Transformer substation component defect early warning method and device, electronic equipment and storage medium

Abstract

The invention discloses a transformer substation component defect early warning method and device, electronic equipment and a storage medium, and the method comprises the steps: firstly determining an area where a fluorescent marker is introduced in a target transformer substation component, obtaining a target area, then obtaining the change data of the fluorescent marker in the target area in a preset time period, and obtaining the change data of the fluorescent marker in the target area; the method comprises the steps of obtaining target change data, determining a target corrosion degree value of a target transformer substation component based on the target change data, determining a defect early warning level of the target transformer substation component based on the target corrosion degree value, and determining target early warning information based on the defect early warning level. By adopting the embodiment of the invention, the accuracy of substation component defect early warning is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer substation component defect early warning technology, and in particular to a transformer substation component defect early warning method, device, electronic equipment and storage medium. Background Art

[0002] As the scale of power systems continues to expand, the safe and stable operation of substation components has become critical to ensuring power supply reliability. However, substation components exposed to complex environments for long periods of time are susceptible to corrosion and aging. In particular, corrosion defects in metal components can seriously threaten equipment performance and grid security. Existing early warning methods are mostly based on single parameters or simple threshold judgments. They lack comprehensive assessment and dynamic monitoring of component corrosion status, making accurate early warning difficult. Therefore, improving the accuracy of early warnings for substation component defects is an urgent issue. Summary of the Invention

[0003] The embodiments of the present application provide a substation component defect early warning method, device, electronic device and storage medium, which improve the accuracy of substation component defect early warning.

[0004] In a first aspect, an embodiment of the present application provides a method for early warning of substation component defects, the method comprising:

[0005] determining an area of the target substation component where the fluorescent marker is introduced to obtain a target area;

[0006] Acquiring change data of the fluorescent marker in the target area within a preset time period to obtain target change data;

[0007] determining a target corrosion degree value of the target substation component based on the target change data;

[0008] The defect warning level of the target substation component is determined based on the target corrosion degree value, and target warning information is determined based on the defect warning level.

[0009] In a second aspect, an embodiment of the present application provides a substation component defect early warning device, the device comprising: a determination unit and a processing unit;

[0010] The determining unit is configured to determine the area in the target substation component where the fluorescent marker is introduced to obtain the target area;

[0011] The processing unit is configured to obtain change data of the fluorescent marker within the target area within a preset time period to obtain target change data;

[0012] determining a target corrosion degree value of the target substation component based on the target change data;

[0013] The defect warning level of the target substation component is determined based on the target corrosion degree value, and target warning information is determined based on the defect warning level.

[0014] In a third aspect, an embodiment of the present invention provides an electronic device comprising: a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor so that the electronic device performs the method of the first aspect.

[0015] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect.

[0016] In a fifth aspect, an embodiment of the present invention provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, so that a computer executes the method of the first aspect.

[0017] The implementation of the present invention has the following beneficial effects:

[0018] It can be seen that the substation component defect warning method described in the embodiment of the present invention first determines the area where the fluorescent marker is introduced in the target substation component to obtain the target area, and then obtains the change data of the fluorescent marker in the target area within a preset time period to obtain target change data, and then determines the target corrosion degree value of the target substation component based on the target change data, and then determines the defect warning level of the target substation component based on the target corrosion degree value, and determines the target warning information based on the defect warning level, thereby improving the accuracy of the substation component defect warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the implementation methods or background technologies of the present application, the drawings required for use in the implementation methods or background technologies of the present application will be described below.

[0020] Figure 1 This is a flow chart of a method for early warning of substation component defects provided by an embodiment of the present application;

[0021] Figure 2 This is a flow chart for determining a target corrosion degree value provided by an embodiment of the present application;

[0022] Figure 3 is a flow chart for determining a first corrosion degree value provided by an embodiment of the present application;

[0023] Figure 4This is a flow chart for determining a target roughness value and a target irregularity value provided by an embodiment of the present application;

[0024] Figure 5 This is a flow chart for determining texture clarity provided by an embodiment of the present application;

[0025] Figure 6 This is a schematic diagram of a mapping table of corrosion degree values and defect warning levels provided in an embodiment of the present application;

[0026] Figure 7 This is a schematic structural diagram of a substation component defect warning device provided by an embodiment of the present application;

[0027] Figure 8 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the present invention, the following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0029] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0030] Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0031] See also Figure 1 , Figure 1 This is a flowchart of a substation component defect early warning method provided by an embodiment of the present application, including but not limited to the following steps:

[0032] S101: Determine the area where the fluorescent marker is introduced in the target substation component to obtain the target area.

[0033] In this embodiment, substation components include conductive and current-carrying components, insulating and protective components, and capacitive and inductive components. Conductive and current-carrying components include transformers, high-voltage circuit breakers, disconnectors, busbars, and cables. Insulating and protective components include insulators, lightning arresters, current transformers, and voltage transformers. Capacitive and inductive components include capacitors and reactors. Corrosion of substation components can seriously threaten the safe and stable operation of the power system. Corrosion of metal components, such as busbars and cable trays, can damage insulation coatings, leading to reduced insulation performance and causing short circuits and leakage. Surface oxidation increases the contact resistance of conductive materials, causing localized heating and even joint erosion. Corrosion of steel structures and brackets can reduce structural strength and potentially cause equipment to tilt or collapse. Corrosion, hardening, and cracking of rubber seals can allow moisture and dust to enter the equipment, compromising sealing performance. Furthermore, corrosion can cause protective devices to malfunction or fail to operate, automation system failures, increase maintenance costs, and shorten equipment life. Corrosion in the grounding system can also pose a risk of electric shock. Leakage of corrosion products can also cause environmental pollution, with even more serious consequences if it leads to equipment failure or even fire.

[0034] Fluorescent markers (such as fluorescent dyes and nanoparticles) are attached to the surface of substation components through physical adsorption or chemical bonding. When corrosion occurs, their fluorescence characteristics (intensity, wavelength, lifetime, etc.) will change due to environmental changes. Specifically, changes in pH and increased metal ion concentration caused by corrosion can cause changes in the molecular structure of the marker (such as breaking of conjugated double bonds), causing fluorescence quenching or spectral shift; the formation of corrosion pits or surface roughening will destroy the uniform distribution of the marker, resulting in local fluorescence signal attenuation or abnormal spatial distribution.

[0035] It should be explained that, depending on the component material and the corrosion environment, a live mineralization probe with acidic / alkaline reactivity can also be selected. The mineralization probe generates fluorescent markers, such as rare earth-doped calcium carbonate or hydroxyapatite, to amplify micron-scale corrosion pits into detectable millimeter-scale fluorescent signals. For example, the red fluorescent marker generated in the pitting corrosion area of aluminum alloy has a fluorescence intensity that is linearly related to the corrosion depth, enabling visual quantification of the degree of corrosion. The live mineralization probe is applied to the corroded area of the component. Through chemical reaction / biomineralization and controlled reaction conditions, the amount and fluorescence characteristics of the characteristic fluorescent marker in the corrosion area are regulated to generate a characteristic fluorescent marker with characteristic fluorescence. For example, the live mineralization probe solution can be evenly sprayed on the corroded area of the component using precision spraying equipment. By controlling the spraying pressure, the distance between the nozzle and the component surface, and the number of spraying times, the distribution amount and thickness of the probe solution in the corrosion area can be precisely controlled. The general spraying pressure is set at 0.2-0.5MPa, and the distance between the nozzle and the surface is maintained at 10-20cm. According to the size and depth of the corrosion area, 2-3 spraying operations are performed so that the probe can accurately act on the target area and reduce the impact on the non-corrosion area. The reaction system is placed in a constant temperature environment and the temperature is accurately controlled by a heating or cooling device. Temperature has a significant effect on chemical reactions and biomineralization processes. In this embodiment, according to the characteristics of the living mineralization probe and the optimal generation conditions of the target fluorescent marker, the reaction temperature is controlled within the range of 25-40°C. At lower temperatures (25-30°C), the reaction rate is relatively slow, but it is conducive to generating fluorescent markers with more regular structures; at higher temperatures (35-40°C), the reaction rate is accelerated, but care should be taken to avoid excessively high temperatures that lead to a decrease in probe activity or changes in the structure of the fluorescent marker. By monitoring the temperature of the reaction system in real time and using a feedback control system to keep the temperature stable, it is ensured that the generation process of the fluorescent marker is carried out under suitable temperature conditions.

[0036] Through the above operations, fluorescent markers with characteristic fluorescence were successfully generated in the corroded areas of the components. These fluorescent markers not only exhibit obvious fluorescent colors (such as red, green, etc.) on a macroscopic scale, but also their fluorescence intensity, emission wavelength and other characteristics are closely related to the degree of corrosion in the corroded area. For example, the red fluorescent marker generated in the pitting corrosion area of aluminum alloy has a linear increase in fluorescence intensity with increasing corrosion depth. Quantitative detection and analysis of the fluorescence signal by fluorescence spectrometer can achieve a visual quantitative assessment of the degree of corrosion. At the same time, the generated fluorescent marker has good binding stability with the corroded area and can maintain its fluorescence characteristics during subsequent detection and analysis, providing a reliable basis for accurately assessing the corrosion condition of the component.

[0037] Metal corrosion can lead to the formation of surface oxide layers or structural damage, changing the efficiency of heat conduction, causing temperature differences or abnormal heat distribution between the corroded area and the normal area. The temperature of the uniformly corroded area may be slightly higher than that of the uncorroded area due to the insulation of the oxide layer. Pitting pits or cracks may cause local temperature mutations due to the interruption of the heat conduction path. Therefore, the corroded area can be detected based on infrared thermal imaging. Infrared thermal imaging can scan the surface of the component non-contact and over a large area to quickly locate areas with abnormal temperature. When using infrared thermal imaging to detect the target area, first use an infrared thermal imager to scan the surface of the component and collect the temperature distribution image. Then, suspicious areas are identified through threshold segmentation or machine learning. The thermal physical properties of the component material are combined to eliminate interference from environmental heat sources (such as sunlight and equipment heating). Then, high-risk areas (such as the top 10% areas with the most significant thermal anomalies) are numbered and marked as target areas for the subsequent introduction of fluorescent markers.

[0038] It can be seen that by introducing fluorescent markers into the target substation components and determining the target area, components susceptible to corrosion in the substation (such as grounding grids, busbar joints, metal brackets in humid environments, etc.) can be targeted and marked, avoiding the blindness of global monitoring. Data collection is only performed on the target area, which can filter out interference information in non-corrosion key areas, making the monitoring data more focused on actual risk points and improving analysis efficiency. Fluorescent markers usually change in fluorescence intensity, color or distribution with the corrosive environment. The location and range of corrosion can be directly observed through optical detection (such as fluorescence imagers). By recording the changing parameters of fluorescent markers (such as fluorescence intensity decay rate and color wavelength offset), the corrosion process can be converted into quantifiable numerical indicators, avoiding the subjective errors of traditional manual inspections. Fluorescent markers are sensitive to changes in the chemical environment of early corrosion (such as the release of trace hydrogen ions and metal ions) and can send signals before corrosion causes obvious structural damage. There is no need to modify the entire station equipment. Markers are only introduced in the target area, which can reduce material and installation costs. Fluorescent signals can be automatically collected by optical sensors and connected to the substation's existing online monitoring system to achieve unattended monitoring, reduce the frequency of manual inspections, and improve operation and maintenance efficiency.

[0039] S102: Acquire change data of the fluorescent marker in the target area within a preset time period to obtain target change data.

[0040] In this embodiment, the preset time period can be adjusted according to the expected corrosion rate, such as setting daily collection for high corrosion risk areas (coastal substations), weekly or monthly collection for ordinary areas, and real-time high-frequency collection can be triggered in an emergency. Specifically, when obtaining the change data of the fluorescent marker in the target area within the preset time period, it is necessary to first use a fluorescence detection device (such as a fluorescence microscope, spectrometer or professional imaging system) to periodically or continuously monitor the target area. The detection device emits excitation light of a specific wavelength to illuminate the marked area, so that the fluorescent marker emits a characteristic fluorescence signal after being excited. The device synchronously collects data such as the intensity, color, distribution morphology and spectral characteristics of the signal. For example, the area is scanned at fixed intervals (such as every day or every week), and the changes in fluorescence parameters at different time points are recorded, including the attenuation or enhancement of fluorescence intensity, the displacement of spectral peaks, and changes in the uniformity of fluorescence distribution. At the same time, the data is calibrated in combination with the timestamp to ensure the timing accuracy of the data at each time point. By integrating and comparing the fluorescence signal data at these different time points and eliminating noise data such as ambient light interference and equipment errors, we can obtain target change data reflecting the changes of fluorescent markers in the target area over time. This data can intuitively reflect the changes in the physical or chemical properties of the markers caused by the influence of the corrosive environment.

[0041] S103: Determine a target corrosion degree value of the target substation component based on the target change data.

[0042] In this implementation, see Figure 2 , Figure 2 This is a flow chart for determining a target corrosion degree value provided by an embodiment of the present application, including but not limited to the following steps:

[0043] S201: Determine a first corrosion degree value based on the fluorescence signal intensity change data.

[0044] In this embodiment, the target change data includes fluorescence signal intensity change data and a topological charge transition value of the fluorescent marker within the preset time period. The fluorescence signal intensity change data includes n fluorescence signal intensity values and n fluorescence signal intensity value recording times within the preset time period, where n is an integer greater than 1, and each fluorescence signal intensity value corresponds to a fluorescence signal intensity value recording time.

[0045] In this implementation, see Figure 3 , Figure 3 A flowchart for determining a first corrosion degree value provided by an embodiment of the present application includes but is not limited to the following steps:

[0046] S301: performing fitting based on the n fluorescence signal intensity values and the n fluorescence signal intensity value recording times to obtain a target fitting straight line.

[0047] In this embodiment, when fitting based on n fluorescence signal intensity values and their corresponding recording times to obtain a target fitting line, each recording time must first be converted into a quantifiable time variable (e.g., with the initial time as the origin, subsequent times are represented as relative time points, and this is used as the horizontal axis coordinate, and the corresponding fluorescence signal intensity value is used as the vertical axis coordinate, forming n data points). Subsequently, a linear fit is performed using the least squares method. The core of this method is to find a straight line through mathematical calculations so that the sum of the squares of the vertical distances of all data points to the line is minimized. The resulting straight line is the target fitting line that best reflects the trend of fluorescence signal intensity changes over time. It can eliminate the accidental errors of individual data points and reflect the overall change pattern.

[0048] S302: Determine the slope of the target fitting line to obtain a target slope.

[0049] In this embodiment, after obtaining the target fitting straight line, its slope is determined to obtain the target slope. If the least squares method is used for fitting, the straight line parameters can be calculated through the data points. By directly selecting any two points on the straight line, the slope of the target fitting straight line can be calculated to obtain the target slope. The negative sign of the slope of the fitting straight line indicates attenuation, and the positive sign indicates enhancement. The absolute value reflects the speed of change.

[0050] S303: Obtain a mapping relationship between the slope and the corrosion degree value.

[0051] In this embodiment, in order to obtain the mapping relationship between the slope and the corrosion degree value, it is necessary to achieve it through experimental calibration and data modeling. Specifically, first, standard samples of different corrosion degrees need to be set up in a laboratory environment (for example, a series of samples of known corrosion levels are prepared by controlling the corrosion time, the concentration of the corrosive medium, etc.). Then, the same fluorescent marker is applied to each standard sample, and the fluorescence signal intensity change data is collected within a preset time period. The slope value corresponding to each sample is calculated according to the above fitting method. Next, the known corrosion degree value of each sample (such as quantitative indicators such as corrosion depth and corrosion rate percentage) is associated with the corresponding slope value to form a set of (slope-corrosion degree) mapping data pairs. Afterwards, these data pairs can be modeled through statistical analysis (such as linear regression, polynomial fitting or machine learning algorithm) to determine the functional relationship or lookup table between the two. If the relationship is complex, a segmented mapping table or nonlinear model may be established. The final mapping relationship needs to be verified for its accuracy through multiple groups of samples to ensure that the corrosion degree can be reliably inferred by the slope, thereby providing a quantitative basis for corrosion monitoring in practical applications, and finally obtaining a mapping relationship between the slope and the corrosion degree value.

[0052] S304: Determine the corrosion degree value corresponding to the target slope based on the mapping relationship to obtain the first corrosion degree value.

[0053] In this embodiment, when determining the first corrosion degree value corresponding to the target slope based on the mapping relationship, the specific form of the mapping relationship must first be clarified. If the mapping relationship is a mathematical expression, the target slope can be directly substituted into the formula for calculation. If the mapping relationship is a segmented lookup table (such as different slope intervals corresponding to different corrosion levels), it is necessary to first determine the interval in which the target slope is located and then match the corresponding corrosion degree value. If the mapping relationship is a nonlinear model (such as a prediction model trained by machine learning), the target slope must be input into the model, and the corresponding corrosion degree value must be output through model calculation or mapping rules. Regardless of the form, the core is to use the obtained target slope as input, convert it through pre-established mapping rules, and finally obtain a quantized first corrosion degree value, achieving accurate mapping from the fluorescence signal change rate to the corrosion state.

[0054] It can be seen that this method of determining the corrosion degree value through the fluorescence signal intensity change data has many advantages: first, the quantification accuracy is high. With the help of mathematical fitting, the discrete fluorescence signal data is converted into a continuous linear relationship. The slope can accurately reflect the rate of change of the signal over time, avoiding subjective judgment errors and making the corrosion degree quantification results more objective; second, the real-time monitoring capability is strong. The dynamic data collection within the preset time period can capture the real-time changes of the corrosion process. Through the mapping relationship between the slope and the corrosion degree, the signal change can be quickly converted into a corrosion status assessment, which is suitable for scenarios that require real-time early warning; third, the degree of automation is high, from data fitting to corrosion The entire process of corrosion degree calculation can be automated through algorithms, reducing manual intervention and improving monitoring efficiency, making it particularly suitable for long-term, large-scale corrosion monitoring tasks. In addition, the method has good reliability and repeatability. The mapping relationship based on experimental calibration has a stable mathematical basis, and the measurement results under the same conditions can be repeatedly verified. The mapping model can be optimized through training with a large number of samples, further improving the reliability of corrosion assessment. Finally, non-destructive testing has significant advantages. Fluorescence signal acquisition does not require contact or destruction of the monitored object. Compared with traditional destructive testing methods, it is more suitable for long-term health monitoring of large structures such as bridges and pipelines, reducing testing costs and the risk of damage to the structure.

[0055] S202: Determine a second corrosion degree value based on the topological charge transition value of the fluorescent marker.

[0056] In this embodiment, a mapping relationship between a preset fluorescent marker topological charge transition and a corrosion severity value can be established, and based on this mapping relationship, a second corrosion severity value can be determined based on the fluorescent marker topological charge transition. Specifically, when determining the second corrosion severity value based on the fluorescent marker topological charge transition, it is necessary to first clarify the association mechanism between the topological charge transition and the corrosion severity. The topological charge of the fluorescent marker (such as the quantum number of the photon orbital angular momentum) will undergo a transition in a corrosive environment due to factors such as changes in the material surface microstructure, changes in molecular arrangement, or chemical reactions. This transition can reflect the degree of influence of corrosion on the microscopic state of the marker. The specific steps are as follows: First, a quantitative relationship between the topological charge transition and the corrosion severity is established through experimental or theoretical analysis. For example, the topological charge transition amplitude under different corrosion levels is measured in a standard corrosion sample to form a "transition-corrosion severity" mapping table or mathematical model (such as a linear equation, exponential function, etc.). After obtaining the topological charge jump variable of the fluorescent marker of the target substation component, the jump variable is used as input and substituted into the established mapping relationship: if the relationship is a formula, it is directly calculated; if it is a segmented interval mapping, the interval to which the jump variable belongs is determined and matched with the corresponding corrosion level; if it is a machine learning model, the result is output through model calculation. Finally, through quantitative analysis of the topological charge jump variable, a second corrosion degree value representing the degree of corrosion is obtained. This value can supplement the corrosion assessment dimension from the perspective of changes in microscopic physical properties and improve the accuracy of the overall judgment.

[0057] S203: Determine the target corrosion level value based on the first corrosion level value and the second corrosion level value.

[0058] In this embodiment, for example, a first weight corresponding to the first corrosion severity value and a second weight corresponding to the second corrosion severity value are determined. Specifically, the sum of the first weight and the second weight is 1. When determining the first weight corresponding to the first corrosion severity value and the second weight corresponding to the second corrosion severity value, it is necessary to first clarify the relative importance of the two in the target corrosion severity calculation. This process is typically based on domain knowledge, historical data, or experimental verification. For example, by analyzing the influence of fluorescence signal intensity change data and topological charge transition variables on the corrosion severity, reasonable weights can be assigned to the two. Since the sum of the first weight and the second weight is 1, when the first weight increases, the second weight decreases accordingly, and vice versa. For example, if research finds that fluorescence signal intensity change data is more critical in reflecting the corrosion severity, the first weight can be set to 0.6 and the second weight to 0.4. This reflects the different contributions of different data indicators and ensures that the weight assignment accurately reflects the importance level of each corrosion severity value.

[0059] Exemplarily, a reference corrosion degree value is obtained by performing calculation based on the first weight, the second weight, the first corrosion degree value, and the second corrosion degree value. Specifically, the reference corrosion degree value is calculated according to the following formula:

[0060] The reference corrosion level value = first corrosion level value × first weight + second corrosion level value × second weight;

[0061] According to the above formula, a reference corrosion degree value can be obtained by performing calculation based on the first weight, the second weight, the first corrosion degree value, and the second corrosion degree value.

[0062] For example, the target roughness value and the target irregularity value of the target area are determined. Specifically, see Figure 4 , Figure 4 The flowchart of determining a target roughness value and a target irregularity value provided by an embodiment of the present application includes but is not limited to the following steps:

[0063] S401: Acquire a target interference pattern obtained after a preset light wave irradiates the target area.

[0064] In this embodiment, a light source (such as a laser) with a stable wavelength and coherence is first selected as a preset light wave. This light wave is collimated by an optical system and then irradiated onto the surface of the target area. When the light wave is projected onto the target area, due to surface topographical features such as microscopic undulations, corrosion pits, or cracks, the reflected light at different locations will produce optical path differences. When these reflected lights, carrying surface topography information, meet the reference light (or different path components of the same beam) on the detector, the phase difference forms alternating light and dark interference fringes, i.e., the target interference pattern. For example, if the target surface has unevenness caused by corrosion, the optical path difference between the reflected light from the protrusions and the reflected light from the pits will cause the interference fringes to appear curved, misaligned, or have varying density. However, the interference fringes on a flat surface are relatively uniform and regular. Finally, an optical interferometer (such as a Michelson interferometer or a Fizeau interferometer) converts these surface topography differences into a recordable interference pattern, resulting in the target interference pattern.

[0065] S402: Acquire texture features and edge features of the target interference pattern.

[0066] In this embodiment, the target interference pattern is first grayscaled or frequency-domain transformed (such as Fourier transform) to extract the periodicity, directionality, and density characteristics of the stripes. For example, by calculating the grayscale co-occurrence matrix to analyze the grayscale correlation of adjacent pixels, texture parameters such as energy, contrast, and entropy are obtained; or a filter is used to detect the response intensity of the stripes in different directions and scales, and the arrangement pattern of the stripes is quantified, thereby obtaining the texture characteristics of the target interference pattern. Texture characteristics may include stripe density: the number of interference stripes per unit area, which reflects the severity of the surface morphology change; periodicity: the regularity of the stripe arrangement. The stripes in the uniformly corroded area have a strong periodicity, while the local damaged area may have periodic disorder; directionality: the main direction of the stripes (such as horizontal, vertical, or inclined), which is related to the surface stress or corrosion extension direction; grayscale uniformity: the consistency of the light and dark contrast of the stripes. A rough surface may cause large fluctuations in the grayscale of the stripes.

[0067] In this embodiment, an edge detection algorithm is used to identify the boundaries of fringes in the interference pattern and extract the geometric features of the contour. For example, edge pixels are skeletonized to analyze the contour curvature, inflection point distribution, and closed area characteristics. Alternatively, morphological operations (dilation and erosion) are used to refine the edges to obtain the contour curve required for fractal analysis, thereby obtaining the edge features of the target interference pattern. Edge features may include edge continuity: the integrity of the fringes' boundaries. Surface defects caused by corrosion may cause edges to appear broken or burred. Inflection point density: the number of points of sudden change in curvature on the contour, reflecting the complex corner characteristics of the surface topography. Closed area morphology: the size and shape of the closed area enclosed by the fringes (such as annular fringes), which is related to the geometric morphology of the corrosion pits. Fractal contour details: the self-similarity characteristics of the edge at different scales, which are used for subsequent fractal dimension calculation.

[0068] Texture features can quantify the macroscopic distribution patterns of interference fringes, while edge features focus on the microscopic geometric details of the fringes’ boundaries. The combination of the two provides multi-dimensional data support for the assessment of surface roughness and irregularity.

[0069] S403: Determine the texture clarity of the target interference pattern based on the texture feature.

[0070] In this embodiment, when the texture features include the number of stripes, the density of stripes and the spacing between stripes, please refer to Figure 5 , Figure 5 This is a flowchart of determining texture clarity provided by an embodiment of the present application, including but not limited to the following steps:

[0071] S501: Determine a first definition corresponding to the number of stripes, a second definition corresponding to the stripe density, and a third definition corresponding to the stripe spacing.

[0072] In this embodiment, the number of stripes refers to the total number of light and dark interference stripes in the pattern, reflecting the overall scale of the surface morphology change (for example, the larger the corrosion area, the more stripes may be produced); the stripe density refers to the number of stripes per unit area, measuring the severity of the morphology change (the higher the density, the denser the surface undulations); the stripe spacing refers to the average distance between the centers of adjacent stripes, reflecting the scale of the morphology change (the larger the spacing, the longer the wavelength of the surface undulations, and vice versa).

[0073] It may be a preset mapping relationship between the number of stripes and the definition, and the first definition corresponding to the number of stripes may be determined based on the mapping relationship.

[0074] It may be a preset mapping relationship between stripe density and definition, and the second definition corresponding to the stripe density may be determined based on the mapping relationship.

[0075] It may be a preset mapping relationship between stripe spacing and definition, and the third definition corresponding to the stripe spacing may be determined based on the mapping relationship.

[0076] S502: Determine an average value of the first definition, the second definition, and the third definition to obtain an average definition.

[0077] In this embodiment, the average value of the first clarity, the second clarity, and the third clarity is determined to obtain the average clarity, which can avoid the one-sidedness of a single feature. For example, when the number of stripes is large but the density is too high, averaging can balance the impact of the two on clarity.

[0078] S503: Obtain the duration of time that the preset light wave irradiates the target area to obtain a target duration.

[0079] In this embodiment, the duration of the preset light wave irradiation on the target area significantly affects the texture clarity of the target interference pattern by influencing light energy accumulation, the dynamic response of the material, and the characteristics of the interference fringes. If the duration is too short, insufficient light energy will result in a low signal-to-noise ratio (SNR) of the interference fringes, blurred fringe edges, poor contrast, and reduced texture clarity. If the duration is too long, the fringes may be overexposed, shifted, or distorted due to detector saturation, thermal deformation of the material, photochemical reactions, and other factors, also reducing texture clarity. Furthermore, if the target surface topography changes over time (e.g., during corrosion), the duration can indirectly affect the number, density, and spacing of fringes. A longer duration may increase surface undulations, the number of fringes, and their density, but overly dense fringes may cling together, reducing clarity. A shorter duration may result in less surface variation and sparse fringes, resulting in insufficient detail. Therefore, the clarity calculation result needs to be corrected using fine-tuning parameters corresponding to the duration to compensate for the systematic impact of duration on pattern quality and ensure evaluation accuracy. Therefore, the duration of the preset light wave irradiation on the target area is obtained to obtain a target duration.

[0080] S504: Determine a target fine-tuning parameter corresponding to the target duration.

[0081] In this embodiment, it may be a mapping relationship between a preset duration and a fine-tuning parameter, and based on the mapping relationship, the target fine-tuning parameter corresponding to the target duration may be determined.

[0082] S505: Adjusting the average clarity based on the target fine-tuning parameter to obtain the texture clarity of the target interference pattern.

[0083] In this embodiment, the texture clarity of the target interference pattern is calculated specifically according to the following formula:

[0084] The texture clarity of the target interference pattern = average clarity × (1 + target fine-tuning parameter);

[0085] According to the above formula, the average clarity can be adjusted based on the target fine-tuning parameter to obtain the texture clarity of the target interference pattern.

[0086] It can be seen that the layered calculation and parameter fine-tuning method significantly improves the accuracy and robustness of texture clarity assessment through multi-dimensional feature fusion and dynamic correction mechanism. First, the number, density, and spacing of fringes are respectively mapped to the first, second, and third clarity, realizing fine-grained quantification of the texture features of the interference pattern, avoiding the one-sidedness of a single feature (for example, relying solely on the number of fringes may ignore the blur caused by excessive density); second, the contribution of the three types of features is integrated through average calculation to balance the impact of different features on the overall clarity. For example, when the number of fringes is moderate but the spacing is uneven, averaging can effectively reduce local noise interference; finally, a fine-tuning parameter related to the illumination duration is introduced to dynamically compensate for systematic deviations caused by underexposure, overexposure, or material thermal effects, making the texture clarity assessment closer to the actual physical scene. This implementation method not only captures the essential texture characteristics of the interference pattern, but also eliminates external interference during the measurement process, providing a more reliable data basis for subsequent roughness assessment based on texture clarity.

[0087] S404: Determine a roughness value corresponding to the texture clarity to obtain the target roughness value.

[0088] In this embodiment, a mapping relationship between texture clarity and roughness value may be preset, and based on the mapping relationship, the roughness value corresponding to the texture clarity may be determined to obtain the target roughness value.

[0089] S405: Determine the fractal dimension of the target interference pattern based on the edge feature.

[0090] In this embodiment, the fractal dimension of the target interference pattern is the core parameter for describing the irregularity of the target interference pattern. The larger the fractal dimension, the more complex the edge and the higher the degree of irregularity. The edge features of the target interference pattern include the geometric shape, grayscale distribution and statistical characteristics of the interference fringe boundary, specifically covering the continuity and curvature of the edge profile (such as whether it is a smooth continuous curve or has broken undulations), direction and symmetry (such as horizontal extension or symmetrical distribution), the transition gradient and contrast of the grayscale from bright area to dark area at the edge (reflecting the steepness of the light intensity change), the degree of edge blur (such as the dispersion quantified by the half-maximum width), and irregularity parameters such as the fractal dimension of the edge profile (reflecting the complexity of the microscopic morphology); in addition, it may also include dynamic characteristics such as edge drift and jitter that change with time, as well as abnormal characteristics related to physical causes such as edge distortion and phase mutation caused by surface defects or optical path anomalies. These characteristics together reflect information such as phase difference, medium properties and environmental interference in the light wave interference process.

[0091] When determining the fractal dimension based on the edge features of the target interference pattern, the pixel coordinate sequence of the stripe boundary is usually extracted through an edge detection algorithm and converted into a one-dimensional or two-dimensional contour curve. Then, the box dimension method is used to cover the edge curve with grids of different scales. The number of grids required to cover all edge points is counted, and a logarithmic relationship between the grid size and the number of grids is established. The fractal dimension is obtained by linearly fitting the absolute value of the slope of this relationship. The differential box counting method or triangular prism method can also be used to optimize the calculation. If the edge has multifractal characteristics, it is also necessary to combine the multifractal spectrum to analyze the differences in irregularities at different scales. Finally, the fractal dimension is quantified by the spatial filling complexity of the edge contour. The larger the fractal dimension, the rougher the edge and the higher the degree of irregularity.

[0092] S406: Determine the irregularity degree value corresponding to the fractal dimension to obtain the target irregularity degree value.

[0093] In this embodiment, a mapping relationship between a preset fractal dimension and an irregularity value may be used. Based on the mapping relationship, the irregularity value corresponding to the fractal dimension may be determined to obtain the target irregularity value.

[0094] As can be seen, by obtaining the interference pattern generated by illuminating the target area with a preset light wave and extracting texture and edge features from it, and then quantifying texture clarity, roughness value, fractal dimension, and irregularity value, this method can analyze the microscopic morphology and physical properties of the target area in multiple dimensions. Specifically, determining texture clarity based on texture features and correlating it with roughness value can intuitively reflect the surface smoothness or particle distribution state, providing a quantitative basis for material surface quality assessment. Calculating the fractal dimension from edge features and converting it into an irregularity value can characterize the complexity of the edge contour from a geometric fractal perspective, effectively capturing subtle features such as surface defects, deformation, or medium inhomogeneities. This analysis method, which combines optical interference patterns with fractal theory, not only utilizes the sensitivity of light wave interference to phase difference, but also overcomes the limitations of traditional geometric measurement through parameters such as fractal dimension. It can achieve multi-level characterization from macroscopic contours to microscopic details. It has significant advantages in high-precision, non-contact, and quantitative analysis in fields such as precision machining inspection, material surface engineering, and optical component quality control, and can provide scientific and comprehensive quantitative indicators for morphological assessment, defect identification, and physical property research of the target area.

[0095] Exemplarily, the first optimization factor corresponding to the target roughness value is determined. Specifically, it may be a mapping relationship between preset roughness values and optimization factors. The first optimization factor corresponding to the target roughness value may be determined based on the mapping relationship.

[0096] Exemplarily, the second optimization factor corresponding to the target irregularity value is determined. Specifically, it can be a mapping relationship between the irregularity value and the optimization factor. Based on the mapping relationship, the second optimization factor corresponding to the target irregularity value can be determined.

[0097] Exemplarily, the reference corrosion level value is optimized based on the first optimization factor and the second optimization factor to obtain the target corrosion level value. Specifically, the target corrosion level value is calculated according to the following formula:

[0098] Target corrosion level value = reference corrosion level value × (1 + first optimization factor) × (1 + second optimization factor);

[0099] According to the above formula, the reference corrosion degree value can be optimized based on the first optimization factor and the second optimization factor to obtain the target corrosion degree value.

[0100] It can be seen that the core advantage of the corrosion degree assessment method that integrates multi-dimensional data and combines weight and morphology optimization is that it achieves more accurate corrosion state quantification through "multi-source information complementation + dynamic parameter calibration": First, the first weight and the second weight (the sum is 1) are used to perform weighted fusion of the fluorescence signal intensity change (first corrosion degree value) and the topological charge jump (second corrosion degree value), and the importance of the two types of features can be flexibly allocated according to the corrosion mechanism. For example, in the uniform corrosion scene, the fluorescence intensity change accounts for the dominant weight, and the topological charge jump is more critical in local pitting corrosion, avoiding the one-sidedness of a single indicator; secondly, the calculation of the reference corrosion degree value integrates the two-dimensional corrosion features, and the target roughness value (reflecting the The actual damage of corrosion to the surface morphology is further correlated with the surface convex and concave macro features) and the target irregularity value (the micro-geometric complexity is characterized by the fractal dimension). The corresponding first and second optimization factors can dynamically calibrate the measurement deviation caused by surface undulations or crack fractals (such as the error of fluorescence scattering amplified by rough surfaces). Ultimately, this two-layer framework of "weighted fusion of initial estimation + re-optimization of morphological features" can not only reduce the noise influence of a single indicator through multi-source data, but also combine the surface physical properties to approach the real hazards of corrosion (such as the influence of deep corrosion pits and complex cracks on the mechanical properties of equipment), providing a quantitative basis that is more in line with engineering practice for corrosion monitoring of industrial equipment, and helping to improve the accuracy and reliability of maintenance decisions.

[0101] S104: Determine a defect warning level of the target substation component based on the target corrosion degree value, and determine target warning information based on the defect warning level.

[0102] In this implementation, see Figure 6 , Figure 6 This is a schematic diagram of a mapping table of corrosion degree values and defect warning levels provided by an embodiment of the present application. Figure 6In the mapping table 600 between corrosion severity values and defect warning levels, multiple defect warning levels and the corresponding corrosion severity value ranges for each of the multiple defect warning levels are included. Defect warning levels include level 1, level 2, and level 3. The range of corrosion severity values corresponding to level 1 warning is less than a first threshold, the range of corrosion severity values corresponding to level 2 warning is greater than or equal to the first threshold and less than a second threshold, and the range of corrosion severity values corresponding to level 3 warning is greater than or equal to the second threshold and less than a third threshold. The first threshold is less than the second threshold, and the second threshold is less than the third threshold.

[0103] Exemplarily, when the target corrosion level value is less than a first threshold value, the defect warning level of the target substation component is determined to be a first-level warning, and the inspection frequency of the target substation component by the target personnel is increased. Specifically, when the target corrosion level value is less than the first threshold value, the defect warning level is determined to be a first-level warning (the lowest risk level), indicating that the current status of the component has not yet posed a serious threat, but attention needs to be paid. At this time, the inspection frequency of the component by the target personnel needs to be increased (such as from once a week to twice a week). By increasing the frequency of manual monitoring, subtle changes in the degree of corrosion can be captured in a timely manner to prevent problems from being ignored in the early stages.

[0104] Exemplarily, when the target corrosion level value is greater than or equal to the first threshold and less than the second threshold, the defect warning level of the target substation component is determined to be a level two warning, and maintenance information is generated. The maintenance information is used to prompt the target personnel to perform anti-corrosion treatment on the target substation component. Specifically, when the target corrosion level value is greater than or equal to the first threshold and less than the second threshold, the warning level is upgraded to a level two warning, indicating that the risk level has increased and active intervention measures need to be taken. At this time, maintenance information needs to be automatically generated to clearly instruct the target personnel to perform anti-corrosion treatment on the component (such as cleaning rust, applying anti-corrosion coating, replacing locally corroded parts, etc.). This information usually includes the processing flow, required materials and precautions to guide personnel to quickly perform maintenance and curb the spread of corrosion.

[0105] Exemplarily, when the target corrosion level value is greater than or equal to the second threshold and less than the third threshold, the defect warning level of the target substation component is determined to be a level three warning, and the target substation component is controlled to stop working. Specifically, when the target corrosion level value is greater than or equal to the second threshold and less than the third threshold, the warning level is determined to be a level three warning, indicating that the component is in a dangerous state and continued operation may cause faults (such as decreased structural strength and electrical performance failure). At this time, it is necessary to directly execute control instructions to force the target substation component to stop working (such as cutting off power and triggering a protective switch). This operation is an emergency measure, the purpose of which is to avoid accidents such as equipment damage and short circuits caused by corrosion, ensure the overall safe operation of the substation, and create conditions for subsequent in-depth maintenance.

[0106] It can be seen that by comparing the target corrosion level value with different thresholds and matching it with the three-level early warning mechanism, it is possible to achieve precise hierarchical control and scientific treatment of the corrosion risk of substation components. Specifically, when the corrosion level is less than the first threshold, the first-level early warning is combined with an increased inspection frequency to promptly detect potential problems in the early stages of corrosion through high-frequency monitoring, preventing minor corrosion from being ignored and worsening; when the corrosion level is between the first and second thresholds, the second-level early warning generates maintenance information and prompts anti-corrosion treatment, actively intervening in the medium corrosion stage, stopping the spread of corrosion through targeted maintenance, and preventing the problem from escalating; when the corrosion level is between the second and third thresholds, the third-level early warning directly controls the shutdown of the component, which can urgently stop losses in the severe corrosion stage, avoiding safety accidents such as structural damage or electrical failure caused by the continued operation of the equipment. This threshold-based disposal method is centered on "threshold quantification of risk + graded corresponding measures". It not only uses threshold division to achieve standardized assessment of corrosion status, but also forms a management closed loop covering the entire "prevention-control-emergency" process through the progressive relationship between warning level and disposal intensity (from monitoring to intervention to shutdown). It can not only avoid waste of resources caused by excessive maintenance, but also reduce manual decision-making delays through automated response, significantly improving the safety, efficiency and scientific nature of substation component operation and maintenance, and providing quantitative guarantees for the reliable operation of power equipment.

[0107] It should be explained that a quantum hybrid model can also be constructed based on corrosion parameters such as roughness, irregularity, and corrosion. The corrosion process is simulated by solving the Schrödinger equation for corrosion evolution, and a three-dimensional corrosion current density distribution map is output. Specifically, based on the results obtained from solving the Schrödinger equation and combined with the component's geometry, the corrosion current density at different locations on the component surface at different times is calculated. This data is then visualized in three dimensions to generate a three-dimensional corrosion current density distribution map, which intuitively displays the distribution of the corrosion current on the component surface. Multi-perspective stereoscopic images of the component surface are then obtained for reconstruction to generate a three-dimensional model. Specifically, multiple cameras are used to capture the substation component surface from different perspectives to obtain multi-perspective two-dimensional images. Cameras are positioned at specific positions and angles to ensure coverage of the entire component surface, with a certain amount of overlap between images from different perspectives. Image quality and consistency are ensured by precisely controlling camera parameters such as focal length, aperture, and exposure time. 3D reconstruction based on multi-view stereo images involves analyzing the features of corresponding pixels in the multi-view 2D images, finding matching relationships between the images, and determining the projected position of the same spatial point in different images. Using triangulation principles, the 3D coordinates of the spatial point are calculated based on the camera's internal and external parameters and the position information of the matching points. By performing similar calculations on all pixels in the image, a 3D point cloud of the component surface is obtained. Finally, the 3D point cloud data is processed through filtering, denoising, and surface fitting to generate a 3D model of the component surface. This 3D model accurately and faithfully reproduces the component surface geometry and detailed features, providing precise geometric information for subsequent integration with the 3D corrosion current density distribution map and defect identification. The 3D model also intuitively displays the overall structure and local features of the component, helping maintenance personnel better understand the component's corrosion status and observe and analyze the location and morphology of corrosion defects from multiple perspectives. Finally, the 3D corrosion current density distribution map is fused with the 3D model. Essentially, this involves aligning and integrating two different types of data—corrosion current density and geometric data—in the same 3D coordinate system. By determining the spatial correspondence between the two types of data, the corrosion current density information is accurately mapped onto the surface of the 3D model. Prior to accurately mapping the corrosion current density information onto the 3D model surface, techniques such as image registration and spatial transformation are utilized to ensure spatial consistency between the two data types. The fused data simultaneously provides both component geometry and corrosion current density information, enabling operations and maintenance personnel to comprehensively analyze component corrosion from multiple dimensions and more accurately determine the severity and impact of corrosion defects.

[0108] In summary, the implementation of the present invention has the following beneficial effects:

[0109] It can be seen that the substation component defect warning method described in the embodiment of the present invention first determines the area where the fluorescent marker is introduced in the target substation component to obtain the target area, and then obtains the change data of the fluorescent marker in the target area within a preset time period to obtain target change data, and then determines the target corrosion degree value of the target substation component based on the target change data, and then determines the defect warning level of the target substation component based on the target corrosion degree value, and determines the target warning information based on the defect warning level, thereby improving the accuracy of the substation component defect warning.

[0110] See also Figure 7 , Figure 7 Schematic diagram of a substation component defect warning device provided in an embodiment of the present application. The substation component defect warning device 700 includes: a determination unit 701 and a processing unit 702;

[0111] The determining unit 701 is configured to determine the area of the target substation component where the fluorescent marker is introduced to obtain the target area;

[0112] The processing unit 702 is configured to obtain change data of the fluorescent marker within the target area within a preset time period to obtain target change data;

[0113] determining a target corrosion degree value of the target substation component based on the target change data;

[0114] The defect warning level of the target substation component is determined based on the target corrosion degree value, and target warning information is determined based on the defect warning level.

[0115] In some possible implementations, the target change data includes fluorescence signal intensity change data and a topological charge jump value of the fluorescent marker within the preset time period. In determining the target corrosion degree value of the target substation component based on the target change data, the processing unit 702 is specifically configured to:

[0116] determining a first corrosion degree value based on the fluorescence signal intensity change data;

[0117] Determining a second corrosion degree value based on the topological charge jump of the fluorescent marker;

[0118] The target corrosion degree value is determined based on the first corrosion degree value and the second corrosion degree value.

[0119] In some possible embodiments, the fluorescence signal intensity change data includes n fluorescence signal intensity values and n fluorescence signal intensity value recording moments within the preset time period, where n is an integer greater than 1, and each fluorescence signal intensity value corresponds to a fluorescence signal intensity value recording moment. In determining the first corrosion degree value based on the fluorescence signal intensity change data, the processing unit 702 is specifically configured to:

[0120] Performing fitting based on the n fluorescence signal intensity values and the n fluorescence signal intensity value recording times to obtain a target fitting straight line;

[0121] Determining the slope of the target fitting straight line to obtain a target slope;

[0122] Obtaining a mapping relationship between the slope and the corrosion degree value;

[0123] The corrosion degree value corresponding to the target slope is determined based on the mapping relationship to obtain the first corrosion degree value.

[0124] In some possible implementations, in determining the target corrosion level value based on the first corrosion level value and the second corrosion level value, the processing unit 702 is specifically configured to:

[0125] Determining a first weight corresponding to the first corrosion degree value and a second weight corresponding to the second corrosion degree value; the sum of the first weight and the second weight is 1;

[0126] Perform calculation based on the first weight, the second weight, the first corrosion degree value, and the second corrosion degree value to obtain a reference corrosion degree value;

[0127] determining a target roughness value and a target irregularity value of the target area;

[0128] Determining a first optimization factor corresponding to the target roughness value;

[0129] Determining a second optimization factor corresponding to the target irregularity value;

[0130] The reference corrosion degree value is optimized based on the first optimization factor and the second optimization factor to obtain the target corrosion degree value.

[0131] In some possible implementations, in determining the target roughness value and the target irregularity value of the target area, the processing unit 702 is specifically configured to:

[0132] Obtaining a target interference pattern obtained after a preset light wave irradiates the target area;

[0133] Acquiring texture features and edge features of the target interference pattern;

[0134] determining a texture clarity of the target interference pattern based on the texture feature;

[0135] Determining a roughness value corresponding to the texture clarity to obtain the target roughness value;

[0136] determining a fractal dimension of the target interference pattern based on the edge features;

[0137] An irregularity degree value corresponding to the fractal dimension is determined to obtain the target irregularity degree value.

[0138] In some possible implementations, the texture features include the number of fringes, the density of fringes, and the spacing between fringes; in determining the texture clarity of the target interference pattern based on the texture features, the processing unit 702 is specifically configured to:

[0139] Determining a first definition corresponding to the number of stripes, a second definition corresponding to the stripe density, and a third definition corresponding to the stripe spacing;

[0140] Determine an average of the first clarity, the second clarity, and the third clarity to obtain an average clarity;

[0141] Obtaining the duration of time the preset light wave irradiates the target area to obtain a target duration;

[0142] Determining a target fine-tuning parameter corresponding to the target duration;

[0143] The average clarity is adjusted based on the target fine-tuning parameter to obtain the texture clarity of the target interference pattern.

[0144] In some possible implementations, in determining the defect warning level of the target substation component based on the target corrosion level value and determining target warning information based on the defect warning level, the processing unit 702 is specifically configured to:

[0145] When the target corrosion degree value is less than a first threshold, determining the defect warning level of the target substation component to be a first-level warning, and increasing the inspection frequency of the target personnel on the target substation component;

[0146] When the target corrosion degree value is greater than or equal to the first threshold and less than the second threshold, the defect warning level of the target substation component is determined to be a level 2 warning, and maintenance information is generated; the maintenance information is used to prompt the target personnel to perform anti-corrosion treatment on the target substation component;

[0147] When the target corrosion degree value is greater than or equal to the second threshold value and less than a third threshold value, determining that the defect warning level of the target substation component is a level three warning, and controlling the target substation component to stop working;

[0148] The first threshold is smaller than the second threshold; and the second threshold is smaller than the third threshold.

[0149] See also Figure 8 , Figure 8 This is a schematic diagram of the structure of an electronic device provided by the embodiment of this application. Figure 8 As shown, electronic device 800 includes a transceiver 801, a processor 802, and a memory 803. These are connected via a bus 804. The memory 803 is used to store computer programs and data, and the transceiver 801 can transmit the data stored in the memory 803 to the processor 802. The above program includes instructions for executing the following steps:

[0150] determining an area of the target substation component where the fluorescent marker is introduced to obtain a target area;

[0151] Acquiring change data of the fluorescent marker in the target area within a preset time period to obtain target change data;

[0152] determining a target corrosion degree value of the target substation component based on the target change data;

[0153] The defect warning level of the target substation component is determined based on the target corrosion degree value, and target warning information is determined based on the defect warning level.

[0154] In some possible implementations, the target change data includes fluorescence signal intensity change data and a topological charge jump value of the fluorescent marker within the preset time period; in determining a target corrosion degree value of the target substation component based on the target change data, the program includes instructions for performing the following steps:

[0155] determining a first corrosion degree value based on the fluorescence signal intensity change data;

[0156] Determining a second corrosion degree value based on the topological charge jump of the fluorescent marker;

[0157] The target corrosion degree value is determined based on the first corrosion degree value and the second corrosion degree value.

[0158] In some possible embodiments, the fluorescence signal intensity change data includes n fluorescence signal intensity values and n fluorescence signal intensity value recording moments within the preset time period, where n is an integer greater than 1, and each fluorescence signal intensity value corresponds to a fluorescence signal intensity value recording moment. In determining the first corrosion degree value based on the fluorescence signal intensity change data, the program includes instructions for performing the following steps:

[0159] Performing fitting based on the n fluorescence signal intensity values and the n fluorescence signal intensity value recording times to obtain a target fitting straight line;

[0160] Determining the slope of the target fitting straight line to obtain a target slope;

[0161] Obtaining a mapping relationship between the slope and the corrosion degree value;

[0162] The corrosion degree value corresponding to the target slope is determined based on the mapping relationship to obtain the first corrosion degree value.

[0163] In some possible implementations, in determining the target corrosion level value based on the first corrosion level value and the second corrosion level value, the program includes instructions for performing the following steps:

[0164] Determining a first weight corresponding to the first corrosion degree value and a second weight corresponding to the second corrosion degree value; the sum of the first weight and the second weight is 1;

[0165] Perform calculation based on the first weight, the second weight, the first corrosion degree value, and the second corrosion degree value to obtain a reference corrosion degree value;

[0166] determining a target roughness value and a target irregularity value of the target area;

[0167] Determining a first optimization factor corresponding to the target roughness value;

[0168] Determining a second optimization factor corresponding to the target irregularity value;

[0169] The reference corrosion degree value is optimized based on the first optimization factor and the second optimization factor to obtain the target corrosion degree value.

[0170] In some possible implementations, in determining the target roughness value and the target irregularity value of the target area, the program includes instructions for performing the following steps:

[0171] Obtaining a target interference pattern obtained after a preset light wave irradiates the target area;

[0172] Acquiring texture features and edge features of the target interference pattern;

[0173] determining a texture clarity of the target interference pattern based on the texture feature;

[0174] Determining a roughness value corresponding to the texture clarity to obtain the target roughness value;

[0175] determining a fractal dimension of the target interference pattern based on the edge features;

[0176] An irregularity degree value corresponding to the fractal dimension is determined to obtain the target irregularity degree value.

[0177] In some possible implementations, the texture features include the number of fringes, the density of fringes, and the spacing between fringes; and in determining the texture clarity of the target interference pattern based on the texture features, the program includes instructions for performing the following steps:

[0178] Determining a first definition corresponding to the number of stripes, a second definition corresponding to the stripe density, and a third definition corresponding to the stripe spacing;

[0179] Determine an average of the first clarity, the second clarity, and the third clarity to obtain an average clarity;

[0180] Obtaining the duration of time the preset light wave irradiates the target area to obtain a target duration;

[0181] Determining a target fine-tuning parameter corresponding to the target duration;

[0182] The average clarity is adjusted based on the target fine-tuning parameter to obtain the texture clarity of the target interference pattern.

[0183] In some possible implementations, in terms of determining the defect warning level of the target substation component based on the target corrosion severity value and determining target warning information based on the defect warning level, the program includes instructions for performing the following steps:

[0184] When the target corrosion degree value is less than a first threshold, determining the defect warning level of the target substation component to be a first-level warning, and increasing the inspection frequency of the target personnel on the target substation component;

[0185] When the target corrosion degree value is greater than or equal to the first threshold and less than the second threshold, the defect warning level of the target substation component is determined to be a level 2 warning, and maintenance information is generated; the maintenance information is used to prompt the target personnel to perform anti-corrosion treatment on the target substation component;

[0186] When the target corrosion degree value is greater than or equal to the second threshold value and less than a third threshold value, determining that the defect warning level of the target substation component is a level three warning, and controlling the target substation component to stop working;

[0187] The first threshold is smaller than the second threshold; and the second threshold is smaller than the third threshold.

[0188] It should be understood that the electronic devices in this application may include smartphones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, PDAs, laptops, mobile Internet devices (MIDs) or wearable devices, or servers, edge computing nodes, etc. The above electronic devices are only examples and are not exhaustive, including but not limited to the above electronic devices.

[0189] The embodiments of the present application further provide a computer-readable storage medium, which stores a computer program. The computer program is executed by a processor to implement part or all of the steps of any one of the methods described in the above method embodiments.

[0190] The embodiments of the present application also provide a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any one of the methods described in the above method embodiments.

[0191] It should be noted that for the aforementioned method implementations, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the implementations described in the specification are all optional implementations, and the actions and modules involved are not necessarily required by this application.

[0192] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0193] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0194] Units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0195] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0196] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, 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, which is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various implementation methods of the present application. The aforementioned memory includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0197] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0198] The above is a detailed introduction to the implementation methods of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above implementation methods is only used to help understand the method and core idea of the present application. At the same time, for those skilled in the art, based on the ideas of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for early warning of substation component defects, characterized in that: The method comprises: determining an area of the target substation component where the fluorescent marker is introduced to obtain a target area; Acquiring change data of the fluorescent marker in the target area within a preset time period to obtain target change data; determining a target corrosion degree value of the target substation component based on the target change data; The defect warning level of the target substation component is determined based on the target corrosion degree value, and target warning information is determined based on the defect warning level.

2. The method according to claim 1, wherein The target change data includes the fluorescence signal intensity change data and the topological charge jump value of the fluorescent marker within the preset time period; and determining the target corrosion degree value of the target substation component based on the target change data includes: determining a first corrosion degree value based on the fluorescence signal intensity change data; Determining a second corrosion degree value based on the topological charge jump of the fluorescent marker; The target corrosion degree value is determined based on the first corrosion degree value and the second corrosion degree value.

3. The method according to claim 2, wherein The fluorescence signal intensity change data includes n fluorescence signal intensity values and n fluorescence signal intensity value recording moments within the preset time period, where n is an integer greater than 1, and each fluorescence signal intensity value corresponds to a fluorescence signal intensity value recording moment; and determining the first corrosion degree value based on the fluorescence signal intensity change data includes: Performing fitting based on the n fluorescence signal intensity values and the n fluorescence signal intensity value recording times to obtain a target fitting straight line; Determining the slope of the target fitting straight line to obtain a target slope; Obtaining a mapping relationship between the slope and the corrosion degree value; The corrosion degree value corresponding to the target slope is determined based on the mapping relationship to obtain the first corrosion degree value.

4. The method according to claim 3, wherein The determining the target corrosion level value based on the first corrosion level value and the second corrosion level value includes: Determining a first weight corresponding to the first corrosion degree value and a second weight corresponding to the second corrosion degree value; the sum of the first weight and the second weight is 1; Perform calculation based on the first weight, the second weight, the first corrosion degree value, and the second corrosion degree value to obtain a reference corrosion degree value; determining a target roughness value and a target irregularity value of the target area; Determining a first optimization factor corresponding to the target roughness value; Determining a second optimization factor corresponding to the target irregularity value; The reference corrosion degree value is optimized based on the first optimization factor and the second optimization factor to obtain the target corrosion degree value.

5. The method according to claim 4, wherein Determining a target roughness value and a target irregularity value of the target area includes: Obtaining a target interference pattern obtained after a preset light wave irradiates the target area; Acquiring texture features and edge features of the target interference pattern; determining a texture clarity of the target interference pattern based on the texture feature; Determining a roughness value corresponding to the texture clarity to obtain the target roughness value; determining a fractal dimension of the target interference pattern based on the edge features; An irregularity degree value corresponding to the fractal dimension is determined to obtain the target irregularity degree value.

6. The method according to claim 5, wherein The texture features include the number of fringes, the density of fringes, and the spacing between fringes; and determining the texture clarity of the target interference pattern based on the texture features includes: Determining a first definition corresponding to the number of stripes, a second definition corresponding to the stripe density, and a third definition corresponding to the stripe spacing; Determine an average of the first clarity, the second clarity, and the third clarity to obtain an average clarity; Obtaining the duration of time the preset light wave irradiates the target area to obtain a target duration; Determining a target fine-tuning parameter corresponding to the target duration; The average clarity is adjusted based on the target fine-tuning parameter to obtain the texture clarity of the target interference pattern.

7. The method according to claim 5, wherein The step of determining the defect warning level of the target substation component based on the target corrosion degree value, and determining target warning information based on the defect warning level, includes: When the target corrosion degree value is less than a first threshold, determining the defect warning level of the target substation component to be a first-level warning, and increasing the inspection frequency of the target personnel on the target substation component; When the target corrosion degree value is greater than or equal to the first threshold and less than the second threshold, the defect warning level of the target substation component is determined to be a level 2 warning, and maintenance information is generated; the maintenance information is used to prompt the target personnel to perform anti-corrosion treatment on the target substation component; When the target corrosion degree value is greater than or equal to the second threshold value and less than a third threshold value, determining that the defect warning level of the target substation component is a level three warning, and controlling the target substation component to stop working; The first threshold is smaller than the second threshold; and the second threshold is smaller than the third threshold.

8. A substation component defect early warning device, characterized in that: The device includes: a determination unit and a processing unit; The determining unit is configured to determine the area in the target substation component where the fluorescent marker is introduced to obtain the target area; The processing unit is configured to obtain change data of the fluorescent marker within the target area within a preset time period to obtain target change data; determining a target corrosion degree value of the target substation component based on the target change data; The defect warning level of the target substation component is determined based on the target corrosion degree value, and target warning information is determined based on the defect warning level.

9. An electronic device, characterized in that: The method comprises a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the one or more programs include instructions for executing the steps in the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 7.

Images