CN114049336B - GIS casing temperature anomaly detection method, device, equipment and readable storage medium - Google Patents

Abstract

The invention discloses a GIS sleeve temperature anomaly detection method, device and equipment and a readable storage medium, wherein the method comprises the following steps: acquiring an infrared image marked with a GIS sleeve area, and acquiring temperatures corresponding to all pixel points in the GIS sleeve area to form a temperature set; constructing a GIS sleeve region temperature space distribution model, removing invalid data, and smoothing single-point noise in an infrared image; constructing a GIS sleeve region temperature frequency distribution model, establishing a double base line, dividing an interference region and a normal region, and extracting main information; and marking the pixel points after noise removal, respectively marking the pixel points after noise removal as suspected abnormal points when the temperature corresponding to the pixel points exceeds a preset threshold value, and marking the pixel points not exceeding the preset threshold value as the highest temperature point and the lowest temperature point. The method, the device, the equipment and the readable storage medium realize automatic detection of the suspected abnormal point of the temperature of the GIS sleeve region, and improve the detection efficiency and the accuracy.

Description

GIS casing temperature anomaly detection method, device, equipment and readable storage medium

Technical Field

The present invention relates to the field of infrared image processing technology, and in particular to a method, device, equipment and readable storage medium for detecting abnormal temperature of a GIS casing.

Background technique

With the widespread application of infrared equipment in live detection of GIS casing areas, power supply companies have accumulated a large number of infrared images of GIS casing area operation and maintenance. For these infrared images of GIS casing areas, it is usually necessary to manually classify and screen these infrared images to detect infrared images of GIS casing areas with abnormal temperature points.

However, due to the large number of GIS casing areas, the corresponding infrared images are also large, and the similarity of many devices is also high, so the detection operation task is large. In addition, the efficiency of manual detection is relatively slow, and it is inevitable that errors and omissions will occur. If the GIS casing area with abnormalities is not detected in time, it is likely to cause power accidents. Therefore, the existing technology has the disadvantages of low efficiency and difficulty in ensuring accuracy.

Therefore, how to improve the detection efficiency and accuracy of suspected abnormal temperature points in the GIS casing area is a problem that technical personnel in this field need to solve.

Summary of the invention

The purpose of the present invention is to provide a GIS casing temperature anomaly detection method, device, equipment and readable storage medium to improve the detection efficiency and accuracy of suspected abnormal temperature points in the GIS casing area; another purpose of the present invention is to provide a GIS casing temperature anomaly detection device, equipment and readable storage medium including the above method, which can also improve the detection efficiency and accuracy of suspected abnormal temperature points in the GIS casing area.

To solve the above technical problems, the embodiments of the present invention provide the following technical solutions:

A method for detecting abnormal temperature of a GIS casing, comprising:

An infrared image with a GIS casing area marked is obtained, and the temperatures corresponding to all pixel points in the GIS casing area are obtained to form a temperature set.

Construct the spatial distribution model of temperature in the GIS casing area, remove invalid data, and smooth the single-point noise in the infrared image;

Construct the GIS casing regional temperature frequency distribution model, set up double baselines, divide the interference area and normal area, and extract the main information;

The pixel points after noise removal are marked separately, and the pixel points whose temperatures exceed the preset threshold are marked as suspected abnormal points, and those that do not exceed the preset threshold are marked as the highest temperature point and the lowest temperature point.

Preferably, it also includes:

The pixel points whose temperature does not exceed the preset threshold are marked with different colors as the highest temperature point and the lowest temperature point, and the remaining unmarked pixels are regarded as normal pixels.

Preferably, a spatial distribution model of the temperature in the GIS casing area is constructed to remove invalid data and smooth the single-point noise in the infrared image, including:

By traversing the temperature set, continuous areas of temperature anomaly or continuous areas where suspected temperature anomaly points reach a specified threshold are determined, rather than points of temperature anomaly. Single points of temperature anomaly are treated as noise and processed; wherein the GIS casing area radius or the specified threshold can be manually specified or determined by learning an algorithm.

Preferably, a GIS casing regional temperature frequency distribution model is constructed, a double baseline is designed, interference areas and normal areas are divided, and main information is extracted, including:

A low temperature baseline L1 and a high temperature baseline L2 are set. The low temperature baseline L1 and the high temperature baseline L2 are parallel to the X-axis and independent of each other. The height is adjustable and can be adjusted to a percentage or an absolute value relative to the highest frequency. Starting from the leftmost low temperature of the temperature-frequency distribution, if a certain temperature frequency is lower than L1, all pixel points corresponding to the temperature are excluded until a certain temperature frequency is higher than L1, and all pixel points of the temperature are retained; continue to judge if a certain temperature frequency is higher than L2, then all pixel points corresponding to the temperature are retained, and if it is lower than L2, then all pixel points corresponding to the temperature are excluded until all temperature judgments are completed; the highest temperature and the lowest temperature among all the retained pixel points are the effective highest temperature and the effective lowest temperature, and the temperature difference between the highest temperature and the lowest temperature is the effective temperature difference; all the excluded pixel points are eliminated.

Preferably, after marking the pixel point corresponding to the temperature exceeding a preset threshold after the noise is removed as a suspected abnormal point, the method further includes:

Suspected abnormal points, as well as the highest temperature point and the lowest temperature point are marked in the infrared image to obtain an infrared marked image.

Preferably, after obtaining the infrared annotated image, the method further includes:

The infrared annotated image and the identification information of the GIS casing area in the infrared annotated image are correspondingly stored in a preset target file.

Preferably, after storing the infrared annotated image and the identification information of the GIS casing area in the infrared annotated image in a preset target file, the method further includes:

The target file is displayed through a preset visualization tool.

In order to solve the above technical problems, the present invention also provides a GIS casing temperature anomaly detection device, comprising:

An acquisition module is used to acquire an infrared image marked with a GIS casing area, and obtain the temperatures corresponding to all pixel points in the GIS casing area to form a temperature set;

The calculation module is used to construct the spatial distribution model of the temperature in the GIS casing area, eliminate invalid data, and smooth the single-point noise in the infrared image;

The division module is used to construct the GIS casing area temperature frequency distribution model, set up a double baseline, divide the interference area and the normal area, and extract the main information;

The marking module is used to mark the pixel points after noise removal, and mark the pixel points whose temperatures exceed the preset threshold as suspected abnormal points, and mark the pixel points whose temperatures do not exceed the preset threshold as the highest temperature point and the lowest temperature point.

In order to solve the above technical problems, the present invention also provides a GIS casing temperature anomaly detection device, comprising:

Memory for storing computer programs;

A processor is used to implement the steps of the GIS casing temperature anomaly detection method as described in any one of the above when executing the computer program.

In order to solve the above technical problems, the present invention also provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the GIS casing temperature anomaly detection method as described in any one of the above are implemented.

Through the above scheme, it can be known that a GIS casing temperature anomaly detection method provided by an embodiment of the present invention includes: obtaining an infrared image marked with a GIS casing area, obtaining the temperatures corresponding to all pixel points in the GIS casing area, and forming a temperature set; constructing a GIS casing area temperature spatial distribution model, removing invalid data, and smoothing the single-point noise in the infrared image; constructing a GIS casing area temperature frequency distribution model, setting up a double baseline, dividing the interference area and the normal area, and extracting the main information; marking the pixel points after noise removal, and marking the pixel points whose temperatures after noise removal exceed a preset threshold as suspected abnormal points, and marking the pixel points that do not exceed the preset threshold as the highest temperature point and the lowest temperature point.

It can be seen that the method can automatically calculate the pixel points with abnormal temperature in the GIS casing area based on the infrared image of the GIS casing area marked with the GIS casing area, thereby realizing the automatic detection of suspected abnormal points of temperature in the GIS casing area, replacing the manual detection process, thereby improving the detection efficiency and accuracy. Among them, due to the improved detection efficiency, the GIS casing area with abnormalities can be detected in time, which can avoid the occurrence of power accidents to a certain extent.

Correspondingly, a GIS casing temperature anomaly detection device, equipment and readable storage medium provided in an embodiment of the present invention also have the above-mentioned technical effects.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

FIG1 is a flow chart of a method for detecting abnormal temperature of a GIS casing disclosed in an embodiment of the present invention;

FIG2 is a schematic diagram of a GIS casing temperature anomaly detection device disclosed in an embodiment of the present invention;

FIG. 3 is a schematic diagram of a GIS casing temperature anomaly detection device disclosed in an embodiment of the present invention.

Detailed ways

The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

The embodiments of the present invention disclose a GIS casing temperature anomaly detection method, device, equipment and readable storage medium to improve the detection efficiency and accuracy of suspected abnormal points of temperature in the GIS casing area.

Referring to FIG1 , a method for detecting abnormal temperature of a GIS casing provided by an embodiment of the present invention includes:

S101, obtaining an infrared image with a GIS casing area marked, obtaining the temperatures corresponding to all pixel points in the GIS casing area, and forming a temperature set;

It should be noted that the infrared image of the GIS casing area can be obtained by: obtaining it from the database through a software interface, obtaining it from a storage medium through a hardware interface, or receiving the infrared image of the GIS casing area sent by the image sender through a network line.

It should be noted that each pixel in the GIS casing area corresponds to a temperature. The higher the temperature, the higher the probability of anomalies in the GIS casing area.

S102, constructing a spatial distribution model of the temperature in the GIS casing area, removing invalid data, and smoothing single-point noise in the infrared image;

By traversing the temperature set, continuous areas of temperature anomalies or continuous areas where suspected temperature anomalies reach a specified threshold are determined, rather than points of temperature anomalies. Single points of temperature anomalies are classified as noise. The area radius or threshold can be specified manually or determined through learning algorithms.

S103, constructing a GIS casing regional temperature frequency distribution model, setting up a double baseline, dividing the interference area and the normal area, and extracting the main information;

Based on the effective temperature set, a temperature frequency distribution model is established, and a low temperature baseline L1 and a high temperature baseline L2 are set. The baselines are parallel to the X-axis and are independently height-adjustable. They can be adjusted to a percentage or an absolute value relative to the highest frequency. Starting from the leftmost low temperature of the temperature-frequency distribution, if a temperature frequency is lower than L1, all pixels of that temperature are excluded; until a temperature frequency is higher than L1, all pixels of that temperature are retained; continue to judge if a temperature frequency is higher than L2, all pixels of that temperature are retained, and if it is lower than L2, all pixels of that temperature are excluded; until all temperatures are judged, the highest and lowest temperatures among all retained pixels are the effective highest and lowest temperatures, and the temperature difference is the effective temperature difference.

S104, marking the pixel points after noise removal, marking the pixel points whose temperatures exceed a preset threshold as suspected abnormal points, and marking the pixel points whose temperatures do not exceed the preset threshold as the highest temperature point and the lowest temperature point.

It should be noted that the pixels exceeding the preset threshold will be marked in purple as suspected abnormal points, and the pixels that do not exceed the preset threshold will be marked with the highest temperature point in red and the lowest temperature point in blue.

It can be seen that this embodiment provides a GIS casing temperature anomaly detection method, which can automatically calculate the pixel points with abnormal temperature in the GIS casing area based on the infrared image of the GIS casing area marked with the GIS casing area, thereby realizing the automatic detection of suspected abnormal points of temperature in the GIS casing area, replacing the manual detection process, thereby improving the detection efficiency and accuracy. Among them, due to the improved detection efficiency, the GIS casing area with abnormalities can be detected in time, which can avoid the occurrence of power accidents to a certain extent.

Based on any of the above embodiments, it should be noted that after marking the pixel points whose temperature exceeds the preset threshold as suspected abnormal points, the method further includes: marking the highest temperature point and the lowest temperature point in the infrared image to obtain an infrared marked image.

Preferably, after obtaining the infrared annotated image, the method further includes: storing the infrared annotated image and the identification information of the GIS casing area in the infrared annotated image in a preset target file in correspondence.

Preferably, after the infrared annotated image and the identification information of the GIS casing area in the infrared annotated image are stored in a preset target file in correspondence, the method further includes: displaying the target file through a preset visualization tool.

According to the identification information of the GIS casing area, it is possible to know which GIS casing area it is. Therefore, the infrared annotated image and the identification information of the GIS casing area in the infrared annotated image are stored in a preset target file, which can facilitate the operation and maintenance technicians to find out which GIS casing area has what temperature suspected abnormal point by searching the target file. Corresponding storage means storing in a one-to-one correspondence, such as storing in a table with a specified format, and recording this information in a unified format for subsequent management and analysis.

Based on any of the above embodiments, it should be noted that the infrared image of the GIS casing area marked with the GIS casing area can be obtained through a deep learning model. That is, the infrared image of the GIS casing area collected by the infrared terminal is input into the deep learning model, and the position information of the GIS casing area in the infrared image (i.e., the GIS casing area) is output, and then the position information is marked in the original infrared image to obtain the GIS casing area marked with the GIS casing area. Among them, the deep learning model can be obtained through SSD algorithm training. The training process of the deep learning model can refer to the existing technology (convolutional neural network model, etc.), and the training framework can use TensorFlow.

A GIS casing temperature anomaly detection device provided in an embodiment of the present invention is introduced below. The GIS casing temperature anomaly detection device described below and the GIS casing temperature anomaly detection method described above can be referenced to each other.

Referring to FIG. 2 , a GIS casing temperature anomaly detection device provided by an embodiment of the present invention includes:

The acquisition module 301 is used to acquire an infrared image with a GIS casing area marked thereon, and acquire the temperatures corresponding to all pixels in the GIS casing area to form a temperature set;

The calculation module 302 is used to construct a spatial distribution model of the temperature in the GIS casing area, remove invalid data, and smooth the single-point noise in the infrared image;

The division module 303 is used to construct a GIS casing area temperature frequency distribution model, set up a double baseline, divide the interference area and the normal area, and extract the main information;

The marking module 304 is used to mark the pixel points after noise removal, and mark the pixel points whose temperatures exceed a preset threshold as suspected abnormal points, and mark the pixel points whose temperatures do not exceed the preset threshold as the highest temperature point and the lowest temperature point.

Preferably, the calculation module includes:

A determination unit, used for determining the temperature in the temperature set that is higher than the average value as the effective temperature, so as to obtain the effective temperature set;

The calculation unit determines the continuous area of temperature anomaly or the continuous area of suspected temperature anomaly points reaching the specified threshold by traversing the temperature set, rather than the point of temperature anomaly. The single point of temperature anomaly is classified as noise for processing; the area radius or threshold can be manually specified or determined by learning algorithm.

Preferably, the dividing unit is specifically used for:

Based on the effective temperature set, a temperature frequency distribution model is established, and a low temperature baseline L1 and a high temperature baseline L2 are set. The baselines are parallel to the X-axis and are independently height-adjustable. They can be adjusted to a percentage or an absolute value relative to the highest frequency. Starting from the leftmost low temperature of the temperature-frequency distribution, if a temperature frequency is lower than L1, all pixels of that temperature are excluded; until a temperature frequency is higher than L1, all pixels of that temperature are retained; continue to judge if a temperature frequency is higher than L2, all pixels of that temperature are retained, and if it is lower than L2, all pixels of that temperature are excluded; until all temperatures are judged, the highest and lowest temperatures among all retained pixels are the effective highest and lowest temperatures, and the temperature difference is the effective temperature difference.

Preferably, it also includes:

The annotation module is used to annotate suspected abnormal temperature points in the infrared image to obtain an infrared annotated image.

Preferably, it also includes:

The storage module is used to store the infrared annotated image and the identification information of the GIS casing area in the infrared annotated image in a preset target file accordingly.

Preferably, it also includes:

The display module is used to display the target file through the preset visualization tool.

It can be seen that this embodiment provides a GIS casing temperature anomaly detection device, including: an acquisition module, a calculation module, a division module and a marking module. First, the acquisition module acquires the infrared image of the GIS casing area marked with the GIS casing area, and obtains the temperature corresponding to all the pixel points in the GIS casing area to form a temperature set; then the calculation module traverses the temperature set, constructs the GIS casing area temperature spatial distribution model, removes invalid data, and smoothes the single point noise in the infrared image; then the division module constructs the GIS casing area temperature frequency distribution model, designs a double baseline, divides the interference area and the normal area, and extracts the main information; finally, the marking module marks the pixel points after the noise is removed, and those exceeding the preset threshold are marked as suspected abnormal points, and those not exceeding the preset threshold are marked as the highest temperature point and the lowest temperature point. In this way, the various modules cooperate with each other and perform their respective duties, thereby realizing the automatic detection of suspected abnormal points in the GIS casing area temperature, and improving the detection efficiency and accuracy.

A GIS casing temperature anomaly detection device provided in an embodiment of the present invention is introduced below. The GIS casing temperature anomaly detection device described below and the GIS casing temperature anomaly detection method and device described above can be referenced to each other.

Referring to FIG3 , a GIS casing temperature anomaly detection device provided in an embodiment of the present invention includes:

Memory 401, used for storing computer programs;

The processor 402 is used to implement the steps of the GIS casing temperature anomaly detection method described in any of the above embodiments when executing the computer program.

A readable storage medium provided in an embodiment of the present invention is introduced below. The readable storage medium described below and the GIS casing temperature anomaly detection method, device and equipment described above can be referenced to each other.

A readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the GIS casing temperature anomaly detection method as described in any of the above embodiments are implemented.

The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims (8)

1. A method for detecting abnormal temperature of a GIS casing, comprising: Obtain an infrared image with a GIS casing area marked, obtain the temperatures corresponding to all pixel points in the GIS casing area, and form a temperature set; Construct the spatial distribution model of temperature in the GIS casing area, remove invalid data, and smooth the single-point noise in the infrared image; Construct the GIS casing regional temperature frequency distribution model, set up double baselines, divide the interference area and normal area, and extract the main information; The pixel points after noise removal are marked respectively, and the pixel points corresponding to the temperature exceeding the preset threshold after noise removal are marked as suspected abnormal points, the point with the highest temperature that does not exceed the preset threshold is marked as the highest temperature point, and the point with the lowest temperature is marked as the lowest temperature point; Construct the spatial distribution model of GIS casing area temperature, remove invalid data, and smooth the single point noise in the infrared image, including: By traversing the temperature set, continuous areas of temperature anomaly or continuous areas where suspected temperature anomaly points reach a specified threshold are determined, rather than points of temperature anomaly, and single points of temperature anomaly are treated as noise and processed; wherein the radius of the GIS casing area or the specified threshold is manually specified or determined by learning through a learning algorithm; Construct the GIS casing regional temperature frequency distribution model, design double baselines, divide the interference area and normal area, and extract the main information, including: A low temperature baseline L1 and a high temperature baseline L2 are set. The low temperature baseline L1 and the high temperature baseline L2 are parallel to the X-axis and independent of each other. The height is adjustable and can be adjusted to a percentage or an absolute value relative to the highest frequency. Starting from the leftmost low temperature of the temperature-frequency distribution, if a certain temperature frequency is lower than L1, all pixel points corresponding to the temperature are excluded until a certain temperature frequency is higher than L1, and all pixel points of the temperature are retained; continue to judge if a certain temperature frequency is higher than L2, then all pixel points corresponding to the temperature are retained, and if it is lower than L2, then all pixel points corresponding to the temperature are excluded until all temperature judgments are completed; the highest temperature and the lowest temperature among all the retained pixel points are the effective highest temperature and the effective lowest temperature, and the temperature difference between the highest temperature and the lowest temperature is the effective temperature difference; all the excluded pixel points are eliminated. 2. The method according to claim 1, further comprising: The highest temperature point and the lowest temperature point whose temperature does not exceed the preset threshold are marked with different colors as the highest temperature point and the lowest temperature point, respectively, and the remaining unmarked pixels are regarded as normal pixels. 3. The method according to any one of claims 1 or 2, characterized in that after marking the pixel point corresponding to the temperature exceeding a preset threshold after the noise is removed as a suspected abnormal point, it also includes: Suspected abnormal points, as well as the highest temperature point and the lowest temperature point are marked in the infrared image to obtain an infrared marked image. 4. The method according to claim 3, characterized in that after obtaining the infrared annotated image, it also includes: The infrared annotated image and the identification information of the GIS casing area in the infrared annotated image are correspondingly stored in a preset target file. 5. The method according to claim 4 is characterized in that after storing the infrared annotated image and the identification information of the GIS casing area in the infrared annotated image in a preset target file, it also includes: The target file is displayed through a preset visualization tool. 6. A GIS casing temperature anomaly detection device, characterized by comprising: An acquisition module is used to acquire an infrared image marked with a GIS casing area, and obtain the temperatures corresponding to all pixel points in the GIS casing area to form a temperature set; The calculation module is used to construct the spatial distribution model of the temperature in the GIS casing area, remove invalid data, and smooth the single-point noise in the infrared image; The division module is used to construct the GIS casing area temperature frequency distribution model, set up a double baseline, divide the interference area and the normal area, and extract the main information; A marking module is used to mark the pixel points after noise removal, and mark the pixel points whose temperatures exceed a preset threshold as suspected abnormal points, mark the points with the highest temperatures that do not exceed the preset threshold as the highest temperature points, and mark the points with the lowest temperatures as the lowest temperature points; Construct the spatial distribution model of GIS casing area temperature, remove invalid data, and smooth the single point noise in the infrared image, including: By traversing the temperature set, continuous areas of temperature anomaly or continuous areas where suspected temperature anomaly points reach a specified threshold are determined, rather than points of temperature anomaly, and single points of temperature anomaly are treated as noise and processed; wherein the radius of the GIS casing area or the specified threshold is manually specified or determined by learning through a learning algorithm; Construct the GIS casing regional temperature frequency distribution model, design double baselines, divide the interference area and normal area, and extract the main information, including: A low temperature baseline L1 and a high temperature baseline L2 are set. The low temperature baseline L1 and the high temperature baseline L2 are parallel to the X-axis and independent of each other. The height is adjustable and can be adjusted to a percentage or an absolute value relative to the highest frequency. Starting from the leftmost low temperature of the temperature-frequency distribution, if a certain temperature frequency is lower than L1, all pixel points corresponding to the temperature are excluded until a certain temperature frequency is higher than L1, and all pixel points of the temperature are retained; continue to judge if a certain temperature frequency is higher than L2, then all pixel points corresponding to the temperature are retained, and if it is lower than L2, then all pixel points corresponding to the temperature are excluded until all temperature judgments are completed; the highest temperature and the lowest temperature among all the retained pixel points are the effective highest temperature and the effective lowest temperature, and the temperature difference between the highest temperature and the lowest temperature is the effective temperature difference; all the excluded pixel points are eliminated. 7. A GIS casing temperature anomaly detection device, characterized by comprising: Memory for storing computer programs; A processor is used to implement the steps of the GIS casing temperature anomaly detection method as described in any one of claims 1 to 5 when executing the computer program. 8. A readable storage medium, characterized in that a computer program is stored on the readable storage medium, and when the computer program is executed by a processor, the steps of the GIS casing temperature anomaly detection method as described in any one of claims 1 to 5 are implemented.