaluation value.

[0021] Step 3: Analyze the initial damage risk based on the magnesium oxide coating application and the environmental harshness, simulate the factory environment erosion evolution process, and predict the pore distribution; Figure 3 In the present embodiment, step 3 includes the following specific steps: The coating initial comprehensive damage risk evaluation value is obtained by weighted summation of the magnesium oxide coating application abnormality evaluation value and the environmental harshness evaluation value. ​The grayscale value of each pixel in the silicon steel image is converted into a thickness value to obtain a thickness distribution map of the silicon steel coating. A mapping relationship between thickness influence and damage risk weight is established, meaning that areas with darker grayscale colors (higher values) in the silicon steel image are assigned a greater risk weight. A risk weight function is defined as follows: ,in, The scaling constant is used to adjust the sensitivity of the weighting function. It is obtained by collecting thickness distribution maps and corresponding defect distribution maps of a batch of silicon steel samples. An objective function is defined, which can be to maximize the average value of the risk map in the actual defect area while minimizing the average value in the defect-free area. A grid search is used to find the optimal value for the objective function. value, For coating thickness, The target coating thickness is obtained from the coating type's process specification document. As a fixed constant, this embodiment sets it to 0.001 to prevent the denominator from being zero and to ensure the stability of the numerical calculation. The silicon steel coating thickness distribution map is then used. Substitute each thickness value into the risk weight function Obtain risk weight values, and then generate a risk weight map for silicon steel coatings based on these risk weight values. The risk weight chart is obtained as follows: The sum of the risk weight map is normalized, and the initial damage risk assessment value is then distributed point-by-point to each pixel of the silicon steel coating thickness distribution map according to the normalized weights. The calculation formula for the distribution is as follows: ,in, The initial damage risk assessment value assigned to location (i,j) is... This is the initial comprehensive damage risk assessment value for the coating. This represents the sum of all risk weight values ​​in the risk weight diagram. Given the risk weight value at position (i,j), output the initial damage risk status map of the silicon steel coating. The color or value of each pixel in the map represents the level of initial damage risk at that position. The brighter the color (or the higher the value), the greater the initial risk at that position. In this embodiment, a silicon steel sample with a known coating thickness is prepared, and an image of the silicon steel is acquired in the same manner. Its average grayscale value is measured, and the thickness value is fitted with the corresponding grayscale value to obtain the functional relationship between the grayscale value and the thickness value. The prediction duration is preset, and the damage increment applied to each pixel is obtained based on the product of the environmental severity assessment value, the environmental damage conversion coefficient and the prediction duration. The damage increment is then superimposed on the initial damage risk assessment value of each pixel to obtain the superimposed damage risk assessment value. The superimposed damage risk assessment value is compared with a preset coating peeling critical damage value, and if the superimposed damage risk assessment value exceeds the preset coating peeling critical damage value, the corresponding pixel point is marked as a pore; The pore merging rule is executed, noise pores with small areas are removed, the pore distribution is updated, a new pore region list is generated after merging, and a pore distribution prediction map is output, wherein the pore merging rule is an 8-neighborhood rule.

[0022] In the implementation of the embodiment, the connectedComponents function is used to mark adjacent pore pixels as the same region by setting the connectivity parameter to 8.

[0023] Step 4, based on the pore distribution and the oxygen concentration of the factory environment, the oxygen entry condition is analyzed, the oxidation weight gain per unit area is analyzed to analyze the oxidation resistance, and the comprehensive oxidation resistance is analyzed based on the oxygen entry condition and the oxidation resistance; In the embodiment, step 4 includes the following specific steps: The oxygen concentration of the factory is obtained by using an oxygen concentration measuring instrument, and the pore data is obtained based on the pore distribution prediction map, the pore data including the number of pores and the area of the pores; The oxygen entry rate is obtained based on the pore data and the oxygen concentration of the factory environment, and the oxygen entry rate calculation formula is: wherein, is an effective diffusion coefficient, reflecting the speed of oxygen diffusion in the pores, and is obtained by an effective diffusion coefficient estimation formula, which can be expressed as: wherein, is a pore rate, that is, the percentage of the pore area to the total area of the coating, is a tortuosity, used to describe the bending degree of the gas path, and the value is greater than 1, for disordered porous media, an empirical relationship can be used: , is a diffusion coefficient of oxygen in air, which can be taken as 2.0*10 -5 m 2 / s, is the number of pores, is the area of the nth pore, is the oxygen concentration of the factory environment, is the average thickness of the coating; An oxygen entry abnormality assessment value is obtained based on the ratio of the oxygen entry rate to a preset oxygen entry rate threshold value; A silicon steel sample is collected for simulated annealing operation to obtain the oxidation weight gain per unit area, and an oxidation resistance abnormality assessment value is analyzed based on the ratio of a preset oxidation weight gain per unit area threshold value to the oxidation weight gain per unit area; In the specific implementation of the embodiment, the steps of the simulated annealing operation are as follows: a silicon steel sample of a set size covered with a magnesium oxide coating is intercepted from a production line, the sample is placed in a controllable atmosphere tube furnace or a box furnace, a temperature (1150°C-1200°C) and a gas atmosphere of a mixture of high-purity nitrogen and a trace amount of hydrogen simulating an annealing environment of a factory are set, a controllable amount of oxygen or water vapor is introduced as an oxidation source, after a set prediction duration, the sample is taken out and cooled, the mass change of the sample before and after the experiment is measured, and the mass increase per unit area is the amount of oxidation; under standard experimental conditions, the lower the mass gain per unit area per unit time, the higher the anti-oxidation function value. The comprehensive anti-oxidation abnormality evaluation value is obtained by weighted summation based on the oxygen entry abnormality evaluation value and the anti-oxidation abnormality evaluation value.

[0024] The oxygen entry abnormality evaluation value quantifies the risk of oxygen intrusion under the combined action of the environment and micro defects of the coating, and the anti-oxidation abnormality evaluation value quantifies the ability to resist oxidation determined by inherent properties such as composition, density, and bonding force of the coating material itself. Through comprehensive evaluation of the oxygen entry abnormality evaluation value and the anti-oxidation abnormality evaluation value, false negatives and false positives can be reduced. For example, a false negative occurs when the coating itself is of high quality, but the current batch has a large number of pores due to extremely harsh environmental conditions or accidental process fluctuations, or a false positive occurs when some minor fluctuations in the coating are detected, but the current factory environment is ideal and has few pores.

[0025] Step 5: Determine whether the anti-oxidation ability of the magnesium oxide coating applied to the silicon steel meets the standard based on the comprehensive anti-oxidation situation.

[0026] In the embodiment, step 5 includes the following specific steps: Based on the comparison result of the comprehensive anti-oxidation abnormality evaluation value and the preset comprehensive anti-oxidation abnormality threshold value, it is determined whether the anti-oxidation ability of the magnesium oxide coating applied to the silicon steel meets the standard. If the comprehensive anti-oxidation abnormality evaluation value is less than the preset comprehensive anti-oxidation abnormality threshold value, it is determined that the anti-oxidation ability of the magnesium oxide coating applied to the silicon steel meets the standard. If the comprehensive anti-oxidation abnormality evaluation value is greater than or equal to the preset comprehensive anti-oxidation abnormality threshold value, it is determined that the anti-oxidation ability of the magnesium oxide coating applied to the silicon steel does not meet the standard.

[0027] In the specific implementation of the embodiment, the weight, coefficient, and preset threshold value can be obtained as follows: historical silicon steel images and historical factory environment data are obtained, and historical oxygen entry rates are obtained to determine whether the anti-oxidation ability of the magnesium oxide coating meets the production standard. The obtained historical silicon steel images and historical factory environment data are imported into each step of the embodiment to obtain the determination result of whether the anti-oxidation ability of the magnesium oxide coating meets the production standard. The two determination results are imported into a matlab fitting software for fitting to obtain the values of the weight, coefficient, and preset threshold value that meet the maximum determination accuracy.

[0028] Referring to Figure 4 The embodiment of the present application also provides a magnesium oxide production evaluation system based on machine vision, comprising: A coating application analysis module is configured to collect a silicon steel image, analyze coating fluctuation and coating leakage, and analyze magnesium oxide coating application based on the coating fluctuation and the coating leakage. An environment analysis module is configured to collect factory environment data and analyze an environment. A pore distribution prediction module is configured to analyze initial damage risk based on the magnesium oxide coating application and the environment, simulate a factory environment erosion evolution process, and predict a pore distribution. An oxygen entry analysis module is configured to analyze oxygen entry based on the pore distribution and a factory environment oxygen concentration, analyze oxidation resistance based on unit area oxidation weight gain, and analyze comprehensive oxidation resistance based on the oxygen entry and the oxidation resistance. A production compliance judgment module is configured to judge whether the magnesium oxide coating application on the silicon steel meets the oxidation resistance requirement based on the comprehensive oxidation resistance.

[0029] The embodiment of the present application also provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-mentioned magnesium oxide production evaluation method based on machine vision by calling the computer program stored in the memory.

[0030] The electronic device can have great differences due to different configurations and performances, and can comprise one or more processors (Central Processing Units, CPUs) and one or more memories, wherein the memory stores at least one computer program, the computer program is loaded and executed by the processor to realize the magnesium oxide production evaluation method based on machine vision provided by the above-mentioned method embodiment. The electronic device can also comprise other components for realizing device functions, for example, the electronic device can also have a wired or wireless network interface and an input and output interface and other components to input and output data, and the present embodiment will not be described here.

[0031] The embodiment of the present application also provides a computer readable storage medium, which stores instructions, when a computer program runs on a computer device, so that the computer device executes the above-mentioned magnesium oxide production evaluation method based on machine vision.

[0032] For example, the computer readable storage medium can be read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0033] It should be understood that the size of the sequence number of each process described above does not mean the order of execution in various embodiments of the present application, and the execution order of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0034] The above embodiments can be realized wholly or partially by software, hardware, firmware or any other combination, when realized by software, the above embodiments can be realized wholly or partially in the form of computer program product, the computer program product includes one or more computer instructions or computer programs, when loaded or executed on a computer, the computer instructions or computer programs wholly or partially produce the flow or function according to the embodiments of the present application, the computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device, the computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired network or / and wireless network, the computer readable storage medium can be any available medium accessible by the computer or a data storage device such as a server, data center, etc. containing one or more available medium collections, the available medium can be magnetic medium (for example, floppy disk, hard disk, magnetic tape), optical medium (for example, DVD) or semiconductor medium, and the semiconductor medium can be solid state disk.

[0035] In the description of the present specification, the description of the terms "one embodiment", "example", "specific example" and the like means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are contained in at least one embodiment or example of the present application, and the illustrative description of the above terms in the present specification does not necessarily refer to the same embodiment or example, and the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0036] The preferred embodiments of the application disclosed above are only used to illustrate the present application, the preferred embodiments do not describe all the details, and the application is not limited to the specific embodiments. Obviously, many modifications and variations can be made according to the contents of the specification. The specification selects and describes these embodiments in order to better explain the principles and practical applications of the application, so that those skilled in the art can well understand and utilize the application. The application is limited by the claims and their full scope and equivalents.

Claims

1. A machine vision-based method for evaluating magnesium oxide production, characterized in that, The specific steps include the following: Step 1: Acquire images of silicon steel, analyze coating fluctuations and coating omissions, and analyze the magnesium oxide coating application based on coating fluctuations and coating omissions. Step 2: Collect factory environmental data and analyze the harsh environmental conditions; Step 3: Analyze the initial damage risk based on the magnesium oxide coating application and harsh environmental conditions, simulate the erosion evolution process in the factory environment, and predict the porosity distribution. Step 4: Analyze oxygen entry based on stomatal distribution and factory environment oxygen concentration; analyze antioxidant capacity based on oxidation weight gain per unit area; and analyze comprehensive antioxidant capacity based on oxygen entry and antioxidant capacity. Step 5: Determine whether the oxidation resistance of the magnesium oxide coating applied to the silicon steel meets the standard based on the overall oxidation resistance.

2. The machine vision-based magnesium oxide production evaluation method according to claim 1, characterized in that, Step 1 includes the following specific steps: Industrial cameras are used to capture images of silicon steel, and these images are then preprocessed. The coating volatility assessment value is obtained based on the ratio of the standard deviation of gray level to the mean gray level of all pixels in the coating area. The coating failure rate is evaluated by the ratio of the total number of pixels in the uncoated area to the total number of pixels in the silicon steel image. The evaluation value of magnesium oxide coating application anomaly is obtained by weighted summation of coating volatility evaluation value and coating omission rate evaluation value.

3. The machine vision-based magnesium oxide production evaluation method according to claim 2, characterized in that, Step 2 includes the following specific steps: Collect factory environmental data, including particulate matter concentration, temperature, humidity, and wind speed; Pollution anomaly assessment values ​​are obtained based on the ratio of suspended particulate matter concentration to the safe particulate matter concentration threshold. The temperature anomaly assessment value is obtained by dividing the absolute value of the difference between the temperature and the safe temperature threshold by the safe temperature threshold. The humidity anomaly assessment value is obtained by dividing the absolute value of the difference between the humidity and the safe humidity threshold by the safe humidity threshold. The wind speed anomaly assessment value is obtained based on the ratio of wind speed to the safe wind speed threshold. The environmental severity assessment value is obtained by weighted summation of the pollution anomaly assessment value, temperature anomaly assessment value, humidity anomaly assessment value and wind speed anomaly assessment value.

4. The machine vision-based magnesium oxide production evaluation method according to claim 3, characterized in that, Step 3 includes the following specific steps: The initial comprehensive damage risk assessment value of the coating is obtained by weighted summation of the assessment values ​​of magnesium oxide coating application anomaly and environmental severity. The grayscale value of each pixel in the silicon steel image is converted into a thickness value to obtain a silicon steel coating thickness distribution map. A mapping relationship between thickness influence and damage risk weight is established, and a risk weight function is defined as follows: ,in, It is a scaling constant. For coating thickness, For the target coating thickness, As a fixed constant, each thickness value of the silicon steel coating thickness distribution map is substituted into the risk weight function to obtain a risk weight value. Based on the risk weight values, a risk weight map of the silicon steel coating is obtained. The sum of the risk weight maps is normalized. The initial damage risk assessment value is then distributed point-by-point to each pixel of the silicon steel coating thickness distribution map according to the normalized weights. The calculation formula for the distribution is as follows: ,in, The initial damage risk assessment value assigned to location (i,j) is... This is the initial comprehensive damage risk assessment value for the coating. This represents the sum of all risk weight values ​​in the risk weight diagram. Output the initial damage risk state map of the silicon steel coating, where the risk weight value is at location (i,j). The prediction duration is preset, and the damage increment applied to each pixel is obtained based on the product of the environmental severity assessment value, the environmental damage conversion coefficient and the prediction duration. The damage increment is then superimposed on the initial damage risk assessment value of each pixel to obtain the superimposed damage risk assessment value. The superimposed damage risk assessment value is compared with the preset coating peeling critical damage value. If the superimposed damage risk assessment value exceeds the preset coating peeling critical damage value, the corresponding pixel is marked as a pore. The stomatal merging rule is executed, and a new list of stomatal regions is generated after merging. The stomatal distribution prediction map is output. The stomatal merging rule is the 8-neighborhood rule.

5. The machine vision-based magnesium oxide production evaluation method according to claim 4, characterized in that, Step 4 includes the following specific steps: Obtain the oxygen concentration in the factory and obtain stomatal data based on the stomatal distribution prediction map, wherein the stomatal data includes the number of pores and the area of ​​pores. The oxygen entry rate is obtained based on pore data and the oxygen concentration in the factory environment. The formula for calculating the oxygen entry rate is as follows: ,in, For the effective diffusion coefficient, The number of pores. Let n be the area of ​​the nth pore. The oxygen concentration in the factory environment. The average thickness of the coating; An abnormal oxygen intake assessment value is obtained based on the ratio of the oxygen intake rate to a preset oxygen intake rate threshold. Silicon steel samples were collected and simulated annealing was performed to obtain the oxidation weight gain per unit area. The oxidation anomaly assessment value was analyzed based on the ratio of the preset oxidation weight gain threshold per unit area to the oxidation weight gain per unit area. The comprehensive antioxidant anomaly assessment value is obtained by weighted summation of the oxygen entry anomaly assessment value and the antioxidant anomaly assessment value.

6. The machine vision-based magnesium oxide production evaluation method according to claim 5, characterized in that, Step 5 includes the following specific steps: The oxidation resistance of the magnesium oxide coating on silicon steel is determined by comparing the comprehensive oxidation resistance anomaly assessment value with the preset comprehensive oxidation resistance anomaly threshold. If the comprehensive oxidation resistance anomaly assessment value is less than the preset comprehensive oxidation resistance anomaly threshold, the oxidation resistance of the magnesium oxide coating on silicon steel is determined to be up to standard. If the comprehensive oxidation resistance anomaly assessment value is greater than or equal to the preset comprehensive oxidation resistance anomaly threshold, the oxidation resistance of the magnesium oxide coating on silicon steel is determined to be down to standard.

7. A machine vision-based magnesium oxide production evaluation system, used to implement the machine vision-based magnesium oxide production evaluation method as described in any one of claims 1-6, characterized in that, include: The coating application analysis module is used to acquire images of silicon steel, analyze coating fluctuations and coating omissions, and analyze the application of magnesium oxide coating based on coating fluctuations and coating omissions. The environmental severity analysis module is used to collect factory environmental data and analyze environmental severity conditions. The porosity distribution prediction module is used to analyze the initial damage risk based on the magnesium oxide coating application and harsh environmental conditions, simulate the erosion evolution process in the factory environment, and predict the porosity distribution. The oxygen entry analysis module is used to analyze oxygen entry based on stomatal distribution and factory environment oxygen concentration, analyze antioxidant capacity based on oxidation weight gain per unit area, and analyze comprehensive antioxidant capacity based on oxygen entry and antioxidant capacity. The production compliance judgment module is used to determine whether the oxidation resistance of the magnesium oxide coating applied to silicon steel meets the standards based on the overall oxidation resistance.

8. An electronic device, characterized in that, include: A memory and a processor, wherein the memory stores a computer program that can be called by the processor, and the processor executes the machine vision-based magnesium oxide production evaluation method according to any one of claims 1-6 by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that, The system stores instructions that, when executed on a computer, cause the computer to perform the machine vision-based magnesium oxide production evaluation method as described in any one of claims 1-6.

Images