Oriented silicon steel plate scribed line optimization method and related equipment

Abstract

The invention discloses an oriented silicon steel plate scribed line optimization method and related equipment, and relates to the technical field of steel plate machining, and the method comprises the following steps: obtaining a plate surface brightness distribution two-dimensional array of a target oriented silicon steel plate; based on the vertical direction of the scribed line, array splitting is carried out on the panel brightness distribution two-dimensional array, and a brightness one-dimensional array set is obtained; based on the brightness one-dimensional array set, determining a scribed line left edge pixel subscript set and a scribed line right edge pixel subscript set; determining the scribed line width of the target oriented silicon steel plate based on the scribed line left edge pixel subscript set and the scribed line right edge pixel subscript set; and based on the difference value between the scribed line width and the preset width, adjusting the scribed line operation parameters of the target oriented silicon steel plate. Through accurate image processing and automatic feedback adjustment, the scribing quality of the oriented silicon steel plate is optimized, the precision and efficiency of production are improved, the stability of scribing operation is ensured, and therefore the purposes of reducing iron loss and improving the performance of silicon steel are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of steel plate processing, and more specifically, to a method for optimizing engraving lines of oriented silicon steel plates and related equipment. Background Art

[0002] With the continuous deepening of the application of oriented silicon steel in equipment such as transformers, fluorescent lamp ballasts and turbine generator stator cores, notching technology has been widely used in the surface treatment process of oriented silicon steel as an effective means to reduce iron loss. By accurately controlling the width of the notch, the magnetic domain structure of silicon steel can be effectively refined, thereby improving its magnetic properties, reducing iron loss, and improving its working efficiency in electromagnetic environments; however, the width of the notch has a direct impact on the magnetic properties of oriented silicon steel. Too large or too small a notch width will lead to increased iron loss and even affect the changes in magnetic induction and hysteresis loss; therefore, how to accurately control and optimize the notch width of oriented silicon steel has become one of the key technologies to improve the performance of silicon steel.

[0003] At present, in the existing technology, the measurement of the notch width usually relies on manual visual inspection or traditional optical measurement equipment. Although these methods can achieve a rough estimate of the notch width, they are often unable to provide sufficiently accurate and efficient notch measurement results due to the subjectivity of the operation process and the limitations of equipment accuracy. At the same time, traditional methods cannot handle high-resolution, high-speed dynamic notch quality detection, and it is difficult to meet the requirements of real-time monitoring and refined control of notch quality in modern production processes. That is, there is a technical problem in the relevant technology of how to detect and optimize the notch width with high precision and efficiency. Summary of the invention

[0004] A series of simplified concepts are introduced in the summary of the invention, which will be further described in detail in the detailed description. The summary of the invention of this application does not mean to attempt to define the key features and essential technical features of the technical solution claimed for protection, nor does it mean to attempt to determine the scope of protection of the technical solution claimed for protection.

[0005] The oriented silicon steel plate engraving optimization method and related devices provided in the present application can optimize the engraving quality of the oriented silicon steel plate through precise image processing and automated feedback adjustment, improve the accuracy and efficiency of production, and ensure the stability of the engraving operation, thereby achieving the goal of reducing iron loss and improving silicon steel performance.

[0006] In a first aspect, the present application provides a method for optimizing the engraving lines of an oriented silicon steel plate, comprising: obtaining a two-dimensional array of the brightness distribution of the surface of a target oriented silicon steel plate; based on a vertical direction of the engraving lines, performing array splitting on the two-dimensional array of the brightness distribution of the surface of the plate to obtain a one-dimensional array set of brightness, wherein the vertical direction of the engraving lines is a direction perpendicular to the engraving line direction, and the one-dimensional array set of brightness includes at least one one-dimensional array of the brightness distribution of the surface of the plate; based on the one-dimensional array set of brightness, determining a pixel subscript set at the left edge of the engraving lines and a pixel subscript set at the right edge of the engraving lines; based on the pixel subscript set at the left edge of the engraving lines and the pixel subscript set at the right edge of the engraving lines, determining the engraving width of the target oriented silicon steel plate; based on the difference between the engraving width and a preset width, adjusting the engraving operation parameters performed on the target oriented silicon steel plate.

[0007] In a feasible implementation manner, the determining of the pixel subscript set of the left edge of the engraved line and the pixel subscript set of the right edge of the engraved line based on the one-dimensional array set of brightness includes: based on a preset maximum screening threshold, performing a local maximum search on the one-dimensional array of the panel brightness distribution to obtain a local maximum subscript; performing a gradient calculation on the one-dimensional array of the panel brightness distribution to obtain a brightness gradient array; based on the brightness gradient array, determining the left inflection point that is closer to the local maximum subscript as the left gradient inflection point, and determining the right inflection point that is closer to the local maximum subscript as the right gradient inflection point; determining the pixel subscript set of the left edge of the engraved line based on the left gradient inflection point, and determining the pixel subscript set of the right edge of the engraved line based on the right gradient inflection point.

[0008] In a feasible implementation, based on a preset maximum value screening threshold, a local maximum value search is performed on the one-dimensional array of the panel surface brightness distribution to obtain a local maximum value subscript, including: smoothing and denoising the one-dimensional array of the panel surface brightness distribution to obtain a smoothed one-dimensional array of the panel surface brightness; based on a preset maximum value screening threshold, a local maximum value search is performed on the one-dimensional array of the smoothed one-dimensional array of the panel surface brightness to obtain a local maximum value subscript.

[0009] In a feasible implementation, determining the pixel subscript set of the left edge of the engraved line based on the left gradient inflection point, and determining the pixel subscript set of the right edge of the engraved line based on the right gradient inflection point, includes: performing curve fitting based on the left gradient inflection point to obtain a first fitting function; based on the first fitting function and a first preset offset coefficient, screening out a first target inflection point among the left gradient inflection points, and determining the subscript of the first target inflection point as an element in the pixel subscript set of the left edge of the engraved line; performing curve fitting based on the right gradient inflection point to obtain a second fitting function; based on the second fitting function and a second preset offset coefficient, screening out a second target inflection point among the right gradient inflection points, and determining the subscript of the second target inflection point as an element in the pixel subscript set of the right edge of the engraved line.

[0010] In a feasible implementation, the two-dimensional array of panel brightness distribution is split based on the vertical direction of the grating lines to obtain a one-dimensional brightness array set, including: based on the vertical direction of the grating lines, the two-dimensional array of panel brightness distribution is split according to a preset pixel interval to obtain a one-dimensional brightness array set, wherein the preset pixel interval is an integer greater than or equal to 0.

[0011] In a feasible implementation manner, obtaining the two-dimensional array of the surface brightness distribution of the target oriented silicon steel plate includes: collecting a surface image by a high-speed camera perpendicular to the target oriented silicon steel plate; performing pixel brightness array conversion on the surface image to obtain the two-dimensional array of the surface brightness distribution.

[0012] In a feasible implementation manner, determining the line width of the target oriented silicon steel plate based on the line left edge pixel subscript set and the line right edge pixel subscript set comprises: performing mean calculations on the line left edge pixel subscript set and the line right edge pixel subscript set, respectively, to obtain the line left edge mean subscript and the line right edge mean subscript; multiplying the absolute difference between the line left edge mean subscript and the line right edge mean subscript by the pixel spacing distance, to obtain the line width of the target oriented silicon steel plate, wherein the pixel spacing distance is obtained by calibrating the high-speed camera using a standard sample of a preset size when the target oriented silicon steel plate is in a stationary state.

[0013] In the second aspect, the present application also provides a device for optimizing the engraving lines of an oriented silicon steel plate, comprising: a two-dimensional array acquisition unit for acquiring a two-dimensional array of the brightness distribution of the surface of a target oriented silicon steel plate; a one-dimensional array acquisition unit for performing array splitting on the two-dimensional array of the brightness distribution of the surface of the plate based on the vertical direction of the engraving line to obtain a one-dimensional array set of brightness, wherein the vertical direction of the engraving line is a direction perpendicular to the engraving line direction, and the one-dimensional array set of brightness includes at least one one-dimensional array of the brightness distribution of the surface of the plate; a table set acquisition unit for determining a set of pixel subscripts of the left edge of the engraving line and a set of pixel subscripts of the right edge of the engraving line based on the one-dimensional array set of brightness; a line width determination unit for determining the line width of the target oriented silicon steel plate based on the set of pixel subscripts of the left edge of the engraving line and the set of pixel subscripts of the right edge of the engraving line; and a line operation adjustment unit for adjusting the line operation parameters performed on the target oriented silicon steel plate based on the difference between the line width and a preset width.

[0014] In a third aspect, the present application further provides an electronic device, comprising: a memory and a processor, wherein the processor is configured to implement the steps of the method for optimizing engraving lines of oriented silicon steel plates described in the first aspect when executing a computer program stored in the memory.

[0015] In a fourth aspect, the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for optimizing engraving lines of oriented silicon steel plates described in the first aspect.

[0016] In a fifth aspect, the present application also provides a computer program product, including a computer program or computer executable instructions, which, when executed by a processor, implements the method for optimizing the engraving lines of oriented silicon steel plates provided in an embodiment of the present application.

[0017] In summary, this application converts the plate surface image into a two-dimensional brightness distribution array, and then splits it into a one-dimensional array. In combination with the image processing algorithm, it can accurately identify the edge of the engraved line and determine the specific width of the engraved line, which not only improves the accuracy of the engraved width measurement, but also reduces human errors; by automatically measuring the engraved line width and comparing it with the preset width, the quality information of the engraved line can be obtained in real time, and then the parameters of the engraved line operation can be automatically adjusted, which greatly improves the automation level of the production line, reduces manual intervention, and enhances the stability and consistency of the production process. In summary, the engraved line optimization method for oriented silicon steel plates provided in this application optimizes the engraved line quality of oriented silicon steel plates through precise image processing and automated feedback adjustment, improves the accuracy and efficiency of production, and ensures the stability of the engraved line operation, thereby achieving the goal of reducing iron loss and improving silicon steel performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0019] Figure 1 A schematic diagram of a process for optimizing the engraving line of an oriented silicon steel plate provided in an embodiment of the present application;

[0020] Figure 2 A schematic diagram of a curve of brightness data provided in an embodiment of the present application before and after smoothing;

[0021] Figure 3 A schematic diagram of selecting a first target inflection point from left gradient inflection points provided in an embodiment of the present application;

[0022] Figure 4 A schematic diagram of selecting a second target inflection point from the right gradient inflection points provided in an embodiment of the present application;

[0023] Figure 5A schematic diagram of a board image provided in an embodiment of the present application;

[0024] Figure 6 A schematic diagram of the positions of the first target inflection point and the second target inflection point in the layout image provided by an embodiment of the present application;

[0025] Figure 7 A schematic diagram of the composition structure of a device for optimizing the engraving line of an oriented silicon steel plate provided in an embodiment of the present application;

[0026] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "is" and "has" and any variations thereof involved in the present application are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] The term "module" or "unit" in this application refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0029] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. In the following description, it is related to "some embodiments", which describes a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0030] See also Figure 1 , Figure 11 is a flow chart of a method for optimizing the engraving line of an oriented silicon steel plate provided in an embodiment of the present application. The method may specifically include the following steps 101 to 105:

[0031] Step 101, obtaining a two-dimensional array of the surface brightness distribution of a target oriented silicon steel plate;

[0032] Specifically, oriented silicon steel refers to a steel plate that has been specially processed, has a clear grain orientation, and has excellent magnetic properties. It is usually used in electrical equipment such as transformers, generators, and motors; target oriented silicon steel plate refers to a specific oriented silicon steel plate that has been processed or is being processed during the production process. The two-dimensional array of plate surface brightness distribution detects the brightness changes on the surface of the target silicon steel plate and stores the brightness data in the form of a two-dimensional coordinate system, where one dimension represents the horizontal direction (X axis) and the other dimension represents the vertical direction (Y axis). For example, each element of the two-dimensional array may represent the brightness value at a certain point (x, y).

[0033] For example, a laser scanner or a high-resolution camera can be used to scan the surface of the target oriented silicon steel plate to obtain a two-dimensional data set with brightness values ​​as elements, where each element represents the brightness intensity of a point on the surface of the steel plate. For example, assuming that the surface size of the steel plate is 1000mm x 1000mm and the scanning resolution is 1mm x 1mm, a 1000x1000 two-dimensional array can be obtained, and each array element corresponds to a brightness value.

[0034] Through the implementation of step 101, high-quality data support is provided for accurately calculating the width of the scribed line and optimizing its parameters.

[0035] Step 102, splitting the two-dimensional array of panel brightness distribution based on the vertical direction of the scribed lines to obtain a one-dimensional array set of brightness, wherein the vertical direction of the scribed lines is a direction perpendicular to the scribed line direction, and the one-dimensional array set of brightness may include at least one one-dimensional array of panel brightness distribution;

[0036] Specifically, the engraving direction refers to the direction in which the engraving operation is actually performed, that is, the direction in which the marks (engraved lines) on the surface of the steel plate are drawn; the engraving vertical direction refers to the direction perpendicular to the engraving (engraving) direction. If the engraving is performed along the horizontal direction of the silicon steel plate, then the engraving vertical direction is the vertical line perpendicular to this direction, that is, the line along the height direction of the steel plate; if the engraving is performed along the vertical direction of the steel plate, then the engraving vertical direction is the horizontal line. The one-dimensional array of the panel brightness distribution is a certain dimension of data (usually brightness information in the horizontal or vertical direction) extracted from the two-dimensional array of the panel brightness distribution; for example, the brightness information of each row or column in the two-dimensional array of the panel brightness distribution can be regarded as a one-dimensional array of the panel brightness distribution; if the two-dimensional array is split in the vertical direction, the brightness data of each column in the two-dimensional array of the panel brightness distribution can constitute a one-dimensional array of the panel brightness distribution; the brightness one-dimensional array set is a set composed of multiple one-dimensional arrays.

[0037] By implementing step 102, the two-dimensional array is split into a one-dimensional array, and the focus is on the direction perpendicular to the scribed line, which can simplify the calculation process and effectively reduce the amount of calculation, which not only improves the processing efficiency, but also focuses more on analyzing the edge information of the scribed line.

[0038] Step 103, determining a set of pixel subscripts at the left edge of a scribed line and a set of pixel subscripts at the right edge of a scribed line based on a one-dimensional array set of brightness;

[0039] Specifically, the pixel subscript set of the left edge of the engraved line refers to the index (i.e., subscript) set of all pixels corresponding to the left edge of the engraved line (or notch) in the board surface brightness distribution; the brightness values ​​of these pixels will change significantly, usually manifested as a transition from a low brightness value (outer area of ​​the notch) to a higher brightness value (inner area of ​​the notch); the pixel subscript set of the right edge of the engraved line refers to the index set of all pixels corresponding to the right edge of the engraved line in the board surface brightness distribution.

[0040] By implementing step 103, the left and right edge pixel subscripts of the scribed line are determined by using a brightness one-dimensional array set, so that the boundary position of the scribed line can be accurately defined, thereby avoiding noise interference and improving detection accuracy.

[0041] Step 104, determining the scribe line width of the target oriented silicon steel plate based on the scribe line left edge pixel subscript set and the scribe line right edge pixel subscript set;

[0042] Specifically, the line width refers to the physical width of the notch on the surface of the target oriented silicon steel plate, that is, the distance from the left edge to the right edge of the line. This width is determined by calculating the difference between the pixel subscript set of the left edge of the line and the pixel subscript set of the right edge of the line; for example, the subscript mean in the pixel subscript set of the left edge of the line is 100, and the subscript mean in the pixel subscript set of the right edge of the line is 150, then the width of the line is 150-100=50 pixels.

[0043] By implementing step 104 and combining the pixel subscript sets of the left and right edges to accurately calculate the line width, it can be ensured that the calculated line width conforms to the actual situation and avoids errors caused by manual measurement or low-precision equipment in traditional methods.

[0044] Step 105, adjusting the marking operation parameters for the target oriented silicon steel plate based on the difference between the marking width and the preset width;

[0045] Specifically, the preset width refers to the ideal line width pre-set according to the process requirements or target product specifications, in order to ensure that the line can achieve the optimized effect, thereby achieving the standard width of the goals of reducing iron loss and improving magnetic properties. The line engraving operation parameters refer to the key operating variables or technical parameters that need to be controlled during the scoring (engraving) operation, which may include the depth of the line, the speed of the line, the frequency of the line, the laser intensity of the line, etc. These parameters will affect the quality and width of the final line; for example, the line engraving process is completed by laser scanning, then the line engraving operation parameters may include laser intensity, laser scanning speed, laser focal length, etc.

[0046] For example, if there is a difference between the measured line width and the preset width, the difference between them needs to be calculated: for example, if the actual line width is 48 pixels and the preset width is 50 pixels, the calculated line width difference is -2 pixels, which means that the line is too narrow; to this end, the laser intensity can be increased (for example, from 80% to 90%) or the line speed can be slowed down (for example, from 10 mm / s to 8 mm / s) to increase the line width until the actual line width is close to the preset width (50 pixels).

[0047] By implementing step 105, the real-time optimization of the engraving quality is ensured, and deviations can be corrected in time during the production process to prevent the engraving width from deviating from the standard range, thereby ensuring product quality, reducing resource waste, and improving production efficiency.

[0048] In summary, the embodiment of the present application converts the plate surface image into a two-dimensional brightness distribution array, and then splits it into a one-dimensional array, and combines it with an image processing algorithm to accurately identify the edge of the engraved line and determine the specific width of the engraved line, which not only improves the accuracy of the engraved width measurement, but also reduces human errors; by automatically measuring the engraved line width and comparing it with the preset width, the quality information of the engraved line can be obtained in real time, and then the parameters of the engraved line operation can be automatically adjusted, which greatly improves the automation level of the production line, reduces manual intervention, and enhances the stability and consistency of the production process. In summary, the engraved line optimization method for oriented silicon steel plates provided in the embodiment of the present application optimizes the engraved line quality of oriented silicon steel plates through precise image processing and automated feedback adjustment, improves the accuracy and efficiency of production, and ensures the stability of the engraved line operation, thereby achieving the goal of reducing iron loss and improving silicon steel performance.

[0049] In some embodiments, the aforementioned step 103 may include: based on a preset maximum screening threshold, performing a local maximum search on the one-dimensional array of the panel brightness distribution to obtain a local maximum subscript; performing a gradient calculation on the one-dimensional array of the panel brightness distribution to obtain a brightness gradient array; based on the brightness gradient array, determining the left inflection point that is closer to the local maximum subscript as the left gradient inflection point, and determining the right inflection point that is closer to the local maximum subscript as the right gradient inflection point; determining the left edge pixel subscript set of the engraved line based on the left gradient inflection point, and determining the right edge pixel subscript set of the engraved line based on the right gradient inflection point.

[0050] Specifically, the preset maximum screening threshold is a critical value for calibrating the brightness of the board surface. The setting of this threshold is based on the statistical characteristics of the board surface brightness, and is usually calculated by statistically analyzing the brightness data in the one-dimensional array of the board surface brightness distribution; for example, the brightness data of the one-dimensional array of the board surface brightness distribution is [10,20,30,25,30,100,20,11,6], and its mean is calculated to be (10+20+30+25+30+100+20+11+6) / 9=28. The maximum value is found to be 100, and the preset maximum screening threshold can be determined to be 100-28=72. The local maximum refers to a brightness value within a certain range of the brightness distribution, which is greater than the values ​​of its adjacent positions, and is a local brightness peak. The local maximum usually corresponds to a middle area or a highlighted part of the notch; the local maximum subscript refers to the array index position corresponding to the local maximum in the one-dimensional array of the board surface brightness distribution. The brightness gradient array is obtained by calculating the rate of change (i.e., the brightness difference) between the brightness of each two adjacent pixels in the one-dimensional array of the panel brightness distribution; the magnitude of the gradient reflects the rate of brightness change, and the place with a larger gradient value usually corresponds to the edge of the engraved line, because the edge of the engraved line is often accompanied by rapid changes in brightness. The left gradient inflection point indicates the brightness gradient inflection point on the left side of the local maximum; the right gradient inflection point indicates the brightness gradient inflection point on the right side of the local maximum.

[0051] Through the implementation of the above-mentioned embodiments, the errors caused by uneven brightness changes or noise influences are effectively avoided by utilizing local maximum search and gradient calculation. Especially in a high-speed production environment, the left and right edge pixels of the engraved lines can be accurately located, thus avoiding the ambiguity and errors of traditional manual recognition and ensuring the accuracy of edge detection.

[0052] In some embodiments, the aforementioned local maximum search for the one-dimensional array of panel surface brightness distribution based on a preset maximum screening threshold to obtain the local maximum subscript may include: smoothing and denoising the one-dimensional array of panel surface brightness distribution to obtain a smoothed one-dimensional array of panel surface brightness; based on the preset maximum screening threshold, local maximum search for the smoothed one-dimensional array of panel surface brightness to obtain the local maximum subscript.

[0053] Specifically, smoothing and denoising is an image processing technology that aims to eliminate noise or abnormal fluctuations in the signal; in the one-dimensional array of the brightness distribution of the board surface, there may be local fluctuations caused by factors such as background noise or uneven illumination. These fluctuations do not reflect the actual notch information. By smoothing the brightness data, the impact of these noises can be reduced, making subsequent feature extraction more accurate; the smoothing and denoising methods used in the embodiments of the present application may include mean filtering, median filtering, or Gaussian filtering. The smoothed one-dimensional array of board surface brightness refers to the brightness array after smoothing and denoising. Compared with the original brightness array, the smoothed array will have a smoother brightness change, reducing brightness fluctuations caused by noise or other non-notch factors.

[0054] For example, Figure 2 The figure shows the brightness data before and after smoothing and denoising. In the figure, the horizontal axis represents the array subscript of the brightness data, the vertical axis represents the brightness value of the brightness data, the red line represents the brightness data before smoothing and denoising, and the blue line represents the brightness data after smoothing and denoising.

[0055] Through the implementation of the above embodiment, the one-dimensional array of the panel brightness distribution is smoothed and denoised, which can remove the noise in the original image caused by surface roughness or external interference, improve the accuracy of local maximum search, reduce the risk of false detection or missed detection, and further improve the reliability of width detection results.

[0056] In some embodiments, the aforementioned determination of the pixel subscript set of the left edge of the engraved line based on the left gradient inflection point, and the determination of the pixel subscript set of the right edge of the engraved line based on the right gradient inflection point may include: performing curve fitting based on the left gradient inflection point to obtain a first fitting function; based on the first fitting function and a first preset offset coefficient, screening out a first target inflection point among the left gradient inflection points, and determining the subscript of the first target inflection point as an element in the pixel subscript set of the left edge of the engraved line; performing curve fitting based on the right gradient inflection point to obtain a second fitting function; based on the second fitting function and the second preset offset coefficient, screening out a second target inflection point among the right gradient inflection points, and determining the subscript of the second target inflection point as an element in the pixel subscript set of the right edge of the engraved line.

[0057] Specifically, the first fitting function refers to a function model obtained by curve fitting the data based on the coordinate data of the left gradient inflection point through a mathematical method (such as the least square method); the first preset offset coefficient is determined by empirical data or experiments, and is used to fine-tune the position of the fitting curve so as to better match the actual notch edge; the first target inflection point refers to the inflection point of the actual edge position determined after curve fitting and offset coefficient adjustment based on the left gradient inflection point; the left edge pixel subscript set of the engraved line refers to the set of positions of all pixels belonging to the left edge of the notch determined according to the left gradient inflection point and the target inflection point after fitting. The second fitting function refers to a function model obtained by curve fitting the data based on the coordinate data of the right gradient inflection point through a mathematical method; the second preset offset coefficient is determined by empirical data or experiments, and is used to fine-tune the position of the fitting curve so as to better match the actual notch edge; the second target inflection point refers to the inflection point of the actual edge position determined after curve fitting and offset coefficient adjustment based on the right gradient inflection point; the right edge pixel subscript set of the engraved line refers to the set of positions of all pixels belonging to the right edge of the notch determined according to the right gradient inflection point and the target inflection point after fitting.

[0058] For example, Figure 3 The point in the middle represents the left gradient inflection point, the red line represents the first fitting function curve, and the green and blue lines represent the range of the first target inflection point determined after adjustment by the first preset offset coefficient (the left gradient inflection point below the green line and above the blue line is the first target inflection point). Figure 4 The point in the middle represents the right gradient inflection point, the red line represents the second fitting function curve, and the green and blue lines represent the range of the second target inflection point determined after adjustment by the second preset offset coefficient (the right gradient inflection point below the green line and above the blue line is the second target inflection point).

[0059] By implementing the above embodiment, fitting the curve and applying the preset offset coefficient, the determination of the edge of the scribed line can be refined, the edge position of the scribed line can be accurately identified and adjusted, and the measurement accuracy of the scribed line width can be further improved.

[0060] In some embodiments, the aforementioned step 102 may include: based on the vertical direction of the grating line, the panel surface brightness distribution two-dimensional array is split according to a preset pixel interval to obtain a brightness one-dimensional array set, wherein the preset pixel interval is an integer greater than or equal to 0.

[0061] Specifically, the preset pixel interval refers to the interval size of the array segmentation unit (ie, step length) selected each time when the two-dimensional array of panel brightness distribution is segmented.

[0062] For example, if the preset pixel interval is 0, it means that the brightness data is extracted one by one in the order of each pixel to form a one-dimensional array; if the preset pixel interval is 1, it means that a brightness value is extracted for every other pixel, that is, a brightness value is selected from every other pixel position in the two-dimensional array to form a one-dimensional array.

[0063] Through the implementation of the above-mentioned embodiments, the pixel interval can be adjusted, and the accuracy of data segmentation can be optimized according to different steel plate thicknesses, surface finishes or production requirements; a larger pixel interval is suitable for low-precision requirements or rapid detection, while a smaller pixel interval is suitable for scenarios with high-precision requirements, ensuring the wide applicability of the method; a reasonable pixel interval can help better capture the details of the engraved lines, especially when the engraved lines are thinner or more complex, the split data set can provide more detailed engraved line width information, thereby improving the accuracy of engraved line width detection and avoiding errors caused by excessive or insufficient splitting; unnecessary calculations can be reduced while ensuring accuracy.

[0064] In some embodiments, the aforementioned step 101 may include: collecting a plate surface image by a high-speed camera perpendicular to the target oriented silicon steel plate; performing pixel brightness array conversion on the plate surface image to obtain a two-dimensional array of plate surface brightness distribution.

[0065] Specifically, the plate surface image refers to the image data obtained by photographing the target oriented silicon steel plate with a high-speed camera. The actual collected plate surface image is as follows: Figure 5 As shown, Figure 6 The positions of the first target inflection point and the second target inflection point in the layout image are shown with white pixels.

[0066] Through the implementation of the above-mentioned embodiments, various irregularities or reflection interferences may exist on the surface of the steel plate, and traditional measurement methods may be difficult to deal with. The embodiments of the present application utilize a high-speed camera perpendicular to the target oriented silicon steel plate to quickly capture and process these irregularities, provide more detailed and accurate brightness distribution data, and ensure the high quality of image acquisition and brightness distribution data.

[0067] In some embodiments, the aforementioned step 104 may include: performing mean calculations on the set of pixel subscripts at the left edge of the scribed line and the set of pixel subscripts at the right edge of the scribed line, respectively, to obtain the mean subscripts of the left edge of the scribed line and the mean subscripts of the right edge of the scribed line; multiplying the absolute difference between the mean subscripts of the left edge of the scribed line and the mean subscripts of the right edge of the scribed line by the pixel spacing distance to obtain the line width of the target oriented silicon steel plate, wherein the pixel spacing distance is obtained by calibrating the high-speed camera using a standard sample of a preset size when the target oriented silicon steel plate is in a stationary state.

[0068] Specifically, the mean subscript of the left edge of the engraved line is the average value of all pixel subscripts in the set of pixel subscripts of the left edge of the engraved line, and the average value representing the position of the left edge of the engraved line is obtained; the mean subscript of the right edge of the engraved line is similar to the mean of the left edge of the engraved line, and is an average value representing the position of the right edge of the engraved line. The pixel spacing distance refers to the actual physical distance represented by a unit pixel when the target oriented silicon steel plate is in a static state. It is obtained by calibrating the high-speed camera, usually using a standard sample of a preset size (i.e., a physical ruler of a known length) for calibration; through the calibration of the standard sample, it can be known how much actual physical distance each pixel represents.

[0069] For example, the mean subscript of the left edge of the scribed line is 13, the mean subscript of the right edge of the scribed line is 33, and the pixel pitch distance is 0.02 mm / pixel, then the scribed line width is |33-13|×0.02=0.4, that is, the final scribed line width is 0.4 mm.

[0070] Through the implementation of the above-mentioned embodiment, the mean of the subscript sets on the left and right edges of the scale line is calculated respectively, which can reduce the influence of single pixel error on the scale line width calculation, not only improve the accuracy of detection, but also ensure that stable measurement results can be obtained under dynamic production or low resolution conditions; and the high-speed camera is calibrated using a standard sample of preset size when the steel plate is stationary, ensuring the accuracy of the pixel spacing.

[0071] Furthermore, as an implementation of the aforementioned method embodiment, the present application also provides a device for optimizing the engraving lines of an oriented silicon steel plate, which is used to implement the aforementioned method embodiment. The device embodiment corresponds to the aforementioned method embodiment. For ease of reading, the present device embodiment for optimizing the engraving lines of an oriented silicon steel plate will no longer repeat the details of the aforementioned method embodiment one by one, but it should be clear that the device in the embodiment of the present application can correspond to and implement all the contents of the aforementioned method embodiment. Figure 7As shown, the oriented silicon steel plate engraving line optimization device 20 comprises: a two-dimensional array acquisition unit 201, a one-dimensional array acquisition unit 202, a following table set acquisition unit 203, an engraving line width determination unit 204 and an engraving line operation adjustment unit 205, wherein the two-dimensional array acquisition unit 201 is used to acquire a two-dimensional array of plate surface brightness distribution of the target oriented silicon steel plate; the one-dimensional array acquisition unit 202 is used to perform array splitting on the two-dimensional array of plate surface brightness distribution based on the vertical direction of the engraving line to obtain a one-dimensional array set of brightness, wherein the vertical direction of the engraving line is perpendicular to the engraving line direction. In the vertical direction, the brightness one-dimensional array set may include at least one one-dimensional array of panel brightness distribution; a table set acquisition unit 203 is used to determine the left edge pixel subscript set and the right edge pixel subscript set of the engraved line based on the brightness one-dimensional array set; a line width determination unit 204 is used to determine the line width of the target oriented silicon steel plate based on the left edge pixel subscript set and the right edge pixel subscript set of the engraved line; a line operation adjustment unit 205 is used to adjust the line operation parameters performed on the target oriented silicon steel plate based on the difference between the line width and the preset width.

[0072] In some embodiments, the following table set acquisition unit 203 is also used to perform local maximum search on the one-dimensional array of panel brightness distribution based on a preset maximum screening threshold to obtain the local maximum subscript; perform gradient calculation on the one-dimensional array of panel brightness distribution to obtain a brightness gradient array; based on the brightness gradient array, determine the left inflection point that is closer to the local maximum subscript as the left gradient inflection point, and determine the right inflection point that is closer to the local maximum subscript as the right gradient inflection point; determine the left edge pixel subscript set of the engraved line based on the left gradient inflection point, and determine the right edge pixel subscript set of the engraved line based on the right gradient inflection point.

[0073] In some embodiments, the following table set acquisition unit 203 is also used to perform smoothing and denoising on the one-dimensional array of panel brightness distribution to obtain a smoothed one-dimensional array of panel brightness; based on a preset maximum value screening threshold, perform local maximum value search on the smoothed one-dimensional array of panel brightness to obtain a local maximum value subscript.

[0074] In some embodiments, the following table set acquisition unit 203 is also used to perform curve fitting based on the left gradient inflection point to obtain a first fitting function; based on the first fitting function and the first preset offset coefficient, filter out a first target inflection point among the left gradient inflection points, and determine the subscript of the first target inflection point as an element in the subscript set of the left edge pixels of the engraved line; perform curve fitting based on the right gradient inflection point to obtain a second fitting function; based on the second fitting function and the second preset offset coefficient, filter out a second target inflection point among the right gradient inflection points, and determine the subscript of the second target inflection point as an element in the subscript set of the right edge pixels of the engraved line.

[0075] In some embodiments, the one-dimensional array acquisition unit 202 is also used to split the two-dimensional array of panel brightness distribution according to a preset pixel interval based on the vertical direction of the grating line to obtain a one-dimensional brightness array set, wherein the preset pixel interval is an integer greater than or equal to 0.

[0076] In some embodiments, the two-dimensional array acquisition unit 201 is also used to collect the board surface image through a high-speed camera perpendicular to the target oriented silicon steel plate; perform pixel brightness array conversion on the board surface image to obtain a two-dimensional array of board surface brightness distribution.

[0077] In some embodiments, the line width determination unit 204 is further used to calculate the mean of the pixel subscript set of the left edge of the line and the pixel subscript set of the right edge of the line, respectively, to obtain the mean subscript of the left edge of the line and the mean subscript of the right edge of the line; the absolute difference between the mean subscript of the left edge of the line and the mean subscript of the right edge of the line is multiplied by the pixel spacing distance to obtain the line width of the target oriented silicon steel plate, wherein the pixel spacing distance is obtained by calibrating the high-speed camera using a standard sample of a preset size when the target oriented silicon steel plate is in a stationary state.

[0078] The present application also provides a computer-readable storage medium, which stores computer-executable instructions or computer programs. When the computer-executable instructions or computer programs are executed by a processor, the processor will be caused to execute any step of the method for optimizing the engraving line of oriented silicon steel plates provided in the present application.

[0079] In some embodiments, the computer-readable storage medium may be a memory such as RAM, read-only memory (ROM), flash memory, magnetic surface memory, optical disk, or compact disc read-only memory (CD-ROM); or it may be various devices including one or any combination of the above memories.

[0080] In some embodiments, computer executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0081] In some embodiments, computer-executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file storing other programs or data, for example, in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0082] In some embodiments, computer executable instructions may be deployed to be executed on one electronic device, or on multiple electronic devices located at one site, or on multiple electronic devices distributed at multiple sites and interconnected by a communication network.

[0083] like Figure 8 As shown, the present application also provides an electronic device 30, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor, and when the processor 320 executes the computer program 311, any step of the above-mentioned method for optimizing the engraving line of the oriented silicon steel plate is implemented.

[0084] The present application also provides a computer program product, which includes a computer program or a computer executable instruction, and the computer program or the computer executable instruction is stored in a computer-readable storage medium. The processor of the electronic device reads the computer program or the computer executable instruction from the computer-readable storage medium, and the processor executes the computer program or the computer executable instruction, so that the electronic device executes any step of the above-mentioned method for optimizing the engraving line of the oriented silicon steel plate of the present application.

[0085] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for optimizing the engraving line of an oriented silicon steel plate, characterized in that: include: Obtaining a two-dimensional array of brightness distribution of a target oriented silicon steel plate; Based on the vertical direction of the scribed lines, the two-dimensional array of panel brightness distribution is split into arrays to obtain a one-dimensional array set of brightness, wherein the vertical direction of the scribed lines is a direction perpendicular to the scribed line direction, and the one-dimensional array set of brightness includes at least one one-dimensional array of panel brightness distribution; Based on the brightness one-dimensional array set, determine a set of pixel subscripts at the left edge of the engraved line and a set of pixel subscripts at the right edge of the engraved line; Determining the scribe line width of the target oriented silicon steel plate based on the scribe line left edge pixel subscript set and the scribe line right edge pixel subscript set; Based on the difference between the engraving width and the preset width, the engraving operation parameters for the target oriented silicon steel sheet are adjusted.

2. The method according to claim 1, characterized in that The step of determining a set of pixel subscripts at the left edge of a scribed line and a set of pixel subscripts at the right edge of a scribed line based on the one-dimensional array set of brightness comprises: Based on a preset maximum value screening threshold, a local maximum value search is performed on the one-dimensional array of the panel brightness distribution to obtain a local maximum value subscript; Performing gradient calculation on the one-dimensional array of panel brightness distribution to obtain a brightness gradient array; Based on the brightness gradient array, determining the left inflection point closer to the local maximum subscript as the left gradient inflection point, and determining the right inflection point closer to the local maximum subscript as the right gradient inflection point; The pixel subscript set of the left edge of the scribed line is determined based on the left gradient inflection point, and the pixel subscript set of the right edge of the scribed line is determined based on the right gradient inflection point.

3. The method according to claim 2, characterized in that The method of searching for a local maximum value on the one-dimensional array of the panel brightness distribution based on a preset maximum value screening threshold value to obtain a local maximum value subscript includes: Performing smoothing and denoising processing on the one-dimensional array of panel surface brightness distribution to obtain a smoothed one-dimensional array of panel surface brightness; Based on a preset maximum screening threshold, a local maximum search is performed on the panel surface brightness smoothing one-dimensional array to obtain a local maximum index.

4. The method according to claim 2, characterized in that: The step of determining the pixel subscript set at the left edge of the scribed line based on the left gradient inflection point, and determining the pixel subscript set at the right edge of the scribed line based on the right gradient inflection point, comprises: Perform curve fitting based on the left gradient inflection point to obtain a first fitting function; Based on the first fitting function and the first preset offset coefficient, a first target inflection point among the left gradient inflection points is screened out, and the subscript of the first target inflection point is determined as an element in the subscript set of the left edge pixel of the scribed line; Perform curve fitting based on the right gradient inflection point to obtain a second fitting function; Based on the second fitting function and the second preset offset coefficient, a second target inflection point among the right gradient inflection points is screened out, and the subscript of the second target inflection point is determined as an element in the subscript set of the right edge pixel of the scribed line.

5. The method according to any one of claims 1 to 4, characterized in that: Based on the vertical direction of the scribed lines, the two-dimensional array of panel brightness distribution is split into arrays to obtain a one-dimensional array set of brightness, including: Based on the vertical direction of the scribed lines, the panel surface brightness distribution two-dimensional array is split according to a preset pixel interval to obtain a brightness one-dimensional array set, wherein the preset pixel interval is an integer greater than or equal to 0.

6. The method according to any one of claims 1 to 4, characterized in that: The method of obtaining a two-dimensional array of the surface brightness distribution of a target oriented silicon steel plate comprises: Collecting a plate surface image by a high-speed camera perpendicular to the target oriented silicon steel plate; The panel surface image is subjected to pixel brightness array conversion to obtain a two-dimensional array of panel surface brightness distribution.

7. The method according to claim 6, characterized in that The step of determining the scribe line width of the target oriented silicon steel plate based on the scribe line left edge pixel subscript set and the scribe line right edge pixel subscript set comprises: Calculate the mean of the pixel subscript set at the left edge of the scribed line and the pixel subscript set at the right edge of the scribed line respectively, to obtain the mean subscript of the left edge of the scribed line and the mean subscript of the right edge of the scribed line; The absolute difference between the mean subscript of the left edge of the engraved line and the mean subscript of the right edge of the engraved line is multiplied by the pixel spacing distance to obtain the engraved line width of the target oriented silicon steel plate, wherein the pixel spacing distance is obtained by calibrating the high-speed camera using a standard sample of a preset size when the target oriented silicon steel plate is in a stationary state.

8. A device for optimizing the engraving line of an oriented silicon steel plate, characterized in that: include: A two-dimensional array acquisition unit, used to acquire a two-dimensional array of brightness distribution of a target oriented silicon steel plate; A one-dimensional array acquisition unit, used for performing array splitting on the two-dimensional array of panel brightness distribution based on the vertical direction of the scribed lines to obtain a one-dimensional array set of brightness, wherein the vertical direction of the scribed lines is a direction perpendicular to the scribed line direction, and the one-dimensional array set of brightness includes at least one one-dimensional array of panel brightness distribution; A table set acquisition unit is used to determine a set of pixel subscripts at the left edge of a scribed line and a set of pixel subscripts at the right edge of a scribed line based on the one-dimensional array set of brightness; A scribe line width determination unit, configured to determine the scribe line width of the target oriented silicon steel plate based on the scribe line left edge pixel subscript set and the scribe line right edge pixel subscript set; The scoring operation adjustment unit is used to adjust the scoring operation parameters performed on the target oriented silicon steel plate based on the difference between the scoring width and the preset width.

9. An electronic device, comprising: A memory and a processor, wherein the processor is used to implement the steps of the method for optimizing the engraving line of a oriented silicon steel plate as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for optimizing the engraving line of a grain-oriented silicon steel sheet according to any one of claims 1 to 7 are implemented.

Images