Converter valve infrared monitoring temperature early warning method and system

Abstract

The invention relates to a converter valve infrared monitoring temperature early warning method and system, and belongs to the technical field of power transmission and transformation operation and maintenance, and the method comprises the steps: obtaining a converter valve reference infrared image in a normal operation state, segmenting the image into a plurality of regions through employing an improved clustering segmentation algorithm, and recording the reference feature information; during continuous monitoring, infrared images are collected in real time, and multi-dimensional monitoring indexes such as a temperature change index, an overheat point index and a temperature change range index are calculated by taking the reference features as initial values; the change rate of each index along with time is analyzed, and when any change rate exceeds a preset threshold value, temperature early warning is triggered. Accurate segmentation, multi-dimensional dynamic monitoring and early warning of the converter valve temperature are realized, and the equipment safety and the operation and maintenance efficiency are effectively improved.

Description

Technical Field

[0001] This application relates to the field of power transmission and transformation operation and maintenance technology, and more specifically, to a method and system for infrared monitoring and early warning of converter valve temperature. Background Technology

[0002] In current power system operation monitoring, temperature monitoring of converter valves primarily relies on infrared thermometry. Measuring surface temperature by capturing the infrared radiation emitted by an object offers advantages such as non-contact and real-time monitoring, effectively avoiding many problems associated with contact measurements, such as interference with equipment operation and corona discharge. However, existing temperature anomaly alarm mechanisms often employ a threshold method; once the monitored temperature exceeds a pre-set threshold, the system triggers an alarm. While this method can provide some warning of temperature anomalies, its limitations become apparent when dealing with converter valve components where temperature changes are relatively slow. In actual operation, the temperature of converter valve components often shows a gradual upward trend. When the temperature gradually approaches and exceeds the threshold, the alarm is already delayed, and the equipment may already be in a dangerous state. The response time left for maintenance personnel is limited, which can easily lead to the expansion of the fault or even cause a system accident. For example, the existing technology publication number "CN107478340A" discloses a converter valve monitoring method. This method divides the converter valve component into regions and filters out the over-temperature areas based on the infrared images of each region. For the over-temperature areas, pixel-weighted fusion processing of visible light images and infrared images is performed to obtain a fused image, which can quickly identify the specific location and surface features of the abnormal over-temperature of the converter valve. However, it still faces challenges such as complex image registration and weight selection, and cannot effectively solve the fundamental problem of temperature trend early warning.

[0003] Therefore, relying solely on a single threshold alarm method is no longer sufficient to meet the refined requirements of converter valve temperature monitoring. There is an urgent need to introduce a more intelligent and efficient early warning mechanism that can accurately predict and promptly warn of potential abnormal changes in converter valve temperature, so that maintenance personnel can prepare in advance and ensure the safe and stable operation of the converter valve and even the entire power system. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention proposes a method and system for infrared monitoring and early warning of temperature in converter valves.

[0005] The technical solution of this invention is as follows: This invention proposes a method for infrared monitoring and temperature early warning of a converter valve, comprising the following steps: A reference infrared image of the converter valve under normal operating conditions is acquired. An improved clustering segmentation algorithm is used to segment the reference infrared image of the converter valve into multiple regions, and the reference feature information of each region is recorded. Continuously monitor the converter valve, acquire infrared images of the converter valve in real time, and use the region segmented from the reference infrared image and the reference feature information as initial values ​​to calculate multi-dimensional monitoring indicators to characterize the temperature state changes of the converter valve. Based on multi-dimensional monitoring indicators, the rate of change of each indicator is calculated. When the rate of change of any indicator exceeds a preset threshold, a temperature warning is triggered.

[0006] Preferably, the improved clustering segmentation algorithm includes the following steps: The reference infrared image of the converter valve is converted from the RGB color space to the LAB color space and uniformly divided into N initial regions. In each initial region, a pixel is randomly selected as the initial cluster center. For each pixel within any initial region, calculate its four types of features relative to the cluster center of that region: position features based on pixel coordinates, color features based on LAB color vectors, gradient features based on color change gradients, and similarity features based on the similarity between the pixel color and the average color within the region. Based on four types of features, a comprehensive distance index between pixels and cluster centers is calculated. Based on the comparison results between the comprehensive distance index and the preset threshold, it is determined whether a pixel belongs to the cluster center. For pixels that have never been assigned a cluster center, a point is selected within the set as the cluster center. The process is iterated until all pixels are assigned a region, and the baseline infrared image is finally divided into N+K regions, with baseline feature information for each region obtained; K is the newly added region composed of unassigned pixels.

[0007] Preferably, the formula for calculating the comprehensive distance index is: ; In the formula: This is the combined distance index between the i-th pixel and the cluster center; The positional difference feature between the i-th pixel and the cluster center; The color difference feature between the i-th pixel and the cluster center; The gradient difference feature between the i-th pixel and the cluster center; Let be the similarity feature between the i-th pixel and the cluster center; , , , These are the normalization coefficients for position difference features, color difference features, gradient difference features, and similarity features, respectively.

[0008] Preferably, the reference feature information includes a reference color feature vector, reference position coordinates, and a reference pixel set.

[0009] Preferably, the multi-dimensional monitoring indicators include temperature change indicators that characterize changes in temperature values, process point indicators that characterize changes in the location of hot spots, and temperature change range indicators that characterize the similarity of temperature distribution.

[0010] Preferably, the specific formula for calculating the temperature change index is as follows: ; In the formula: This is an indicator of temperature change. , , These represent the luminance component, red-green component, and blue-yellow component of the color feature vector of a certain cluster center in the reference infrared image in the LAB color space. , , These represent the luminance component, red-green component, and blue-yellow component of the color feature vector of a cluster center in a real-time infrared image in the LAB color space.

[0011] Preferably, the specific formula for calculating the temperature variation range index is as follows: ; In the formula: This is an indicator of the range of temperature changes. , These are the average pixel brightness values ​​of the pixel set of a certain region in the reference infrared image and the pixel set of the corresponding region in the real-time infrared image, respectively. , These are the pixel brightness variances of the pixel set of a certain region in the reference infrared image and the pixel set of the corresponding region in the real-time infrared image, respectively. The pixel brightness covariance is the pixel set of a certain region in the reference infrared image and the pixel set of the corresponding region in the real-time infrared image. , These are the standard deviations of pixel brightness for a certain region in the reference infrared image and the corresponding region in the real-time infrared image, respectively.

[0012] On the other hand, the present invention also provides an infrared monitoring and temperature early warning system for a converter valve, comprising: The image segmentation and modeling module acquires the reference infrared image of the converter valve under normal operating conditions, uses an improved clustering segmentation algorithm to segment the reference infrared image of the converter valve into multiple regions, and records the reference feature information of each region. The multi-dimensional indicator monitoring module continuously monitors the converter valve, acquires infrared images of the converter valve in real time, and uses the region segmented from the reference infrared image and the reference feature information as initial values ​​to calculate multi-dimensional monitoring indicators used to characterize the temperature state changes of the converter valve. The trend analysis and early warning module calculates the rate of change of each indicator based on multi-dimensional monitoring indicators. When the rate of change of any indicator exceeds a preset threshold, a temperature early warning is triggered.

[0013] In another aspect, the present invention also provides an electronic device having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements a converter valve infrared monitoring temperature early warning method as described in any embodiment of the present invention.

[0014] In another aspect, the present invention also provides a computer-readable medium for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement a converter valve infrared monitoring temperature early warning method as described in any embodiment of the present invention.

[0015] The present invention has the following beneficial effects: 1. By using an improved clustering segmentation algorithm, combined with four types of feature constraints—position, color, gradient, and similarity—precise region division of each component in the infrared image of the converter valve was achieved, avoiding the problems of blurred boundaries or erroneous merging in traditional methods.

[0016] 2. A multi-dimensional monitoring indicator system was proposed, including temperature change indicators, hot spot indicators, and temperature change range indicators, to comprehensively capture changes in temperature values, location offsets, and distribution similarities, thereby enhancing the physical significance and comprehensiveness of the monitoring.

[0017] 3. By calculating the rate of change of each indicator and triggering an early warning when the rate of change exceeds the threshold, the system enables early prediction of slow and abnormal temperature changes in the converter valve, overcoming the lag of existing threshold alarm methods and effectively preventing equipment failures. Attached Figure Description

[0018] Figure 1 This is a flowchart for the temperature detection and early warning process of the converter valve. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] It should be understood that the step numbers used in the text are for ease of description only and are not intended to limit the order in which the steps are performed.

[0021] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0022] The terms “comprising” and “including” indicate the presence of the described feature, whole, step, operation, element and / or component, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0023] The term “and / or” refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes these combinations.

[0024] Example 1: To make the objectives, technical solutions, and advantages of this invention clearer, specific embodiments of this application will be described below, with reference to the accompanying drawings. Figure 1 The technical solution of the present invention will be clearly and completely described.

[0025] To address the problems in the existing technology, this embodiment provides a method for infrared monitoring and temperature early warning of a converter valve, comprising the following steps: A reference infrared image of the converter valve under normal operating conditions is acquired. An improved clustering segmentation algorithm is used to segment the reference infrared image of the converter valve into multiple regions, and the reference feature information of each region is recorded. The specific steps are as follows: A reference infrared image of the converter valve under normal operating conditions is selected as the baseline infrared image. The image contains the converter valve assembly components to be monitored. The reference infrared image of the converter valve is converted from the RGB color space to the LAB color space and uniformly divided into N initial regions. A pixel is randomly selected in each initial region as the initial cluster center. For each pixel within any initial region, calculate its four features relative to the cluster center of that region: positional features based on pixel coordinates, color features based on the LAB color vector, gradient features based on color change gradients, and similarity features based on the pixel color and the average color similarity within the region; where: The formula for calculating location features is: ; In the formula: The positional difference feature between the i-th pixel and the cluster center; Let i be the position of pixel i; The location of cluster center o; The formula for calculating color characteristics is: ; In the formula: The color difference feature between the i-th pixel and the cluster center; , , These are the luminance component, red-green component, and blue-yellow component of the color feature vector of pixel i in the LAB color space, respectively. , , These represent the luminance component, red-green component, and blue-yellow component of the color feature vector of cluster center o in the LAB color space.

[0026] The formula for calculating echelon characteristics is: ; In the formula: The gradient difference feature between the i-th pixel and the cluster center; The formula for calculating similarity features is: ; In the formula: Let be the similarity feature between the i-th pixel and the cluster center; This is the average value of the color vectors within this region.

[0027] Therefore, for any pixel i within the region, it has the following characteristics. Based on the four types of features, calculate the comprehensive distance index between pixel i and cluster center o; the formula for calculating the comprehensive distance index is: ; In the formula: This is the combined distance index between the i-th pixel and the cluster center; The positional difference feature between the i-th pixel and the cluster center; The color difference feature between the i-th pixel and the cluster center; The gradient difference feature between the i-th pixel and the cluster center; Let be the similarity feature between the i-th pixel and the cluster center; , , , These are the normalization coefficients for position difference features, color difference features, gradient difference features, and similarity features, respectively.

[0028] Based on the comparison between the comprehensive distance index and the preset threshold, it is determined whether a pixel belongs to the cluster center, and the position of the cluster center is updated; specifically: for a cluster center o within the region, its surrounding area is searched. The region contains all pixels, where M represents the total number of pixels in the entire infrared image. A comprehensive distance index is calculated for each pixel, and its value is compared to a threshold D. If the index is less than the threshold, the pixel belongs to the cluster center o; otherwise, it does not.

[0029] The iteration continues until all pixels are assigned a location, ultimately segmenting the baseline infrared image into N+K regions and obtaining the baseline feature information for each region. During the iteration, for pixels that remain unassigned, a point within their set is selected as the cluster center, and the above steps are repeated until all unassigned pixels are eliminated. K represents the region formed by the newly added unassigned pixels. For each region, region features are defined. ,in This represents all pixel information for that region.

[0030] In a preferred embodiment of this invention, the reference feature information includes a reference color feature vector. Reference position coordinates and reference pixel set .

[0031] Continuous monitoring of the converter valve involves real-time acquisition of its infrared images. Using the segmented regions and baseline feature information of a reference infrared image as initial values, multi-dimensional monitoring indicators characterizing temperature changes in the converter valve are calculated. These multi-dimensional indicators include temperature change indicators characterizing temperature value changes, process point indicators characterizing hot spot location changes, and temperature change range indicators characterizing temperature distribution similarity. Specifically, during monitoring, for the real-time acquired converter valve infrared images, N+K regions and cluster centers obtained using the segmentation method of the reference infrared image are used as the initial regions and cluster centers for the real-time acquired converter valve infrared images. For each region, there are feature... .

[0032] The specific formula for calculating the temperature change index is as follows: ; In the formula: As an indicator of temperature change, This indicates that the temperature has not changed; otherwise, the temperature has drifted. , , These represent the luminance component, red-green component, and blue-yellow component of the color feature vector of a certain cluster center in the reference infrared image in the LAB color space. , , These represent the luminance component, red-green component, and blue-yellow component of the color feature vector of a cluster center in a real-time infrared image in the LAB color space.

[0033] The specific calculation formula for the process point index of hotspot location change is as follows: ; In the formula: This refers to the process point indicators of changes in hotspot locations; This indicates that the temperature center position has not shifted; otherwise, it indicates that temperature changes have occurred at other locations.

[0034] The specific formula for calculating the temperature change range index is as follows: ; In the formula: This is an indicator of the range of temperature changes. , These are the average pixel brightness values ​​of the pixel set of a certain region in the reference infrared image and the pixel set of the corresponding region in the real-time infrared image, respectively. , These are the pixel brightness variances of the pixel set of a certain region in the reference infrared image and the pixel set of the corresponding region in the real-time infrared image, respectively. The pixel brightness covariance is the pixel set of a certain region in the reference infrared image and the pixel set of the corresponding region in the real-time infrared image. , These are the standard deviations of pixel brightness for a certain region in the reference infrared image and the corresponding region in the real-time infrared image, respectively.

[0035] Based on multi-dimensional monitoring indicators, the rate of change of each indicator is calculated. When the rate of change of any indicator exceeds a preset threshold, a temperature warning is triggered.

[0036] Based on the infrared images of the converter valve acquired at different time scales, a series of temperature change indicators, hot spot indicators, and temperature change range indicators were obtained. These indicators are from different image regions and at different times. For any region, on a long time scale, we have: Rate of temperature change: Indicates a period of time The temperature change within t; the higher the value, the faster the temperature rises or falls. Position offset rate: Indicates a period of time The location of the hot spot changes within t; the higher the value, the faster the abnormal temperature spreads. Temperature diffusivity: ,in R represents the difference between the number of pixels in the clustered region at the beginning and the number of pixels in the clustered region at the end. The higher the value, the faster the temperature range changes.

[0037] Set thresholds for the above three indicators, and trigger a temperature alarm when the thresholds are exceeded.

[0038] Example 2: This embodiment provides an infrared monitoring and temperature early warning system for a converter valve, including: The image segmentation and modeling module acquires the reference infrared image of the converter valve under normal operating conditions, uses an improved clustering segmentation algorithm to segment the reference infrared image of the converter valve into multiple regions, and records the reference feature information of each region. The multi-dimensional indicator monitoring module continuously monitors the converter valve, acquires infrared images of the converter valve in real time, and uses the region segmented from the reference infrared image and the reference feature information as initial values ​​to calculate multi-dimensional monitoring indicators used to characterize the temperature state changes of the converter valve. The trend analysis and early warning module calculates the rate of change of each indicator based on multi-dimensional monitoring indicators. When the rate of change of any indicator exceeds a preset threshold, a temperature early warning is triggered.

[0039] Example 3: This embodiment provides an electronic device that stores a computer program. When the computer program is executed by a processor, it implements a converter valve infrared monitoring temperature early warning method as described in any embodiment of the present invention.

[0040] Example 4: This embodiment provides a computer-readable medium for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement a converter valve infrared monitoring temperature early warning method as described in any embodiment of the present invention.

[0041] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, A and B simultaneously, or B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0042] Those skilled in the art will recognize that the units and algorithm steps described in the embodiments disclosed herein can be implemented using electronic hardware, computer software, or a combination of electronic hardware and software. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0043] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0044] In the several embodiments provided in this application, any function, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0045] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for infrared monitoring and temperature early warning of a converter valve, characterized in that, Includes the following steps: A reference infrared image of the converter valve under normal operating conditions is acquired. An improved clustering segmentation algorithm is used to segment the reference infrared image of the converter valve into multiple regions, and the reference feature information of each region is recorded. Continuously monitor the converter valve, acquire infrared images of the converter valve in real time, and use the region segmented from the reference infrared image and the reference feature information as initial values ​​to calculate multi-dimensional monitoring indicators to characterize the temperature state changes of the converter valve. Based on multi-dimensional monitoring indicators, the rate of change of each indicator is calculated. When the rate of change of any indicator exceeds a preset threshold, a temperature warning is triggered.

2. The method for infrared monitoring and temperature early warning of a converter valve according to claim 1, characterized in that: The improved clustering and segmentation algorithm includes the following steps: The reference infrared image of the converter valve is converted from the RGB color space to the LAB color space and uniformly divided into N initial regions. In each initial region, a pixel is randomly selected as the initial cluster center. For each pixel within any initial region, calculate its four types of features relative to the cluster center of that region: position features based on pixel coordinates, color features based on LAB color vectors, gradient features based on color change gradients, and similarity features based on the similarity between the pixel color and the average color within the region. Based on four types of features, a comprehensive distance index between pixels and cluster centers is calculated. Based on the comparison results between the comprehensive distance index and the preset threshold, it is determined whether a pixel belongs to the cluster center. For pixels that have never been assigned a cluster center, a point is selected within the set as the cluster center. The process is iterated until all pixels are assigned a region, and the baseline infrared image is finally divided into N+K regions, with baseline feature information for each region obtained; K is the newly added region composed of unassigned pixels.

3. The method for infrared monitoring and temperature early warning of a converter valve according to claim 2, characterized in that: The formula for calculating the comprehensive distance index is as follows: ； In the formula: This is the combined distance index between the i-th pixel and the cluster center; The positional difference feature between the i-th pixel and the cluster center; The color difference feature between the i-th pixel and the cluster center; The gradient difference feature between the i-th pixel and the cluster center; Let be the similarity feature between the i-th pixel and the cluster center; , , , These are the normalization coefficients for position difference features, color difference features, gradient difference features, and similarity features, respectively.

4. The method for infrared monitoring and temperature early warning of a converter valve according to claim 1, characterized in that: The reference feature information includes a reference color feature vector, reference position coordinates, and a reference pixel set.

5. The method for infrared monitoring and temperature early warning of a converter valve according to claim 1, characterized in that: The multi-dimensional monitoring indicators include temperature change indicators that characterize changes in temperature values, process point indicators that characterize changes in the location of hot spots, and temperature change range indicators that characterize the similarity of temperature distribution.

6. The method for infrared monitoring and temperature early warning of a converter valve according to claim 5, characterized in that: The specific formula for calculating the temperature change index is as follows: ； In the formula: This is an indicator of temperature change. , , These represent the luminance component, red-green component, and blue-yellow component of the color feature vector of a certain cluster center in the reference infrared image in the LAB color space. , , These represent the luminance component, red-green component, and blue-yellow component of the color feature vector of a cluster center in a real-time infrared image in the LAB color space.

7. The method for infrared monitoring and temperature early warning of a converter valve according to claim 5, characterized in that: The specific formula for calculating the temperature change range index is as follows: ； In the formula: This is an indicator of the range of temperature changes. , These are the average pixel brightness values ​​of the pixel set of a certain region in the reference infrared image and the pixel set of the corresponding region in the real-time infrared image, respectively. , These are the pixel brightness variances of the pixel set of a certain region in the reference infrared image and the pixel set of the corresponding region in the real-time infrared image, respectively. The pixel brightness covariance is the pixel set of a certain region in the reference infrared image and the pixel set of the corresponding region in the real-time infrared image. , These are the standard deviations of pixel brightness for a certain region in the reference infrared image and the corresponding region in the real-time infrared image, respectively.

8. A converter valve infrared monitoring temperature early warning system, characterized in that, include: The image segmentation and modeling module acquires the reference infrared image of the converter valve under normal operating conditions, uses an improved clustering segmentation algorithm to segment the reference infrared image of the converter valve into multiple regions, and records the reference feature information of each region. The multi-dimensional indicator monitoring module continuously monitors the converter valve, acquires infrared images of the converter valve in real time, and uses the region segmented from the reference infrared image and the reference feature information as initial values ​​to calculate multi-dimensional monitoring indicators used to characterize the temperature state changes of the converter valve. The trend analysis and early warning module calculates the rate of change of each indicator based on multi-dimensional monitoring indicators. When the rate of change of any indicator exceeds a preset threshold, a temperature early warning is triggered.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements a converter valve infrared monitoring temperature early warning method as described in claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the infrared monitoring temperature early warning method for a converter valve as described in claims 1-7.

Images