Hydropower station transformer risk early warning method, system, equipment and medium

Abstract

The invention discloses a hydropower station transformer risk early warning method, system and device and a medium, and relates to the technical field of transformer operation monitoring, and the method comprises the following steps: obtaining an infrared image of a target transformer, so as to obtain a temperature abnormal value; obtaining vibration data of the target transformer to obtain a vibration abnormal value; obtaining an oil tank image in the target transformer to obtain an oil leakage abnormal value; obtaining an image of the insulating sleeve in the target transformer to obtain an abnormal value of the sleeve; inputting the temperature abnormal value, the vibration abnormal value, the oil leakage abnormal value and the sleeve abnormal value into a preset risk early warning model to obtain a risk early warning value; and judging whether the risk early warning value is greater than a preset risk threshold value, if so, sending early warning information, and if not, returning to obtain the infrared image of the target transformer to obtain a temperature abnormal value. The method has the advantages that various parameter indexes of the transformer can be comprehensively considered, the early-warning evaluation system is more perfect, and the operation state of the transformer can be accurately early-warned and monitored.

Description

Technical Field

[0001] This application relates to the technical field of transformer operation monitoring, and particularly to a risk early warning method, system, device and medium for hydropower station transformers. Background Art

[0002] The main transformer in a hydropower station, abbreviated as the main transformer, is the main step-down transformer mainly used for power transmission and transformation in a unit or substation, and is also the core part of the substation. When the main transformer is in operation, its operating status needs to be monitored in real time. When a fault is detected, maintenance needs to be carried out in time to avoid serious accidents. At present, various sensors are generally used to detect whether a corresponding fault occurs, and the fault can only be detected after it occurs. It is difficult to accurately carry out early warning monitoring based on the operating status of the main transformer, so it is difficult to achieve the purpose of preventing problems before they occur. Summary of the Invention

[0003] The main purpose of this application is to provide a risk early warning method, system, device and medium for hydropower station transformers, aiming to solve the technical problem that it is difficult to accurately carry out early warning monitoring by the existing transformer monitoring methods.

[0004] To achieve the above purpose, this application provides a risk early warning method for hydropower station transformers, including the following steps: Obtain an infrared image of the target transformer to obtain a temperature anomaly value; wherein, the temperature anomaly value is the degree value of temperature anomaly of the target transformer; Obtain the vibration data of the target transformer to obtain a vibration anomaly value; wherein, the vibration anomaly value is the degree value of abnormal vibration of the target transformer; Obtain an image of the oil tank in the target transformer to obtain an oil leakage anomaly value; wherein, the oil leakage anomaly value is the degree value of oil leakage of the oil tank; Obtain an image of the insulating bushing in the target transformer to obtain a bushing anomaly value; wherein, the bushing anomaly value is the degree value of deformation and offset and / or having cracks of the insulating bushing; Input the temperature anomaly value, vibration anomaly value, oil leakage anomaly value and bushing anomaly value into a preset risk early warning model to obtain a risk early warning value; Judge whether the risk early warning value is greater than a preset risk threshold. If so, send an early warning message. If not, return to obtain an infrared image of the target transformer to obtain a temperature anomaly value.

[0005] Optionally, obtaining an image of the insulating bushing in the target transformer to obtain a bushing anomaly value includes: Obtain a first image of the insulating bushing based on the top view of the target transformer; According to the first image, obtain the offset value H of the axis center point of the insulating bushing; Obtain multiple second images of the insulating bushing from multiple perspectives of the target transformer; wherein, the second images are depth images; According to the multiple second images, obtain the crack opening value L of the insulating bushing; wherein, L = a * b, a is the crack length of the insulating bushing, and b is the crack depth of the insulating bushing; According to the axis center point offset value H and the crack opening value L, obtain the bushing anomaly value Q1; wherein, Q1 = H * L.

[0006] Optionally, obtaining the axis center point offset value H of the insulating bushing according to the first image includes: According to the first image, identify and extract the axis center points of multiple insulating bushings; Connect the multiple axis center points end to end to obtain a closed polygon; Select a reference point in the middle area of the closed polygon; Obtain the measured distance between each axis center point and the reference point; Obtain the absolute value of the difference between each measured distance and the corresponding standard value; wherein, the standard value is the distance value between the corresponding axis center point when it has not shifted and the reference point; Output the sum of the multiple absolute values of the differences as the axis center point offset value H.

[0007] Optionally, obtaining the infrared image of the target transformer to obtain the temperature anomaly value includes: Obtain multiple infrared images from multiple perspectives of the target transformer; According to the infrared image, identify and extract the temperature anomaly area of the target transformer; Obtain the area S of the temperature anomaly area and the temperature excess value ΔT; wherein, ΔT = T1 - T2, T1 is the highest temperature value corresponding to the temperature anomaly area, and T2 is the standard temperature value; According to the area S and the temperature excess value ΔT, obtain the temperature anomaly value Q2; wherein, Q2 = S * ΔT.

[0008] Optionally, obtaining the vibration data of the target transformer to obtain the vibration anomaly value includes: Obtain the pressure change data at the target position of the target transformer within a preset unit time; wherein, the target position is the position where the target transformer is prone to vibration, and the pressure change data includes multiple measured pressure values; Classify and screen the pressure change data to obtain the first type of pressure data and the second type of pressure data; wherein, the first type of pressure data is the set of measured pressure values greater than or equal to the preset first warning pressure value, and the second type of pressure data is the set of measured pressure values less than the first warning pressure value and greater than or equal to the preset second warning pressure value; Obtain the first average pressure value P1 corresponding to the first type of pressure data and the second average pressure value P2 corresponding to the second type of pressure data; According to the first average pressure value P1 and the second average pressure value P2, obtain the vibration anomaly value Q3; where, Q3 = W 1 *P1 + W 2 *P2, W 1 and W 2 are both weight values, and W 1 > W 2 .

[0009] Optionally, obtain the oil tank image in the target transformer to obtain the oil leakage anomaly value, including: Obtain the oil tank image in the target transformer; According to the oil tank image, identify and extract the oil stain feature area; Divide the oil stain feature area into multiple sub - oil stain feature areas according to the gray - value interval; Obtain the measured areas of multiple sub - oil stain feature areas; Sort the multiple measured areas in ascending order according to the gray - value interval to which the corresponding sub - oil stain feature area belongs, and obtain the area data set {S1, S2, S3,..., Sn}, where n is the number of sub - oil stain feature areas, and n≥2; According to the area data set {S1, S2,..., Sn}, obtain the oil leakage anomaly value Q4; where, Q4 = W 3 *S1 + W 4 *S2 +... + W （n+2） *Sn, W 3 、W 4 ...W （n+2） are both weight values, and W 3 > W 4 >... > W （n+2） .

[0010] Optionally, the expression of the risk warning model is: F = K1*Q1 + K2*Q2 + K3*Q3 + K4*Q4; In the formula, F is the risk warning value, Q1 is the bushing anomaly value, Q2 is the temperature anomaly value, Q3 is the vibration anomaly value, Q4 is the oil leakage anomaly value, K1 is the first adjustment coefficient, K2 is the second adjustment coefficient, K3 is the third adjustment coefficient, and K4 is the fourth adjustment coefficient.

[0011] To achieve the above - mentioned purpose, the present application also provides a risk warning system for a hydropower station transformer, including: The first image acquisition module is used to obtain the infrared image of the target transformer to obtain the temperature anomaly value; where, the temperature anomaly value is the degree value of the temperature anomaly of the target transformer; A vibration data acquisition module, configured to acquire vibration data of a target transformer to obtain vibration anomaly values; wherein, the vibration anomaly value is a degree value of abnormal vibration of the target transformer. A second image acquisition module, configured to acquire an image of an oil tank in the target transformer to obtain an oil leakage anomaly value; wherein, the oil leakage anomaly value is a degree value of oil leakage in the oil tank. A third image acquisition module, configured to acquire an image of an insulating bushing in the target transformer to obtain a bushing anomaly value; wherein, the bushing anomaly value is a degree value of deformation and / or crack of the insulating bushing. An early warning module, configured to input the temperature anomaly value, the vibration anomaly value, the oil leakage anomaly value and the bushing anomaly value into a preset risk early warning model to obtain a risk early warning value. A data processing module, configured to determine whether the risk early warning value is greater than a preset risk threshold. If so, an early warning message is sent. If not, return to acquiring an infrared image of the target transformer to obtain a temperature anomaly value.

[0012] To achieve the above object, the present application further provides a computer device, which includes a memory and a processor. A computer program is stored in the memory, and the processor executes the computer program to implement the above method.

[0013] To achieve the above object, the present application further provides a computer-readable storage medium, on which a computer program is stored, and the processor executes the computer program to implement the above method.

[0014] The beneficial effects that the present application can achieve are as follows: The present application comprehensively considers typical abnormal manifestations that may cause transformer failures, including temperature, vibration, oil leakage, and insulating bushing abnormal information, and quantifies and calculates each abnormal information. That is, a temperature anomaly value is obtained based on the infrared image of the target transformer, a vibration anomaly value is obtained based on the vibration data of the target transformer, and an oil leakage anomaly value is obtained based on the image of the oil tank in the target transformer. Then, the calculated values are input into a risk early warning model to obtain a risk early warning value, and it is determined whether the risk early warning value is greater than the risk threshold. If so, an early warning message is sent. Therefore, the present application comprehensively considers the parameter indicators corresponding to the potential abnormal manifestations that cause failures and obtains a specific quantified risk early warning value. The early warning evaluation system is more perfect, so that the operation state of the transformer can be accurately monitored for early warning to achieve the purpose of preventing problems before they occur. Description of the Drawings

[0015] To more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts do not necessarily draw according to the actual scale.

[0016] Figure 1 It is a schematic flowchart of a risk warning method for a hydropower station transformer in an embodiment of the present application; Figure 2 It is a schematic structural diagram of a hydropower station transformer in an embodiment of the present application; Figure 3 It is a schematic structural diagram of the target transformer from a side view in an embodiment of the present application; Figure 4 It is a schematic structural diagram of the target transformer from a top view in an embodiment of the present application; Figure 5 It is a schematic diagram when constructing a closed polygon based on the first image in an embodiment of the present application; Figure 6 It is a schematic diagram when selecting a reference point based on the closed polygon in an embodiment of the present application; Figure 7 It is a schematic diagram when identifying crack features based on the second image in an embodiment of the present application.

[0017] Reference numerals: 110 - Target transformer, 120 - Insulating bushing, 130 - Axis center point, 140 - Closed polygon, 150 - Reference point.

[0018] The realization of the objectives of the present application, functional features and advantages will be further described in conjunction with the embodiments and with reference to the drawings. Specific embodiments

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0020] It should be noted that all the directional indications (such as up, down, left, right, front, back...) in the embodiments of the present application are only used to explain the relative position relationship and movement conditions between components in a specific posture. If the specific posture changes, the directional indications will also change accordingly.

[0021] In this application, unless otherwise clearly specified and defined, terms such as "connection" and "fixation" shall be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral one; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components or the interaction relationship between two components, unless otherwise clearly defined. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0022] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of this application, such descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, the meaning of "and / or" appearing throughout the text includes three parallel scenarios. Taking "A and / or B" as an example, it includes scenario A, or scenario B, or the scenario where both A and B are satisfied simultaneously. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the fact that those of ordinary skill in the art can implement them. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0023] Embodiment 1 Refer to Figures 1-7 , this embodiment provides a risk early warning method for a hydropower station transformer, including the following steps: Obtain the infrared image of the target transformer 110 to obtain the temperature anomaly value; wherein, the temperature anomaly value is the degree value of the temperature anomaly of the target transformer 110; Obtain the vibration data of the target transformer 110 to obtain the vibration anomaly value; wherein, the vibration anomaly value is the degree value of the abnormal vibration of the target transformer 110; Obtain the image of the oil tank in the target transformer 110 to obtain the oil leakage anomaly value; wherein, the oil leakage anomaly value is the degree value of the oil leakage of the oil tank; Obtain the image of the insulating bushing in the target transformer 110 to obtain the bushing anomaly value; wherein, the bushing anomaly value is the degree value of the deformation and / or crack of the insulating bushing 120; Input the temperature anomaly value, vibration anomaly value, oil leakage anomaly value, and bushing anomaly value into a preset risk early warning model to obtain a risk early warning value; Judge whether the risk early warning value is greater than a preset risk threshold. If so, send a warning message; if not, return to obtain the infrared image of the target transformer 110 to obtain the temperature anomaly value.

[0024] In this embodiment, typical abnormal manifestations that may cause faults in the transformer are comprehensively considered, including temperature, vibration, oil leakage, and abnormal information of the insulating bushing 120. Each abnormal information is quantitatively calculated. That is, a temperature anomaly value is obtained based on the infrared image of the target transformer 110, a vibration anomaly value is obtained based on the vibration data of the target transformer 110, and an oil leakage anomaly value is obtained based on the oil tank image in the target transformer 110. Then, the calculated values are input into the risk warning model to obtain a risk warning value, and it is judged whether the risk warning value is greater than the risk threshold. If so, a warning message is sent. Therefore, in this embodiment, the parameter indicators corresponding to the potential abnormal manifestations that cause faults are comprehensively considered to obtain a specific quantified risk warning value, and the warning evaluation system is more perfect, so that the operation status of the transformer can be accurately monitored for early warning to achieve the purpose of preventing problems before they occur.

[0025] As an alternative implementation, an insulating bushing image in the target transformer 110 is acquired to obtain a bushing anomaly value, including: Obtain a first image of the insulating bushing 120 based on the top view of the target transformer 110; According to the first image, obtain the axial center point offset value H of the insulating bushing 120; Obtain multiple second images of the insulating bushing 120 based on multiple side views of the target transformer 110; wherein, the second image is a depth image; According to the multiple second images, obtain the crack opening value L of the insulating bushing 120; wherein, L = a * b, a is the crack length of the insulating bushing 120, and b is the crack depth of the insulating bushing 120; According to the axial center point offset value H and the crack opening value L, obtain the bushing anomaly value Q1; wherein, Q1 = H * L.

[0026] In this embodiment, the insulating bushing 120 is used to protect the high-voltage and low-voltage outgoing terminals at the top of the target transformer 110, so it is divided into a high-voltage bushing and a low-voltage bushing. When the insulating bushing 120 is deformed and offset or has cracks, there is a risk of internal components getting damp and leaking electricity, which may ultimately lead to transformer failure. Therefore, considering the two possible abnormal conditions of the insulating bushing 120, a first image of the insulating bushing 120 is obtained based on the top view. The first image contains the position information of the top center point 130 of the insulating bushing 120 (i.e., the point formed by the axis line of the insulating bushing 120 at the top position), so that the corresponding center point offset value H can be calculated. The reason for using the top view instead of the side view to collect the first image here is that it is difficult to determine the offset direction of the insulating bushing 120, and it is difficult to accurately calculate the offset of the insulating bushing 120 from the side view. However, the position of the top center point 130 is determined, and it can be accurately captured and identified regardless of the offset. Then, multiple second images of the insulating bushing 120 are obtained based on multiple side views. Since the position of the crack on the insulating bushing 120 is uncertain, corresponding second images need to be obtained based on multiple sides for detection. At the same time, since the second image is a depth image, it contains the depth values of each pixel point on the outer wall of the corresponding insulating bushing 120 (i.e., the distance value between the pixel point and the plane where the depth camera is located), so that the crack feature information of the insulating bushing 120, including the crack length and crack depth, can be identified. The product of the two is used as the crack opening value L of the insulating bushing 120. Therefore, whether the value corresponding to the crack length or the crack depth is relatively large, it will cause the crack opening value L to be relatively large, so that the risk influence degree of both the crack length and the crack depth can be characterized at the same time. Similarly, finally, the product of the center point 130 offset value H and the crack opening value L is output as the bushing abnormality value Q1, which can simultaneously characterize the influence degree of the center point offset value H and the crack opening value L on the bushing abnormality value Q1, and the calculation is accurate and effective. When it is detected that there is no deformation offset or crack defect, the corresponding center point offset value H and crack opening value L are output as the default value 1.

[0027] It should be noted that when obtaining multiple second images of the insulating bushing 120 based on multiple side views of the target transformer 110, if multiple insulating bushings 120 are not blocked from the side view, depth images containing multiple insulating bushings 120 can be collected simultaneously. If there is a certain blockage, a depth camera is separately set at the corresponding position for the blocked insulating bushing 120 to collect the depth image of the corresponding blocked part, so as to ensure the full coverage of image data collection and provide reliable data for accurately calculating the bushing abnormality value Q1 later.

[0028] As an alternative embodiment, obtaining the center point offset value H of the insulating bushing 120 according to the first image includes: Identifying and extracting the center points 130 of multiple insulating bushings 120 according to the first image; Connect the head and tail of multiple pivot points 130 to obtain a closed polygon 140; Select a reference point 150 in the middle area of the closed polygon 140; Obtain the measured distance between each pivot point 130 and the reference point 150; Obtain the absolute value of the difference between each measured distance and the corresponding standard value; wherein, the standard value is the distance value between the corresponding pivot point 130 and the reference point 150 when the pivot point 130 has not shifted; Output the sum of multiple absolute values of differences as the pivot point offset value H.

[0029] In this embodiment, since the positions of multiple insulating sleeves 120 are different and not on the same straight line, when detecting whether the corresponding pivot points 130 deviate from the theoretical positions, a reference position point, that is, the reference point 150, should be selected. Here, first connect the head and tail of multiple pivot points 130 to form a closed polygon 140, and select a reference point 150 in the middle area of the closed polygon 140. In this way, the distance between the reference point 150 and the position of each theoretical pivot point 130 will not be too long, so as to reduce the data processing pressure and improve the calculation efficiency. After determining the position of the reference point 150, the theoretical distance (i.e., the standard value) between the reference point 150 and the position of each theoretical pivot point 130 can be obtained. The theoretical distances corresponding to each theoretical pivot point 130 may be different. Then calculate the measured distance between the reference point 150 and each actual pivot point 130, calculate the difference between the measured distance and the corresponding standard value, and form the absolute value of the difference, so as to form multiple absolute values of differences corresponding to each actual pivot point 130. The sum of multiple absolute values of differences is the pivot point offset value H, and the calculation is reliable and reasonable.

[0030] It should be noted that when selecting the reference point 150, it is possible to find whether there is a target feature point in the middle area of the closed polygon 140. The target feature point is the contour feature formed by the fixed parts (such as screws) on the top of the target transformer 110 in the first image. Since the position of the target feature point is fixed and does not shift, it can be used as a reference point to ensure the calculation accuracy.

[0031] As an alternative embodiment, obtain the infrared image of the target transformer 110 to obtain the temperature anomaly value, including: Obtain multiple infrared images based on the multi-side views of the target transformer 110; According to the infrared image, identify and extract the temperature anomaly area of the target transformer 110; Obtain the area S of the temperature anomaly area and the temperature excess difference ΔT; wherein, ΔT = T1 - T2, T1 is the highest temperature value corresponding to the temperature anomaly area, and T2 is the standard temperature value; According to the area S and the temperature excess difference ΔT, obtain the temperature anomaly value Q2; wherein, Q2 = S * ΔT.

[0032] In this embodiment, multiple infrared images can be obtained based on the multi-faceted perspectives (generally four sides) of the target transformer 110, so that the temperature information corresponding to each side of the target transformer 110 can be obtained. If the temperature is abnormally too high, the temperature abnormal area of the target transformer 110 can be identified and extracted according to the infrared image, and by obtaining the area S of the temperature abnormal area and the temperature overshoot value ΔT, the product of the two is output as the temperature abnormal value Q2. Therefore, not only the influence of the temperature overshoot value ΔT is considered here, but also the influence of the area S of the temperature abnormal area is considered, further improving the accuracy of risk assessment.

[0033] As an alternative embodiment, vibration data of the target transformer 110 is obtained to obtain a vibration abnormal value, including: Obtaining the pressure change data of the target position of the target transformer 110 within a preset unit time; wherein, the target position is the position where the target transformer 110 is prone to vibration, and the pressure change data includes multiple measured pressure values; Classifying and screening the pressure change data to obtain first-class pressure data and second-class pressure data; wherein, the first-class pressure data is a set of measured pressure values greater than or equal to a preset first warning pressure value, and the second-class pressure data is a set of measured pressure values less than the first warning pressure value and greater than or equal to a preset second warning pressure value; Obtaining a first average pressure value P1 corresponding to the first-class pressure data and a second average pressure value P2 corresponding to the second-class pressure data; According to the first average pressure value P1 and the second average pressure value P2, obtain the vibration abnormal value Q3; wherein, Q3 = W 1 *P1 + W 2 *P2, W 1 and W 2 are both weight values, and W 1 > W 2 .

[0034] In this embodiment, the vibration condition of the target transformer 110 is characterized indirectly by the pressure change data. When abnormal vibration occurs, the detected pressure data surges. Considering the degree of abnormal vibration, the collected pressure change data is classified and screened into two levels. The first level is the first type of pressure data greater than or equal to the first warning pressure value, and the second level is the second type of pressure data less than the first warning pressure value and greater than or equal to the second warning pressure value. The pressure data less than the second warning pressure value is regarded as normal data and is excluded. Therefore, the probability of the first type of pressure data causing a fault is greater than that of the second type of pressure data. After calculating the corresponding first average pressure value P1 and second average pressure value P2 respectively, different weight values are assigned to the first average pressure value P1 and the second average pressure value P2 here. Among them, the first average pressure value P1 corresponds to a greater probability of causing a fault, so the corresponding weight value W 1 should be greater. Therefore, in this embodiment, by classifying the pressure data and assigning weight values, the influence degree of abnormal vibrations of different degrees on faults can be characterized more accurately, further improving the warning reliability and accuracy.

[0035] It should be noted that a component of a spring and a pressure sensor can be set at the corresponding position on the side wall of the target transformer 110, so that the pressure data generated when the target transformer 110 vibrates can be collected.

[0036] As an alternative embodiment, an oil tank image in the target transformer 110 is obtained to obtain an oil leakage anomaly value, including: Obtain an oil tank image of the target transformer 110; According to the oil tank image, identify and extract the oil stain feature area; Divide the oil stain feature area into multiple sub-oil stain feature areas according to the gray value interval; Obtain the measured areas of the multiple sub-oil stain feature areas; Sort the multiple measured areas in ascending order according to the gray value interval to which the corresponding sub-oil stain feature area belongs, and obtain an area data set {S1, S2, S3,..., Sn}, where n is the number of sub-oil stain feature areas and n≥2; According to the area data set {S1, S2,..., Sn}, obtain the oil leakage anomaly value Q4; where Q4 = W 3 *S1 + W 4 *S2 +... + W （n+2） *Sn, W 3 、W 4 ...W （n+2） are all weight values, and W 3 >W 4 >...>W （n+2） .

[0037] In this embodiment, when an oil spill occurs, a fire risk may be triggered. Therefore, it is necessary to accurately evaluate the degree of the oil spill. Here, the characteristic area of the oil stain can be identified and extracted through the fuel tank image. Considering that the covering thickness of the oil stain on the fuel tank is different during an oil spill, the greater the thickness of the oil stain, the greater the amount of oil leaked, and the corresponding gray value is smaller, and the color is darker. The total range of the gray value is 0-255. Therefore, in this embodiment, the characteristic area of the oil stain is divided into multiple sub-characteristic areas of the oil stain according to the gray value range. The gray value range can be set according to the detection accuracy requirements. For example, 0-50 is an interval, 51-150 is an interval, and 151-250 is an interval. Then, the measured area of the sub-characteristic area of the oil stain is calculated respectively, and they are sorted in ascending order according to the gray value range to obtain the area data set {S1, S2, S3,..., Sn}. S1 is the measured area of the sub-characteristic area of the oil stain corresponding to the smallest gray value interval, and Sn is the measured area of the sub-characteristic area of the oil stain corresponding to the largest gray value interval. The sub-characteristic area of the oil stain corresponding to the smallest gray value interval has the darkest oil stain color and the largest oil stain thickness. Therefore, the maximum weight value W is given. 3 And so on, weight values from large to small are given to the area data set {S1, S2, S3,..., Sn}, so as to more reasonably characterize the influence degree of the oil spill degree corresponding to different sub-characteristic areas of the oil stain on the risk, and the calculation is more reasonable and reliable.

[0038] As an alternative embodiment, the expression of the risk warning model is: F = K1*Q1 + K2*Q2 + K3*Q3 + K4*Q4; In the formula, F is the risk warning value, Q1 is the casing anomaly value, Q2 is the temperature anomaly value, Q3 is the vibration anomaly value, Q4 is the oil spill anomaly value, K1 is the first adjustment coefficient, K2 is the second adjustment coefficient, K3 is the third adjustment coefficient, and K4 is the fourth adjustment coefficient.

[0039] In this embodiment, the risk warning value F can be accurately calculated based on the expression of the risk warning model. Since Q1, Q2, Q3, and Q4 are parameters of different attributes, here, K1, K2, K3, and K4 are respectively used for parameter adjustment, so that the above parameters of different attributes can be quantitatively superimposed. If there is no corresponding abnormal situation, the corresponding values of Q1, Q2, Q3, or Q4 are 0. When one of the parameters Q1, Q2, Q3, and Q4 is too large, it may cause the risk warning value F to exceed the risk threshold. It is also possible that all four parameters are relatively small, but due to the simultaneous presence of four abnormal situations, their total value may also exceed the risk threshold. Therefore, it can effectively reflect various abnormal situations and the probability of the abnormal degree causing a failure, and has reliable reference and guidance in practical applications.

[0040] Embodiment 2 Based on the same inventive concept as the foregoing embodiments, with reference to Figures 1-4 , this embodiment further provides a risk early warning system for a hydropower station transformer, including: A first image acquisition module, configured to acquire an infrared image of the target transformer 110 to obtain a temperature anomaly value; wherein, the temperature anomaly value is the degree value of temperature anomaly occurring in the target transformer 110; A vibration data acquisition module, configured to acquire vibration data of the target transformer 110 to obtain a vibration anomaly value; wherein, the vibration anomaly value is the degree value of abnormal vibration occurring in the target transformer 110; A second image acquisition module, configured to acquire an image of the fuel tank in the target transformer 110 to obtain an oil leakage anomaly value; wherein, the oil leakage anomaly value is the degree value of oil leakage occurring in the fuel tank; A third image acquisition module, configured to acquire an image of the insulating bushing in the target transformer 110 to obtain a bushing anomaly value; wherein, the bushing anomaly value is the degree value of deformation and offset and / or having cracks in the insulating bushing 120; An early warning module, configured to input the temperature anomaly value, vibration anomaly value, oil leakage anomaly value, and bushing anomaly value into a preset risk early warning model to obtain a risk early warning value; A data processing module, configured to determine whether the risk early warning value is greater than a preset risk threshold. If so, send an early warning message. If not, return to acquiring the infrared image of the target transformer 110 to obtain a temperature anomaly value. For the relevant explanations and examples of each module in the device of this embodiment, reference can be made to the methods of the foregoing embodiments, which will not be elaborated here.

[0041] Embodiment 3 Based on the same inventive concept as the foregoing embodiments, this embodiment provides a computer device, which includes a memory and a processor. A computer program is stored in the memory, and the processor executes the computer program to implement the above method.

[0042] Embodiment 4 Based on the same inventive concept as the foregoing embodiments, this embodiment provides a computer-readable storage medium, on which a computer program is stored, and the processor executes the computer program to implement the above method.

[0043] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied to other related technical fields, shall be included in the patent protection scope of the present application by the same token.

Claims

1. A risk warning method for a hydropower station transformer, characterized in that: The following steps are involved: Acquire an infrared image of the target transformer to obtain a temperature anomaly value; wherein the temperature anomaly value is a degree value of temperature anomaly occurring in the target transformer; Acquire vibration data of the target transformer to obtain a vibration abnormality value; wherein the vibration abnormality value is a value of the degree of abnormal vibration of the target transformer; Obtain an image of the oil tank in the target transformer to obtain an abnormal value of oil leakage; wherein the abnormal value of oil leakage is a value of the degree of oil leakage in the oil tank; Acquire an image of the insulating bushing in the target transformer to obtain an abnormal value of the bushing; wherein the abnormal value of the bushing is a value of the degree of deformation and / or cracks of the insulating bushing; Inputting temperature abnormal values, vibration abnormal values, oil leakage abnormal values ​​and casing abnormal values ​​into a preset risk warning model to obtain risk warning values; Determine whether the risk warning value is greater than the preset risk threshold. If so, send a warning message. If not, return to obtaining the infrared image of the target transformer to obtain the temperature abnormality value.

2. A hydropower station transformer risk early warning method as claimed in claim 1, characterized in that: Acquire images of bushings in target transformers to obtain bushing anomaly values, including: Acquire a first image of the insulating bushing based on a top surface perspective of the target transformer; According to the first image, obtaining an axis point offset value H of the insulating sleeve; Acquire multiple second images of the insulating bushing based on multiple side perspectives of the target transformer; wherein the second image is a depth image; According to the plurality of second images, a crack opening value L of the insulating sleeve is obtained; wherein L=a*b, a is the crack length of the insulating sleeve, and b is the crack depth of the insulating sleeve; According to the axis point offset value H and the crack opening value L, the casing abnormal value Q1 is obtained; wherein Q1=H*L.

3. A hydropower station transformer risk early warning method as claimed in claim 2, characterized in that: According to the first image, the axis point offset value H of the insulating sleeve is obtained, including: According to the first image, identifying and extracting the axis points of a plurality of insulating sleeves; Connect multiple pivot points end to end to obtain a closed polygon; Select a reference point in the middle area of ​​the closed polygon; Get the measured distance between each pivot point and the reference point; Obtain the absolute value of the difference between each measured spacing and the corresponding standard value; wherein the standard value is the spacing value between the corresponding axis point and the reference point when there is no offset; The sum of the absolute values ​​of the multiple differences is output as the pivot point offset value H.

4. A hydropower station transformer risk early warning method as claimed in claim 1, characterized in that: Acquire infrared images of the target transformer to obtain temperature anomaly values, including: Acquire multiple infrared images based on multiple side views of the target transformer; According to the infrared image, the temperature abnormality area of ​​the target transformer is identified and extracted; Obtain the area S of the temperature anomaly region and the temperature deviation value ΔT; wherein ΔT=T1-T2, T1 is the highest temperature value corresponding to the temperature anomaly region, and T2 is the standard temperature value; According to the area S and the temperature deviation value ΔT, the temperature anomaly value Q2 is obtained; wherein Q2=S*ΔT.

5. A hydropower station transformer risk early warning method as claimed in claim 1, characterized in that: Obtain vibration data of the target transformer to obtain vibration abnormality values, including: Obtaining pressure change data of a target position of a target transformer in a preset unit time; wherein the target position is a position where the target transformer is prone to vibration, and the pressure change data includes a plurality of measured pressure values; Classify and filter the pressure change data to obtain first-category pressure data and second-category pressure data; wherein the first-category pressure data is a set of measured pressure values ​​greater than or equal to a preset first warning pressure value, and the second-category pressure data is a set of measured pressure values ​​less than the first warning pressure value and greater than or equal to a preset second warning pressure value; Obtain a first average pressure value P1 corresponding to the first type of pressure data and a second average pressure value P2 corresponding to the second type of pressure data; According to the first average pressure value P1 and the second average pressure value P2, a vibration abnormality value Q3 is obtained; wherein Q3=W1*P1+W2*P2, W1 and W2 are both weight values, and W1>W2.

6. A hydropower station transformer risk early warning method as claimed in claim 1, characterized in that: Obtain images of the oil tank in the target transformer to obtain oil leakage anomalies, including: Acquire the oil tank image in the target transformer; According to the oil tank image, identify and extract the oil pollution feature area; Divide the oil pollution characteristic region into a plurality of sub-oil pollution characteristic regions according to the gray value interval; Obtaining the measured areas of multiple sub-oil pollution characteristic areas; Sort the multiple measured areas from small to large according to the gray value interval of the corresponding sub-oil pollution characteristic area, and obtain the area data set {S1, S2, S3, ..., Sn}, where n is the number of sub-oil pollution characteristic areas, and n ≥ 2; According to the area data set {S1, S2, ..., Sn}, the oil leakage abnormal value Q4 is obtained; where Q4=W3*S1+W4*S2+...+W （n+2） *Sn, W3, W4...W （n+2） All are weight values, and W3>W4>...>W （n+2） .

7. A hydropower station transformer risk early warning method according to any one of claims 1 to 6, characterized in that: The expression of the risk early warning model is: F=K1*Q1+K2*Q2+K3*Q3+K4*Q4; Wherein, F is the risk warning value, Q1 is the casing abnormal value, Q2 is the temperature abnormal value, Q3 is the vibration abnormal value, Q4 is the oil leakage abnormal value, K1 is the first adjustment coefficient, K2 is the second adjustment coefficient, K3 is the third adjustment coefficient, and K4 is the fourth adjustment coefficient.

8. A hydropower station transformer risk early warning system, characterized in that: include: The first image acquisition module is used to acquire an infrared image of a target transformer to obtain a temperature anomaly value; wherein the temperature anomaly value is a degree value of temperature anomaly occurring in the target transformer; A vibration data acquisition module is used to acquire vibration data of a target transformer to obtain a vibration abnormality value; wherein the vibration abnormality value is a value of the degree of abnormal vibration of the target transformer; The second image acquisition module is used to acquire an image of the oil tank in the target transformer to obtain an abnormal value of oil leakage; wherein the abnormal value of oil leakage is a value of the degree of oil leakage in the oil tank; The third image acquisition module is used to acquire an image of the insulating bushing in the target transformer to obtain an abnormal value of the bushing; wherein the abnormal value of the bushing is a value of the degree of deformation and / or cracks of the insulating bushing; An early warning module is used to input temperature abnormal values, vibration abnormal values, oil leakage abnormal values ​​and casing abnormal values ​​into a preset risk early warning model to obtain a risk early warning value; The data processing module is used to determine whether the risk warning value is greater than a preset risk threshold. If so, a warning message is sent; if not, the module returns to obtain an infrared image of the target transformer to obtain the temperature anomaly value.

9. A computer device, characterized in that: The computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a hydropower station transformer risk early warning method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the processor executes the computer program to implement a hydropower station transformer risk warning method according to any one of claims 1 to 7.

Images