Method for detecting oil contamination of oil-filled equipment based on fluorescence reflection

Abstract

The invention relates to the technical field of oil stain detection, and discloses an oil-filled equipment oil stain detection method based on fluorescence reflection. The method comprises the following steps: carrying out cleaning pretreatment on a to-be-detected surface; an ultraviolet light source is utilized to excite the oil stain to generate fluorescence; collecting a fluorescence image through an imaging device with a filter; performing noise reduction and edge processing on the image to extract an oil stain area; and finally judging the existence and type of oil stain and estimating the thickness according to image features. According to the invention, the fluorescence characteristic of the oil stain is utilized, no fluorescent agent needs to be added, and pollution-free, high-precision and high-efficiency non-contact detection is realized.

Description

Technical Field

[0001] This invention belongs to the field of oil pollution detection technology, specifically relating to a method for detecting oil pollution in oil-filled equipment based on fluorescence reflection. Background Technology

[0002] Oil contamination detection is crucial for equipment maintenance and safety assurance in fields such as power equipment (e.g., oil-immersed transformers), industrial pipelines, and mechanical systems. Currently, common oil contamination detection methods have several limitations: contact detection methods, such as test strip wiping or gravimetric methods, are inefficient and may contaminate samples, making large-area rapid detection difficult; traditional fluorescence detection technology, while highly sensitive, requires the addition of fluorescent agents, which may contaminate the test object and the environment, and its accuracy is also affected by the compatibility between the fluorescent agent and the oil contamination; non-contact detection methods such as ultrasound and infrared are easily affected by environmental interference and lack sufficient sensitivity for identifying thin layers of oil contamination; and manual visual inspection is highly subjective, relies on experience, and is prone to missed or incorrect detections.

[0003] Existing research confirms that most industrial oil contaminants (such as transformer oil, lubricating oil, hydraulic oil, and diesel oil) contain fluorescent structures such as double bonds and large π bonds, and can produce characteristic fluorescence under ultraviolet light excitation (especially around 365 nm). Furthermore, the fluorescence intensity is correlated with the properties and thickness of the oil contaminant. Based on this common characteristic, this invention proposes a universal fluorescence detection method applicable to various industrial oil contaminants without the need for added fluorescent agents, thereby addressing the problems of narrow applicability, easy contamination, and low efficiency of existing technologies. Summary of the Invention

[0004] The present invention aims to solve the following problems existing in the existing oil pollution detection technology: low detection efficiency, potential secondary pollution, insufficient sensitivity to thin oil layers, high susceptibility to environmental interference, narrow applicability, and strong subjectivity leading to misjudgment.

[0005] To achieve the above objectives, this invention provides a method for detecting oil contamination in oil-filled equipment based on fluorescence reflection. The core of this method lies in utilizing the characteristic fluorescence generated by the fluorescent structure inherent in oil contamination under ultraviolet light excitation for non-contact detection. The technical solution mainly includes the following steps: Pretreatment: The surface to be tested is cleaned to remove non-oil and other contaminants. Specific methods can be chosen based on the surface characteristics, such as using compressed air to blow, a soft brush, or wiping with solutions of ethanol, isopropanol, or neutral detergents.

[0006] Fluorescence excitation: The surface to be tested is irradiated with an ultraviolet light source of a specific wavelength (such as 365nm), which excites the oil stains to produce fluorescence. The light source power (10W-20W), irradiation distance (20cm-40cm), and irradiation angle (vertical or 60°-75° tilt) can be adjusted for different environments and surface shapes. A multi-light source array can also be used to eliminate irradiation dead zones.

[0007] Signal acquisition: Imaging devices (such as high-resolution cameras) equipped with filters (such as 400nm) and light shields are used to acquire images of the excited fluorescence, effectively filtering out ambient stray light interference.

[0008] Signal processing: The acquired fluorescence images are digitally processed, including noise reduction using algorithms such as Gaussian filtering, and edge detection algorithms such as the Canny operator are applied to automatically extract the contours of the oil stain areas.

[0009] Judgment and Analysis: Comprehensive judgment based on processed image features: Presence and Location: By analyzing the image grayscale values ​​(usually the grayscale values ​​of oily areas are between 50 and 150) and edge information, the presence and location of oil stains can be determined.

[0010] Type differentiation: By analyzing the continuity of the edge of the oil-contaminated area and the characteristics of the light intensity-position function, we can distinguish between defective oil contamination caused by leakage (discontinuous edge, nonlinear function) and non-defective oil contamination left over from production (continuous edge, linear function).

[0011] Thickness estimation: Based on the linear relationship between fluorescence intensity and oil film thickness established by the modified Beer-Lambert law, the oil film thickness is quantitatively estimated by comparing the fluorescence gray value of the oil stain area to be tested with the gray value of a standard oil film sample with known thickness.

[0012] This invention also includes an oil film thickness estimation step, which is based on a modified Beer-Lambert law. This law simultaneously considers the excitation light absorption and the internal filtering effect of the emitted light, establishing a linear relationship between fluorescence intensity and oil film thickness. By preparing a standard oil film sample of known thickness and obtaining its average gray value, the actual oil film thickness can be quantitatively estimated.

[0013] Furthermore, this invention provides an oil contamination type identification step, which analyzes the derivative continuity of the oil film edge based on the lubrication approximation and film thickness equation in fluid mechanics: leaked oil has a source term that causes discontinuous edge thickness changes; residual oil, on the other hand, forms a smooth and continuous edge due to static spreading. Through image edge detection and derivative analysis, leaked oil and residual oil can be automatically distinguished.

[0014] The advantages of this invention compared to the prior art are as follows: (1) High versatility: Based on the common fluorescent characteristics of various industrial oil stains, there is no need to customize solutions for specific oils or scenarios, and the application range is wide.

[0015] (2) No secondary pollution: The oil stains themselves are used directly for fluorescence, without the need to add any external fluorescent agents, and there is no pollution to the environment and equipment.

[0016] (3) High detection accuracy: Combining optical filtering and image processing technology, it can effectively identify thin oil stains with a thickness of more than 0.1 mm and accurately distinguish the defect type.

[0017] (4) High efficiency and easy automation: The single detection process takes a short time (≤30 minutes) and can be integrated with automated equipment such as robotic arms to achieve efficient and unmanned detection.

[0018] (5) Rich information dimensions: A single detection can simultaneously obtain multi-dimensional information such as the presence, location, type (leakage or residue) and thickness of oil stains, providing accurate data support for maintenance decisions. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein: Figure 1 The flowchart shows the oil contamination detection method for oil-filled equipment based on fluorescence reflection provided by the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0021] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0022] Furthermore, in this invention, descriptions involving "first," "second," etc., are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0023] In this invention, unless otherwise explicitly specified and limited, the terms "connection," "fixed," etc., should be interpreted broadly. For example, "fixed" can mean a fixed connection, a detachable connection, or an integral part; it can mean a mechanical connection; it can mean a direct connection or an indirect connection through an intermediate medium; it can mean the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0024] Furthermore, the technical solutions of the various embodiments of the present invention can be combined with each other, but only if they are feasible for those skilled in the art. If the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0025] Please see Figure 1 As shown, this embodiment of the invention provides a method for detecting oil contamination in oil-filled equipment based on fluorescence reflection. It utilizes the characteristic that oil contamination itself fluoresces under ultraviolet light excitation for non-contact detection, and includes the following steps: Step S101, Pretreatment: Clean the surface to be tested to remove interfering substances; Step S102, Fluorescence excitation: Irradiate the surface to be tested with an ultraviolet light source to excite the oil stains to produce fluorescence; Step S103, Signal acquisition: The imaging device is equipped with a filter to filter out stray light and acquire fluorescence images of the surface to be detected. Step S104, Signal processing: Denoising and edge detection are performed on the fluorescence image to extract the oil stain area and obtain image features; Step S105, Determination: Based on the image features, determine at least one of the following: the presence, type, or thickness of the oil stain.

[0026] In step S101, the preprocessing step includes at least one of the following methods: The surface to be tested is cleaned by blowing with compressed air or by brushing with a soft brush. Wipe the surface to be tested with a lint-free cloth or soft cloth dampened with ethanol, isopropanol or neutral detergent.

[0027] In step S102, during the fluorescence excitation step: The ultraviolet light source has a wavelength of 365nm and a power of 10W to 20W; The distance between the ultraviolet light source and the surface to be tested is 20cm to 40cm; The ultraviolet light source is irradiated at a vertical or oblique angle, with the oblique angle being 60° to 75°; and / or The surface to be tested is illuminated from different angles using a multi-light source array.

[0028] In step S103, the signal acquisition step includes: The imaging device is a camera with a resolution of at least 12 million pixels; The filter is a 400nm filter used to filter out excitation light and allow fluorescence to pass through; The imaging device is equipped with a light shield; and / or The acquisition method is either vertical shooting or shooting while moving along the axis of the object to be inspected.

[0029] In step S104, the signal processing step includes: The fluorescence image was denoised using a Gaussian filter. Edge detection was performed using the Canny operator to extract the edges of the oil-stained areas; Calculate the average gray value of the oil-stained area.

[0030] In step S105, the determination step includes: When the average gray value is in the range of 50 to 150, it is determined that oil stains are present; When the average gray value is greater than 200, it is determined that there is no oil stain; Based on the linear and nonlinear characteristics of the light intensity-position function and edge continuity, we can distinguish between defective oil leaks and non-defective residual oil stains.

[0031] The method also includes an oil film thickness estimation step: Prepare standard oil film samples and measure their thickness; Acquire fluorescence images of the standard oil film samples and obtain their average grayscale values; Based on the linear relationship between fluorescence intensity and oil film thickness, the actual oil film thickness is estimated by comparing the average gray value of the actual oil-stained area with that of the standard sample.

[0032] Furthermore, the relationship between fluorescence intensity and oil film thickness is based on a modified Beer-Lambert law, taking into account the internal filtering effect of excitation light absorption and emission light, and its formula is as follows: ; in, Fluorescence intensity; The initial light intensity of the light source; It is the sum of fluorescence quantum yield and instrument efficiency factor; To excite light absorbance; For optical path length.

[0033] The method also includes an oil stain type identification step: Based on derivative continuity analysis at the oil film edge, leaked oil is distinguished from residual oil; Among them, the thickness of the oil film at the edge of the leaked oil is discontinuous, while the edge of the oil film at the edge of the residual oil is smooth and continuous.

[0034] Furthermore, the objects to be tested include oil-immersed transformers, oil pipelines, gearboxes, or oil storage containers.

[0035] The following detailed description of the oil contamination detection method for oil-filled equipment based on fluorescence reflection provided by the present invention is illustrated with specific embodiments.

[0036] Example 1: Oil Leakage Detection of Oil-Immersed Transformers This embodiment is applied to the detection of oil leakage on the surface of the outer casing of an oil-immersed transformer in a substation.

[0037] 1. Pre-treatment: Use compressed air at a pressure of 0.3 MPa to blow away surface dust from the transformer casing. Then, wipe key inspection areas such as welds and flange connections with a lint-free cloth dampened with 50% ethanol solution to remove stubborn stains. After wiping, allow to air dry for 10 minutes.

[0038] After preprocessing, the weld area was vertically irradiated with a 365nm ultraviolet lamp. After image acquisition, Gaussian filtering and Canny edge detection were applied to extract the oil-stained area and calculate the average gray value. If the value was between 50 and 150, and the light intensity-position function was non-linear and the edges were discontinuous, it was determined to be an oil leak caused by a welding defect.

[0039] 2. Fluorescence excitation: A 15W ultraviolet lamp with a center wavelength of 365nm was used as the light source. The ultraviolet lamp was vertically aimed at the area to be detected, and an irradiation distance of 30cm was maintained.

[0040] 3. Signal Acquisition: A 12-megapixel industrial camera was used as the imaging device, with a 400nm bandpass filter and a light shield mounted on the front of the camera. The camera was vertically aimed at the surface being measured to capture images, with the image resolution set to 4000×3000 pixels.

[0041] 4. Signal Processing: The acquired fluorescence images were imported into ImageJ software. First, Gaussian filtering was performed for noise reduction, and then the images were converted to grayscale for analysis. Calibration showed that the grayscale value range of the oil-film-covered area was 50-150, while the grayscale value of the oil-free, clean area was greater than 200.

[0042] 5. Judgment: At a certain weld, the image shows a continuous region with a grayscale value between 80 and 120. The light intensity-position function of this region exhibits a non-linear variation, and its edge contour shows a break. Based on these characteristics, the oil leak is determined to be caused by a welding defect. Furthermore, based on the average grayscale value of this region and a pre-calibrated thickness-grayscale curve, the oil film thickness at this location is estimated to be approximately 0.2 mm.

[0043] Example 2: Detection of oil stains on the outer wall of oil pipelines This embodiment is applied to the inspection of the outer wall of long-distance oil pipelines.

[0044] 1. Pre-treatment: Use a soft-bristled brush to clean the outer wall of the pipe to remove any adhering substances. For stubborn stains, wipe with isopropyl alcohol and then allow to air dry.

[0045] 2. Fluorescence excitation: A multi-source array consisting of two 365nm ultraviolet lamps (each with a power of 10W) ​​is used. The two ultraviolet lamps are symmetrically arranged on both sides of the pipe, 40cm away from the pipe surface, and the irradiation angle is adjusted to 75° to ensure uniform circumferential illumination of the outer wall of the pipe without any dead angles.

[0046] 3. Signal Acquisition: A 16-megapixel camera equipped with a 400nm filter was used. The camera was controlled to move along the pipe axis at 0.5-meter intervals to capture a series of continuous fluorescence images.

[0047] 4. Signal Processing: All acquired images were stitched together using OpenCV software to form a complete fluorescence image of the pipe's outer wall. Subsequently, suspected oil-contaminated areas were extracted through image analysis, and their average grayscale values ​​were calculated.

[0048] 5. Judgment: At one interface of the pipeline, the image shows an area with an average grayscale value between 60 and 90, and the edges of this area are discontinuous. Based on this, it is determined that there is an oil leak at this location due to a sealing defect. The grayscale values ​​of the rest of the pipeline are uniform and greater than 200, and are therefore determined to be free of oil contamination.

[0049] Example 3: Detection of residual oil stains on the surface of a gearbox This embodiment is used to determine whether the oil stains at the mating surface of a mechanical gearbox are from leakage or assembly residue.

[0050] 1. Pretreatment: First, blow the surface of the gearbox with compressed air, then wipe the mating surfaces with a neutral surfactant solution, and finally rinse with pure water and let it dry.

[0051] 2. Fluorescence excitation: Use a 365nm, 20W ultraviolet lamp to irradiate the mating surface at a 60° angle from a distance of 25cm from the gearbox surface.

[0052] 3. Signal Acquisition: Vertical shooting was performed using a 12-megapixel smartphone camera equipped with an external 400nm filter.

[0053] 4. Signal processing: The image was imported into ImageJ software for analysis, and the grayscale value of the local area was measured to be between 120 and 140.

[0054] 5. Judgment: The light intensity-position function in this area exhibits a linear variation, and the edge contour is continuous and smooth. Based on this characteristic, the oil stain is determined to be a non-defective oil stain left over from the assembly process, rather than a leak generated during operation; therefore, no maintenance is required.

[0055] Implementation methods for estimating oil film thickness To quantitatively measure oil film thickness, a quantitative relationship between fluorescence intensity and thickness needs to be established. The specific steps are as follows: Standard sample preparation: Take a clean plate of the same material as the surface of the device to be tested, add the same type of oil using a micro-dropper, and after it spreads naturally to form a uniform oil film, use a vernier caliper to accurately measure the thickness of the standard oil film.

[0056] Standard sample measurement: Under standard conditions (e.g., a vertical distance of 30 cm from a UV light source), the standard sample is excited to produce fluorescence, and its fluorescence image is acquired. The average gray value of the oil film area in the image is calculated.

[0057] Actual measurement: In actual detection, the above fluorescence excitation and image acquisition steps were repeated for the unknown oil stain to obtain its average gray value.

[0058] Thickness Calculation: Based on the modified Beer-Lambert law, under specific conditions, fluorescence intensity (represented by grayscale value) and oil film thickness exhibit a linear relationship within a certain range. By comparing the average grayscale value of the oil stain to be tested with the grayscale value of the standard oil film, the actual oil film thickness can be calculated based on this linear relationship.

[0059] Implementation methods for identifying oil stain types The difference between "leaked oil" and "residual oil" can be determined based on the shape and edge characteristics of the oil film: For continuously leaking oil slicks, the film thickness equation includes a discontinuity term caused by the leakage source. Numerically, this manifests as a discontinuity in the thickness variation at the oil film edge under steady-state conditions.

[0060] For static assembly residual oil stains, their edge shape is smooth and continuous, and can be described by a parabolic model under the lubrication approximation.

[0061] In images, this physical difference manifests as follows: the edges of the fluorescent image of the leaked oil area show discontinuities after multiple derivatives; while the edges of the residual oil area remain smooth and continuous. By using image edge detection algorithms (such as the Canny operator) combined with derivative analysis of the edge contour, the type of oil contamination can be automatically identified.

[0062] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0063] Furthermore, it should be noted that the scope of the methods and systems in the embodiments of the present invention is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.

[0064] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of the present invention.

Claims

1. A method for detecting oil contamination in oil-filled equipment based on fluorescence reflection, characterized in that, Utilizing the property of oil stains to fluoresce under ultraviolet light excitation, a non-contact detection method is performed, including the following steps: Pretreatment steps: Clean the surface to be tested to remove interfering substances; Fluorescence excitation step: Irradiate the surface to be tested with an ultraviolet light source to excite the oil stains to produce fluorescence; Signal acquisition steps: Use an imaging device to acquire a fluorescence image of the surface to be detected. The imaging device is equipped with a filter to filter out stray light. Signal processing steps: Denoising and edge detection are performed on the fluorescence image to extract the oil stain area and obtain image features; Determination Steps: Based on the image features, determine at least one of the following: the presence, type, or thickness of the oil stain.

2. The method for detecting oil contamination in oil-filled equipment based on fluorescence reflection as described in claim 1, characterized in that, The preprocessing step includes at least one of the following methods: The surface to be tested is cleaned by blowing with compressed air or by brushing with a soft brush. Wipe the surface to be tested with a lint-free cloth or soft cloth dampened with ethanol, isopropanol or neutral detergent.

3. The method for detecting oil contamination in oil-filled equipment based on fluorescence reflection as described in claim 1, characterized in that, In the fluorescence excitation step: The ultraviolet light source has a wavelength of 365nm and a power of 10W to 20W; The distance between the ultraviolet light source and the surface to be tested is 20cm to 40cm; The ultraviolet light source is irradiated at a vertical or oblique angle, with the oblique angle being 60° to 75°; and / or The surface to be tested is illuminated from different angles using a multi-light source array.

4. The method for detecting oil contamination in oil-filled equipment based on fluorescence reflection as described in claim 1, characterized in that, In the signal acquisition step: The imaging device is a camera with a resolution of at least 12 million pixels; The filter is a 400nm filter; The imaging device is equipped with a light shield; and / or The acquisition method is either vertical shooting or shooting while moving along the axis of the object to be inspected.

5. The method for detecting oil contamination in oil-filled equipment based on fluorescence reflection as described in claim 1, characterized in that, The signal processing steps include: The fluorescence image was denoised using a Gaussian filter. Edge detection was performed using the Canny operator to extract the edges of the oil-stained areas; Calculate the average gray value of the oil-stained area.

6. The method for detecting oil contamination in oil-filled equipment based on fluorescence reflection as described in claim 5, characterized in that, In the determination step: When the average gray value is in the range of 50 to 150, it is determined that oil stains are present; When the average gray value is greater than 200, it is determined that there is no oil stain; Based on the linear and nonlinear characteristics of the light intensity-position function and edge continuity, we can distinguish between defective oil leaks and non-defective residual oil stains.

7. The method for detecting oil contamination in oil-filled equipment based on fluorescence reflection as described in claim 1, characterized in that, It also includes an oil film thickness estimation step: Prepare standard oil film samples and measure their thickness; Acquire fluorescence images of the standard oil film samples and obtain their average grayscale values; Based on the linear relationship between fluorescence intensity and oil film thickness, the actual oil film thickness is estimated by comparing the average gray value of the actual oil-stained area with that of the standard sample.

8. The method for detecting oil contamination in oil-filled equipment based on fluorescence reflection as described in claim 7, characterized in that, The relationship between fluorescence intensity and oil film thickness is based on a modified Beer-Lambert law, taking into account the internal filtering effect of excitation light absorption and emission light, and the relationship is as follows: ； in, Fluorescence intensity; The initial light intensity of the light source; It is the sum of fluorescence quantum yield and instrument efficiency factor; To excite light absorbance; For optical path length.

9. The method for detecting oil contamination in oil-filled equipment based on fluorescence reflection as described in claim 1, characterized in that, It also includes steps for identifying the type of oil stain: Based on derivative continuity analysis at the oil film edge, leaked oil is distinguished from residual oil; Among them, the thickness of the oil film at the edge of the leaked oil is discontinuous, while the edge of the oil film at the edge of the residual oil is smooth and continuous.

10. The method for detecting oil contamination in oil-filled equipment based on fluorescence reflection as described in claim 4, characterized in that, The objects to be tested include oil-immersed transformers, oil pipelines, gearboxes, or oil storage containers.

Images