A power transmission line accessory fitting temperature anomaly control method and system

Abstract

The application discloses a kind of power transmission and distribution line iron accessory fitting temperature anomaly control method and system, it is related to electric power component control technical field, method includes: obtaining the infrared thermal image of target fitting;According to preset separation temperature threshold, the hot spot separation is carried out to the infrared thermal image, and the hot spot area is obtained;Boundary sharpness evaluation is carried out to the hot spot area, and boundary sharpness evaluation result is obtained;The shape regularity analysis is carried out to the hot spot area, and shape regularity analysis result is obtained;According to the boundary sharpness evaluation result and the shape regularity analysis result, the heat source of the hot spot area is determined.The application can be combined with boundary sharpness and shape regularity to analyze heat source to realize fitting temperature anomaly control, improve temperature anomaly detection accuracy, effectively control iron accessory fitting to maintain normal state.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power component control, and in particular to a power transmission and distribution line iron accessory fitting temperature anomaly control method and system. BACKGROUND

[0002] The power transmission and distribution line is an important part of the power system, and its safe and stable operation is directly related to the normal conduct of social production and life. In the line, the iron accessory fitting is a key component that connects the conductor, fixes the insulator, and carries the current, and its operating state is crucial. When there is a problem in the internal connection of the fitting, such as loose fastening bolts or deteriorated contact surfaces, it will cause the contact resistance to increase, and in turn produce abnormal local high temperature, which is often an early signal of a major failure of the line. In order to timely discover and handle these hidden dangers, technicians usually use a drone to carry an infrared thermal imaging device for inspection, and measure the surface temperature of the fitting to determine its health status. However, in outdoor environments, the actual temperature of the fitting not only includes its internal electrical heating, but also is affected by external environmental factors such as solar radiation. A single temperature reading is a mixed information that combines internal electrical heating and solar radiation and other factors. Existing control methods are difficult to effectively deconstruct this mixed information, and are difficult to separate the fault signal from the complex environmental noise, resulting in low temperature anomaly detection accuracy, making it difficult to control the iron accessory fitting to maintain a normal state.

[0003] In summary, the technical problems in the related art need to be improved. SUMMARY

[0004] The main purpose of the embodiments of the present application is to provide a power transmission and distribution line iron accessory fitting temperature anomaly control method and system, which can analyze the heat source by combining the boundary sharpness and shape regularity to realize fitting temperature anomaly control, improve the temperature anomaly detection accuracy, and effectively control the iron accessory fitting to maintain a normal state.

[0005] In one aspect, the present application provides a power transmission and distribution line iron accessory fitting temperature anomaly control method, comprising the following steps:

[0006] Obtaining an infrared thermal image of a target fitting;

[0007] According to a preset separation temperature threshold, performing hot spot separation on the infrared thermal image to obtain a hot spot region;

[0008] Performing boundary sharpness evaluation on the hot spot region to obtain a boundary sharpness evaluation result;

[0009] Performing shape regularity analysis on the hot spot region to obtain a shape regularity analysis result;

[0010] According to the boundary sharpness evaluation result and the shape regularity analysis result, a heat source of the hot spot region is determined.

[0011] In some embodiments, the boundary sharpness evaluation on the hot spot region is performed to obtain a boundary sharpness evaluation result, including:

[0012] A pixel point is selected from a boundary of the hot spot region as a target pixel point;

[0013] A temperature difference analysis window is constructed, and the temperature difference analysis window is centered on the target pixel point;

[0014] A temperature difference between each pixel point in the temperature difference analysis window and the target pixel point is calculated;

[0015] Absolute values of a plurality of temperature differences are averaged to obtain a local temperature change rate;

[0016] If the local temperature change rate is greater than a preset temperature gradient threshold, the boundary sharpness evaluation result is determined as high sharpness;

[0017] If the local temperature change rate is less than the preset temperature gradient threshold, the boundary sharpness evaluation result is determined as low sharpness.

[0018] In some embodiments, the shape regularity analysis on the hot spot region is performed to obtain a shape regularity analysis result, including:

[0019] Morphological feature extraction is performed on the hot spot region, and an area and a perimeter of the hot spot region are calculated;

[0020] According to the area and the perimeter, a circularity is calculated;

[0021] An aspect ratio of a minimum circumscribed rectangle of the hot spot region is calculated;

[0022] If the circularity is greater than a preset circularity threshold and the aspect ratio is greater than a preset aspect ratio threshold, the shape regularity analysis result is determined as high regularity; otherwise, the shape regularity analysis result is determined as low regularity.

[0023] In some embodiments, the determination of the heat source of the hot spot region according to the boundary sharpness evaluation result and the shape regularity analysis result includes:

[0024] A visible light image of the target fitting is collected, and a time stamp of the visible light image is the same as a time stamp of the infrared thermal image;

[0025] Contour extraction is performed on the infrared thermal image to obtain a hot spot boundary contour;

[0026] performing contour extraction on the visible light image to obtain a shadow boundary contour;

[0027] calculating a boundary coincidence degree according to the hot spot boundary contour and the shadow boundary contour;

[0028] determining a heat source of the hot spot region according to the boundary sharpness evaluation result, the shape regularity analysis result and the boundary coincidence degree.

[0029] In some embodiments, the contour extraction on the infrared thermal image to obtain a hot spot boundary contour comprises:

[0030] performing Gaussian smoothing on the infrared thermal image to obtain a Gaussian smoothed image;

[0031] calculating gradient intensity and direction of the Gaussian smoothed image;

[0032] performing boundary thinning on the Gaussian smoothed image by a double threshold suppression method according to the gradient intensity and direction to obtain the hot spot boundary contour.

[0033] In some embodiments, the contour extraction on the visible light image to obtain a shadow boundary contour comprises:

[0034] performing color space conversion on the visible light image to convert the visible light image from an RGB color space to an HSV color space, parameters of the HSV color space including hue, saturation and brightness;

[0035] performing binarization processing on a brightness component in the visible light image converted in color space by a Gaussian adaptive threshold method to obtain a binarization image, so as to separate a shadow region from a non-shadow region;

[0036] performing boundary extraction on the binarization image by an edge detection algorithm to obtain the shadow boundary contour.

[0037] In some embodiments, the binarization processing on the brightness component in the visible light image converted in color space by the Gaussian adaptive threshold method to obtain a binarization image comprises:

[0038] obtaining a brightness variation region of the brightness component from the visible light image converted in color space;

[0039] extracting a brightness value range of the brightness variation region;

[0040] calculating a brightness distribution of the brightness value range;

[0041] calculating skewness and kurtosis of the brightness distribution;

[0042] determine a brightness value upper limit according to the skewness and the kurtosis;

[0043] update the brightness value range according to the brightness value upper limit;

[0044] determine a shadow boundary brightness threshold according to the updated brightness value range;

[0045] perform a binarization process on the brightness component according to the shadow boundary brightness threshold to obtain a binarization image.

[0046] In some embodiments, the determining the heat source of the hot spot region according to the boundary sharpness evaluation result, the shape regularity analysis result, and the boundary coincidence degree comprises:

[0047] if the boundary sharpness evaluation result is low sharpness and the shape regularity analysis result is low regularity, determining that the heat source is solar irradiation;

[0048] if the boundary sharpness evaluation result is high sharpness and the shape regularity analysis result is high regularity, determining whether the boundary coincidence degree is greater than a preset coincidence degree threshold;

[0049] if the boundary coincidence degree is greater than the preset coincidence degree threshold, determining that the heat source is an environmental heat-induced artifact;

[0050] if the boundary coincidence degree is less than the preset coincidence degree threshold, determining that the heat source is internal electrical heat generation.

[0051] In some embodiments, the method further comprises:

[0052] obtaining an infrared thermal image sequence;

[0053] selecting an image from the infrared thermal image sequence as a to-be-processed image;

[0054] extracting a temperature peak value from the to-be-processed image as a hot spot center point;

[0055] constructing a hot spot core region according to a preset pixel side length and the hot spot center point;

[0056] selecting a pixel point from the hot spot core region as a to-be-processed pixel point;

[0057] combining temperature values corresponding to the to-be-processed pixel point in each image of the infrared thermal image sequence according to coordinate information of the to-be-processed pixel point to obtain a temperature value sequence;

[0058] calculating an average temperature according to the temperature value sequence;

[0059] According to the temperature value sequence and the average temperature, a standard deviation is calculated as a temperature fluctuation amplitude;

[0060] A temperature fluctuation rate is obtained by statistically analyzing the temperature fluctuation amplitude corresponding to each pixel point in the hot spot core area.

[0061] If the temperature fluctuation rate is greater than a preset fluctuation threshold and the heat source is internal electrical heating, the heat source is updated to be solar irradiation.

[0062] In another aspect, an embodiment of the present application provides a power transmission and distribution line iron accessory fitting temperature anomaly control system, comprising:

[0063] An image acquisition module is configured to acquire an infrared thermal image of a target fitting.

[0064] A hot spot identification module is configured to perform hot spot separation on the infrared thermal image according to a preset separation temperature threshold to obtain a hot spot area.

[0065] A boundary sharpness evaluation module is configured to perform boundary sharpness evaluation on the hot spot area to obtain a boundary sharpness evaluation result.

[0066] A shape regularity analysis module is configured to perform shape regularity analysis on the hot spot area to obtain a shape regularity analysis result.

[0067] A hot spot source judgment module is configured to determine a heat source of the hot spot area according to the boundary sharpness evaluation result and the shape regularity analysis result.

[0068] Embodiments of the present application have at least the following beneficial effects: an infrared thermal image of a target fitting is first acquired, then hot spot separation is performed on the infrared thermal image according to a preset separation temperature threshold to obtain a hot spot area, boundary sharpness evaluation is performed on the hot spot area to obtain a boundary sharpness evaluation result, shape regularity analysis is performed on the hot spot area to obtain a shape regularity analysis result, and finally a heat source of the hot spot area is determined according to the boundary sharpness evaluation result and the shape regularity analysis result, so that the heat source can be analyzed in combination with the boundary sharpness and the shape regularity to realize fitting temperature anomaly control, thereby improving temperature anomaly detection accuracy and effectively controlling iron accessory fittings to maintain a normal state.

[0069] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application can be achieved and obtained by means of the structures particularly pointed out in the description and the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0070] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments description will be briefly introduced. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0071] Figure 1 The flow chart of the power transmission and distribution line iron accessory fitting temperature abnormality control method according to an embodiment of the present application;

[0072] Figure 2 The structural schematic diagram of the power transmission and distribution line iron accessory fitting temperature abnormality control system according to an embodiment of the present application. DETAILED DESCRIPTION

[0073] In order to make the purposes, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated.

[0074] Before the embodiments of the present application are described in detail, first, some nouns and terms involved in the embodiments of the present application will be described, and the nouns and terms involved in the embodiments of the present application are applicable to the following explanations.

[0075] Fitting: It is an iron or aluminum accessory in the power system for overhead transmission line and substation connection, fixation and protection, collectively known as power fittings. Its core function is to transfer mechanical load, ensure stable electrical contact, and undertake the task of conductor suspension, connection and interval control, which is directly related to the safe operation of the line. According to the use, it can be divided into line fittings, substation fittings, busbar fittings and other categories, covering tens of types such as suspension clamps, strain clamps, anti-vibration hammers and spacer rods.

[0076] In the related art, the power transmission and distribution line is an important part of the power system, and its safe and stable operation is directly related to the normal conduct of social production and life. In the line, the iron accessory fittings are the key components for connecting the conductors and fixing the insulators and carrying the current, and their operating state is crucial. When there are problems in the internal connection of the fittings, such as loose fastening bolts or deteriorated contact surfaces, the contact resistance will increase, and then abnormal local high temperature will be generated, which is often an early signal of a major failure of the line. In order to timely discover and handle these hidden dangers, the power department usually uses a drone carrying an infrared thermal imaging device for inspection, and measures the surface temperature of the fittings to judge their health status. However, in the actual outdoor environment, the measured temperature of the fittings not only includes the internal electrical heating, but also is significantly affected by external environmental factors, especially solar radiation. More complexly, the new and old, cleanliness and corrosion degree of the surface of the fittings will dynamically change over time, and these changes will directly affect the absorption capacity of the fittings to solar radiation, so that the existing temperature anomaly judgment method faces severe challenges and is prone to false positives or false negatives.

[0077] Specifically, the power transmission and distribution network is a key infrastructure to ensure the normal operation of society, and its stability and reliability are crucial. In the line, the conductors carrying huge current are fixed on the insulator string and suspended on the power transmission tower through various iron accessory fittings, such as strain clamps, suspension clamps, etc. These fittings, as key nodes of the current path, directly affect the safety of the entire line. Since the fittings themselves have resistance, plus the contact resistance of the contact surface between the conductor and the clamp, when a large current passes through, heat will be generated due to the Joule effect. Under normal circumstances, this heating is stable and controllable. However, if the fastening bolts of the fittings are loose due to long-term exposure to wind and sun, vibration, etc., or the contact surface is deteriorated due to environmental corrosion, electrochemical reaction, the contact resistance will increase sharply. At this time, the heating power at this point will increase significantly, forming a local high temperature, and this abnormal temperature rise is a typical precursor of a major failure of the line. Continuous overheating will reduce the mechanical strength of the metal material and cause annealing effect, and in severe cases, it may even cause the fittings to melt, the conductor to fall off, and cause a large-scale power outage accident.

[0078] To prevent such accidents, technicians usually monitor the temperature of these key nodes by regular inspection. Traditional infrared temperature measurement guns are inefficient and dangerous, so unmanned aerial vehicle (UAV) inspection with an infrared thermal imaging device has become the mainstream technology. The UAV flies along a preset route, takes thermal images of each fitting along the route, and transmits the collected thermal image information to a background analysis system in real time or afterwards. After receiving the thermal images, the background system extracts the highest temperature point of each fitting. To determine whether the temperature is abnormal, the system usually uses a comparative analysis method: comparing the temperature of the target fitting with other fittings on the same phase, on the same tower, or at the same position on different phases. Under ideal conditions, the temperatures of these fittings should be similar. If the temperature of a fitting is significantly higher than that of the other reference fittings, the system determines that it is an abnormal heating point and generates an alarm to notify the maintenance personnel for repair.

[0079] However, in actual outdoor environments, this seemingly reliable temperature difference comparison method faces serious challenges. One key interference factor is direct sunlight. When the UAV is inspected during a sunny day, sunlight directly shines on the tower and the line, and the metal fittings absorb solar radiation and heat up. This heating caused by sunlight is not uniform. For example, due to the change in the position of the sun in the sky, the intensity and angle of sunlight received by fittings of different orientations are completely different. A fitting facing east will be hotter than a fitting facing west in the morning, and the situation is reversed in the afternoon. In addition, the structure of the tower itself also blocks the fittings, forming complex shadows, resulting in fittings on the same tower being exposed to sunlight or in the shade, with completely different sunlight heating effects.

[0080] The root of the problem lies in the fact that a single temperature reading is a mixed information body that combines electrical heating, environmental heat exchange, sunlight heating, and other factors, which are modulated by a surface parameter that changes over time and is difficult to quantify. Existing control methods cannot effectively deconstruct this mixed information and accurately separate the true fault signal from the complex environmental noise.

[0081] In the temperature monitoring and fault diagnosis process of transmission and distribution line accessory fittings, the actual temperature of the fittings has a complex situation of superimposed internal electrical heating and external solar radiation heat absorption, which increases the difficulty of controlling the fittings. It is necessary to distinguish and separate the "internal electrical heating component" and "solar irradiation component" in the temperature of the fittings, so as to accurately identify the real abnormal temperature rise caused by increased contact resistance and avoid misjudging old fittings with good electrical connections as faults.

[0082] Therefore, the embodiment of the present application can effectively distinguish internal electrical heating and external environmental influence by evaluating the boundary sharpness and analyzing the shape regularity of the hot spot region in the infrared thermal image, comprehensively judging the heat source of the hot spot, improving the accuracy of fault diagnosis, and effectively controlling the iron accessory hardware to maintain a normal state.

[0083] The embodiment of the present application will be specifically explained below in combination with the drawings:

[0084] Figure 1 is an optional flowchart of a power transmission and distribution line iron accessory hardware temperature anomaly control method provided by the embodiment of the present application, Figure 1 The method in can include but is not limited to steps S101 to S105.

[0085] Step S101, acquiring an infrared thermal image of a target hardware;

[0086] Step S102, performing hot spot separation on the infrared thermal image according to a preset separation temperature threshold to obtain a hot spot region;

[0087] Step S103, performing boundary sharpness evaluation on the hot spot region to obtain a boundary sharpness evaluation result;

[0088] Step S104, performing shape regularity analysis on the hot spot region to obtain a shape regularity analysis result;

[0089] Step S105, determining the heat source of the hot spot region according to the boundary sharpness evaluation result and the shape regularity analysis result.

[0090] The steps S101 to S105 shown in the embodiment of the present application can analyze the heat source in combination with the boundary sharpness and the shape regularity to realize hardware temperature anomaly control, thereby improving the temperature anomaly detection accuracy and effectively controlling the iron accessory hardware to maintain a normal state.

[0091] In some embodiments, steps S101 to S105 can first acquire an infrared thermal image of a target hardware. For example, the hardware can be scanned and photographed by manually operating an infrared thermal imager, or periodic image acquisition can be performed by using an infrared thermal imaging device fixedly installed on a power transmission and distribution line tower. In addition, a drone can be used to carry an infrared thermal imaging device to perform inspection and obtain large-range infrared thermal image data. These image data can be transmitted to a processing unit for subsequent analysis.

[0092] Then, according to a preset separation temperature threshold, the hot spot in the infrared thermal image is separated to obtain a hot spot region. For example, a set of pixel points in the image with a temperature higher than the preset separation temperature threshold can be identified as a potential hot spot region. Alternatively, the hot spot region can be directly specified on the infrared thermal image by manual framing. Thus, a region with a temperature anomaly can be preliminarily identified. The preset separation temperature threshold can be set by expert experience or according to the median temperature in the infrared thermal image.

[0093] The boundary sharpness of the hot spot region is evaluated to obtain a boundary sharpness evaluation result. For example, a technician can judge the edge definition of the hot spot region by visual inspection, or measure the temperature difference between the edge pixel points of the hot spot region and the adjacent non-hot spot region pixel points. If the temperature difference is large, it is considered that the boundary sharpness is high; otherwise, it is low. The shape regularity of the hot spot region is analyzed to obtain a shape regularity analysis result. For example, a technician can judge the geometric shape of the hot spot region according to experience, such as whether it is close to a circle or a rectangle. Alternatively, an image processing method can be used, such as calculating the minimum circumscribed rectangle of the hot spot region, and judging the regularity of the shape according to the aspect ratio.

[0094] Finally, according to the boundary sharpness evaluation result and the shape regularity analysis result, the heat source of the hot spot region is determined. For example, a preset judgment rule or a preset judgment table can be used to determine the heat source of the hot spot region. For example, when the boundary sharpness is low and the shape regularity is low, it is judged to be solar radiation; when the boundary sharpness is high and the shape regularity is high, it is judged to be internal electrical heating. These judgment rules can be set based on historical data and expert experience.

[0095] Through the above technical solutions, the embodiment introduces the boundary sharpness evaluation and shape regularity analysis of the hot spot region in the infrared thermal image, which can more deeply explore the internal physical characteristics of the hot spot, and effectively distinguish the heating caused by internal electrical faults of the fitting from the temperature increase caused by external solar radiation and other environmental factors. By comprehensively analyzing the geometric characteristics of the hot spot, such as the definition of its edge and the regularity of its overall shape, the real source of heat can be more accurately identified. Thus, the false positive and false negative problems can be effectively avoided, and the accuracy and reliability of the temperature anomaly diagnosis of the power transmission and distribution line fitting can be significantly improved, thereby ensuring the safe and stable operation of the power system.

[0096] In some embodiments, in step S103, the boundary sharpness of the hot spot region is evaluated to obtain a boundary sharpness evaluation result, which can include but is not limited to the following steps:

[0097] A pixel point is selected from the boundary of the hot spot region as a target pixel point;

[0098] constructing a temperature difference analysis window, the temperature difference analysis window being centered on the target pixel point;

[0099] calculating temperature difference values between each pixel point in the temperature difference analysis window and the target pixel point respectively;

[0100] averaging absolute values of the plurality of temperature difference values to obtain a local temperature change rate;

[0101] if the local temperature change rate is greater than a preset temperature gradient threshold, determining that the boundary sharpness evaluation result is high sharpness;

[0102] if the local temperature change rate is less than the preset temperature gradient threshold, determining that the boundary sharpness evaluation result is low sharpness.

[0103] In some embodiments, a pixel point can be first selected from the boundary of the hot spot region as a target pixel point, which is a reference point for subsequent temperature gradient analysis. Then, a temperature difference analysis window is constructed centered on the target pixel point, which can be a rectangular or circular region of a preset size, the size of which should be sufficient to cover the target pixel point and the pixel points within a certain range around it for local temperature change analysis. For example, the temperature difference analysis window can be set as a 3x3 or 5x5 pixel matrix.

[0104] Then, temperature difference values between each pixel point in the temperature difference analysis window and the target pixel point are calculated, which reflect the local change of temperature at the boundary of the hot spot. To quantify this change, the absolute values of these temperature difference values can be averaged to obtain a local temperature change rate. Using absolute values can eliminate the influence of the positive and negative directions of the temperature difference values, and only the amplitude of the temperature change is concerned. The higher the local temperature change rate, the greater the temperature gradient of the region, and the sharper the boundary.

[0105] Finally, the calculated local temperature change rate is compared with a preset temperature gradient threshold. The preset temperature gradient threshold is determined according to experience or experimental data, and is used to distinguish between high sharpness and low sharpness boundaries. If the local temperature change rate is greater than the preset temperature gradient threshold, it is determined that the boundary sharpness evaluation result of the hot spot region is high sharpness, which usually means that the heat is concentrated and the boundary is clear. Conversely, if the local temperature change rate is less than the preset temperature gradient threshold, it is determined that the boundary sharpness evaluation result is low sharpness, which may indicate heat diffusion or a blurred boundary.

[0106] The embodiment can effectively evaluate the sharpness of the hot spot boundary by quantitatively analyzing the local temperature change rate of the hot spot boundary. When internal electrical heating occurs in the iron accessory fittings of the power transmission and distribution line, heat is usually concentrated at the fault point, resulting in a significant temperature gradient between the hot spot area and the surrounding environment, thereby forming a boundary with high sharpness. On the contrary, when the fittings are heated by external environmental factors such as solar radiation, the heat distribution is usually more uniform, and the temperature gradient of the hot spot boundary is relatively small, which is a boundary with low sharpness. By calculating the local temperature change rate and comparing it with the preset threshold, the physical characteristics of the hot spot boundary can be objectively reflected, providing a key basis for subsequent judgment of the heat source.

[0107] Through the above technical solutions, the embodiment accurately calculates the local temperature change rate of the hot spot boundary and classifies it based on a preset threshold, avoiding the subjectivity and inaccuracy of traditional manual visual judgment, making the identification of the characteristics of the hot spot boundary more accurate and automated. Thus, a solid foundation is laid for the accurate judgment of the heat source, improving the accuracy and reliability of the temperature anomaly control of the iron accessory fittings of the power transmission and distribution line.

[0108] In some embodiments, in step S104, the shape regularity analysis of the hot spot area is performed to obtain a shape regularity analysis result, which can include but is not limited to the following steps:

[0109] Morphological feature extraction is performed on the hot spot area to calculate the area and perimeter of the hot spot area.

[0110] The circularity is calculated based on the area and perimeter.

[0111] The aspect ratio of the minimum circumscribed rectangle of the hot spot area is calculated.

[0112] If the circularity is greater than a preset circularity threshold and the aspect ratio is greater than a preset aspect ratio threshold, the shape regularity analysis result is determined to be high regularity; otherwise, the shape regularity analysis result is determined to be low regularity.

[0113] In some embodiments, morphological feature extraction can be performed on the hot spot area to calculate the area and perimeter of the hot spot area. Morphological feature extraction refers to quantitatively describing the geometric shape of the hot spot area through image processing techniques. Specifically, methods such as connected component analysis and contour tracking can be used to accurately obtain the pixel set of the hot spot area, and then calculate the number of pixels it occupies (i.e. area) and the length of its boundary (i.e. perimeter), providing basic data for subsequent shape regularity quantification.

[0114] Then, the circularity is calculated based on the area and perimeter. The circularity is an index that measures the degree to which the shape of the hot spot area approximates a circle, and its calculation method is , where is the circularity. Area, Perimeter. The closer the circularity value is to 1, the closer the shape of the hot spot region is to a circle, which aims to characterize the compactness of the hot spot through a dimensionless parameter.

[0115] The aspect ratio of the minimum circumscribed rectangle of the hot spot region is recalculated. It can be understood that the aspect ratio of the minimum circumscribed rectangle refers to the ratio of the long side to the short side of the smallest rectangle that can completely surround the hot spot region. This parameter is used to evaluate the spread or flatness of the hot spot region. For example, an elongated hot spot region will have a larger aspect ratio, while a square or circular region will have an aspect ratio close to 1. The purpose is to reflect the geometric characteristics of the hot spot from another dimension.

[0116] Finally, different shape characteristics of the hot spot region can be distinguished by threshold values. If the circularity is greater than a preset circularity threshold and the aspect ratio is greater than a preset aspect ratio threshold, it indicates that the shape of the hot spot region is relatively regular, which may be related to a specific heat source, and the shape regularity analysis result can be determined as high regularity. Otherwise, it indicates that the shape is irregular, for example, caused by environmental factors, and the shape regularity analysis result can be determined as low regularity. The preset circularity threshold and the preset aspect ratio threshold are critical values pre-set according to experience or a large amount of experimental data.

[0117] The embodiment can quantitatively evaluate the shape regularity of the hot spot region by comprehensively analyzing the morphological characteristics such as the area, perimeter, circularity, and aspect ratio of the minimum circumscribed rectangle of the hot spot region. Specifically, the area and perimeter provide basic size information of the hot spot region; the circularity reflects the compactness of the hot spot from the perspective of circular similarity; and the aspect ratio of the minimum circumscribed rectangle reveals the spread of the hot spot. The combination of these parameters enables the shape characteristics of the hot spot to be captured comprehensively and accurately. By comparing these quantitative characteristics with preset thresholds, the hot spot region can be objectively divided into high regularity or low regularity, thereby providing key shape characteristic basis for subsequent heat source judgment.

[0118] Through the above technical solutions, the embodiment can perform fine shape regularity analysis on the hot spot region in the infrared thermal image of the power transmission and distribution line iron accessory fitting. This analysis method not only considers the overall size of the hot spot, but also deeply quantifies its geometric shape characteristics, such as compactness and spread. As a result, hot spots with specific shape characteristics can be more accurately identified, such as hot spots caused by internal electrical heating, which are usually more regular, or hot spots caused by external environmental factors (such as solar radiation), which are irregular in shape. This fine shape analysis capability significantly improves the accuracy and reliability of hot spot source judgment, helps to avoid misjudgment, and thus improves the intelligent level of temperature anomaly control of power transmission and distribution line iron accessory fittings.

[0119] In some embodiments, in step S105, determining the heat source of the hot spot region according to the boundary sharpness evaluation result and the shape regularity analysis result can include but is not limited to the following steps:

[0120] Step S201, collect the visible light image of the target fitting, the time stamp of the visible light image is the same as that of the infrared thermal image;

[0121] Step S202, contour extraction is performed on the infrared thermal image to obtain a hot spot boundary contour;

[0122] Step S203, contour extraction is performed on the visible light image to obtain a shadow boundary contour;

[0123] Step S204, calculate the boundary coincidence degree according to the hot spot boundary contour and the shadow boundary contour;

[0124] Step S205, determine the heat source of the hot spot region according to the boundary sharpness evaluation result, the shape regularity analysis result and the boundary coincidence degree.

[0125] In some embodiments, it can be difficult to accurately distinguish between surface temperature rise caused by external environmental factors (such as solar radiation, environmental heat-induced artifacts) and real heat generated by internal electrical faults, relying only on boundary sharpness and shape regularity. For example, strong solar radiation can form a region with higher temperature on the surface of the fitting, which can have similarities in boundary sharpness and shape regularity with the hot spot generated by internal electrical heating, leading to misjudgment, unnecessary on-site inspection, increased operation and maintenance costs, and even delayed discovery and handling of real electrical faults.

[0126] Therefore, the visible light image of the target fitting can be collected first. For example, the visible light image of the same target fitting can be obtained at the same time as the infrared thermal image. The visible light image provides complementary visual information to the infrared thermal image, such as the shape, color, texture of the object, and whether there is a shadow, etc. The time stamp of the visible light image is the same as that of the infrared thermal image, which aims to ensure that both images capture the scene at the same time, thereby ensuring the consistency and correspondence of the image content, and providing an accurate basis for subsequent image fusion and analysis.

[0127] Then, contour extraction is performed on the infrared thermal image to obtain a hot spot boundary contour, which can be obtained by an image processing algorithm to identify and outline the precise boundary of the hot spot region in the infrared thermal image. The hot spot boundary contour reflects the actual range and shape of heat distribution. Contour extraction is also performed on the visible light image to obtain a shadow boundary contour, which can be identified and extracted from the shadow region formed by the lighting conditions in the visible light image. The shadow boundary contour can indicate the blocking of the object under visible light.

[0128] According to the hot spot boundary profile and the shadow boundary profile, the boundary coincidence degree is calculated to quantify the matching degree between the hot spot boundary in the infrared thermal image and the shadow boundary in the visible light image. The boundary coincidence degree can be calculated by various image matching or similarity measurement algorithms, such as by calculating the ratio of the intersection to the union of the two profiles, or by calculating the average distance between the profile points, etc. A higher coincidence degree generally means that the hot spot region and the shadow region correspond highly in space.

[0129] Finally, according to the boundary sharpness evaluation result, the shape regularity analysis result, and the boundary coincidence degree, the heat source of the hot spot region is determined. This means that the features extracted from the infrared thermal image (boundary sharpness and shape regularity) are comprehensively judged with the features extracted from the visible light image (boundary coincidence degree). The fusion of multi-modal information makes the judgment of the heat source more comprehensive and accurate.

[0130] This embodiment effectively solves the limitations of relying only on infrared thermal image features to judge the heat source by introducing the visible light image and calculating the coincidence degree of the hot spot boundary profile and the shadow boundary profile. The traditional method may have ambiguity in distinguishing between solar irradiation, environmental heat-induced artifacts, and internal electrical heating. For example, solar irradiation can cause the surface temperature of the gold fitting to rise, forming a hot spot on the infrared thermal image, and its boundary sharpness and shape regularity may be similar to that of a hot spot generated by internal electrical heating. However, solar irradiation usually produces a clear shadow in the visible light image, and the boundary of the hot spot region often corresponds to the shadow boundary to some extent. By collecting a visible light image with the same timestamp as the infrared thermal image, and extracting the hot spot boundary profile and the shadow boundary profile respectively, this embodiment can calculate the boundary coincidence degree between the two. When the heat source of the hot spot region is solar irradiation, the hot spot boundary profile and the shadow boundary profile in the visible light image usually exhibit a high coincidence degree, because there is a clear temperature gradient and boundary between the area blocked by sunlight (shadow) and the area not blocked by sunlight (heated by direct sunlight). On the contrary, for internal electrical heating, its heat source is the current effect inside the gold fitting, which usually does not produce a corresponding shadow boundary in the visible light image, so the coincidence degree of the hot spot boundary profile and the shadow boundary profile is low. For environmental heat-induced artifacts, such as hot spots caused by reflection of nearby high-temperature objects, they may exhibit specific boundary and shape characteristics on the infrared thermal image, but they usually do not have a corresponding shadow in the visible light image, or the coincidence degree of their boundary and shadow boundary is low. By comprehensively considering the boundary sharpness evaluation result, the shape regularity analysis result, and the newly added boundary coincidence degree, a more refined judgment logic can be constructed to more accurately distinguish different types of heat sources.

[0131] To make the technical solution clearer, specific examples are used for explanation below. Assume that during infrared thermal imaging detection of a certain power transmission and distribution line accessory fitting, a hot spot area is found. First, the infrared thermal image of the fitting is acquired, and hot spot separation is performed to obtain the hot spot area. Next, the hot spot area is subjected to boundary sharpness evaluation to obtain the boundary sharpness evaluation result, and the hot spot area is subjected to shape regularity analysis to obtain the shape regularity analysis result. On this basis, in order to more accurately determine the heat source, the visible light image of the fitting with the same time stamp as the infrared thermal image is further acquired. Subsequently, the infrared thermal image is subjected to contour extraction to obtain the hot spot boundary contour, and the visible light image is subjected to contour extraction to obtain the shadow boundary contour.

[0132] For example, if the boundary sharpness evaluation result of the hot spot area is low sharpness and the shape regularity analysis result is low regularity, it is preliminarily suggested that it may be solar irradiation. At this time, by calculating the coincidence degree of the hot spot boundary contour and the shadow boundary contour, if the coincidence degree is high (for example, greater than a preset coincidence degree threshold), it can be further confirmed that the hot spot is caused by solar irradiation. This shows that the formation of the hot spot has a spatial correspondence with the shadow area in the visible light image, which is consistent with the characteristics of solar irradiation. If the boundary sharpness evaluation result of the hot spot area is high sharpness and the shape regularity analysis result is high regularity, it is preliminarily suggested that it may be internal electrical heating or environmental heat-induced artifact. At this time, if the calculated boundary coincidence degree is low (for example, less than a preset coincidence degree threshold), it can be determined that the hot spot is caused by internal electrical heating. This is because internal electrical heating usually does not produce a corresponding shadow in the visible light image, and the coincidence degree of the hot spot boundary and the shadow boundary is naturally low. On the contrary, if the boundary coincidence degree is high, it may be an environmental heat-induced artifact, such as a hot spot caused by reflection of a nearby high-temperature object, which may exhibit sharp and regular boundaries on the infrared image, but may have some degree of coincidence with the shadow boundary in the visible light image (for example, the reflection source itself has a shadow under visible light). In this way, by combining the inherent characteristics of the infrared thermal image and the environmental information provided by the visible light image, misjudgment can be effectively avoided, the accuracy of heat source determination can be improved, and more reliable basis can be provided for fault diagnosis and maintenance of power transmission and distribution lines.

[0133] By the above technical solution, the embodiment significantly improves the accuracy and reliability of heat source judgment of the heat spot area of the power transmission and distribution line accessory hardware. By introducing visible light images and calculating the overlap of the heat spot boundary contour and the shadow boundary contour, the surface temperature rise caused by external environmental factors (such as solar radiation and environmental heat artifacts) can be effectively distinguished from the real heat caused by internal electrical faults. This avoids the misjudgment that may occur in the traditional method, such as misjudging the heat spot caused by solar radiation as internal electrical heating, thereby reducing unnecessary on-site inspection and maintenance costs. At the same time, it also reduces the risk of missing real internal electrical faults, ensuring the safe and stable operation of the power transmission and distribution line. The fusion analysis of multi-modal image information makes the heat source judgment more comprehensive and objective, providing more solid technical support for the intelligent operation and maintenance of the power transmission and distribution line.

[0134] In some embodiments, the contour extraction of the infrared thermal image in step S202 to obtain the heat spot boundary contour can include but is not limited to the following steps:

[0135] Gaussian smoothing is performed on the infrared thermal image to obtain a Gaussian smoothed image;

[0136] The gradient strength and direction of the Gaussian smoothed image are calculated;

[0137] According to the gradient strength and direction, the Gaussian smoothed image is refined by a double-threshold suppression method to obtain the heat spot boundary contour.

[0138] In some embodiments, the infrared thermal image can be first Gaussian smoothed to obtain a Gaussian smoothed image to achieve denoising and reduce random noise in the image, thereby providing a clearer image basis for subsequent edge detection. Gaussian smoothing is a linear smoothing filter whose weight coefficients follow a Gaussian distribution, which can effectively blur the image, reduce image details, and at the same time preserve the overall structure of the image.

[0139] Then the gradient strength and direction of the Gaussian smoothed image are calculated. Exemplarily, a specific operator (such as Sobel, Prewitt or Canny operator) can be used to process each pixel point of the Gaussian smoothed image to obtain the gray level change rate of the pixel point in the horizontal and vertical directions. The gradient strength represents the degree of gray level change, while the gradient direction indicates the direction of gray level change. These information is crucial for identifying image edges.

[0140] According to the gradient intensity and direction, the boundary of the hot spot is refined by a double threshold suppression method on the Gaussian smoothed image to obtain the hot spot boundary contour for accurately locating the edge in the image. The double threshold suppression method usually includes two thresholds: a high threshold and a low threshold. First, all pixel points with gradient intensity higher than the high threshold are determined as strong edge pixels. Then, for pixel points with gradient intensity between the high threshold and the low threshold, if they are connected to strong edge pixels, they are also considered as edge pixels. Meanwhile, pixel points lower than the low threshold are suppressed. This method helps to eliminate false edges and connect broken edges, thereby obtaining a continuous and refined hot spot boundary contour.

[0141] The embodiment introduces Gaussian smoothing, gradient calculation and double threshold suppression method to optimize the contour extraction process of infrared thermal images. Specifically, Gaussian smoothing can effectively filter out noise in the image, avoiding interference of noise on subsequent edge detection, and ensuring that the extracted edge information is more pure. Subsequently, by calculating the gradient intensity and direction of the Gaussian smoothed image, the areas of sharp temperature change in the image can be accurately captured, which usually correspond to the boundaries of hot spots. Finally, using the double threshold suppression method to process these gradient information can accurately screen out the real hot spot boundaries, suppress false edges, and connect possible broken edges, thereby forming a complete and fine hot spot boundary contour. This step-by-step processing ensures that the hot spot boundary contour extracted from the original infrared thermal image has higher accuracy and robustness, providing reliable image basis for subsequent heat source judgment.

[0142] Through the above technical solutions, the embodiment can realize accurate extraction of the hot spot boundary contour in the infrared thermal image. Gaussian smoothing can effectively reduce the interference of image noise on edge detection, making the extracted boundary clearer. The calculation of gradient intensity and direction ensures the sensitive capture of temperature changes in the hot spot edge. Further, the application of double threshold suppression method effectively avoids the misjudgment of weak edges and the omission of strong edges, thereby obtaining a continuous and refined hot spot boundary contour. Thus, the obtained hot spot boundary contour has higher accuracy and reliability, significantly improving the accuracy of subsequent heat source judgment, and helping to more accurately identify the temperature abnormality reason of the iron accessory hardware of the power transmission and distribution line.

[0143] In some embodiments, the step S203 of performing contour extraction on the visible light image to obtain a shadow boundary contour can include but is not limited to the following steps:

[0144] In step S301, the color space of the visible light image is converted so that the visible light image is converted from RGB color space to HSV color space, and the parameters of the HSV color space include hue, saturation and brightness.

[0145] In step S302, the luminance component in the visible light image converted by the color space is binarized by a Gaussian adaptive threshold method to obtain a binary image, so as to separate the shadow area from the non-shadow area.

[0146] In step S303, the boundary of the binary image is extracted by an edge detection algorithm to obtain a shadow boundary profile.

[0147] In some embodiments, the visible light image can be converted by color space first, so that the visible light image is converted from RGB color space to HSV color space, wherein the parameters of HSV color space include hue, saturation and brightness. RGB color space is an additive color model, which represents color by different combinations of red, green and blue three primary colors. HSV color space (Hue, Saturation, Value / Brightness) is a color model more consistent with human visual perception, wherein hue represents color type, saturation represents color purity, and brightness represents color lightness. Converting the visible light image from RGB color space to HSV color space aims to separate the brightness information of the image from the color information, because the recognition of shadow mainly depends on the change of brightness, and the brightness component is more sensitive to light change, which is helpful for subsequent shadow area recognition.

[0148] Then the luminance component in the visible light image converted by the color space is binarized by a Gaussian adaptive threshold method to obtain a binary image, so as to separate the shadow area from the non-shadow area. The Gaussian adaptive threshold method can dynamically determine the threshold according to the pixel value distribution of the local area of the image, instead of using a single global threshold. Specifically, for each pixel point in the image, this method considers the pixel values in its neighborhood, and calculates a local threshold according to the statistical characteristics (such as mean or weighted mean) of these pixel values. In this way, even if there is uneven illumination or different shadow depth in the image, the shadow area can be effectively separated from the non-shadow area, and a binary image can be generated. After binarization, the shadow area in the image is marked as a value (such as black), and the non-shadow area is marked as another value (such as white), so as to realize the clear separation of the shadow area and the non-shadow area.

[0149] Then, an edge detection algorithm is applied to the binary image to extract the shadow boundary contour. The edge detection algorithm is used to identify regions in the image where there is a significant change in brightness or color, which usually corresponds to the boundaries or contours of objects. After obtaining the binary image, there is a clear brightness difference between the shadow region and the non-shadow region, so the edge detection algorithm can be used to accurately extract the boundary contour of the shadow. In practical applications, various mature edge detection algorithms can be used, such as Canny algorithm, Sobel operator, Prewitt operator, Roberts operator, or Laplacian operator, etc. These algorithms identify edges by calculating the gradient information of the image.

[0150] By converting the visible light image from the RGB color space to the HSV color space, the embodiment can effectively decouple the brightness information and color information of the image, so that the subsequent shadow recognition process can focus more on the core feature of brightness change. Using the Gaussian adaptive threshold method to binarize the brightness component can overcome the limitations of traditional global threshold method in uneven lighting scenes, ensuring that the shadow region can be accurately separated from the non-shadow region, generating a clear binary image. On this basis, by applying the edge detection algorithm, the boundary between the shadow region and the non-shadow region in the binary image can be accurately identified and extracted, thereby obtaining an accurate shadow boundary contour. This series of processing steps work together to ensure that shadow information can be reliably obtained under complex lighting conditions, providing key auxiliary data for subsequent heat source judgment.

[0151] Through the above technical solutions, the embodiment can overcome the challenge that traditional methods are difficult to accurately identify the shadow region under complex lighting conditions. By combining color space conversion and Gaussian adaptive threshold method, the identification of the shadow region is no longer limited to a single global brightness threshold, thereby improving the accuracy and robustness of the separation of the shadow region and the non-shadow region. As a result, the extracted shadow boundary contour is more accurate, providing a more reliable basis for subsequent heat source judgment of the hot spot region, effectively improving the accuracy of temperature anomaly control of the iron accessory hardware of the power transmission and distribution line.

[0152] In some embodiments, in step S302, the brightness component in the visible light image converted by the color space is binarized by the Gaussian adaptive threshold method to obtain a binary image, which can include but is not limited to the following steps:

[0153] Obtain the brightness change region of the brightness component from the visible light image converted by the color space;

[0154] Extract the brightness value range of the brightness change region;

[0155] Calculate the brightness distribution of the brightness value range;

[0156] skewness of the luminance distribution;

[0157] determining a luminance value upper limit according to the skewness and the kurtosis;

[0158] updating the luminance value range according to the luminance value upper limit;

[0159] determining a shadow boundary luminance threshold according to the updated luminance value range;

[0160] binarizing the luminance component according to the shadow boundary luminance threshold to obtain a binarized image.

[0161] In some embodiments, the luminance variation region of the luminance component can be obtained from the converted visible light image in color space. For example, the luminance variation region can be identified by analyzing the luminance value difference of the pixels in the image. These regions usually correspond to the edges or the boundaries between light and dark in the image, such as the boundaries of the shadow. In practical applications, the local luminance gradient can be calculated or a specific filter can be used to achieve this.

[0162] Then the luminance value range of the luminance variation region is extracted. The minimum and maximum values of the luminance values of all pixels in the identified luminance variation region can be determined, thereby defining a luminance interval containing potential shadow and non-shadow regions as the luminance value range. At the same time, the luminance distribution of the luminance value range can be calculated. The luminance values of the pixels in the luminance value range can be statistically analyzed, for example, a luminance histogram can be generated. The histogram can intuitively show the frequency of different luminance values as the luminance distribution. The skewness and the kurtosis of the luminance distribution can be calculated by statistical analysis of the luminance distribution. Skewness is used to measure the symmetry of the luminance distribution, indicating whether the tail of the distribution is skewed towards high or low luminance; kurtosis is used to measure the sharpness or flatness of the luminance distribution, reflecting the degree of concentration or dispersion of the luminance values. These statistics can more finely characterize the characteristics of the luminance distribution, which helps to distinguish the luminance changes caused by shadows from those caused by other factors.

[0163] According to the skewness and the kurtosis, a luminance value upper limit is determined. For example, when the luminance distribution shows a significant low luminance skew (i.e., the skewness is negative) and a high kurtosis, it may indicate the presence of a concentrated shadow region. At this time, a suitable luminance upper limit can be adaptively set according to these statistical characteristics to better frame the luminance range of the shadow region. At the same time, according to the luminance value upper limit, the luminance value range is updated. The original luminance value range can be adjusted according to the newly determined luminance value upper limit, so that the subsequent analysis focuses more on the luminance interval related to the shadow.

[0164] Finally, according to the updated brightness value range, a shadow boundary brightness threshold is determined, and the brightness component is binarized according to the shadow boundary brightness threshold to obtain a binarized image. The shadow boundary brightness threshold is a key parameter for binarizing the brightness component in the image, which can divide the pixels into shadow regions and non-shadow regions. The determination of the threshold is adaptive and can be adjusted according to the actual brightness distribution characteristics of the image, thereby improving the accuracy of shadow segmentation.

[0165] The embodiment can adaptively determine an accurate shadow boundary brightness threshold by conducting in-depth statistical analysis on the brightness component of the visible light image, especially using skewness and kurtosis to characterize the brightness distribution. This method overcomes the problem of inaccurate shadow region segmentation under complex lighting conditions in traditional fixed threshold or simple adaptive threshold methods, especially in visible light images of power transmission and distribution line accessories, due to factors such as environmental lighting, structural complexity, etc. The shadow shape and brightness may vary. By analyzing the skewness and kurtosis of the brightness distribution, the brightness characteristics of the shadow region can be more accurately captured, thereby achieving more robust separation of the shadow region and the non-shadow region.

[0166] Through the above technical solutions, the embodiment can significantly improve the accuracy and robustness of the binarization processing of the shadow region in the visible light image. Since the threshold is adaptively determined according to the statistical characteristics (skewness and kurtosis) of the brightness distribution, this method can better adapt to the shadow changes under different lighting conditions and scenes, avoiding the over-segmentation or under-segmentation problems caused by fixed threshold or simple adaptive threshold methods. This makes the subsequent shadow boundary contour extraction more accurate, thereby providing a reliable image processing foundation for accurately determining the heat source of the hot spot region, effectively improving the overall performance of the temperature anomaly control method for power transmission and distribution line accessories.

[0167] In some embodiments, in step S205, determining the heat source of the hot spot region according to the boundary sharpness evaluation result, the shape regularity analysis result, and the boundary coincidence degree can include but is not limited to the following steps:

[0168] If the boundary sharpness evaluation result is low sharpness and the shape regularity analysis result is low regularity, it is determined that the heat source is solar irradiation;

[0169] If the boundary sharpness evaluation result is high sharpness and the shape regularity analysis result is high regularity, it is determined whether the boundary coincidence degree is greater than a preset coincidence degree threshold;

[0170] If the boundary coincidence degree is greater than the preset coincidence degree threshold, it is determined that the heat source is an environmental heat artifact;

[0171] If the boundary coincidence degree is less than the preset coincidence degree threshold, it is determined that the heat source is internal electrical heating.

[0172] In some embodiments, the boundary sharpness evaluation result, the shape regularity analysis result and the boundary coincidence degree can be determined to determine the heat source of the hot spot region. If the boundary sharpness evaluation result is low sharpness and the shape regularity analysis result is low regularity, it indicates that the heat spreads widely, the boundary is fuzzy and the shape is irregular, which is consistent with the phenomenon of surface temperature rise caused by solar irradiation. It can be determined that the heat source is solar irradiation. Solar irradiation usually causes the whole object surface to be heated, and the heat distribution is relatively uniform, the boundary is not obvious, and the hot spot shape is affected by the object surface geometry and the illumination angle, and is often irregular.

[0173] If the boundary sharpness evaluation result is high sharpness and the shape regularity analysis result is high regularity, it indicates that the heat of the hot spot region is concentrated, the boundary is clear, and the shape is relatively regular. This feature is usually related to local temperature rise caused by internal heat sources (such as electrical heating) or specific environmental factors (such as reflection, shadow). It is necessary to further determine whether the boundary coincidence degree is greater than the preset coincidence degree threshold to determine the heat source.

[0174] If the boundary coincidence degree is greater than the preset coincidence degree threshold, that is, when the hot spot boundary contour is highly coincident with the shadow boundary contour in the visible light image, it indicates that the formation of the hot spot may be related to the shadow or reflection phenomenon in the environment, rather than the internal heating of the fitting itself, and the heat source can be determined to be the environmental heat-induced artifact. For example, when sunlight is blocked by nearby objects to form a shadow, or light is reflected on a smooth surface, a region similar to a hot spot may be generated on the infrared image.

[0175] If the boundary coincidence degree is less than the preset coincidence degree threshold, that is, when the coincidence degree of the hot spot boundary contour and the shadow boundary contour is low, the possibility of environmental heat-induced artifact is excluded, and the hot spot is more likely to be caused by electrical failure or abnormal heating in the fitting. It can be determined that the heat source is internal electrical heating.

[0176] The embodiment realizes accurate differentiation of heat sources by comprehensively analyzing the boundary sharpness evaluation result, shape regularity analysis result and coincidence degree with the shadow boundary in the visible light image of the hot spot area. Specifically, when the hot spot shows low sharpness and low regularity, its heat distribution characteristics are highly consistent with the surface heating phenomenon caused by solar irradiation, and therefore is determined as solar irradiation. When the hot spot shows high sharpness and high regularity, it indicates that there is a local and concentrated heat source, and visible light information needs to be further used for judgment. By calculating the boundary coincidence degree of the hot spot boundary contour and the shadow boundary contour, it can be effectively distinguished whether it is a pseudo hot spot caused by environmental factors (such as reflection, shadow) or an actual electrical heating inside the fitting. High coincidence degree points to environmental heat pseudo image, because environmental factors often leave traces on visible light and infrared images; and low coincidence degree points to internal electrical heating, because internal heating is usually not highly associated with external environmental shadow or reflection. This multi-dimensional and cross-verification judgment mechanism significantly improves the accuracy and reliability of heat source determination.

[0177] Through the above technical solutions, the embodiment can effectively distinguish various heat sources of temperature abnormities of the power transmission and distribution line fitting, including solar irradiation, environmental heat pseudo image and internal electrical heating. This avoids misjudging non-fault heat rise as internal electrical fault, thereby reducing unnecessary on-site inspection and maintenance cost. At the same time, for the real internal electrical heating, it can be accurately identified in time, providing a reliable basis for subsequent fault diagnosis and treatment, and ensuring the safe and stable operation of the power transmission and distribution line.

[0178] In some embodiments, the method further comprises:

[0179] obtaining an infrared thermal image sequence;

[0180] selecting an image from the infrared thermal image sequence as a to-be-processed image;

[0181] extracting a temperature peak value from the to-be-processed image as a hot spot center point;

[0182] constructing a hot spot core area according to a preset pixel side length and the hot spot center point;

[0183] selecting a pixel point from the hot spot core area as a to-be-processed pixel point;

[0184] combining temperature values corresponding to each image in the infrared thermal image sequence of the to-be-processed pixel point according to coordinate information of the to-be-processed pixel point, to obtain a temperature value sequence;

[0185] calculating an average temperature according to the temperature value sequence;

[0186] calculating a standard deviation as a temperature fluctuation amplitude according to the temperature value sequence and the average temperature;

[0187] The temperature fluctuation rate is obtained by statistically analyzing the temperature fluctuation amplitude of each pixel point in the hot spot core area.

[0188] If the temperature fluctuation rate is greater than the preset fluctuation threshold and the heat source is internal electrical heating, the heat source is updated to solar irradiation.

[0189] In some embodiments, since the heat source determination only relies on the static features of the infrared thermal image, there may be limitations. For example, the infrared features of the hot spot caused by certain environmental factors (such as solar irradiation) may be similar to the hot spot caused by internal electrical heating under certain conditions, resulting in misjudgment, and the heat caused by solar irradiation is misidentified as internal electrical heating, which may cause unnecessary maintenance or resource waste. Therefore, the temperature fluctuation information within a certain period of time can be used to further determine the heat source. The infrared thermal image sequence can be obtained, for example, the infrared thermal image of the target fitting can be continuously or periodically collected within a period of time to form an image set containing time dimension information. The sequence is obtained to capture the temperature dynamics of the hot spot area over time.

[0190] Then, an image is selected from the infrared thermal image sequence as a to-be-processed image, and a temperature peak value is extracted from the to-be-processed image as a hot spot center point. The pixel point with the highest temperature in the identified hot spot area can be located, and the coordinates thereof are taken as the center reference point of the hot spot. At the same time, according to the preset pixel side length and the hot spot center point, the hot spot core area can be constructed. A sub-area of a preset size (for example, a 5x5 pixel rectangular area or a circular area with a preset radius) can be demarcated with the hot spot center point as the center. This area is considered to be the core part of the hot spot with the most significant temperature change. A pixel point is selected from the hot spot core area as a to-be-processed pixel point. In subsequent statistical analysis, each pixel point in the hot spot core area can be statistically analyzed.

[0191] According to the coordinate information of the to-be-processed pixel point, the temperature values corresponding to the to-be-processed pixel point in each image of the infrared thermal image sequence are combined to obtain a temperature value sequence. For example, by tracking the temperature values of the pixel point at the same spatial position at different time points, a sequence reflecting the temperature change of the pixel point over time is formed. For example, if the hot spot core area contains multiple pixel points, a corresponding temperature value sequence is generated for each pixel point. For each pixel point, the average temperature in the observation period can be calculated according to the temperature value sequence, and the standard deviation as the temperature fluctuation amplitude can be calculated according to the temperature value sequence and the average temperature. The standard deviation in statistics can be used to quantify the dispersion degree of the temperature value sequence of each pixel point. The greater the standard deviation, the more intense the temperature fluctuation of the pixel point.

[0192] Finally, the temperature fluctuation amplitude corresponding to each pixel point in the hot spot core region is statistically analyzed to obtain a temperature fluctuation rate. For example, the temperature fluctuation amplitudes of all pixel points in the hot spot core region can be analyzed, for example, the average, maximum or certain percentile of these fluctuation amplitudes can be calculated to obtain a comprehensive index representing the temperature fluctuation degree of the entire hot spot core region, i.e. the temperature fluctuation rate. The temperature fluctuation rate reflects the overall temperature stability of the hot spot. If the temperature fluctuation rate is greater than a preset fluctuation threshold and the heat source is internal electrical heating, the heat source is updated to be solar radiation. This means that when the heat source is initially determined to be internal electrical heating through static image features, if further dynamic temperature fluctuation analysis shows that the hot spot has significant temperature fluctuations (i.e. the temperature fluctuation rate exceeds the preset threshold), the heat source determination will be corrected to be solar radiation. The preset fluctuation threshold can be set according to actual experience or experimental data to distinguish between temperature fluctuations caused by environmental factors (such as solar radiation, cloud cover, wind changes) and relatively stable heating caused by internal electrical faults.

[0193] The present embodiment effectively makes up for the shortcomings of relying solely on static image features to determine the heat source by introducing analysis of the temperature fluctuation characteristics of the hot spot region. Specifically, the temperature of a hot spot caused by solar radiation is often affected by factors such as sunlight intensity, cloud cover, and environmental wind speed, showing significant temperature fluctuation. While heating caused by internal electrical faults is usually relatively stable or shows a continuous upward trend during the fault duration, with less fluctuation. Therefore, by obtaining a sequence of infrared thermal images and quantitatively analyzing the temperature fluctuation amplitude of the hot spot core region, important time dimension information can be provided for heat source determination. When a high temperature fluctuation rate is detected, even if its static features (such as boundary sharpness, shape regularity, and boundary overlap) are similar to internal electrical heating, it can be more accurately attributed to solar radiation based on its dynamic characteristics, thereby avoiding misjudgment.

[0194] To make the technical solution clearer, specific examples are used for explanation below. Suppose in a certain inspection, the system analyzes the infrared thermal image of the target fitting and preliminarily judges that the heat source of a certain heat spot is "internal electrical heating" according to the sharpness of the heat spot boundary, the regularity of the shape, and the boundary coincidence degree with the shadow of the visible light image. However, in order to further verify the accuracy of this judgment, the system will start the temperature fluctuation analysis module. This module will continuously obtain a sequence of infrared thermal images of the fitting, for example, one image every 5 minutes for 30 minutes. During this period, the system will track the temperature changes of the pixel points in the core area of the heat spot. If it is found through calculation that the temperature fluctuation rate (for example, by calculating the average of the standard deviation of the temperatures of the pixel points in the core area) of the core area of the heat spot is greater than the preset fluctuation threshold (for example, 2°C), even if the previous judgment is "internal electrical heating", the system will update the judgment of the heat source to "solar radiation". This correction mechanism can effectively avoid misjudging the temporary high temperature caused by solar radiation as an electrical fault, thereby avoiding unnecessary on-site inspection and outage maintenance, saving manpower and material resources, and improving the reliability of the transmission and distribution line operation.

[0195] Through the above technical solution, the embodiment can significantly improve the accuracy of heat source judgment, especially in distinguishing between solar radiation and internal electrical heating. This helps to reduce unnecessary maintenance and resource waste caused by misjudgment, improve the accuracy of fault diagnosis, optimize the operation and maintenance efficiency of the transmission and distribution line, and ensure the safe and stable operation of the power system.

[0196] The beneficial effects of implementing the embodiment of the present application include that the embodiment of the present application first obtains an infrared thermal image of a target fitting, then separates heat spots from the infrared thermal image according to a preset separation temperature threshold to obtain a heat spot area, then evaluates the sharpness of the boundary of the heat spot area to obtain a sharpness evaluation result, analyzes the regularity of the shape of the heat spot area to obtain a shape regularity analysis result, and finally determines the heat source of the heat spot area according to the sharpness evaluation result and the shape regularity analysis result, so as to analyze the heat source in combination with the sharpness of the boundary and the regularity of the shape to realize fitting temperature anomaly control, thereby improving the temperature anomaly detection accuracy and effectively controlling the iron accessory fitting to maintain a normal state.

[0197] As shown in Figure 2 , the embodiment of the present application also provides a transmission and distribution line iron accessory fitting temperature anomaly control system, which comprises:

[0198] An image acquisition module 401 is configured to obtain an infrared thermal image of a target fitting.

[0199] A heat spot identification module 402 is configured to separate heat spots from the infrared thermal image according to a preset separation temperature threshold to obtain a heat spot area.

[0200] The boundary sharpness evaluation module 403 is configured to perform boundary sharpness evaluation on the hot spot region to obtain a boundary sharpness evaluation result.

[0201] The shape regularity analysis module 404 is configured to perform shape regularity analysis on the hot spot region to obtain a shape regularity analysis result.

[0202] The hot spot source judgment module 405 is configured to determine the heat source of the hot spot region according to the boundary sharpness evaluation result and the shape regularity analysis result.

[0203] The contents in the method embodiments are applicable to the system embodiments. The system embodiments specifically implement the same functions as the method embodiments, and achieve the same beneficial effects as the method embodiments.

[0204] The embodiments described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

Claims

1. A power transmission line accessory fitting temperature anomaly control method, characterized by, The method comprises the following steps: acquiring an infrared thermal image of a target fitting; performing hot spot separation on the infrared thermal image according to a preset separation temperature threshold to obtain a hot spot region; performing boundary sharpness evaluation on the hot spot region to obtain a boundary sharpness evaluation result; performing shape regularity analysis on the hot spot region to obtain a shape regularity analysis result; determining a heat source of the hot spot region according to the boundary sharpness evaluation result and the shape regularity analysis result; the determination of the heat source of the hot spot region according to the boundary sharpness evaluation result and the shape regularity analysis result comprises: collecting a visible light image of the target fitting, the time stamp of the visible light image being the same as that of the infrared thermal image; performing contour extraction on the infrared thermal image to obtain a hot spot boundary contour; performing contour extraction on the visible light image to obtain a shadow boundary contour; calculating a boundary overlap degree according to the hot spot boundary contour and the shadow boundary contour; determining the heat source of the hot spot region according to the boundary sharpness evaluation result, the shape regularity analysis result and the boundary overlap degree; selecting a pixel point in a hot spot core region as a pixel point to be processed; combining temperature values corresponding to the pixel point to be processed in each image of the infrared thermal image sequence according to coordinate information of the pixel point to be processed to obtain a temperature value sequence; calculating an average temperature according to the temperature value sequence; calculating a standard deviation as a temperature fluctuation amplitude according to the temperature value sequence and the average temperature; statistically analyzing temperature fluctuation amplitudes corresponding to each pixel point in the hot spot core region to obtain a temperature fluctuation rate; if the temperature fluctuation rate is greater than a preset fluctuation threshold and the heat source is internal electrical heating, updating the heat source to be solar irradiation.

2. The method of claim 1, wherein, the boundary sharpness evaluation on the hot spot region to obtain a boundary sharpness evaluation result comprises: selecting a pixel point from a boundary of the hot spot region as a target pixel point; constructing a temperature difference analysis window, the temperature difference analysis window being centered on the target pixel point; calculating temperature difference values between each pixel point in the temperature difference analysis window and the target pixel point; averaging absolute values of a plurality of temperature difference values to obtain a local temperature change rate; if the local temperature change rate is greater than a preset temperature gradient threshold, determining that the boundary sharpness evaluation result is high sharpness; if the local temperature change rate is less than a preset temperature gradient threshold, determining that the boundary sharpness evaluation result is low sharpness.

3. The method of claim 1, wherein, the shape regularity analysis on the hot spot region to obtain a shape regularity analysis result comprises: performing morphological feature extraction on the hot spot region to calculate an area and a perimeter of the hot spot region; calculating a circularity according to the area and the perimeter; calculating an aspect ratio of a minimum circumscribed rectangle of the hot spot region; if the circularity is greater than a preset circularity threshold and the aspect ratio is greater than a preset aspect ratio threshold, determining that the shape regularity analysis result is high regularity; otherwise, determining that the shape regularity analysis result is low regularity.

4. The method of claim 1, wherein, The profile extraction on the infrared thermal image comprises: Gaussian smoothing is performed on the infrared thermal image to obtain a Gaussian smoothed image; Gradient intensity and direction of the Gaussian smoothed image are calculated; Boundary refinement is performed on the Gaussian smoothed image by a double-threshold suppression method according to the gradient intensity and direction to obtain the hot spot boundary profile.

5. The method of claim 1, wherein, The profile extraction on the visible light image comprises: Color space conversion is performed on the visible light image to convert the visible light image from an RGB color space to an HSV color space, wherein parameters of the HSV color space include hue, saturation and brightness; Binaryzation is performed on a brightness component in the visible light image after color space conversion by a Gaussian adaptive threshold method to obtain a binary image, so as to separate a shadow region from a non-shadow region; Boundary extraction is performed on the binary image by an edge detection algorithm to obtain the shadow boundary profile.

6. The method of claim 5, wherein, The binaryzation on the brightness component in the visible light image after color space conversion by the Gaussian adaptive threshold method to obtain the binary image comprises: A brightness variation region of the brightness component is obtained from the visible light image after color space conversion; A brightness value range of the brightness variation region is extracted; Brightness distribution of the brightness value range is calculated; Skewness and kurtosis of the brightness distribution are calculated; An upper limit of brightness value is determined according to the skewness and kurtosis; The brightness value range is updated according to the upper limit of brightness value; A shadow boundary brightness threshold is determined according to the updated brightness value range; Binaryzation is performed on the brightness component according to the shadow boundary brightness threshold to obtain a binary image.

7. The method of claim 1, wherein, The determination of the heat source of the hot spot region according to the boundary sharpness evaluation result, the shape regularity analysis result and the boundary coincidence degree comprises: If the boundary sharpness evaluation result is low sharpness and the shape regularity analysis result is low regularity, it is determined that the heat source is solar irradiation; If the boundary sharpness evaluation result is high sharpness and the shape regularity analysis result is high regularity, it is determined whether the boundary coincidence degree is greater than a preset coincidence threshold; If the boundary coincidence degree is greater than the preset coincidence threshold, it is determined that the heat source is an environmental heat artifact; If the boundary coincidence degree is less than the preset coincidence threshold, it is determined that the heat source is internal electrical heating.

8. The method of claim 1, wherein, The method further comprises: An infrared thermal image sequence is obtained; An image is selected from the infrared thermal image sequence as a to-be-processed image; A temperature peak value is extracted from the to-be-processed image as a hot spot center point; A hot spot core region is constructed according to a preset pixel side length and the hot spot center point.

9. A temperature anomaly control system for iron fittings of power transmission and distribution lines, characterized in that, The method comprises: An image acquisition module is configured to acquire an infrared thermal image of a target fitting; The image acquisition module is further configured to acquire a visible light image of the target fitting, wherein a time stamp of the visible light image is the same as a time stamp of the infrared thermal image; The profile extraction on the infrared thermal image comprises: The profile extraction on the visible light image comprises: According to the hot spot boundary contour and the shadow boundary contour, a boundary coincidence degree is calculated; a hot spot identification module configured to perform hot spot separation on the infrared thermal image according to a preset separation temperature threshold to obtain a hot spot region; a boundary sharpness evaluation module configured to perform boundary sharpness evaluation on the hot spot region to obtain a boundary sharpness evaluation result; a shape regularity analysis module configured to perform shape regularity analysis on the hot spot region to obtain a shape regularity analysis result; a hot spot source judgment module configured to determine a heat source of the hot spot region according to the boundary sharpness evaluation result and the shape regularity analysis result; selecting a pixel point in the hot spot core region as a pixel point to be processed; combining temperature values corresponding to the pixel point to be processed in each image of the infrared thermal image sequence according to coordinate information of the pixel point to be processed to obtain a temperature value sequence; calculating an average temperature according to the temperature value sequence; calculating a standard deviation as a temperature fluctuation amplitude according to the temperature value sequence and the average temperature; performing statistical analysis on temperature fluctuation amplitudes corresponding to each pixel point in the hot spot core region to obtain a temperature fluctuation rate; if the temperature fluctuation rate is greater than a preset fluctuation threshold and the heat source is internal electrical heating, updating the heat source to be solar irradiation.

Images