Electrical steel color evaluation method and related equipment

Abstract

The invention discloses an electrical steel color evaluation method and related equipment, relates to the field of industrial detection automation, and mainly aims to solve the problems of large subjective error and lack of objective quantitative standards during manual visual detection of the coating color of electrical steel. The method comprises the following steps: respectively constructing different electrical steel surface color standards based on different electrical steel types; color data of the target electrical steel is detected, and the color data comprises an actual brightness value, an actual red-green deviation value and an actual yellow-blue deviation value; and evaluating the color of the target electrical steel based on a comparison result of an electrical steel surface color standard corresponding to the electrical steel type of the target electrical steel and the color data. The method is used for the electrical steel color evaluation process.

Description

Technical Field

[0001] This invention relates to the field of industrial inspection automation, and in particular to a method and related equipment for evaluating the color of electrical steel. Background Technology

[0002] As the core soft magnetic material for motor and transformer cores, electrical steel's surface insulating coating directly affects key indicators such as core lamination performance, interlayer resistance, and corrosion resistance. Among these, coating adhesion is a core criterion for product release.

[0003] However, traditional testing methods have serious flaws: according to national standards and industry-standard methods, the sample must be bent 180° and the coating peeled off with tape, and then rated by visually comparing it with standard charts or textual descriptions (such as "no peeling" or "rare peeling"). This method relies on subjective human judgment, so the industry has long faced the pain points of large subjective errors and lack of objective quantitative standards when manually visually inspecting coating adhesion. There is an urgent need for a testing method that is cost-effective, easy to operate, and can output continuous quantitative results to replace the subjective rating system. Summary of the Invention

[0004] In view of the above problems, the present invention provides a method and related equipment for evaluating the color of electrical steel, the main purpose of which is to solve the problems of large subjective error and lack of objective quantitative standards in the manual visual inspection of the color of electrical steel coating.

[0005] To solve at least one of the above-mentioned technical problems, in a first aspect, the present invention provides a color evaluation method for electrical steel. square Law The method includes:

[0006] Different surface color standards for electrical steel are constructed based on different types of electrical steel;

[0007] The color data of the target electrical steel is detected, wherein the color data includes the actual brightness value, the actual red-green bias value, and the actual yellow-blue bias value;

[0008] The color of the target electrical steel is evaluated based on the comparison between the surface color standard of the electrical steel corresponding to the electrical steel type and the color data.

[0009] Optionally, the construction of different electrical steel surface color standards based on different types of electrical steel includes:

[0010] Ideal electrical steel samples were selected based on the type of electrical steel.

[0011] The color standard value and allowable deviation range of the ideal electrical steel sample are determined to construct the surface color standard of electrical steel.

[0012] Optionally, the color standard values ​​include brightness standard values, red-green bias standard values, and yellow-blue bias standard values;

[0013] The allowable deviation range includes the allowable deviation range for brightness, the allowable deviation range for red-green bias, and the allowable deviation range for yellow-blue bias.

[0014] Optionally, the color data of the target electrical steel can be detected, including:

[0015] The actual brightness value, actual red-green bias value, and actual yellow-blue bias value of the target electrical steel are detected.

[0016] Optionally, the above methods also include:

[0017] The brightness deviation value is determined based on the difference between the actual brightness value of the target electrical steel and the brightness standard value.

[0018] The red-green bias deviation value is determined based on the difference between the actual red-green bias value of the target electrical steel and the standard red-green bias value.

[0019] The yellow-blue bias deviation value is determined based on the difference between the actual yellow-blue bias value of the target electrical steel and the standard value of the yellow-blue bias.

[0020] Optionally, the above methods also include:

[0021] The total color difference is determined based on the brightness deviation value, the red-green bias deviation value, and the yellow-blue bias deviation value.

[0022] Optionally, the comparison results include the brightness deviation value, the red-green bias deviation value, the yellow-blue bias deviation value, and the total color difference. The evaluation of the color of the target electrical steel based on the comparison results of the electrical steel surface color standard and color data corresponding to the electrical steel type includes:

[0023] The color of the target electrical steel is evaluated based on the comparison results of the brightness deviation value and the brightness allowable deviation range, the comparison results of the red-green bias deviation value and the red-green bias allowable deviation range, the comparison results of the yellow-blue bias deviation value and the yellow-blue bias allowable deviation range, and the total color difference.

[0024] Secondly, embodiments of the present invention also provide an electrical steel color evaluation device, comprising:

[0025] The building blocks are used to construct different surface color standards for electrical steel based on different types of electrical steel.

[0026] The detection unit is used to detect the color data of the target electrical steel, wherein the color data includes the actual brightness value, the actual red-green bias value, and the actual yellow-blue bias value;

[0027] The evaluation unit is used to evaluate the color of the target electrical steel based on the comparison result between the electrical steel surface color standard corresponding to the electrical steel type of the target electrical steel and the color data.

[0028] To achieve the above objectives, according to a third aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium comprising a stored program, wherein, when the program is executed by a processor, the steps of the above-described electrical steel color evaluation method are implemented.

[0029] To achieve the above objectives, according to a fourth aspect of the present invention, an electronic device is provided, comprising at least one processor and at least one memory connected to the processor; wherein the processor is configured to invoke program instructions in the memory to execute the steps of the above-described electrical steel color evaluation method.

[0030] By employing the above technical solution, the electrical steel color evaluation method and related equipment provided by this invention address the problems of large subjective errors and lack of objective quantitative standards in manual visual inspection of electrical steel coating colors. This invention constructs different electrical steel surface color standards based on different electrical steel types; detects the color data of the target electrical steel, wherein the color data includes actual brightness values, actual red-green bias values, and actual yellow-blue bias values; and evaluates the color of the target electrical steel based on the comparison results between the electrical steel surface color standards corresponding to the electrical steel type and the color data. In the above solution, firstly, a dedicated color standard library is constructed for the differences in electrical steel types; secondly, objective color data acquisition is achieved through the photoelectric conversion principle of a colorimeter; and finally, objectification of evaluation is achieved based on a type-adaptive comparison mechanism. By establishing a color standard database that strictly matches electrical steel types and based on a type-adaptive optical parameter comparison mechanism, subjective color evaluation is transformed into objective quantitative analysis, thereby significantly reducing the subjectivity and standard ambiguity of manual visual inspection.

[0031] Correspondingly, the electrical steel color evaluation device, equipment, and computer-readable storage medium provided in the embodiments of the present invention also have the above-mentioned technical effects.

[0032] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0033] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0034] Figure 1 A schematic flowchart of a color evaluation method for electrical steel provided by an embodiment of the present invention is shown;

[0035] Figure 2 This diagram shows a schematic block diagram of the composition of an electrical steel color evaluation device provided in an embodiment of the present invention;

[0036] Figure 3 This diagram illustrates the composition of an electronic device for evaluating the color of electrical steel according to an embodiment of the present invention. Detailed Implementation

[0037] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0038] To address the issues of significant subjective error and lack of objective quantitative standards in manual visual inspection of electrical steel coating color, this invention provides a method for evaluating the color of electrical steel, such as... Figure 1 As shown, the method includes:

[0039] S101. Construct different surface color standards for electrical steel based on different types of electrical steel;

[0040] For example, firstly, this application constructs a dedicated color standard library for the differences in electrical steel types. The principle is based on the fact that differences in the reflective properties of the substrate, coating composition, and processing of different types of electrical steel lead to different optical characteristics on the surface (for example, M0 type coatings may have a cooler tone, while M1 type may have a warmer tone). By pre-setting target parameters for each type (such as M0, M1, etc.)—brightness value (L), red-green bias value (A), and yellow-blue bias value (B)—a type-specific set of reference optical features is formed. The essence of this step is to abstract the differences in the optical properties of the material into quantifiable color space coordinates (using the CIE Lab* color model), providing an objective reference system for type adaptation in subsequent detection, and avoiding misjudgment due to a single standard caused by differences in substrate or coating.

[0041] In one embodiment, constructing different electrical steel surface color standards based on different types of electrical steel includes:

[0042] Ideal electrical steel samples were selected based on the type of electrical steel.

[0043] The color standard value and allowable deviation range of the ideal electrical steel sample are determined to construct the surface color standard of electrical steel.

[0044] For example, "electrical steel type" refers to different coating codes for different types of electrical steel (such as M0, M1, M1B, etc.). Differences in substrate characteristics, coating composition, and processes lead to different surface optical properties. An ideal electrical steel sample refers to a benchmark sample that conforms to the coating process specifications and passes all performance tests, representing the surface color state of this type of electrical steel under optimal process conditions. Color standard values ​​include three key optical parameters: brightness standard value: representing the lightness or darkness of light reflected from the coating surface (higher values ​​are closer to white, lower values ​​are closer to black); red-green bias standard value: representing the baseline tendency of the coating color in the red-green spectrum (larger positive values ​​are more reddish, larger negative values ​​are more greenish); yellow-blue bias standard value: representing the baseline tendency of the coating color in the yellow-blue spectrum (larger positive values ​​are more yellowish, larger negative values ​​are more bluish). The allowable deviation range refers to the acceptable fluctuation range of the color standard values, used to define the flexible boundaries of acceptable colors.

[0045] The core principle of the above scheme lies in isolating the interference of material differences on color evaluation through a type-specific benchmark calibration method. The surface condition of the electrical steel substrate (such as the smoothness of cold-rolled steel or the roughness of hot-rolled steel) significantly affects the light reflection characteristics, while the coating composition (such as chromium-containing / chromium-free formulation) determines the spectral absorption rate. If a single color standard is used, the same coating on different substrates will be perceived as different colors by the human eye due to differences in reflectivity (for example, a coating on a smooth substrate may appear brighter), leading to misjudgment during manual visual rating.

[0046] Ideal samples were selected based on the type of electrical steel: For each type (e.g., M0, M1B), samples with stable processes were screened, ensuring that their coating thickness, compositional uniformity, and surface smoothness met optimal standards, thus guaranteeing the authenticity of the color reference. The CIE Lab* color model was used to decouple the differences in the optical properties of the materials into independent spectral coordinates, avoiding interference from substrate reflections on the true expression of the coating color. For example, for M1B type, due to the strong light absorption of the substrate, a sample with higher brightness was selected to offset the substrate's influence.

[0047] Determine the color standard value and allowable deviation range: The brightness, red-green bias, and yellow-blue bias data of an ideal sample are collected using the photoelectric conversion principle of a colorimeter. The statistical mean of these values ​​is set as the standard value, and the allowable deviation is set based on the process fluctuation range (such as baking temperature tolerance). The principle is to quantify color attributes into calculable deviation vectors (such as ΔL, ΔA, ΔB), allowing subsequent detection to clearly identify process defects (such as insufficient baking leading to a bluish bias) through the direction of the deviation (e.g., an excessively large positive ΔA value indicates a red bias) and its degree, while also accommodating reasonable process fluctuations.

[0048] The above solution reduces subjective errors through a type-bound benchmark construction mechanism: it transforms the vague descriptions of "reddish" and "dark" to quantitative deviation values ​​of brightness, red-green bias, and yellow-blue bias, avoiding interference from lighting conditions and visual fatigue; it improves standard adaptability, making it compatible with the optical characteristics of different substrate-coating combinations (e.g., high-reflectivity substrates require a lower brightness standard value), avoiding false detections caused by a "one-size-fits-all" standard; and it supports automated judgment by providing clear physical definitions for standard values ​​and deviation ranges, enabling photoelectric measurement equipment to directly call type-matched benchmark data to achieve objective judgment of coating color compliance.

[0049] In one embodiment, the color standard values ​​include a brightness standard value, a red-green bias standard value, and a yellow-blue bias standard value;

[0050] The allowable deviation range includes the allowable deviation range for brightness, the allowable deviation range for red-green bias, and the allowable deviation range for yellow-blue bias.

[0051] For example, the brightness standard value refers to the baseline quantization value of the light intensity reflected by the coating surface, representing the light reflection intensity range from pure black (low value) to pure white (high value). The red-green bias standard value refers to the baseline quantization value of the coating color's tendency along the red-green spectral axis; a positive value indicates a tendency to shift towards the red spectrum, and a negative value indicates a tendency to shift towards the green spectrum. The yellow-blue bias standard value refers to the baseline quantization value of the coating color's tendency along the yellow-blue spectral axis; a positive value indicates a tendency to shift towards the yellow spectrum, and a negative value indicates a tendency to shift towards the blue spectrum. The allowable fluctuation range of brightness standard values ​​defines the acceptable boundary for light intensity. The allowable fluctuation range of red-green bias standard values ​​defines the acceptable boundary for red-green bias. The allowable fluctuation range of yellow-blue bias standard values ​​defines the acceptable boundary for yellow-blue bias.

[0052] This application decouples the human eye's comprehensive perception of color from independent benchmarks along the spectral axes, replacing subjective descriptions with quantified biases. The human eye's recognition of color is essentially based on mixed spectral stimuli (e.g., the superposition of red and green light produces a yellow sensation), but human vision cannot separate the three independent optical dimensions of brightness, red-green bias, and yellow-blue bias, leading to vague descriptions such as "dark" or "reddish." This solution is based on the optical separation principle of the CIE Lab* color model: the brightness standard value corresponds to the total light reflection (L-axis), reflecting the overall brightness of the coating; the red-green bias standard value corresponds to the red-green complementary spectral axis (A-axis), with positive values ​​indicating a higher proportion of red in the spectral reflection and negative values ​​indicating a higher proportion of green; the yellow-blue bias standard value corresponds to the yellow-blue complementary spectral axis (B-axis), with positive values ​​indicating a higher proportion of yellow in the spectral reflection and negative values ​​indicating a higher proportion of blue.

[0053] Since coating color changes are triggered by various process defects (such as insufficient baking causing a blue shift and a negative B value, or excessive curing temperature causing a red shift and a positive A value), using a mixed color difference index would fail to pinpoint the root cause. This solution sets the allowable deviation range independently along the spectral axis: the brightness allowable deviation range defines the range of light and dark changes, covering differences in substrate reflectivity and coating thickness fluctuations; the red-green bias allowable deviation range defines the red-green balance range, monitoring red shift caused by oxidation in the baking atmosphere or green shift caused by reduction; and the yellow-blue bias allowable deviation range defines the yellow-blue balance range, tracking blue shift caused by insufficient solvent evaporation or yellowing caused by overheating.

[0054] By employing the above technical solutions, the ambiguity of human visual perception is reduced, and the subjective "color difference" is decoupled into independent deviations along three axes: brightness, red-green bias, and yellow-blue bias (e.g., "reddish tinge" is explicitly quantified as a positive A-value bias), avoiding misjudgment of mixed spectra by the human eye. Defect tracing capabilities are enhanced by directly linking the deviation direction to process steps (e.g., a negative B-value bias indicates insufficient baking), providing precise basis for adjustments. The solutions are compatible with material optical properties, and independent parameter benchmarks can be individually calibrated for different substrates (e.g., cold-rolled steel with high reflectivity requires a lower brightness standard value) or coatings (chromium-free coatings naturally have a yellowish tint, requiring a higher B-standard value). This establishes a quantitative foundation for color evaluation, providing an operational optical judgment dimension for the "comparison result evaluation" step, eliminating reliance on human experience.

[0055] S102. Detect the color data of the target electrical steel, wherein the color data includes the actual brightness value, the actual red-green bias value, and the actual yellow-blue bias value;

[0056] Secondly, objective color data acquisition is achieved through the photoelectric conversion principle of the colorimeter. When light shines on the surface of the electrical steel, the difference in reflectivity of the coating to different wavelengths of light is converted into electrical signals. These signals are then analyzed by the instrument's built-in optical sensor into quantitative data in three dimensions: brightness (L value, representing the degree of lightness or darkness), red-green bias (A value, positive values ​​indicate redness / negative values ​​indicate greenness), and yellow-blue bias (B value, positive values ​​indicate yellowness / negative values ​​indicate blueness). This process utilizes the human eye's color perception model, but replaces the human eye's neural response with photoelectric signals, thereby avoiding subjective biases caused by lighting conditions, visual fatigue, or individual differences.

[0057] In one embodiment, detecting the color data of the target electrical steel includes:

[0058] The actual brightness value, actual red-green bias value, and actual yellow-blue bias value of the target electrical steel are detected.

[0059] For example, the actual brightness value refers to the quantified value of the light intensity reflected from the surface of the target electrical steel, representing the actual light reflection intensity from pure black (low value) to pure white (high value), and is used to determine the overall brightness of the coating. The actual red-green bias value refers to the quantified value of the actual color bias of the target electrical steel along the red-green spectral axis. A larger positive value indicates a higher proportion of red in the reflected spectrum (reddish color), and a larger negative value indicates a higher proportion of green (greenish color). The actual yellow-blue bias value refers to the quantified value of the actual color bias of the target electrical steel along the yellow-blue spectral axis. A larger positive value indicates a higher proportion of yellow in the reflected spectrum (yellowish color), and a larger negative value indicates a higher proportion of blue (bluish color).

[0060] This application relies on photoelectric sensing technology to quantitatively simulate the human visual mechanism. When the human eye perceives color, retinal nerve cells simultaneously receive mixed spectral signals (such as the superposition of red and green light producing a yellow sensation), but cannot separate the three independent optical dimensions of brightness, red-green bias, and yellow-blue bias, leading to vague descriptions such as "reddish" or "dark" in human evaluation. This solution replaces the human eye with an optical sensor from a colorimeter: when a light source illuminates the surface of electrical steel, the reflection / absorption characteristics of the coating material for specific wavelengths of light change the spectral composition of the incident light. Following the resolution principle of the CIE Lab* color model, the optical sensor decomposes the mixed spectrum into three independent physical quantities: the actual brightness value corresponds to the total light reflection (L-axis), determined by the intensity of reflected light across the entire wavelength range. If the coating baking is insufficient, resulting in microscopic unevenness on the surface, diffuse reflection will weaken the total reflected light, thus reducing this value; the actual red-green bias value corresponds to the red-green complementary spectral axis (A-axis), calculated by the difference between the red and green spectral reflectance. If the coating is too thick or the baking atmosphere enhances oxidation, the red light reflectance increases, and this value increases positively. The actual yellow-blue bias value corresponds to the yellow-blue complementary spectral axis (B-axis) and is calculated by the difference between the yellow and blue spectral reflectance. If the solvent does not evaporate sufficiently, resulting in incomplete curing of the coating, the blue light reflectance increases, and this value increases negatively.

[0061] By employing the above technical solutions, subjective perception bias can be reduced by decoupling the mixed color signal, which is beyond the quantification of the human eye, into three independent parameters along orthogonal axes (brightness, red-green bias, and yellow-blue bias), thus avoiding misjudgments caused by differences in light intensity and observation angle. This enables the tracing of defect mechanisms, with each parameter independently reflecting specific process defects (e.g., a negative yellow-blue bias value directly correlates with the blue shift effect of insufficient baking), avoiding ambiguity in attribution during manual evaluation. Furthermore, it adapts to a typified standard library, providing comparable measured inputs for the constructed color standard values ​​(brightness standard value, red-green bias standard value, and yellow-blue bias standard value), supporting an objective closed loop for subsequent deviation calculations and conformity assessments. Essentially, this process establishes a bridge for the physical quantification of color through optical-electrical signal conversion, enabling the coating color state to leap from empirical description to a measurable and analyzable spectral data system, providing an indivisible data foundation for core evaluation steps.

[0062] In one embodiment, the above method further includes:

[0063] The brightness deviation value is determined based on the difference between the actual brightness value of the target electrical steel and the brightness standard value.

[0064] The red-green bias deviation value is determined based on the difference between the actual red-green bias value of the target electrical steel and the standard red-green bias value.

[0065] The yellow-blue bias deviation value is determined based on the difference between the actual yellow-blue bias value of the target electrical steel and the standard value of the yellow-blue bias.

[0066] For example, the brightness deviation value refers to the difference between the actual brightness value of the target electrical steel and the corresponding type of brightness standard value, reflecting the deviation of the coating's brightness from the reference (positive value indicates brighter, negative value indicates darker). The red-green bias deviation value refers to the difference between the actual red-green bias value of the target electrical steel and the corresponding type of red-green bias standard value, reflecting the deviation of the coating's red-green spectral tendency from the reference (positive value indicates more red or less green, negative value indicates more green or less red). The yellow-blue bias deviation value refers to the difference between the actual yellow-blue bias value of the target electrical steel and the corresponding type of yellow-blue bias standard value, reflecting the deviation of the coating's yellow-blue spectral tendency from the reference (positive value indicates more yellow or less blue, negative value indicates more blue or less yellow).

[0067] This application utilizes the independent deviation of the spectral axes to quantify the directional impact of process fluctuations on color. While the human eye can perceive "darker" or "bluish" colors, it cannot separate the independent effects of the three dimensions: brightness, red-green balance, and yellow-blue balance. Based on the coordinate axis separation characteristics of the CIE Lab* color model: the principle for determining the brightness deviation value is to calculate the algebraic difference between the actual brightness value and the standard brightness value. Its physical meaning is that increasing coating thickness or reducing substrate roughness reduces light reflection, leading to a negative bias (darker), while excessive baking causing surface vitrification will result in a positive bias (overbright). The principle for determining the red-green bias deviation value is to calculate the algebraic difference between the actual red-green bias value and the standard red-green bias value. Its physical relationship is that when the oxidizing atmosphere of the baking atmosphere is enhanced (e.g., excessive oxygen penetration), the increase in iron oxides in the coating will increase red light reflectivity, resulting in a positive increase in this value (redder); a reducing atmosphere enhances green light reflection, resulting in a negative increase in this value (greener). The principle for determining the yellow-blue bias deviation value is to calculate the algebraic difference between the actual yellow-blue bias value and the standard yellow-blue bias value. The mechanism is as follows: insufficient solvent evaporation leaves residual organic molecules that absorb yellow light, leading to a relative increase in blue light reflection; this value is negatively biased (blue-biased). Conversely, excessively high baking temperatures promote the decomposition of chromates to produce yellow compounds; this value is positively biased (yellow-biased).

[0068] By employing the above technical solutions, attribution ambiguity is reduced, and the mixed color difference perceived by the human eye is decoupled into independent deviations along three orthogonal axes (e.g., separating "dark and bluish" into negative brightness bias and negative yellow-blue bias), clearly pointing to specific process steps (the former relates to coating thickness, the latter to curing conditions); supporting precise process adjustments, the deviation direction and degree directly guide production optimization (e.g., reducing baking oxidation when red-green bias is too large); adapting to dynamic process windows, each deviation value independently corresponds to the allowable deviation range in a typified standard library (e.g., allowable brightness deviation range), making the judgment results compatible with reasonable process fluctuations (e.g., substrate batch differences), avoiding misjudgments caused by oversensitivity. Essentially, this process transforms color differences into operable process diagnostic signals, establishing a quantifiable and traceable deviation data foundation for color evaluation steps, thereby transforming subjective experience into an objective analytical system with axial separation.

[0069] In one embodiment, the above method further includes:

[0070] The total color difference is determined based on the brightness deviation value, the red-green bias deviation value, and the yellow-blue bias deviation value.

[0071] This application simulates the overall perceptual mechanism of color differences by the human eye. When observing colors, the human eye does not perceive brightness, red-green bias, or yellow-blue bias independently (e.g., when a coating is simultaneously dark and blue, it produces a combined visual perception of "grayish-blue"), but it cannot quantify the overall degree of difference. This solution overcomes this limitation through the principle of optical spatial vector synthesis: The formation mechanism of total color difference: In the CIE Lab* color model, brightness deviation, red-green bias, and yellow-blue bias represent three axial displacements in the three-dimensional color space. The physical essence of total color difference is the combined vector magnitude of the three orthogonal axial deviations, similar to the concept of diagonal length in space. When a coating simultaneously exhibits negative brightness bias (darker) and negative yellow-blue bias (bluer), its overall color state will deviate further from the reference point. This magnitude value integrates the directional and magnitude information of color deviation, transforming the "overall color difference" perceived by the human eye into a comparable single scalar value. For example, if the brightness deviation is slight but the red-green bias deviation is significant, the total color difference is reflected as a moderate difference (corresponding to the human eye's perception of "obvious redness"); if the deviations in all three axes are at the boundary values ​​but in opposite directions (such as positive brightness bias + negative red-green bias + negative yellow-blue bias), their vector magnitude may still exceed the critical value (corresponding to the human eye's perception of "strange but difficult-to-describe color").

[0072] By employing the above technical solutions, the blind spots in comprehensive judgment are reduced, avoiding missed detections caused by insignificant single-axis offsets during manual evaluation (e.g., small deviations in brightness and yellow-blue, but overall color difference exceeding the standard after vector superposition); the overall deviation degree is quantified, providing an overall difference benchmark for the "evaluating color" step (without relying on manual descriptions of "significantly different" or "slightly different"); and it is compatible with multi-dimensional fluctuation compensation, so that when an axial deviation is offset by other axes (e.g., negative brightness bias is compensated by positive yellow-blue bias), the overall color difference can still identify overall anomalies. Essentially, this process reconstructs discrete spectral axis data into visual consistency indicators, retaining the diagnostic advantages of axial separation while adding an overall evaluation dimension, establishing a foundation for stratified judgment of color compliance.

[0073] S103. Evaluate the color of the target electrical steel based on the comparison result between the electrical steel surface color standard corresponding to the electrical steel type of the target electrical steel and the color data.

[0074] Ultimately, objectivity in evaluation is achieved through a type-matching comparison mechanism. The measured L, A, and B values ​​are compared with the standard values ​​corresponding to the target electrical steel type to calculate the differences (ΔL, ΔA, ΔB). This quantification of deviation reflects the direction and degree of color shift (e.g., a large positive ΔA value indicates a reddish tint). This step relies on the Euclidean distance calculation principle in color space (i.e., ΔE = √(ΔL / ΔB)). 2 +ΔA 2 +ΔB 2 However, no explicit formula is needed; instead, the pass / fail status is determined by a preset deviation threshold logic. Its core innovation lies in the dynamic binding of material type and color standard, which makes the evaluation process both avoid the subjectivity of human eyes and accommodate the differences in optical properties of different types of electrical steel, thereby solving the misjudgment caused by the "one-size-fits-all" standard or inconsistency of human eyes in traditional methods.

[0075] In one embodiment, the comparison result includes the brightness deviation value, the red-green bias deviation value, the yellow-blue bias deviation value, and the total color difference. The evaluation of the color of the target electrical steel based on the comparison result between the electrical steel surface color standard and color data corresponding to the electrical steel type includes:

[0076] The color of the target electrical steel is evaluated based on the comparison results of the brightness deviation value and the brightness allowable deviation range, the comparison results of the red-green bias deviation value and the red-green bias allowable deviation range, the comparison results of the yellow-blue bias deviation value and the yellow-blue bias allowable deviation range, and the total color difference.

[0077] This application achieves multi-dimensional process anomaly tracing through a complementary mechanism of independent diagnosis of spectral axes and overall perception. While human visual inspection can perceive "overall color difference," it cannot quantify the contribution of each spectral axis (e.g., it cannot distinguish whether "greenness" is caused by a negative bias in red and green or by the superposition of a positive bias in yellow and blue and a negative bias in brightness). This solution is based on a dual mechanism of optical parameter separation and fusion: through the principle of axial deviation comparison, the brightness deviation value is compared with the allowable range to determine whether the brightness exceeds the tolerance. If the negative brightness deviation exceeds the limit (e.g., -ΔL exceeds the lower limit), it directly points to excessive coating thickness or reduced substrate reflectivity (the coating amount needs to be adjusted); if the positive deviation exceeds the limit, it reflects excessive baking and surface glassization (the temperature needs to be reduced). The principle is to isolate substrate interference and focus on coating thickness and curing state. The red-green bias deviation value is compared with the allowable range to detect the red-green balance shift. If the positive deviation exceeds the limit (e.g., +ΔA exceeds the upper limit), it indicates excessive oxidation enhancing red light reflection (the baking atmosphere needs to be adjusted); if the negative deviation exceeds the limit, it corresponds to excessive reduction enhancing green light reflection (oxygen needs to be increased). The principle is to correlate atmospheric process parameters with spectral response. The yellow-blue bias deviation value is compared with the allowable range to track abnormalities in the yellow-blue balance. If the negative bias exceeds the limit (e.g., -ΔB exceeds the lower limit), it indicates that solvent residue is causing increased blue light reflection (requiring extended baking time); a positive bias exceeding the limit corresponds to overheating causing yellowing (requiring shortened baking time). The principle is to link solvent evaporation efficiency with spectral characteristics. The core compensation mechanism for total color difference: When the deviations of the three axes are all within the allowable range but their directions cancel each other out (e.g., negative brightness bias, positive red-green bias, and negative yellow-blue bias combined), a noticeable difference may be perceived visually (e.g., "dullness with a bluish tinge"). Total color difference integrates the contributions of each axis through vector magnitude: even if a single parameter does not exceed the limit, if the combined effect of the three parameters causes a significant overall shift, the total color difference will still exceed the standard. For example: axial deviations are all close to the boundary value but in opposite directions → single parameter is deemed acceptable, total color difference reveals "overall color abnormality"; a single parameter significantly exceeds the limit → total color difference simultaneously exceeds the standard (strengthening the confidence level of the judgment).

[0078] By employing the above technical solutions, the false negative rate can be reduced, and specific process defects can be located uniaxially (such as red-green bias anomalies accurately pointing to atmosphere problems). Total color difference can capture multi-parameter coupling anomalies (such as slight underbaking superimposed on substrate fluctuations). The traceability efficiency can be improved, and out-of-limit parameters can be directly associated with process steps (such as when only the yellow-blue bias exceeds the limit, the baking line speed is immediately identified as too fast). It is compatible with quality grading and provides quantitative input for subsequent judgment rules (such as when the total color difference is moderately excessive and no single item exceeds the limit, it is marked as a process fluctuation warning, which is not a fatal defect).

[0079] Furthermore, as a response to the above Figure 1 In addition to the method shown, this embodiment of the invention also provides an electrical steel color evaluation device for evaluating the above-mentioned steel color. Figure 1The method shown is implemented accordingly. This device embodiment corresponds to the foregoing method embodiment. For ease of reading, this device embodiment will not repeat the details of the foregoing method embodiment, but it should be clear that the device in this embodiment can implement all the contents of the foregoing method embodiment. Figure 2 As shown, the device includes: a construction unit 21, a detection unit 22, and an evaluation unit 23, wherein...

[0080] Construction unit 21 is used to construct different electrical steel surface color standards based on different types of electrical steel;

[0081] The detection unit 22 is used to detect the color data of the target electrical steel, wherein the color data includes the actual brightness value, the actual red-green bias value, and the actual yellow-blue bias value;

[0082] Evaluation unit 23 is used to evaluate the color of the target electrical steel based on the comparison result between the electrical steel surface color standard corresponding to the electrical steel type of the target electrical steel and the color data.

[0083] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and by adjusting kernel parameters, a method for evaluating the color of electrical steel can be implemented. This method addresses the problems of large subjective errors and lack of objective quantitative standards in manual visual inspection of electrical steel coating colors.

[0084] This invention provides a computer-readable storage medium including a stored program that, when executed by a processor, implements the electrical steel color evaluation method.

[0085] This invention provides a processor for running a program, wherein the program executes the electrical steel color evaluation method during runtime.

[0086] This invention provides an electronic device, which includes at least one processor and at least one memory connected to the processor; wherein the processor is used to call program instructions in the memory to execute the electrical steel color evaluation method described above.

[0087] This invention provides an electronic device 30, such as... Figure 3 As shown, the electronic device includes at least one processor 301, and at least one memory 302 and bus 303 connected to the processor; wherein, the processor 301 and the memory 302 communicate with each other through the bus 303; the processor 301 is used to call program instructions in the memory to execute the above-mentioned electrical steel color evaluation method.

[0088] The smart electronic devices mentioned in this article can be PCs, tablets, mobile phones, etc.

[0089] This application also provides a computer program product that, when executed on a process management electronic device, is suitable for executing a program that initializes the steps of the above-described electrical steel color evaluation method.

[0090] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0091] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0093] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0094] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1The steps of the function specified in one or more boxes.

[0095] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to perform actions such as... Figure 1 The control flow of the memory in the corresponding embodiment.

[0096] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0097] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0098] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. 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 coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0099] 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 can be selected to achieve the purpose of this embodiment according to actual needs.

[0100] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0101] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0102] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for evaluating the color of electrical steel, characterized in that, include: Different surface color standards for electrical steel are constructed based on different types of electrical steel; The color data of the target electrical steel is detected, wherein the color data includes the actual brightness value, the actual red-green bias value, and the actual yellow-blue bias value; The color of the target electrical steel is evaluated based on the comparison between the surface color standard of the electrical steel corresponding to the electrical steel type and the color data.

2. The method according to claim 1, characterized in that, The different surface color standards for electrical steel based on different types of electrical steel are constructed respectively, including: Ideal electrical steel samples were selected based on the type of electrical steel. The color standard value and allowable deviation range of the ideal electrical steel sample are determined to construct the surface color standard of electrical steel.

3. The method according to claim 2, characterized in that, The color standard values ​​include brightness standard values, red-green bias standard values, and yellow-blue bias standard values; The allowable deviation range includes the allowable deviation range for brightness, the allowable deviation range for red-green bias, and the allowable deviation range for yellow-blue bias.

4. The method according to claim 3, characterized in that, The color data of the target electrical steel is detected, including: The actual brightness value, actual red-green bias value, and actual yellow-blue bias value of the target electrical steel are detected.

5. The method according to claim 4, characterized in that, Also includes: The brightness deviation value is determined based on the difference between the actual brightness value of the target electrical steel and the brightness standard value. The red-green bias deviation value is determined based on the difference between the actual red-green bias value of the target electrical steel and the standard red-green bias value. The yellow-blue bias deviation value is determined based on the difference between the actual yellow-blue bias value of the target electrical steel and the standard value of the yellow-blue bias.

6. The method according to claim 5, characterized in that, Also includes: The total color difference is determined based on the brightness deviation value, the red-green bias deviation value, and the yellow-blue bias deviation value.

7. The method according to claim 6, characterized in that, The comparison results include the brightness deviation value, the red-green bias deviation value, the yellow-blue bias deviation value, and the total color difference. The comparison results between the electrical steel surface color standard and color data corresponding to the electrical steel type of the target electrical steel evaluate the color of the target electrical steel, including: The color of the target electrical steel is evaluated based on the comparison results of the brightness deviation value and the brightness allowable deviation range, the comparison results of the red-green bias deviation value and the red-green bias allowable deviation range, the comparison results of the yellow-blue bias deviation value and the yellow-blue bias allowable deviation range, and the total color difference.

8. A color evaluation device for electrical steel, characterized in that, Also includes: The building blocks are used to construct different surface color standards for electrical steel based on different types of electrical steel. The detection unit is used to detect the color data of the target electrical steel, wherein the color data includes the actual brightness value, the actual red-green bias value, and the actual yellow-blue bias value; The evaluation unit is used to evaluate the color of the target electrical steel based on the comparison result between the electrical steel surface color standard corresponding to the electrical steel type of the target electrical steel and the color data.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed by a processor, it implements the steps of the electrical steel color evaluation method as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, The electronic device includes at least one processor and at least one memory connected to the processor; wherein the processor is configured to call program instructions in the memory to execute the steps of the electrical steel color evaluation method as described in any one of claims 1 to 7.

Images