A power cable on-line monitoring system

Abstract

The present application relates to the field of cable monitoring, especially to a kind of power cable on-line monitoring system, the present application is by being provided microservice module, data receiving module and data processing module, obtain the image data of power cable that microservice module is collected, and obtain image data set, the difference state of image data in image data set is parsed, and the data in image data set is parsed by different analysis unit, obtains abnormal determination result, for the image data set of first difference state, the abnormal determination result of first image data is as the abnormal determination result of remaining image data in image data set, for the image data set of second difference state, is divided into several image data subsets, the abnormal determination result of image data in image data subset is as the abnormal determination result of remaining image data in image data subset, under the premise of guaranteeing system reliability, reduce data operation load, improve power cable anomaly identification efficiency.

Description

Technical Field

[0001] This invention relates to the field of cable monitoring, and more particularly to an online monitoring system for power cables. Background Technology

[0002] With the continuous growth of China's economic strength, the process of urbanization is also accelerating. Urban power supply is the basic guarantee for urban development. Cable lines are valued for their high power supply reliability and small footprint. Furthermore, due to the complexity of the power supply network, the monitoring of abnormalities in cable lines is crucial in the power supply field. Among the existing technologies, there are related technologies that determine whether abnormalities have occurred by collecting infrared thermal images of power cables.

[0003] Chinese Patent Publication No. CN113433167A discloses a method and system for monitoring the status of power cable terminal equipment based on infrared thermography. The method includes segmenting the infrared thermography i to be processed into a foreground region and a background region of the target power cable terminal equipment; calculating the average temperature Ta of the background region; segmenting the foreground region into foreground sub-regions and calculating the average temperature TN within the foreground sub-regions; and determining whether a fault exists in the target power cable terminal equipment based on the temperature difference between the average temperature TN of any m-th row and n-th column of the foreground sub-region and the average temperature Ta of the background region. This invention utilizes infrared thermography, an effective means of detecting overheating defects in cable terminals. By analyzing various cable terminal defects using background temperature differences, it can effectively improve monitoring efficiency and provide accurate and timely judgment of the operating temperature status of the target power cable terminal equipment. It has the advantages of high detection accuracy, long-distance detection capability, and safety and reliability.

[0004] However, existing technologies do not consider the enormous amount of data in thermal imaging images of related power cables when multiple data acquisition terminals are connected, which puts a load on data processing. They also do not consider splitting the data and processing it centrally to reduce the data processing load and improve data processing efficiency. Summary of the Invention

[0005] To address the problem that existing technologies do not consider the massive data volume of related thermal imaging images when multiple data acquisition terminals are connected, which places a heavy load on data processing, and do not consider data diversion and centralized processing to reduce the data processing load and improve data processing efficiency, this invention provides an online monitoring system for power cables, comprising:

[0006] The microservice module includes an image acquisition unit for collecting power cable image data and an image transmission unit for transmitting the collected image data;

[0007] The data receiving module stores the data request interval of the microservice module, and is used to send data call requests to the microservice module based on the data request interval, and to obtain image data returned based on the data call request;

[0008] The data processing module includes interconnected data fusion units, a first parsing unit, a second parsing unit, and a third parsing unit;

[0009] The data fusion unit is connected to the data receiving module and is used to receive image data sent by the data receiving module in real time, and store the received image data into the same data set at preset intervals to obtain an image dataset, and determine the difference status of the image dataset based on the image parameters of each image data in the image dataset.

[0010] The first parsing unit is connected to the data receiving module and is used to call the image dataset of the first difference state and determine the first image data in the image dataset to obtain the anomaly determination result of the first image data, and use the anomaly determination result as the anomaly determination result of the remaining image data in the image dataset;

[0011] The second parsing unit is connected to the data receiving module and is used to call the image dataset of the second difference state. Based on the image parameters of each image data in the called image dataset, the image dataset is divided to obtain several image data subsets. For any image data subset, a single image data in the image data subset is parsed to obtain an anomaly determination result. The anomaly determination result is used as the anomaly determination result of the remaining image data in the image data subset.

[0012] The third parsing unit is connected to the data receiving module and is used to adjust the data request interval based on the anomaly determination results obtained by the first parsing unit and the second parsing unit.

[0013] Further, the data fusion unit determines image parameters in the image data, including the average area S of the object contour in the image data and the average chromaticity value Q of the pattern in the object contour, and calculates the image feature standard value K corresponding to the image data according to formula (1).

[0014] (1)

[0015] In formula (1), S0 represents the preset standard comparison value of the outline area, and Q0 represents the preset standard comparison value of the pattern color.

[0016] Furthermore, the data fusion unit compares the standard values ​​K of the image features corresponding to each image data in the image dataset, and determines the difference status of the image dataset based on the comparison results, wherein...

[0017] Based on the first image parameter comparison result, the data fusion unit determines that the image dataset is in a first difference state;

[0018] Based on the second image parameter comparison result, the data fusion unit determines that the image dataset is in a second difference state;

[0019] The first image parameter comparison result is that the difference ΔK between the standard values ​​of the image feature standard values ​​corresponding to any two image data in the image dataset is less than or equal to the first preset parameter difference comparison parameter ΔK1.

[0020] The second image parameter comparison condition is that there exists a difference ΔK between the standard values ​​of the image feature standard values ​​corresponding to two image data in the image dataset that is greater than the first preset parameter difference comparison parameter ΔK1, wherein ΔK is set to |K1-K2|, K1 represents the standard value of the image feature corresponding to the first image data, and K2 represents the standard value of the image feature corresponding to the second image data.

[0021] Further, the first parsing unit acquires the first image data in the image dataset, determines the temperature value represented by each image region in the first image data, and compares each temperature value with a preset temperature comparison parameter to obtain an anomaly determination result for the first image data based on the comparison result.

[0022] Under the condition of comparing the first temperature value, the first analysis unit determines that the first image data is abnormal;

[0023] Under the condition of comparing the second temperature value, the first analysis unit determines that the first image data is normal;

[0024] The first temperature value comparison condition is that the temperature value corresponding to any image region is greater than or equal to the preset temperature comparison parameter, and the second temperature value comparison condition is that the temperature value corresponding to each image region is less than the preset temperature comparison parameter.

[0025] Further, the second parsing unit determines the image parameters of each image data in the called image dataset, calculates the standard value K of the image feature corresponding to each image data according to formula (1), and compares the standard value K of the image feature corresponding to each image data in the image dataset to divide it into several image data subsets. Any image data subset must satisfy the following: the standard value difference ΔK of the standard value K of any two image data in the image data subset is less than the second preset parameter difference comparison parameter ΔK2, and ΔK2 < ΔK1.

[0026] Further, the second parsing unit acquires the first image data in the subset of image data, determines the temperature value represented by each image region in the first image data, and compares each temperature value with a preset temperature comparison parameter to obtain an anomaly determination result for the first image data based on the comparison result.

[0027] Under the condition of comparing the first temperature value, the second analysis unit determines that the first image data is abnormal;

[0028] Under the condition of comparing the second temperature value, the second analysis unit determines that the first image data is normal;

[0029] The first temperature value comparison condition is that the temperature value corresponding to any image region is greater than or equal to the preset temperature comparison parameter, and the second temperature value comparison condition is that the temperature value corresponding to each image region is less than the preset temperature comparison parameter.

[0030] Furthermore, the third parsing unit acquires the anomaly determination results acquired by the first parsing unit and the second parsing unit in real time, and determines the number of times N1 and N2 that the first parsing unit continuously acquires the first anomaly result. It then compares the number of times N1 and N2 with a preset quantity comparison parameter N01, and determines whether to adjust the data request interval based on the comparison result. Here, the first anomaly result is the first image data being normal.

[0031] Based on the first comparison, it is determined that the data request interval needs to be adjusted;

[0032] Under the second comparison condition, it is determined that there is no need to adjust the data request interval;

[0033] The first comparison condition is N1≥N01 or N2≥N01, and the second comparison condition is N1<N01 and N2<N01.

[0034] Furthermore, the third parsing unit determines the adjustment method when adjusting the data request interval, wherein,

[0035] The first adjustment method is to adjust the current data request interval P0 to the first data request adjustment interval P01 according to the preset first interval adjustment parameter p1, and set P01=P0+p1;

[0036] The second adjustment method is to adjust the current data request interval P0 to the second data request adjustment interval P02 according to the preset second interval adjustment parameter p2, and set P02=P0+p2;

[0037] The first adjustment method requires N1≥N01, the second adjustment method requires N2≥N01, and p2>p1.

[0038] Furthermore, the third parsing unit has a preset maximum data request interval. If the current data request interval is adjusted to exceed the maximum data request interval, the third parsing unit will not adjust the current data request interval.

[0039] Furthermore, the image data acquired by the image acquisition unit includes at least infrared thermal images.

[0040] Compared with existing technologies, this invention acquires image data of power cables collected by the microservice module, obtains an image dataset, analyzes the difference states of the image data in the image dataset, and uses different analysis units to analyze the data in the image dataset to obtain anomaly judgment results. For the image dataset with the first difference state, the anomaly judgment result of the first image data is used as the anomaly judgment result of the remaining image data in the image dataset. For the image dataset with the second difference state, it is divided into several image data subsets, and the anomaly judgment result of the image data in the image data subset is used as the anomaly judgment result of the remaining image data in the image data subset. Under the premise of ensuring system reliability, this invention reduces the data computing load and improves the efficiency of power cable anomaly identification.

[0041] In particular, the microservice module of the present invention is used to acquire infrared thermal images of power cables in urban power supply systems in real time. For example, in reality, the number of power cables in urban power supply systems is very large, and the entire power supply system generates a large amount of data, which makes the data processing load of the system large. Therefore, the present invention sets up a data fusion unit and stores the received image data into the same data set at preset intervals to generate an image dataset, so as to centrally distribute the processing, thereby reducing the data computing load and improving the efficiency of power cable anomaly identification.

[0042] In particular, the first parsing unit of the present invention determines the anomaly determination result of the first image data in the image dataset and uses the anomaly determination result as the anomaly determination result of the remaining image data in the image dataset. Since the first parsing unit is used to process the image dataset of the first difference state, the image parameters of each image data in the image dataset of the first difference state are relatively similar. In reality, the occurrence of anomalies is an accidental phenomenon. Therefore, there will be a large number of duplicate infrared thermal images. However, it would waste data processing resources to judge each infrared thermal image. Therefore, the present invention pre-distinguishes the image dataset into difference states. For the image dataset of the first difference state, only the first image data is parsed to obtain the anomaly determination result. The anomaly determination result is used as the anomaly determination result of the remaining image data in the image dataset. This can reduce the waste of data processing resources, reduce the data computing load while ensuring system reliability, and improve the efficiency of power cable anomaly identification.

[0043] In particular, the second parsing unit of the present invention divides the image dataset of the second difference state into several image data subsets. Since there are image data with large differences in the image dataset of the second difference state, it is necessary to divide it into several image data subsets for anomaly determination. Under the premise of ensuring system reliability, the data computing load is reduced and the efficiency of power cable anomaly identification is improved.

[0044] In particular, the third parsing unit of the present invention adjusts the data request interval based on the anomaly determination results obtained by the first parsing unit and the second parsing unit. In actual practice, since the reliability of power cables in some areas is relatively high, the image data acquired by the image acquisition unit is mostly repetitive data. Therefore, in this case, the data request interval can be increased to reduce the amount of image data acquired. Under the premise of ensuring system reliability, the data computing load is reduced and the efficiency of power cable anomaly identification is improved. Attached Figure Description

[0045] Figure 1 This is a schematic diagram of the structure of an online power cable monitoring system according to an embodiment of the invention;

[0046] Figure 2 This is a schematic diagram of the data processing module structure in an embodiment of the invention;

[0047] Figure 3 This is a schematic diagram of the microservice module structure in an embodiment of the invention. Detailed Implementation

[0048] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0049] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0050] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0051] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0052] Please see Figure 1 , Figure 2 as well as Figure 3 As shown, Figure 1 This is a schematic diagram of the structure of an online power cable monitoring system according to an embodiment of the invention. Figure 2 This is a schematic diagram of the data processing module structure according to an embodiment of the invention. Figure 3 This is a schematic diagram of a microservice module structure according to an embodiment of the invention. The online monitoring system for power cables of the present invention includes:

[0053] The microservice module includes an image acquisition unit for collecting power cable image data and an image transmission unit for transmitting the collected image data;

[0054] The data receiving module stores the data request interval of the microservice module, and is used to send data call requests to the microservice module based on the data request interval, and to obtain image data returned based on the data call request;

[0055] The data processing module includes interconnected data fusion units, a first parsing unit, a second parsing unit, and a third parsing unit;

[0056] The data fusion unit is connected to the data receiving module and is used to receive image data sent by the data receiving module in real time, and store the received image data into the same data set at preset intervals to obtain an image dataset, and determine the difference status of the image dataset based on the image parameters of each image data in the image dataset.

[0057] The first parsing unit is connected to the data receiving module and is used to call the image dataset of the first difference state and determine the first image data in the image dataset to obtain the anomaly determination result of the first image data, and use the anomaly determination result as the anomaly determination result of the remaining image data in the image dataset;

[0058] The second parsing unit is connected to the data receiving module and is used to call the image dataset of the second difference state. Based on the image parameters of each image data in the called image dataset, the image dataset is divided to obtain several image data subsets. For any image data subset, a single image data in the image data subset is parsed to obtain an anomaly determination result. The anomaly determination result is used as the anomaly determination result of the remaining image data in the image data subset.

[0059] The third parsing unit is connected to the data receiving module and is used to adjust the data request interval based on the anomaly determination results obtained by the first parsing unit and the second parsing unit.

[0060] Specifically, the present invention does not limit the specific form of the data receiving module and the data processing module. They can be independent computers with information exchange functions, or functional modules with corresponding functions in a single computer. Further details will not be provided here.

[0061] Specifically, the data fusion unit determines the image parameters in the image data, including the average area S of the object contour in the image data and the average chromaticity value Q of the pattern in the object contour, and calculates the image feature standard value K corresponding to the image data according to formula (1).

[0062] (1)

[0063] In formula (1), S0 represents the preset standard comparison value of the outline area, and Q0 represents the preset standard comparison value of the pattern color.

[0064] Specifically, the microservice module of this invention is used to acquire infrared thermal images of power cables in urban power supply systems in real time. For example, in reality, the number of power cables in urban power supply systems is very large, and the entire power supply system generates a large amount of data, resulting in a large data processing load on the system. Therefore, this invention sets up a data fusion unit and stores the received image data into the same data set at preset intervals to generate an image dataset, so as to centrally distribute the processing, thereby reducing the data computing load and improving the efficiency of power cable anomaly identification.

[0065] Specifically, the data fusion unit compares the standard values ​​K of the image features corresponding to each image data in the image dataset, and determines the difference status of the image dataset based on the comparison results.

[0066] Based on the first image parameter comparison result, the data fusion unit determines that the image dataset is in a first difference state;

[0067] Based on the second image parameter comparison result, the data fusion unit determines that the image dataset is in a second difference state;

[0068] The first image parameter comparison result is that the difference ΔK between the standard values ​​of the image feature standard values ​​corresponding to any two image data in the image dataset is less than or equal to the first preset parameter difference comparison parameter ΔK1.

[0069] The second image parameter comparison condition is that there exists a difference ΔK between the standard values ​​of the image feature standard values ​​corresponding to two image data in the image dataset that is greater than the first preset parameter difference comparison parameter ΔK1, wherein ΔK is set to |K1-K2|, K1 represents the standard value of the image feature corresponding to the first image data, and K2 represents the standard value of the image feature corresponding to the second image data.

[0070] Specifically, those skilled in the art can set △K1 according to specific circumstances, as long as it can reflect the difference between the two image data. In this embodiment, several abnormal image data of power cables exhibiting overheating phenomena can be selected to calculate the image feature standard value K corresponding to each abnormal image data, and the first average value Ke1 of the image feature standard value K corresponding to each abnormal image data can be solved accordingly. At the same time, several normal image data of power cables when they are in normal condition can be selected, and the image feature standard value K corresponding to each normal image data can be calculated, and the second average value Ke2 of the image feature standard value K corresponding to each normal image data can be solved accordingly. △K1 = Ke1 - Ke1, △K2 = 1.3△K1 is set.

[0071] Specifically, the first parsing unit acquires the first image data in the image dataset, determines the temperature value represented by each image region in the first image data, and compares each temperature value with a preset temperature comparison parameter to obtain an anomaly determination result for the first image data based on the comparison result.

[0072] Under the condition of comparing the first temperature value, the first analysis unit determines that the first image data is abnormal;

[0073] Under the condition of comparing the second temperature value, the first analysis unit determines that the first image data is normal;

[0074] The first temperature value comparison condition is that the temperature value corresponding to any image region is greater than or equal to the preset temperature comparison parameter, and the second temperature value comparison condition is that the temperature value corresponding to each image region is less than the preset temperature comparison parameter.

[0075] Specifically, the first parsing unit of the present invention determines the anomaly determination result of the first image data in the image dataset and uses the anomaly determination result as the anomaly determination result of the remaining image data in the image dataset. Since the first parsing unit is used to process the image dataset of the first difference state, the image parameters of each image data in the image dataset of the first difference state are relatively similar. In reality, the occurrence of anomalies is an accidental phenomenon. Therefore, there will be a large number of duplicate infrared thermal images. However, it would waste data processing resources to judge each infrared thermal image. Therefore, the present invention pre-distinguishes the image dataset into difference states. For the image dataset of the first difference state, only the first image data is parsed to obtain the anomaly determination result. The anomaly determination result is used as the anomaly determination result of the remaining image data in the image dataset. This can reduce the waste of data processing resources, reduce the data computing load while ensuring system reliability, and improve the efficiency of power cable anomaly identification.

[0076] Specifically, the second parsing unit determines the image parameters of each image data in the called image dataset, calculates the standard value K of the image feature corresponding to each image data according to formula (1), and compares the standard value K of the image feature corresponding to each image data in the image dataset to divide it into several image data subsets. Any image data subset must satisfy the following: the standard value difference ΔK of the standard value K of any two image data in the image data subset is less than the second preset parameter difference comparison parameter ΔK2, and ΔK2 < ΔK1.

[0077] Specifically, the second parsing unit acquires the first image data in the subset of image data, determines the temperature value represented by each image region in the first image data, and compares each temperature value with a preset temperature comparison parameter to obtain an anomaly determination result for the first image data based on the comparison result.

[0078] Under the condition of comparing the first temperature value, the second analysis unit determines that the first image data is abnormal;

[0079] Under the condition of comparing the second temperature value, the second analysis unit determines that the first image data is normal;

[0080] The first temperature value comparison condition is that the temperature value corresponding to any image region is greater than or equal to the preset temperature comparison parameter, and the second temperature value comparison condition is that the temperature value corresponding to each image region is less than the preset temperature comparison parameter.

[0081] Specifically, after obtaining the anomaly determination results for the image data in each image data subset, the second parsing unit performs anomaly determination on the remaining image data for which no anomaly determination results have been obtained.

[0082] Specifically, the second parsing unit of the present invention divides the image dataset of the second difference state into several image data subsets. Since there are image data with large differences in the image dataset of the second difference state, it is necessary to divide it into several image data subsets for anomaly determination. Under the premise of ensuring system reliability, the data computing load is reduced and the efficiency of power cable anomaly identification is improved.

[0083] Specifically, the third parsing unit acquires the anomaly determination results acquired by the first parsing unit and the second parsing unit in real time, determines the number of times the first parsing unit continuously acquires the first anomaly result N1 and the number of times the second parsing unit continuously acquires the first anomaly result N2, and compares the number of times N1 and N2 with a preset quantity comparison parameter N01. Based on the comparison result, it determines whether to adjust the data request interval, wherein the first anomaly result is that the first image data is normal.

[0084] Based on the first comparison, it is determined that the data request interval needs to be adjusted;

[0085] Under the second comparison condition, it is determined that there is no need to adjust the data request interval;

[0086] The first comparison condition is N1≥N01 or N2≥N01, and the second comparison condition is N1<N01 and N2<N01.

[0087] Specifically, the third parsing unit determines the adjustment method when adjusting the data request interval, wherein...

[0088] The first adjustment method is to adjust the current data request interval P0 to the first data request adjustment interval P01 according to the preset first interval adjustment parameter p1, and set P01=P0+p1;

[0089] The second adjustment method is to adjust the current data request interval P0 to the second data request adjustment interval P02 according to the preset second interval adjustment parameter p2, and set P02=P0+p2;

[0090] The first adjustment method requires N1≥N01, the second adjustment method requires N2≥N01, and p2>p1.

[0091] Specifically, when setting p1 and p2, 0.3P0 > p2 > p1 should be used to avoid excessive adjustment.

[0092] The third parsing unit of the present invention adjusts the data request interval based on the anomaly determination results obtained by the first and second parsing units. In practice, due to the high reliability of power cables in some areas, the image data acquired by the image acquisition unit is mostly repetitive data. Therefore, in this case, the data request interval can be increased to reduce the amount of image data acquired. Under the premise of ensuring system reliability, the data processing load is reduced and the efficiency of power cable anomaly identification is improved.

[0093] Specifically, the third parsing unit has a preset maximum data request interval. If the current data request interval is greater than the maximum data request interval after adjustment, the third parsing unit will not adjust the current data request interval.

[0094] Specifically, the image data acquired by the image acquisition unit includes at least infrared thermal images.

[0095] Specifically, the present invention does not limit the specific structure of the image acquisition unit. It can be an infrared camera, and the specific installation method can be adhesive, threaded connection or other connection method. It is set at a position where the power cable can be acquired. This is not limited. Of course, preferably, the image acquisition unit of this embodiment can be a camera module with image processing function, or it can be a combination device of camera and processor. These are all existing technologies and are not limited here.

[0096] Specifically, the method for recognizing the contour patterns and chromaticity of image data in the data fusion unit of the present invention can be to train an image processing model through model training and then import the trained image processing model into a computer to achieve the above functions. This is prior art and will not be described in detail here.

[0097] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A power cable on-line monitoring system, characterized by The application relates to a power cable image data processing method and device. The method comprises the following steps: a micro-service module comprises an image acquisition unit for acquiring power cable image data and an image sending unit for sending the acquired image data; a data receiving module stores a data request interval of the micro-service module, sends a data calling request to the micro-service module based on the data request interval, and acquires image data returned based on the data calling request; a data processing module comprises a data fusion unit, a first analysis unit, a second analysis unit and a third analysis unit which are connected with each other; the data fusion unit is connected with the data receiving module, acquires image data sent by the data receiving module in real time, stores the acquired image data into a same data set every preset time, obtains an image data set, and judges a difference state of the image data set based on image parameters of each image data in the image data set; the first analysis unit is connected with the data receiving module, calls an image data set of a first difference state, determines a first image data in the image data set, acquires an abnormality judgment result of the first image data, and takes the abnormality judgment result as an abnormality judgment result of remaining image data in the image data set; the second analysis unit is connected with the data receiving module, calls an image data set of a second difference state, divides the image data set based on image parameters of each image data in the called image data set, obtains a plurality of image data subsets, analyzes a single image data in the image data subset for any image data subset, acquires an abnormality judgment result, and takes the abnormality judgment result as an abnormality judgment result of remaining image data in the image data subset; 2. The power cable online monitoring system according to claim 1, characterized in that, the third analysis unit is connected with the data receiving module, adjusts the data request interval based on abnormality judgment results obtained by the first analysis unit and the second analysis unit. （1） The data fusion unit determines image parameters in the image data, the image parameters comprise an average area S of an object contour in the image data and an average chroma value Q of a pattern in the object contour, and calculates an image characteristic standard value K corresponding to the image data according to formula (1), 3. The power cable online monitoring system according to claim 2, characterized in that, in formula (1), S0 represents a preset contour area standard contrast value, and Q0 represents a preset pattern chroma standard contrast value. The data fusion unit compares the image characteristic standard values K corresponding to each image data in the image data set, and judges a difference state of the image data set according to a comparison result, wherein under a first image parameter comparison result, the data fusion unit judges that the image data set is in a first difference state; under a second image parameter comparison result, the data fusion unit judges that the image data set is in a second difference state; the first image parameter comparison result is that a standard value difference value Delta K of the image characteristic standard values corresponding to any two image data in the image data set is less than or equal to a first preset parameter difference contrast parameter Delta K1, The second image parameter comparison condition is that a standard value difference △K of the standard values of the image feature of any two image data in the image data set is greater than a first preset parameter difference comparison parameter △K1, wherein, △K=|K1-K2|, K1 represents the standard value of the image feature of the first image data, and K2 represents the standard value of the image feature of the second image data.

4. The power cable online monitoring system according to claim 3, characterized in that, The first analysis unit obtains the first image data in the image data set, determines the temperature value represented by each image region in the first image data, and compares the temperature value with the preset temperature comparison parameter one by one to obtain the abnormality determination result of the first image data according to the comparison result, wherein, In the first temperature value comparison condition, the first analysis unit determines that the first image data is abnormal; In the second temperature value comparison condition, the first analysis unit determines that the first image data is normal; The first temperature value comparison condition is that the temperature value of any image region is greater than or equal to the preset temperature comparison parameter, and the second temperature value comparison condition is that the temperature value of each image region is less than the preset temperature comparison parameter.

5. The power cable online monitoring system according to claim 4, characterized in that, The second analysis unit determines the image parameters of each image data in the image data set that has been called, calculates the standard value K of the image feature corresponding to each image data according to formula (1), and compares the standard value K of the image feature corresponding to each image data in the image data set to obtain a plurality of image data subsets, wherein any image data subset needs to satisfy that the standard value difference △K of the standard values K of the image feature corresponding to any two image data in the image data subset is less than a second preset parameter difference comparison parameter △K2, and △K2<△K1.

6. The power cable online monitoring system according to claim 5, characterized in that, The second analysis unit obtains the first image data in the image data subset, determines the temperature value represented by each image region in the first image data, and compares the temperature value with the preset temperature comparison parameter one by one to obtain the abnormality determination result of the first image data according to the comparison result, wherein, In the first temperature value comparison condition, the second analysis unit determines that the first image data is abnormal; In the second temperature value comparison condition, the second analysis unit determines that the first image data is normal; The first temperature value comparison condition is that the temperature value of any image region is greater than or equal to the preset temperature comparison parameter, and the second temperature value comparison condition is that the temperature value of each image region is less than the preset temperature comparison parameter.

7. The power cable online monitoring system of claim 1, wherein, The third analysis unit obtains the abnormality determination results obtained by the first analysis unit and the second analysis unit in real time, determines the number N1 of times that the first analysis unit continuously obtains a first abnormal result and the number N2 of times that the second analysis unit continuously obtains the first abnormal result, compares the number N1 and the number N2 with a preset quantity comparison parameter N01, and determines whether to adjust the data request interval according to the comparison result, wherein the first abnormal result is that the first image data is normal, In the first number comparison condition, it is determined that the data request interval needs to be adjusted. In the second number comparison condition, it is determined that the data request interval does not need to be adjusted; The first number comparison condition is N1≥N01 or N2≥N01, and the second number comparison condition is N1 8. The power cable online monitoring system according to claim 7, characterized in that, The third analysis unit determines an adjustment mode for adjusting the data request interval, wherein, The first adjustment mode is to adjust the current data request interval P0 to a first data request adjustment interval P01 according to a preset first interval adjustment parameter p1, and P01=P0+p1 is set; The second adjustment mode is to adjust the current data request interval P0 to a second data request adjustment interval P02 according to a preset second interval adjustment parameter p2, and P02=P0+p2 is set; Wherein, the first adjustment mode needs to satisfy N1≥N01, the second adjustment mode needs to satisfy N2≥N01, and p2>p1.

9. The power cable online monitoring system according to claim 8, characterized in that, The third analysis unit is preset with a maximum data request interval, and if the current data request interval is greater than the maximum data request interval after adjustment, the third analysis unit does not adjust the current data request interval.

10. The power cable online monitoring system of claim 1, wherein, The image data collected by the image acquisition unit at least includes an infrared thermal image.

Images