Defect detection system and method for silicon steel grade magnesium oxide coating

Abstract

The application discloses a defect detection system and method for a silicon steel grade magnesium oxide coating, relates to the technical field of coating defect detection, and acquires coating equipment operation data, obtains a magnesium oxide coating image through a visual module, analyzes coating defect positioning and defect conditions based on the coating equipment operation data and the magnesium oxide coating image, obtains power equipment operation data at a defect positioning position in a use scene, analyzes power equipment operation abnormal conditions based on the power equipment operation data, predicts future development conditions of the defect based on the defect positioning, the defect conditions and the power equipment operation abnormal conditions of the magnesium oxide coating, and analyzes whether the magnesium oxide coating can meet work requirements in a power equipment working process based on the future development conditions of the defect. The application combines defect data, coating equipment operation data and power equipment operation data abnormalities to perform differentiated defect prediction, and is favorable for improving defect detection precision.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of coating defect detection, in particular to a defect detection system and method for silicon steel grade magnesium oxide coating. BACKGROUND

[0002] In the operation and maintenance of power equipment, magnesium oxide coating as an important insulation and protection barrier, its integrity is directly related to the safe and stable operation of the equipment, once the coating appears defects such as cracks, peeling, holes, etc., it will significantly reduce its insulation performance, may cause partial discharge, creeping and even breakdown and other serious faults, causing huge economic losses and social influence, therefore, it is extremely important to diagnose and develop the magnesium oxide coating defects early and judge whether the insulation performance meets the future work requirements.

[0003] The prior art relies on single visual detection or offline sampling analysis, lacks effective correlation and fusion for coating detection and operation monitoring of power equipment, and relies on defect size for dynamic prediction of defects, ignores the differentiated influence of defect type and equipment operation anomaly on expansion rate, resulting in low defect detection accuracy.

[0004] In order to solve the above problems, the present application designs a defect detection system and method for silicon steel grade magnesium oxide coating. SUMMARY

[0005] In order to overcome the defects and deficiencies of the prior art, the present application provides a defect detection system and method for silicon steel grade magnesium oxide coating, which combines defect data, coating equipment operation data and power equipment operation data to make differentiated defect prediction, which is beneficial to improve the accuracy of defect detection.

[0006] To achieve the above purpose, the present application provides the following technical scheme:

[0007] In the first aspect, the present application provides a defect detection method for silicon steel grade magnesium oxide coating, comprising the following specific steps:

[0008] Step 1, obtaining coating equipment operation data, obtaining magnesium oxide coating image through visual module, and analyzing coating defect positioning and defect condition based on coating equipment operation data and magnesium oxide coating image;

[0009] Step 2, obtaining power equipment operation data at the defect positioning in the use scene, and analyzing power equipment operation anomaly condition based on the power equipment operation data;

[0010] Step 3, predicting the future development of the defect based on the defect positioning, defect condition and power equipment operation anomaly condition of the magnesium oxide coating;

[0011] Step 4, analyzing whether the magnesium oxide coating can meet the working requirements in the working process of the power equipment based on the future development of the defects.

[0012] Preferably, the step 1 comprises the following specific steps:

[0013] Obtaining coating equipment operation data, the coating equipment operation data comprising coating roller pressure, coating roller rotation speed and coating liquid flow rate;

[0014] Obtaining magnesium oxide coating layer images through a visual module, and obtaining magnesium oxide coating layer data based on the magnesium oxide coating layer images, the magnesium oxide coating layer data comprising coating layer thickness, defect depth and defect area;

[0015] Obtaining historical coating equipment operation data and historical magnesium oxide coating layer data, and obtaining historical defect types of the magnesium oxide coating layer for defect type probabilistic neural network model training;

[0016] Dividing the historical coating equipment operation data and the historical magnesium oxide coating layer data into 80% training data set and 20% test data set, inputting the 80% training data set into the defect type probabilistic neural network model for training and obtaining an initial defect type probabilistic neural network model, and testing the initial defect type probabilistic neural network model through the 20% test data set to obtain a defect type probabilistic neural network model most accurate for defect type judgment;

[0017] Obtaining the trained defect type probabilistic neural network model, inputting coating equipment operation data and magnesium oxide coating layer data, outputting defect type probability, and obtaining a defect type corresponding to a maximum probability and coordinates of the defect.

[0018] Preferably, the step 2 comprises the following specific steps:

[0019] Obtaining power equipment operation data at the defect positioning position in the use scenario, the power equipment operation data comprising electric field intensity, load current, vibration and temperature;

[0020] Obtaining electric field intensity abnormal value based on a sum of ratios of electric field intensity collected in all time periods to a safe electric field intensity threshold value divided by a number of collection time periods;

[0021] Obtaining load current abnormal value based on a sum of ratios of load current collected in all time periods to a safe load current threshold value divided by a number of collection time periods;

[0022] Obtaining vibration amplitude abnormal value based on a sum of ratios of vibration amplitude collected in all time periods to a safe vibration amplitude threshold value divided by a number of collection time periods;

[0023] obtaining a temperature abnormal value based on a sum of ratios of temperatures collected in all time periods to a safety temperature threshold value, and dividing the sum by a number of the collection time periods;

[0024] obtaining a power equipment operation abnormal value based on a weighted sum of the electric field intensity abnormal value, the load current abnormal value, the vibration amplitude abnormal value and the temperature abnormal value.

[0025] Preferably, the step 3 comprises the following specific steps:

[0026] constructing a defect development prediction model, inputting a future set time length, a defect location of the magnesium oxide coating, a defect type, a defect depth, a defect area and the power equipment operation abnormal value, and outputting a defect prediction value at a future set time point.

[0027] Preferably, the step 4 comprises the following specific steps:

[0028] obtaining an insulation resistance prediction value based on the defect prediction value at the future set time point, the insulation resistance prediction value being obtained through an insulation resistance calculation formula, the insulation resistance calculation formula being: wherein, is an initial insulation resistance, is a material attenuation coefficient, is the defect prediction value at the future set time point, wherein the defect prediction value is a predicted volume of the defect, is a defect safety volume, is a defect type influence coefficient;

[0029] comparing the insulation resistance prediction value with an insulation resistance threshold value to analyze whether the magnesium oxide coating can meet the working requirements in the working process of the power equipment, if the insulation resistance prediction value is greater than or equal to the insulation resistance threshold value, the magnesium oxide coating can meet the working requirements in the working process of the power equipment, and if the insulation resistance prediction value is less than the insulation resistance threshold value, the magnesium oxide coating cannot meet the working requirements in the working process of the power equipment.

[0030] In a second aspect, the present application further provides a defect detection system for a silicon steel grade magnesium oxide coating, which is used to implement the defect detection method for the silicon steel grade magnesium oxide coating, and comprises:

[0031] a defect condition analysis module, configured to obtain coating equipment operation data, obtain a magnesium oxide coating image through a visual module, and analyze coating defect location and defect conditions based on the coating equipment operation data and the magnesium oxide coating image;

[0032] a device abnormality analysis module, configured to obtain power equipment operation data at the defect location in a use scenario, and analyze power equipment operation abnormal conditions based on the power equipment operation data;

[0033] A defect development prediction module is configured to predict future development of the defect based on the defect location, defect condition and abnormal operation condition of the power equipment of the magnesium oxide coating.

[0034] An insulation performance analysis module is configured to analyze whether the magnesium oxide coating can meet the working requirements during the working process of the power equipment based on the future development of the defect.

[0035] In a third aspect, the present application further 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 defect detection method for the silicon steel grade magnesium oxide coating by calling the computer program stored in the memory.

[0036] In a fourth aspect, the present application further provides a computer readable storage medium storing instructions, which, when executed on a computer, cause the computer to execute the defect detection method for the silicon steel grade magnesium oxide coating.

[0037] Compared with the prior art, the present application has the following beneficial effects:

[0038] The coating equipment operation data is acquired, the magnesium oxide coating image is acquired through the visual module, the coating defect location and defect condition are analyzed based on the coating equipment operation data and the magnesium oxide coating image, the power equipment operation data at the defect location in the use scene is acquired, the abnormal operation condition of the power equipment is analyzed based on the power equipment operation data, the future development of the defect is predicted based on the defect location, defect condition and abnormal operation condition of the power equipment of the magnesium oxide coating, and whether the magnesium oxide coating can meet the working requirements during the working process of the power equipment is analyzed based on the future development of the defect. The present application combines the defect data, coating equipment operation data and abnormal power equipment operation data to make differentiated defect prediction, which is beneficial to improve the precision of defect detection. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0040] Figure 1 A flowchart of the defect detection method for the silicon steel grade magnesium oxide coating of the present application;

[0041] Figure 2 A flowchart of step 1 of the defect detection method for the silicon steel grade magnesium oxide coating of the present application;

[0042] Figure 3This is a schematic diagram of step 2 of the defect detection method for silicon steel grade magnesium oxide coating of the present invention;

[0043] Figure 4 This is a schematic diagram of the overall framework of the defect detection system for silicon steel grade magnesium oxide coating of the present invention. Detailed Implementation

[0044] 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 are within the scope of protection of the present invention.

[0045] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of this application. The phrase "in an embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is exclusive to or selectively mutually exclusive with other embodiments.

[0046] Example 1

[0047] Please see Figure 1 This embodiment provides a defect detection method for silicon steel grade magnesium oxide coatings, which includes the following specific steps:

[0048] Step 1: Obtain the operating data of the coating equipment, acquire the image of the magnesium oxide coating through the vision module, and analyze the location and condition of coating defects based on the operating data of the coating equipment and the image of the magnesium oxide coating.

[0049] Please see Figure 2 In this embodiment, step 1 includes the following specific steps:

[0050] Acquire coating equipment operating data, including coating roller pressure, coating roller speed, and coating liquid flow rate;

[0051] In one specific embodiment, the coating equipment operation data is collected synchronously at high frequency through the equipment PLC, sensors and SCADA system, and stamped with a unified timestamp;

[0052] The pressure of the coating roller affects the uniformity of the magnesium oxide coating thickness and its adhesion. Uneven pressure distribution can lead to stripes and thickness gradients in the coating, forming local stress concentration points, which can cause cracks or peeling. Appropriate pressure ensures that the coating liquid and the substrate are fully wetted. Insufficient pressure can easily lead to a decrease in adhesion and cause the coating to peel off when the power equipment vibrates or when it expands and contracts due to heat.

[0053] The speed of the coating roller affects the coating thickness and uniformity. The higher the speed, the shorter the residence time of the coating on the substrate and the thinner the coating. Conversely, the lower the speed, the thicker the coating. High speed can also cause coating splashing or uneven distribution.

[0054] The flow rate of the coating liquid affects the stability of the supply and the consistency of the coating composition. Fluctuations in flow rate can lead to sudden changes in coating thickness, forming weak points in insulation. Abnormal flow rate reflects coating liquid sedimentation, pipeline blockage or pumping failure, causing the coating composition to deviate from the design value.

[0055] Magnesium oxide coating images are acquired through a vision module, and magnesium oxide coating data is obtained based on the magnesium oxide coating images. The magnesium oxide coating data includes coating thickness, defect depth, and defect area.

[0056] In one specific embodiment, a high-definition inspection system integrating multiple vision modules is installed, and the vision system is triggered and synchronized with the production line encoder.

[0057] A 3D line laser profilometer is used to emit a laser beam to scan the coating surface. Point cloud data of the coating surface is obtained through the principle of triangulation. The vertical distance between the coating and the substrate is calculated, which is the coating thickness.

[0058] The defect region is segmented from the magnesium oxide coating image, the point cloud of the coating surface in the region is extracted, and the vertical difference between the bottom of the defect and the surrounding normal coating surface is calculated, which is the defect depth.

[0059] The defect contours are extracted by segmenting the magnesium oxide coating image, and then the number of pixels combined with the pixel resolution is converted into the actual area.

[0060] In one specific embodiment, a unified time-space coordinate system is established to align each image frame and its detected defects with the corresponding coating equipment operation data.

[0061] Acquire historical operating data of coating equipment and historical magnesium oxide coating data, and obtain historical defect types of magnesium oxide coatings to train a probabilistic neural network model for defect types.

[0062] The historical operating data of the coating equipment and the historical magnesium oxide coating data were divided into 80% training dataset and 20% test dataset. The 80% training dataset was input into the defect type probabilistic neural network model for training and obtaining the initial defect type probabilistic neural network model. The initial defect type probabilistic neural network model was then tested using the 20% test dataset to obtain the defect type probabilistic neural network model that is most accurate in judging defect types.

[0063] Obtain the trained defect type probability neural network model, input the coating equipment operation data and magnesium oxide coating data, output the defect type probability, and obtain the defect type corresponding to the maximum probability of the defect type and the coordinates of the defect location.

[0064] The defect types include:

[0065] Coating peeling: The magnesium oxide coating may peel off partially or completely from the silicon steel surface, possibly in the form of flakes, blocks, or powder. Insufficient adhesion between the coating and the silicon steel substrate is the main cause of coating peeling. For example, if the silicon steel surface is not thoroughly cleaned and contains oil, impurities, etc., it will affect the adhesion between the coating and the substrate. Or, improper temperature and time control during the coating drying process may also lead to poor adhesion between the coating and the substrate. Coating peeling will expose the silicon steel to the air directly, making it prone to rust and corrosion, reducing the service life of the silicon steel. At the same time, the peeled coating may cause pollution in production equipment or electrical equipment, affecting the normal operation of the equipment.

[0066] Coating pinholes: Tiny holes exist on the coating surface. Pinholes may be caused by air bubbles in the magnesium oxide coating, which burst during the coating process to form pinholes, or by impurities such as dust and particles in the coating environment, which embed in the coating to form holes. Pinholes will damage the integrity of the coating, allowing external moisture, oxygen, etc. to easily reach the silicon steel surface through the pinholes, causing corrosion. Pinholes will also affect the insulation performance of the coating and reduce the electrical performance of the silicon steel.

[0067] Coating cracks: Cracks appear on the surface of the coating. The size and shape of the cracks vary. During the drying and curing process, the coating is prone to cracking due to uneven shrinkage or external forces. Mechanical stress on silicon steel during processing and transportation may also cause cracks in the coating. Cracks will reduce the protective performance of the coating, making the silicon steel more susceptible to corrosion and oxidation. Cracks may also extend, further damaging the integrity of the coating and affecting the long-term performance of the silicon steel.

[0068] In one specific embodiment, the defect type probabilistic neural network model includes an output formula for a specific neuron, which is: ,in, The output of the m-th neuron in the (n+1)th layer of the defect type probabilistic neural network model is... Activation function The number of neurons in the nth layer. Let i be the connection weight between neuron i in the nth layer and neuron m in the (n+1)th layer of the probabilistic neural network model for defect types. This represents the output of neuron i in the nth layer of the probabilistic neural network model for defect types. This represents the bias of the linear relationship between neuron i in the nth layer and the m-term neurons in the (n+1)th layer of the defect type probabilistic neural network model.

[0069] Step 2: Obtain the power equipment operation data at the defect location in the usage scenario, and analyze the abnormal operation of the power equipment based on the power equipment operation data;

[0070] Please see Figure 3 In this embodiment, step 2 includes the following specific steps:

[0071] Acquire the operating data of the power equipment at the defect location in the usage scenario, the operating data of the power equipment includes electric field strength, load current, vibration and temperature;

[0072] In one specific embodiment, based on the slitting and lamination scheme of the silicon steel coil, the defects on the strip are located and mapped to the final core components, such as the second silicon steel sheet of the second layer of the transformer A-phase core.

[0073] High temperatures can accelerate the sintering and grain growth of magnesium oxide coatings, and may even cause an interface reaction with the silicon steel substrate, altering its insulation and mechanical properties. The coating is more likely to generate new microcracks or expand existing cracks under mechanical stress.

[0074] The powerful alternating magnetic field generated by the short-circuit current will produce a huge electromagnetic force in the iron core, causing the silicon steel sheet to vibrate or undergo micro-deformation, which will lead to the peeling of the coating and the propagation of cracks around the defect. The electrodynamic force may cause irreversible changes in the micro-magnetic domain structure of the silicon steel sheet, exacerbating the magnetic field distortion at the defect.

[0075] Excessive electric field strength can cause irreversible electrical breakdown traces at defects, forming carbonized channels and reducing the insulation strength at that point. Tiny bubbles or impurities may also become fixed sources of partial discharge.

[0076] Abnormal vibration during operation can generate cyclic stress at the defect site. Defects such as scabs and lumps may become loose or even fall off under long-term vibration, creating new sources of contamination.

[0077] The abnormal electric field strength values ​​are obtained by summing the ratios of the electric field strength collected in all time periods to the safe electric field strength threshold and then dividing by the number of time periods collected.

[0078] The abnormal load current value is obtained by summing the ratios of the load current collected in all time periods to the safe load current threshold and then dividing by the number of time periods collected.

[0079] The abnormal vibration amplitude value is obtained by summing the ratios of vibration amplitude collected in all time periods to the safe vibration amplitude threshold and then dividing by the number of time periods collected.

[0080] The abnormal temperature value is obtained by summing the ratios of the temperatures collected in all time periods to the safe temperature threshold and then dividing by the number of time periods collected.

[0081] Abnormal values ​​of power equipment operation are obtained by weighted summation of abnormal values ​​of electric field strength, load current, vibration amplitude, and temperature.

[0082] Step 3: Based on the defect location, defect status, and abnormal operation of the power equipment, predict the future development of the defects;

[0083] In this embodiment, step 3 includes the following specific steps:

[0084] Construct a defect development prediction model, inputting a future set time length, defect location of magnesium oxide coating, defect type, defect depth, defect area, future set time point, and abnormal values ​​of power equipment operation, and output the defect prediction value at the future set time point.

[0085] In one specific embodiment, the training steps for constructing a defect development prediction model are as follows: acquire one normally operating power device and several power devices with operational abnormalities, acquire the defects in the magnesium oxide coating at the defect location of the power device, continuously record the changes in the defects, divide the recorded defect data into an 80% training dataset and a 20% test dataset, initialize the defect development prediction model, obtain the residual of each sample by subtracting the current predicted value from the true value, correct the initial error, then obtain a new prediction by adding the old prediction to the product of the learning rate and the tree's prediction, correct the prediction results, continuously iterate to build more trees until the number of trees reaches a preset value, input the test set into the trained defect development prediction model to obtain the defect prediction value, compare the defect prediction value with the true value, calculate the error index to evaluate the performance of the defect development prediction model.

[0086] Step 4: Analyze the future development of the defects to determine whether the magnesium oxide coating can meet the working requirements of the power equipment during operation.

[0087] In this embodiment, step 4 includes the following specific steps:

[0088] The predicted insulation resistance value is obtained based on the defect prediction value at a future predetermined time point. This predicted insulation resistance value is obtained using an insulation resistance calculation formula, which is as follows: ,in, The initial insulation resistance, The material attenuation coefficient is obtained by simulating the effect of defects on the electric field distribution using COMSOL and then extrapolating from this result. For example, in this embodiment, the material attenuation coefficient can be set to 0.05. The defect prediction value is set for a future time point, where the defect prediction value is the predicted volume of the defect, which is obtained through area and depth. The defect safety volume is obtained by measuring the average defect volume of the scrapped magnesium oxide coating. The defect type influence coefficient quantifies the differences in the harm caused by different defects. The steps to obtain the defect type influence coefficient are as follows: different types of defects are manufactured on a standard specimen, and the percentage decrease in insulation resistance is measured. For example, if a crack causes a 20% decrease in insulation, the defect type influence coefficient is 1.2. The above formula adopts an exponential decay model to reflect the process of insulation performance degradation caused by defect propagation in the corresponding material. The larger the defect prediction value, the faster the insulation resistance decreases.

[0089] Based on the comparison between the predicted insulation resistance value and the insulation resistance threshold, this analysis examines whether the magnesium oxide coating can meet the operational requirements of power equipment. If the predicted insulation resistance value is greater than or equal to the insulation resistance threshold, the magnesium oxide coating can meet the operational requirements of the power equipment, and monitoring can continue, extending the maintenance cycle. If the predicted insulation resistance value is less than the insulation resistance threshold, the magnesium oxide coating cannot meet the operational requirements of the power equipment, and partial repair or shutdown maintenance can be performed.

[0090] In one specific embodiment, the weights and thresholds can be obtained by: acquiring historical data on the location of magnesium oxide coating defects, defect conditions, and the operation of power equipment at the defect location; simultaneously acquiring data on whether the magnesium oxide coating can meet the working requirements during defect development; importing the acquired historical data into each step of this embodiment to obtain the judgment result on whether the magnesium oxide coating meets the working requirements; importing the two judgment results into MATLAB fitting software for fitting to obtain the weights and thresholds that meet the maximum judgment accuracy.

[0091] Example 2

[0092] Please see Figure 4 This embodiment provides a defect detection system for silicon steel grade magnesium oxide coatings, implemented based on the above-described defect detection method for silicon steel grade magnesium oxide coatings, including:

[0093] The defect analysis module is used to acquire coating equipment operation data, obtain magnesium oxide coating images through the vision module, and analyze coating defect location and defect status based on coating equipment operation data and magnesium oxide coating images;

[0094] The equipment anomaly analysis module is used to acquire the power equipment operation data at the defect location in the usage scenario, and analyze the abnormal operation of the power equipment based on the power equipment operation data;

[0095] The defect development prediction module is used to predict the future development of defects based on the location of defects in magnesium oxide coatings, defect conditions, and abnormal operation of power equipment.

[0096] The insulation performance analysis module is used to analyze whether the magnesium oxide coating can meet the working requirements of power equipment during operation based on the future development of defects.

[0097] Example 3

[0098] This embodiment provides an electronic device, including 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-described defect detection method for silicon steel grade magnesium oxide coating by calling the computer program stored in the memory.

[0099] The electronic device can vary considerably depending on its configuration or performance. It may include one or more Central Processing Units (CPUs) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the defect detection method for silicon steel grade magnesium oxide coatings provided in the above-described method embodiments. The electronic device may also include other components for implementing the device's functions. For example, the electronic device may also have wired or wireless network interfaces and input / output interfaces for data input and output. Further details are omitted here.

[0100] Example 4

[0101] This embodiment provides a computer-readable storage medium storing instructions that, when a computer program is run on a computer device, cause the computer device to execute the aforementioned defect detection method for silicon steel grade magnesium oxide coatings.

[0102] For example, computer-readable storage media 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 devices.

[0103] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0104] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, they generate in whole or in part the flow or function according to the embodiments of the present invention. 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, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network and / or wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more sets of available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DiD), or semiconductor media. The semiconductor media can be a solid-state drive.

[0105] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. 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 to be beyond the scope of this invention.

[0106] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0107] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only one, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical or other forms.

[0108] 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 units may be selected to achieve the purpose of this embodiment according to actual needs.

[0109] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example, and the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0110] The preferred embodiments of the present invention disclosed above are only for the purpose of illustrating the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to specific implementation methods. Obviously, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A defect detection method for silicon steel grade magnesium oxide coatings, characterized in that, The specific steps include the following: Step 1: Obtain the operating data of the coating equipment, acquire the image of the magnesium oxide coating through the vision module, and analyze the location and condition of coating defects based on the operating data of the coating equipment and the image of the magnesium oxide coating. Step 2: Obtain the power equipment operation data at the defect location in the usage scenario, and analyze the abnormal operation of the power equipment based on the power equipment operation data; Step 3: Based on the defect location, defect status, and abnormal operation of the power equipment, predict the future development of the defects; Step 4: Analyze the future development of the defects to determine whether the magnesium oxide coating can meet the working requirements of the power equipment during operation. Step 3 includes the following specific steps: Construct a defect development prediction model, inputting a future set time length, defect location of magnesium oxide coating, defect type, defect depth, defect area, and abnormal values ​​of power equipment operation, and outputting the defect prediction value at a future set time point; Step 4 includes the following specific steps: The predicted insulation resistance value is obtained based on the defect prediction value at a future predetermined time point. This predicted insulation resistance value is obtained using an insulation resistance calculation formula, which is as follows: ,in, The initial insulation resistance, The material attenuation coefficient, The defect prediction value is set for a future time point, where the defect prediction value is the predicted volume of the defect. For defect safety volume, This is the defect type influence coefficient; Based on the comparison between the predicted insulation resistance value and the insulation resistance threshold, this analysis examines whether the magnesium oxide coating can meet the working requirements of the power equipment. If the predicted insulation resistance value is greater than or equal to the insulation resistance threshold, the magnesium oxide coating can meet the working requirements of the power equipment. If the predicted insulation resistance value is less than the insulation resistance threshold, the magnesium oxide coating cannot meet the working requirements of the power equipment.

2. The defect detection method for silicon steel grade magnesium oxide coating according to claim 1, characterized in that, Step 1 includes the following specific steps: Acquire coating equipment operating data, including coating roller pressure, coating roller speed, and coating liquid flow rate; Magnesium oxide coating images are acquired through a vision module, and magnesium oxide coating data is obtained based on the magnesium oxide coating images. The magnesium oxide coating data includes coating thickness, defect depth, and defect area. Acquire historical operating data of coating equipment and historical magnesium oxide coating data, and obtain historical defect types of magnesium oxide coatings to train a probabilistic neural network model for defect types. The historical operating data of the coating equipment and the historical magnesium oxide coating data were divided into 80% training dataset and 20% test dataset. The 80% training dataset was input into the defect type probabilistic neural network model for training and obtaining the initial defect type probabilistic neural network model. The initial defect type probabilistic neural network model was then tested using the 20% test dataset to obtain the defect type probabilistic neural network model that is most accurate in judging defect types. Obtain the trained defect type probability neural network model, input the coating equipment operation data and magnesium oxide coating data, output the defect type probability, and obtain the defect type corresponding to the maximum probability of the defect type and the coordinates of the defect location.

3. The defect detection method for silicon steel grade magnesium oxide coating according to claim 2, characterized in that, Step 2 includes the following specific steps: Acquire the operating data of the power equipment at the defect location in the usage scenario, the operating data of the power equipment includes electric field strength, load current, vibration and temperature; The abnormal electric field strength values ​​are obtained by summing the ratios of the electric field strength collected in all time periods to the safe electric field strength threshold and then dividing by the number of time periods collected. The abnormal load current value is obtained by summing the ratios of the load current collected in all time periods to the safe load current threshold and then dividing by the number of time periods collected. The abnormal vibration amplitude value is obtained by summing the ratios of vibration amplitude collected in all time periods to the safe vibration amplitude threshold and then dividing by the number of time periods collected. The abnormal temperature value is obtained by summing the ratios of the temperatures collected in all time periods to the safe temperature threshold and then dividing by the number of time periods collected. Abnormal values ​​of power equipment operation are obtained by weighted summation of abnormal values ​​of electric field strength, load current, vibration amplitude, and temperature.

4. A defect detection system for silicon steel grade magnesium oxide coatings, used to implement the defect detection method for silicon steel grade magnesium oxide coatings as described in any one of claims 1-3, characterized in that, include: The defect analysis module is used to acquire coating equipment operation data, obtain magnesium oxide coating images through the vision module, and analyze coating defect location and defect status based on coating equipment operation data and magnesium oxide coating images; The equipment anomaly analysis module is used to acquire the power equipment operation data at the defect location in the usage scenario, and analyze the abnormal operation of the power equipment based on the power equipment operation data; The defect development prediction module is used to predict the future development of defects based on the location of defects in magnesium oxide coatings, defect conditions, and abnormal operation of power equipment. The insulation performance analysis module is used to analyze whether the magnesium oxide coating can meet the working requirements of power equipment during operation based on the future development of defects.

5. 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 defect detection method for silicon steel grade magnesium oxide coating as described in any one of claims 1-3 by calling the computer program stored in the memory.

6. A computer-readable storage medium, characterized in that, The device stores instructions that, when executed on a computer, cause the computer to perform the defect detection method for silicon steel grade magnesium oxide coatings as described in any one of claims 1-3.

Images