Method and device for measuring trace water content in transformer oil

Abstract

A method and device for measuring the trace moisture content in transformer oil. The method comprises: capturing a first image of a laser beam passing through the transformer oil; preprocessing the first image of the laser beam to obtain a second image of the laser beam; counting the number of pixels of the laser beam in the second image of the laser beam; and calculating the trace moisture content of the transformer oil using a trace moisture detection model based on the number of pixels. The method and device provided by embodiments of the present invention effectively address the issues of existing trace moisture measurement technologies, such as susceptibility to interference, high cost, and inconvenience, making the measurement and monitoring of the trace moisture content of transformer oil more accurate, convenient, and rapid. Furthermore, because the images can be reused repeatedly, the cost and risk of monitoring are significantly reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer oil detection, in particular to a method and a device for measuring the trace water content in transformer oil. Background Art

[0002] Transformer oil faces three major challenges during operation: heat dissipation, moisture resistance, and degradation. To address these issues, transformer oil is typically measured using indicators such as moisture content, chromatography, and insulation properties. Moisture content is a key indicator of oil oxidation. Moisture in oil originates from oxidation of the oil itself, catalytic effects of metal additives, aging of insulation paper, and external intrusion. A moisture concentration of less than 1000 mg / L is considered moisture content. Transformer oil moisture detection technology has been a focus of recent attention for transformer safety. Currently, moisture detection primarily involves sampling (offline) and online testing. Sampling testing primarily includes distillation, chromatography, and Karl Fischer methods. Online testing primarily involves capacitive sensing, microwave sensing, and infrared spectroscopy. While sampling offers high accuracy, it generally requires periodic oil sampling, making it difficult to monitor changes in moisture content in real time and requiring high operator skill. Current online testing methods, however, are susceptible to interference and are costly. When using electrical sensors such as capacitive and microwave sensors for trace water monitoring, electromagnetic interference near electrical equipment can affect the sensor's measurement results. Non-electrical sensors such as infrared spectroscopy and optical fiber are expensive and difficult to maintain, and infrared spectroscopy is easily affected by background light intensity. Furthermore, direct use of electrical or non-electrical sensors for on-site monitoring requires consideration of sensor placement issues such as inserting the sensor into the insulating oil, making their use extremely inconvenient. Summary of the Invention

[0003] In view of this, the present invention proposes a method and device for measuring the trace water content in transformer oil, aiming to solve the problems of existing trace water measurement technology such as susceptibility to interference, high cost, and inconvenience in use.

[0004] In a first aspect, an embodiment of the present invention provides a method for measuring the trace water content in transformer oil, comprising: acquiring a first image of a laser beam passing through the transformer oil; preprocessing the first image of the laser beam to obtain a second image of the laser beam; counting the number of pixel points of the laser beam in the second image of the laser beam; and calculating the trace water content of the transformer oil using a trace water detection model based on the number of pixel points.

[0005] Furthermore, the preprocessing of the first image of the laser light column to obtain the second image of the laser light column includes: binarizing the first image of the laser light column to obtain a grayscale image of the first image of the laser light column; and segmenting the grayscale image of the first image of the laser light column to obtain the second image of the laser light column.

[0006] Furthermore, counting the number of pixel points of the laser beam in the second image of the laser beam includes: reading the grayscale value of each pixel point in the second image of the laser beam; counting the number of pixel points with the same grayscale value in the laser beam area in the second image of the laser beam, and obtaining the total number of pixel points of the laser beam and the grayscale histogram of the laser beam.

[0007] Furthermore, the method of calculating the water content of the transformer oil using a water detection model based on the number of pixels includes: calculating the water content TW of the transformer oil using the following formula:

[0008] TW=1.0444+5.52×10 -4 Gr+3.161×10 -7 Gr 2 ;

[0009] Here, Gr is the number of pixels of the laser beam in the second image of the laser beam.

[0010] In a second aspect, an embodiment of the present invention further provides a device for measuring the trace water content in transformer oil, comprising: an image acquisition unit for acquiring a first image of a laser beam passing through the transformer oil; an image preprocessing unit for preprocessing the first image of the laser beam to obtain a second image of the laser beam; a pixel point counting unit for counting the number of pixel points of the laser beam in the second image of the laser beam; and a trace water content calculation unit for calculating the trace water content of the transformer oil using a trace water detection model based on the number of pixel points.

[0011] Furthermore, the image preprocessing unit is further configured to: perform binarization processing on the first image of the laser beam to obtain a grayscale image of the first image of the laser beam; and segment the grayscale image of the first image of the laser beam to obtain a second image of the laser beam.

[0012] Furthermore, the pixel point counting unit is also used to: read the grayscale value of each pixel point in the second image of the laser light column; count the number of pixel points with the same grayscale value in the laser light column area in the second image of the laser light column, and obtain the total number of pixel points of the laser light column and the grayscale histogram of the laser light column.

[0013] Furthermore, the water content calculation unit is further configured to calculate the water content TW of the transformer oil using the following formula:

[0014] TW=1.0444+5.52×10 -4 Gr+3.161×10 -7 Gr 2 ;

[0015] Here, Gr is the number of pixels of the laser beam in the second image of the laser beam.

[0016] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the methods provided in each embodiment of the present invention.

[0017] The method and device for measuring the water content in transformer oil provided by the embodiments of the present invention process and analyze laser beam images to measure the water content in transformer oil. This effectively addresses the problems of existing water content measurement technologies, such as susceptibility to interference, high cost, and inconvenience, and avoids measurement deviations caused by sensing equipment, making the measurement and monitoring of the water content in transformer oil more accurate and convenient. Furthermore, because the captured images can be reused, if the monitoring results deviate, only the images need to be reanalyzed, without having to rearrange the monitoring equipment and start monitoring from the beginning, significantly reducing the cost and risk of monitoring. Furthermore, the method provided by this embodiment simply requires importing the captured laser images into a program for analysis to obtain the water content, enabling real-time measurement. Compared to traditional methods (such as the Karl Fischer method, which takes approximately 10 to 20 minutes), the measurement speed is faster and more efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flow chart of a method for measuring trace water content in transformer oil provided by an exemplary embodiment of the present invention;

[0019] Figure 2 (a) Figure 2 (b) Figure 2 (c) a first image of a laser beam, a grayscale image of the first image of the laser beam, and a second image of the laser beam, respectively, provided by an exemplary embodiment of the present invention;

[0020] Figure 3 (a) Figure 3 (b) Figure 3 (c) First images of laser beams of sample 1, sample 2, and sample 3, respectively, provided according to an exemplary embodiment of the present invention;

[0021] Figure 4 (a)- Figure 4(d) is an original cross-sectional view of the laser beam of different samples provided by an exemplary embodiment of the present invention, taken with a 5° offset and a 10x magnification lens, wherein: Figure 4 (a) is a cross-sectional view of the laser beam collected in air. Figure 4 (b) is a cross-sectional view of the laser beam collected in pure water. Figure 4 (c) is a cross-sectional view of the laser beam collected in transformer oil with a water content of 13.29 mg / L. Figure 4 (d) is a cross-sectional view of the laser beam collected in transformer oil with a trace water content of 31.61 mg / L;

[0022] Figure 5 A fitting curve of a micro-water detection model provided by an exemplary embodiment of the present invention;

[0023] Figure 6 A schematic structural diagram of a device for measuring trace water content in transformer oil provided in an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0024] Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided to provide a thorough and complete disclosure of the present invention and to fully convey the scope of the present invention to those skilled in the art. The terminology used in the exemplary embodiments shown in the accompanying drawings is not intended to limit the present invention. In the accompanying drawings, identical elements are denoted by the same reference numerals.

[0025] Unless otherwise specified, the terms used herein (including technical terms) have the meanings commonly understood by those skilled in the art. In addition, it is understood that terms defined in commonly used dictionaries should be understood to have the same meanings as those in the context of the relevant fields, and should not be understood as idealized or overly formal meanings.

[0026] Figure 1 A flow chart of a method for measuring trace water content in transformer oil provided in an exemplary embodiment of the present invention.

[0027] like Figure 1 As shown, the method includes:

[0028] Step S101: capturing a first image of a laser beam passing through transformer oil.

[0029] In the embodiment of the present invention, the first image of the laser beam passing through the transformer oil can be acquired by an image acquisition device, that is, the original image of the laser beam can be acquired. Figure 2(a) is a first image of a laser beam of transformer oil collected according to an exemplary embodiment of the present invention.

[0030] Step S102: pre-processing the first image of the laser beam to obtain a second image of the laser beam.

[0031] In the embodiment of the present invention, preprocessing may be processing performed on an image before feature extraction, such as stretching, compression, binarization, segmentation, etc. The main purpose of preprocessing is to eliminate irrelevant information in the image and restore useful real information.

[0032] Furthermore, step S102 includes:

[0033] performing binarization processing on the first image of the laser beam to obtain a grayscale image of the first image of the laser beam;

[0034] The grayscale image of the first image of the laser beam is segmented to obtain a second image of the laser beam.

[0035] Figure 2 (b) is a grayscale image of a first image of a laser beam provided by an exemplary embodiment of the present invention. Figure 2 (b) shows that Figure 2 (a) After binarization, the data can be simplified while enhancing the feature information of the graphic boundary.

[0036] Since the optical platform and acrylic resin oil tank can cause stray light scattering and enter the image acquisition device, after obtaining the grayscale image of the laser beam, it is necessary to further segment it to eliminate the stray light scattering caused by the background, equipment light and transparent oil tank wall, so as to reduce the brightness impact caused by stray light scattering on the oil tank wall and other parts. Figure 2 (c) is a second image of a laser beam provided by an exemplary embodiment of the present invention. Figure 2 (c) shows that Figure 2 (b) Cropping is performed to remove image information outside the laser beam area and shield the scattered light from the transparent oil tank wall and possible background light. The image size after cropping is always 1000×150, thus ensuring the consistency of the shielded information amount.

[0037] Step S103: Counting the number of pixels of the laser beam in the second image of the laser beam.

[0038] In the embodiment of the present invention, the total number of pixels of the laser beam in the second image is counted.

[0039] Furthermore, step S103 includes:

[0040] Reading the grayscale value of each pixel in the second image of the laser beam;

[0041] The number of pixels with the same grayscale value in the laser beam area in the second image of the laser beam is counted to obtain the total number of pixels in the laser beam and a grayscale histogram of the laser beam.

[0042] In the embodiment of the present invention, any method of reading the grayscale value of a pixel point can be used, for example, the image reading function imread in matlab can be used for reading, or cv2.imread in opencv can be used for reading. After reading the grayscale value of each pixel point, the envelope boundary of the laser beam on the image after removing the background information is calculated using the sensitivity setting, and the following can be obtained: Figure 2 (c) shows a second image clearly displaying the laser beam, i.e., a contour image of the laser beam. In this image, black denotes an invalid statistical region, and white denotes a valid statistical region. The number of pixels at each grayscale value within the valid white region is further counted to obtain a grayscale histogram of the second laser beam image.

[0043] Step S104: Based on the number of pixels, the water content of the transformer oil is calculated using a water detection model.

[0044] In the embodiment of the present invention, the trace water detection model may be a polynomial function curve obtained by pre-fitting the number of pixels and the trace water content of a large number of test samples.

[0045] Furthermore, step S104 includes:

[0046] The water content TW of transformer oil is calculated using the following formula:

[0047] TW=1.0444+5.52×10 -4 Gr+3.161×10 -7 Gr 2 ;

[0048] Here, Gr is the number of pixels of the laser beam in the second image of the laser beam.

[0049] In the embodiment of the present invention, a large number of experiments were conducted before using laser brightness to detect the water content in transformer oil to verify the relationship between the two. The specific experimental process is as follows:

[0050] Transformer oils containing different trace water contents were collected as experimental samples. Since too many samples were collected, this embodiment will not list them one by one, and only three samples are selected for exemplary description.

[0051] Before the laser was applied, the trace water content in the above three samples was measured using the Karl Fischer reagent method. Among them, the trace water content in sample one was 6.61 mg / L; the trace water content in sample two was 16.61 mg / L; and the trace water content in sample three was 40.23 mg / L.

[0052] Next, laser light was injected into each transformer oil sample in the order of the water content from low to high, and the laser beam image was collected in the direction perpendicular to the optical axis of the laser beam. Figure 3 (a) Figure 3 (b) Figure 3 (c) The first images (original images) of the laser beams of sample 1, sample 2, and sample 3 provided by an exemplary embodiment of the present invention. Figure 3 (a)- Figure 3 As shown in (c), as the water content in the transformer oil increases, the photosensitivity of the laser beam gradually increases.

[0053] In addition, in order to more clearly illustrate the effect of micro-water content on the laser photosensitivity effect, this embodiment captures images of the laser beam along the optical axis of the laser beam. Since the energy of the laser entering the lens vertically is too strong, the image is taken with a 5° offset and the lens uses a 10x magnification. Figure 4 (a)- Figure 4 (d) is an original cross-sectional view of the laser beam of different samples provided by an exemplary embodiment of the present invention, taken with a 5° offset and a 10x magnification. Figure 4 (a) is a cross-sectional view of the laser beam collected in air; Figure 4 (b) is a cross-sectional view of the laser beam collected in pure water; Figure 4 (c) is a cross-sectional view of the laser beam collected in transformer oil with a trace water content of 13.29 mg / L; Figure 4 (d) is a cross-sectional view of the laser beam collected in transformer oil with a water content of 31.61 mg / L. Figure 4 (a)- Figure 4 As shown in (d), with the increase of the water content, the transmission brightness of the laser beam shows obvious mottled cross phenomenon, which further confirms that there is a certain correlation between the laser brightness and the water content in the transformer oil.

[0054] In the embodiment of the present invention, the number of pixels and the trace water content of a large number of test samples can be fitted. Figure 5 FIG. 1 is a fitting curve of a micro-water detection model provided by an exemplary embodiment of the present invention. Figure 5The curve shown is a polynomial function fit, with the 90% confidence interval boundaries on both sides. The triangles represent the actual measured values ​​of the insulating oil moisture content and the number of pixels. It can be seen that most points fall within the 90% confidence interval, demonstrating the feasibility of this method.

[0055] In the above-described embodiment, the trace moisture content of transformer oil is measured by processing and analyzing the laser beam image. This effectively addresses the problems of existing trace moisture measurement technologies, such as susceptibility to interference, high cost, and inconvenience, and avoids measurement deviations caused by sensing equipment, making the measurement and monitoring of the trace moisture content of transformer oil more accurate and convenient. Furthermore, because the captured images can be reused, if the monitoring results deviate, only the images need to be reanalyzed, without having to rearrange the monitoring equipment and start monitoring from scratch, significantly reducing the cost and risk of monitoring. Furthermore, the method provided in this embodiment simply requires importing the captured laser images into a program for analysis to obtain the trace moisture content, enabling real-time measurement. Compared to traditional methods (such as the Karl Fischer method, which takes approximately 10 to 20 minutes), the measurement speed is faster and more efficient.

[0056] Figure 6 A schematic structural diagram of a device for measuring trace water content in transformer oil provided in an exemplary embodiment of the present invention.

[0057] like Figure 6 As shown, the device includes:

[0058] The image acquisition unit 601 is configured to acquire a first image of the laser beam passing through the transformer oil.

[0059] In the embodiment of the present invention, the first image of the laser beam passing through the transformer oil can be acquired by an image acquisition device, that is, the original image of the laser beam can be acquired. Figure 2 (a) is a first image of a laser beam of transformer oil collected according to an exemplary embodiment of the present invention.

[0060] The image preprocessing unit 602 is configured to preprocess the first image of the laser beam to obtain a second image of the laser beam.

[0061] In the embodiment of the present invention, preprocessing may be processing performed on an image before feature extraction, such as stretching, compression, binarization, segmentation, etc. The main purpose of preprocessing is to eliminate irrelevant information in the image and restore useful real information.

[0062] Furthermore, the image pre-processing unit 602 is further configured to:

[0063] performing binarization processing on the first image of the laser beam to obtain a grayscale image of the first image of the laser beam;

[0064] The grayscale image of the first image of the laser beam is segmented to obtain a second image of the laser beam.

[0065] Figure 2 (b) is a grayscale image of a first image of a laser beam provided by an exemplary embodiment of the present invention. Figure 2 (b) shows that Figure 2 (a) After binarization, the data can be simplified while enhancing the feature information of the graphic boundary.

[0066] Since the optical platform and acrylic resin oil tank can cause stray light scattering and enter the image acquisition device, after obtaining the grayscale image of the laser beam, it is necessary to further segment it to eliminate the stray light scattering caused by the background, equipment light and transparent oil tank wall, so as to reduce the brightness impact caused by stray light scattering on the oil tank wall and other parts. Figure 2 (c) is a second image of a laser beam provided by an exemplary embodiment of the present invention. Figure 2 (c) shows that Figure 2 (b) Cropping is performed to remove image information outside the laser beam area and shield the scattered light from the transparent oil tank wall and possible background light. The image size after cropping is always 1000×150, thus ensuring the consistency of the shielded information amount.

[0067] The pixel counting unit 603 is configured to count the number of pixels of the laser beam in the second image of the laser beam.

[0068] In the embodiment of the present invention, the total number of pixels of the laser beam in the second image is counted.

[0069] Furthermore, the pixel counting unit 603 is further configured to:

[0070] Reading the grayscale value of each pixel in the second image of the laser beam;

[0071] The number of pixels with the same grayscale value in the laser beam area in the second image of the laser beam is counted to obtain the total number of pixels in the laser beam and a grayscale histogram of the laser beam.

[0072] In the embodiment of the present invention, any method of reading the grayscale value of a pixel point can be used, for example, the image reading function imread in matlab can be used for reading, or cv2.imread in opencv can be used for reading. After reading the grayscale value of each pixel point, the envelope boundary of the laser beam on the image after removing the background information is calculated using the sensitivity setting, and the following can be obtained: Figure 2(c) shows a second image clearly displaying the laser beam, i.e., a contour image of the laser beam. In this image, black denotes an invalid statistical region, and white denotes a valid statistical region. The number of pixels at each grayscale value within the valid white region is further counted to obtain a grayscale histogram of the second laser beam image.

[0073] The trace water content calculation unit 604 is used to calculate the trace water content of the transformer oil based on the number of pixel points using a trace water detection model.

[0074] In the embodiment of the present invention, the trace water detection model may be a polynomial function curve obtained by pre-fitting the number of pixels and the trace water content of a large number of test samples.

[0075] Furthermore, the trace water content calculation unit 604 is further configured to:

[0076] The water content TW of transformer oil is calculated using the following formula:

[0077] TW=1.0444+5.52×10 -4 Gr+3.161×10 -7 Gr 2 ;

[0078] Here, Gr is the number of pixels of the laser beam in the second image of the laser beam.

[0079] In the embodiment of the present invention, a large number of experiments were conducted before using laser brightness to detect the water content in transformer oil to verify the relationship between the two. The specific experimental process is as follows:

[0080] Transformer oils containing different trace water contents were collected as experimental samples. Since too many samples were collected, this embodiment will not list them one by one, and only three samples are selected for exemplary description.

[0081] Before the laser was applied, the trace water content in the above three samples was measured using the Karl Fischer reagent method. Among them, the trace water content in sample one was 6.61 mg / L; the trace water content in sample two was 16.61 mg / L; and the trace water content in sample three was 40.23 mg / L.

[0082] Next, laser light was injected into each transformer oil sample in the order of the water content from low to high, and the laser beam image was collected in the direction perpendicular to the optical axis of the laser beam. Figure 3 (a) Figure 3 (b) Figure 3 (c) The first images (original images) of the laser beams of sample 1, sample 2, and sample 3 provided by an exemplary embodiment of the present invention. Figure 3 (a)- Figure 3 As shown in (c), as the water content in the transformer oil increases, the photosensitivity of the laser beam gradually increases.

[0083] In addition, in order to more clearly illustrate the effect of micro-water content on the laser photosensitivity effect, this embodiment captures images of the laser beam along the optical axis of the laser beam. Since the energy of the laser entering the lens vertically is too strong, the image is taken with a 5° offset and the lens uses a 10x magnification. Figure 4 (a)- Figure 4 (d) is an original cross-sectional view of the laser beam of different samples provided by an exemplary embodiment of the present invention, taken with a 5° offset and a 10x magnification. Figure 4 (a) is a cross-sectional view of the laser beam collected in air; Figure 4 (b) is a cross-sectional view of the laser beam collected in pure water; Figure 4 (c) is a cross-sectional view of the laser beam collected in transformer oil with a trace water content of 13.29 mg / L; Figure 4 (d) is a cross-sectional view of the laser beam collected in transformer oil with a water content of 31.61 mg / L. Figure 4 (a)- Figure 4 As shown in (d), with the increase of the water content, the transmission brightness of the laser beam shows obvious mottled cross phenomenon, which further confirms that there is a certain correlation between the laser brightness and the water content in the transformer oil.

[0084] In the embodiment of the present invention, the number of pixels and the trace water content of a large number of test samples can be fitted. Figure 5 FIG. 1 is a fitting curve of a micro-water detection model provided by an exemplary embodiment of the present invention. Figure 5 The curve shown is a polynomial function fit, with the 90% confidence interval boundaries on both sides. The triangles represent the actual measured values ​​of the insulating oil moisture content and the number of pixels. It can be seen that most points fall within the 90% confidence interval, demonstrating the feasibility of this method.

[0085] In the above-described embodiment, the trace moisture content of transformer oil is measured by processing and analyzing the laser beam image. This effectively addresses the problems of existing trace moisture measurement technologies, such as susceptibility to interference, high cost, and inconvenience, and avoids measurement deviations caused by sensing equipment, making the measurement and monitoring of the trace moisture content of transformer oil more accurate and convenient. Furthermore, because the captured images can be reused, if the monitoring results deviate, only the images need to be reanalyzed, without having to rearrange the monitoring equipment and start monitoring from scratch, significantly reducing the cost and risk of monitoring. Furthermore, the method provided in this embodiment simply requires importing the captured laser images into a program for analysis to obtain the trace moisture content, enabling real-time measurement. Compared to traditional methods (such as the Karl Fischer method, which takes approximately 10 to 20 minutes), the measurement speed is faster and more efficient.

[0086] The present invention also provides a computer-readable storage medium storing one or more programs, which, when executed by one or more processors, implement any of the above methods for measuring trace water content in transformer oil.

[0087] The invention has been described above with reference to a few embodiments. However, it is readily apparent to a person skilled in the art that other embodiments than the ones disclosed above are equally within the scope of the invention, as defined by the appended patent claims.

[0088] Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a / the [means, component, etc.]" are to be interpreted openly as referring to at least one instance of the means, component, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not necessarily need to be performed in the exact order disclosed, unless explicitly stated otherwise.

[0089] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0090] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0091] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0092] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for measuring the water content in transformer oil, characterized in that: The method comprises: capturing a first image of the laser beam passing through the transformer oil; Preprocessing the first image of the laser beam to obtain a second image of the laser beam; Counting the number of pixels of the laser beam in the second image of the laser beam; Based on the number of pixels, the moisture content of the transformer oil is calculated using a moisture detection model; The counting of the number of pixels of the laser beam in the second image of the laser beam includes: Reading the grayscale value of each pixel in the second image of the laser beam; The number of pixels with the same grayscale value in the laser beam area in the second image of the laser beam is counted to obtain the total number of pixels in the laser beam and a grayscale histogram of the laser beam.

2. The method according to claim 1, characterized in that The preprocessing of the first image of the laser beam to obtain a second image of the laser beam includes: performing binarization processing on the first image of the laser beam to obtain a grayscale image of the first image of the laser beam; The grayscale image of the first image of the laser beam is segmented to obtain a second image of the laser beam.

3. The method according to claim 1, characterized in that The method of calculating the moisture content of the transformer oil based on the number of pixels using a moisture detection model includes: The water content TW of transformer oil is calculated using the following formula: TW=1.0444+5.52×10 -4 Gr+3.161×10 -7 Gr 2 ; Here, Gr is the number of pixels of the laser beam in the second image of the laser beam.

4. A device for measuring the water content in transformer oil, characterized in that: The device comprises: An image acquisition unit, configured to acquire a first image of the laser beam passing through the transformer oil; an image preprocessing unit, configured to preprocess the first image of the laser beam to obtain a second image of the laser beam; a pixel counting unit, configured to count the number of pixels of the laser beam in the second image of the laser beam; a trace water content calculation unit, configured to calculate the trace water content of the transformer oil using a trace water detection model based on the number of pixels; The pixel counting unit is further configured to: Reading the grayscale value of each pixel in the second image of the laser beam; The number of pixels with the same grayscale value in the laser beam area in the second image of the laser beam is counted to obtain the total number of pixels in the laser beam and a grayscale histogram of the laser beam.

5. The device according to claim 4, characterized in that The image preprocessing unit is further used for: performing binarization processing on the first image of the laser beam to obtain a grayscale image of the first image of the laser beam; The grayscale image of the first image of the laser beam is segmented to obtain a second image of the laser beam.

6. The device according to claim 4, characterized in that The trace water content calculation unit is further used for: The water content TW of transformer oil is calculated using the following formula: TW=1.0444+5.52×10 -4 Gr+3.161×10 -7 Gr 2 ; Here, Gr is the number of pixels of the laser beam in the second image of the laser beam.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images