GIS equipment expansion joint hidden danger intelligent detection method based on deep learning

Abstract

The invention discloses a GIS equipment expansion joint hidden danger intelligent detection method based on deep learning, and relates to the technical field of intelligent power grid equipment monitoring and maintenance, and the method comprises the steps: processing a constructed information source data set; extracting a data relationship of the information features; automatically evaluating the health condition of the GIS equipment according to a preset rule; and improving the feedback optimization flow process, and completing the intelligent detection of the hidden danger of the expansion joint of the GIS equipment. According to the method, efficient and accurate detection of the hidden danger of the expansion joint of the GIS equipment is realized, the fault risk of a power system is greatly reduced, the safety and stability of a power grid are improved, the maintenance cost and time consumption are reduced, and the method has important application value and wide market prospect.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grid equipment monitoring and maintenance, and in particular to a method for intelligent detection of hidden dangers in expansion joints of GIS equipment based on deep learning. Background Art

[0002] With the acceleration of urbanization and the continued growth of electricity demand, the scale of the power grid continues to expand, placing higher demands on the safety and reliability of power grid equipment. As a key component in modern power systems, GIS gas-insulated switchgear plays a vital role in high-voltage transmission and substations.

[0003] Currently, traditional methods for detecting hidden dangers in GIS equipment expansion joints rely primarily on regular manual inspections and simple physical testing. These methods are not only time-consuming and labor-intensive, but also subject to human influence, making it difficult to ensure the consistency and accuracy of detection results. Furthermore, traditional methods often struggle to detect some hidden dangers or those in their early stages, leading to delays in timely resolution and potentially serious safety incidents. Although some sensor-based data monitoring methods have emerged in recent years, these methods have poor adaptability in complex environments and lack effective data analysis capabilities, making them unable to achieve intelligent identification and early warning of hidden dangers. Therefore, existing detection technologies have significant deficiencies in automation, accuracy, and real-time performance, necessitating an urgent need for a more intelligent and efficient solution to address these shortcomings. Summary of the Invention

[0004] In view of the problems existing in the existing intelligent detection method for hidden dangers of expansion joints of GIS equipment based on deep learning, the present invention is proposed.

[0005] Therefore, the present invention addresses the problems in the existing technology of detecting hidden dangers in the expansion joints of GIS equipment, such as being time-consuming and labor-intensive, having poor accuracy, and difficulty in discovering hidden dangers. The present invention adopts comprehensive data integration and intelligent analysis, real-time monitoring and dynamic early warning, and a continuous optimization mechanism based on feedback loops to achieve efficient, accurate and intelligent detection of hidden dangers in the expansion joints of GIS equipment.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides an intelligent detection method for hidden dangers of expansion joints of GIS equipment based on deep learning, which includes collecting information source data from GIS equipment, constructing an information source data set, and processing the constructed information source data set; after completing the processing of the information source data set, using data processing technology to mine the information features of the information source data set and refine the data relationship of the information features; establishing a monitoring system to monitor the status of GIS equipment and automatically evaluate the health status of GIS equipment according to preset rules; introducing a feedback optimization process, and improving the feedback optimization process through the processed information source data set to complete the intelligent detection of hidden dangers of expansion joints of GIS equipment.

[0008] As a preferred solution of the deep learning-based intelligent detection method for expansion joint hazards of GIS equipment described in the present invention, the construction of the information source data set includes integrating data from the operating parameters, historical maintenance records and environmental influencing factors of the GIS equipment to form an information source data set, classifying the information source data set, eliminating inconsistencies between data from different sources, and introducing a dynamic time window mechanism to capture the trend of GIS equipment status changes over time.

[0009] As a preferred solution of the deep learning-based intelligent detection method for expansion joint hazards of GIS equipment described in the present invention, the method of extracting data relationships of information features includes, after completing the processing of the information source data set, using a multi-level data analysis method to mine implicit information features in the data, focusing on the changes in individual data points, and analyzing cross-dimensional data correlations;

[0010] The data correlation analysis includes the fluctuation pattern in the time series and the interaction between different parameters, extracts the characteristics that are indicative of the health status of the equipment from the data, designs an adaptive data screening mechanism, and automatically adjusts the analysis focus to improve the accuracy of detection.

[0011] As a preferred solution of the deep learning-based intelligent detection method for expansion joint hazards of GIS equipment described in the present invention, the establishment of a monitoring system includes constructing a monitoring system to monitor the status of GIS equipment and automatically assess its health status according to preset rules;

[0012] The monitoring system is used to customize alarm thresholds according to different application scenarios and needs in its flexible and configurable early warning system. It adopts a distributed architecture to process status requests for monitoring GIS equipment without affecting system performance, and integrates visualization tools to enable operation and maintenance personnel to view the development trend of GIS equipment status;

[0013] When an abnormal situation is detected, the system will trigger an alarm mechanism to notify relevant operation and maintenance personnel to take measures to ensure the safety of the power system through monitoring, and adjust the monitoring strategy and alarm thresholds based on the design scalability.

[0014] As a preferred embodiment of the deep learning-based intelligent detection method for expansion joint hazards of GIS equipment described in the present invention, the improved feedback optimization process includes introducing a continuous optimization mechanism based on a feedback loop, making improvements based on the results of operations. The improvements include automatically adjusting the internal logic of the GIS equipment based on the learning elements of the GIS equipment by comparing the predicted results with the actual situation to improve the accuracy of the prediction.

[0015] A user interaction module was designed to directly participate in the optimization process, enhance the adaptability and intelligence of the system, and complete the intelligent detection of hidden dangers in the expansion joints of GIS equipment with the optimization of power grid environment technology.

[0016] As a preferred solution to the deep learning-based intelligent detection method for expansion joint hazards of GIS equipment described in the present invention, the monitoring system includes a dynamic adaptive monitoring network with an architectural design, which automatically adjusts the location and density of monitoring nodes according to the layout and operating environment of the GIS equipment, and seamlessly accesses various types of information through an integrated multi-dimensional data input interface.

[0017] Analyze the massive data streams from GIS devices, identify specific patterns to determine the current working status of the equipment, and use a multi-level health scoring mechanism to assign corresponding weights to different types of hidden danger risks to generate a health index;

[0018] Customize alarm thresholds based on application scenarios and requirements, and automatically recommend warning parameter combinations by combining machine learning technology and learning from historical data;

[0019] Adopt a distributed architecture and take advantage of its edge capabilities to perform processing close to the data source, reducing the load on central servers. By introducing containerization technology, collaboration between components is expanded.

[0020] Display the real-time status of GIS equipment, present the development trend of equipment status in the form of dashboard, and view the internal structure of GIS equipment through mobile devices.

[0021] As a preferred embodiment of the deep learning-based intelligent detection method for expansion joint hazards of GIS equipment described in the present invention, the automatic adjustment of the internal logic of the GIS equipment includes introducing a continuous optimization mechanism based on a feedback loop, designing a dynamic comparative analysis framework, collecting actual operating data of the GIS equipment for a second time, and performing a multi-dimensional comparative analysis of the data with the predicted results. The system automatically identifies the deviation pattern between the predicted value and the actual value, and infers the deficiencies of the current model.

[0022] When the prediction of hidden dangers of a certain type is lower than the actual occurrence rate, the system will automatically adjust the actual operation data rules;

[0023] Integrate intelligent learning elements to predict the learning of historical data; when using time series analysis technology, the system identifies the development pattern of hidden dangers over time, adjusts the internal logic of GIS equipment, and adopts adaptive learning strategies to automatically adjust learning methods according to changes in power grid environment and technology;

[0024] Design a user interaction module to allow users to participate in the optimization process; when the system encounters an abnormal situation, the user interaction module can be used to issue a consultation request and submit observation suggestions;

[0025] A differentiated feedback optimization strategy is proposed, which uses differentiated feedback optimization paths according to different types of GIS equipment, different operating environments, and different types of hidden dangers.

[0026] When it comes to equipment affected by the external environment, the system optimizes the data input of the external conditions and completes the detection.

[0027] In a second aspect, an embodiment of the present invention provides a deep learning-based intelligent detection system for expansion joint hazards in GIS equipment, which includes:

[0028] A construction module collects information source data from GIS equipment, constructs an information source data set, and processes the constructed information source data set;

[0029] The extraction module, after completing the processing of the information source data set, uses data processing technology to mine the information features of the information source data set and extract the data relationships of the information features;

[0030] The evaluation module establishes a monitoring system to monitor the status of GIS equipment and automatically evaluates the health of GIS equipment according to preset rules;

[0031] The detection module introduces a feedback optimization process, improves the feedback optimization process through the processed information source data set, and completes the intelligent detection of hidden dangers in the expansion joints of GIS equipment.

[0032] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, it implements any step of the above-mentioned deep learning-based intelligent detection method for expansion joint hazards of GIS equipment.

[0033] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, wherein: when the computer program is executed by a processor, any step of the above-mentioned deep learning-based intelligent detection method for hidden dangers of expansion joints of GIS equipment is implemented.

[0034] The beneficial effects of the present invention are as follows: the present invention significantly improves the efficiency and accuracy of hidden danger detection of expansion joints of GIS equipment through a series of innovative technical means. First, by integrating multi-source data and performing standardized processing, a high-quality information source data set is constructed, laying a solid foundation for subsequent analysis. Then, a multi-level data analysis method is used to mine implicit information features and identify early signs of hidden dangers, greatly improving the detection accuracy. The established intelligent monitoring system can not only monitor the equipment status in real time and automatically evaluate the health status, but also support flexible configuration of the early warning system to ensure that operation and maintenance personnel can respond to potential problems in a timely manner. In addition, the introduction of a continuous optimization mechanism based on a feedback loop enables the system to continuously self-adjust according to actual operation results, thereby enhancing the adaptability and intelligence of the system. Finally, the present invention achieves efficient and accurate detection of hidden dangers in expansion joints of GIS equipment, greatly reduces the risk of power system failures, improves the safety and stability of the power grid, and at the same time reduces maintenance costs and time consumption. It has important application value and broad market prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0036] Figure 1 This is a flow chart of the method for intelligent detection of hidden dangers in expansion joints of GIS equipment based on deep learning.

[0037] Figure 2 This is a system diagram of the intelligent detection method for hidden dangers of expansion joints of GIS equipment based on deep learning. DETAILED DESCRIPTION

[0038] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0039] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0040] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0041] The present invention is described in detail with reference to schematic diagrams. For ease of illustration, cross-sectional views of device structures may be partially enlarged and not to scale when describing embodiments of the present invention. Furthermore, the schematic diagrams are merely illustrative and should not limit the scope of the present invention. Furthermore, in actual production, the three-dimensional dimensions of length, width, and depth should be included.

[0042] In the description of the present invention, it should be noted that the terms "upper, lower, inner, and outer" and other references to orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0043] In this disclosure, unless otherwise specified or limited, the terms "mounted," "connected," and "connected" should be interpreted broadly. For example, they may refer to fixed, removable, or integral connections. They may also refer to mechanical, electrical, or direct connections, indirect connections through an intermediary, or internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in this disclosure.

[0044] Example 1

[0045] Reference Figure 1 and Figure 2, which is the first embodiment of the present invention, provides an intelligent detection method for hidden dangers of expansion joints of GIS equipment based on deep learning, including:

[0046] S1: By collecting information source data from GIS equipment, constructing an information source data set, and processing the constructed information source data set.

[0047] Among them, building an information source data set includes integrating data from the operating parameters, historical maintenance records and environmental influencing factors of GIS equipment to form an information source data set, classifying the information source data set, eliminating inconsistencies between data from different sources, and introducing a dynamic time window mechanism to capture the trend of GIS equipment status changes over time.

[0048] S2: After completing the processing of the information source data set, use data processing technology to mine the information features of the information source data set and refine the data relationships of the information features.

[0049] Among them, extracting the data relationship of information features includes, after completing the processing of the information source data set, using multi-level data analysis methods to mine the implicit information features in the data, focusing on the changes of single data points, and analyzing the cross-dimensional data correlation;

[0050] Data correlation analysis includes fluctuation patterns in time series and interactions between different parameters. Features that are indicative of equipment health are extracted from the data. An adaptive data screening mechanism is designed to automatically adjust the analysis focus and improve detection accuracy.

[0051] S3: Establish a monitoring system to monitor the status of GIS equipment and automatically evaluate the health status of GIS equipment based on preset rules.

[0052] Among them, establishing a monitoring system includes building a monitoring system to monitor the status of GIS equipment and automatically evaluate its health status according to preset rules;

[0053] The monitoring system is used to customize alarm thresholds based on different application scenarios and requirements in its flexible and configurable early warning system. It adopts a distributed architecture to process status requests for monitoring GIS equipment without affecting system performance. It also integrates visualization tools to enable operation and maintenance personnel to view the development trend of GIS equipment status.

[0054] When an abnormal situation is detected, the system will trigger an alarm mechanism to notify relevant operation and maintenance personnel to take measures to ensure the safety of the power system through monitoring, and adjust the monitoring strategy and alarm thresholds based on the design scalability.

[0055] S4: Introduce the feedback optimization process, improve the feedback optimization process through the processed information source data set, and complete the intelligent detection of hidden dangers in the expansion joints of GIS equipment.

[0056] Among them, improving the feedback optimization process includes introducing a continuous optimization mechanism based on feedback loops, making improvements based on the results of operations, and automatically adjusting the internal logic of the GIS equipment based on the learning elements of the GIS equipment by comparing the predicted results with the actual situation to improve the accuracy of the prediction;

[0057] A user interaction module was designed to directly participate in the optimization process, enhance the adaptability and intelligence of the system, and complete the intelligent detection of hidden dangers in the expansion joints of GIS equipment with the optimization of power grid environment technology.

[0058] S4.1: Building a monitoring system includes adopting a dynamic and adaptive monitoring network with architectural design, automatically adjusting the location and density of monitoring nodes based on the layout and operating environment of GIS equipment, and seamlessly accessing various types of information through integrated multi-dimensional data input interfaces;

[0059] Analyze the massive data streams from GIS devices, identify specific patterns to determine the current working status of the equipment, and use a multi-level health scoring mechanism to assign corresponding weights to different types of hidden danger risks to generate a health index;

[0060] Customize alarm thresholds based on application scenarios and requirements, and automatically recommend warning parameter combinations by combining machine learning technology and learning from historical data;

[0061] Adopt a distributed architecture and take advantage of its edge capabilities to perform processing close to the data source, reducing the load on central servers. By introducing containerization technology, collaboration between components is expanded.

[0062] Display the real-time status of GIS equipment, present the development trend of equipment status in the form of dashboard, and view the internal structure of GIS equipment through mobile devices.

[0063] S4.2: Automatically adjust the internal logic of GIS equipment, including introducing a continuous optimization mechanism based on feedback loops, designing a dynamic comparative analysis framework, collecting actual GIS equipment operating data for secondary collection, and performing multi-dimensional comparative analysis with the predicted results. The system automatically identifies deviation patterns between predicted and actual values ​​and infers deficiencies in the current model.

[0064] When the prediction of hidden dangers of a certain type is lower than the actual occurrence rate, the system will automatically adjust the actual operation data rules;

[0065] Integrate intelligent learning elements to predict the learning of historical data; when using time series analysis technology, the system identifies the development pattern of hidden dangers over time, adjusts the internal logic of GIS equipment, and adopts adaptive learning strategies to automatically adjust learning methods according to changes in power grid environment and technology;

[0066] Design a user interaction module to allow users to participate in the optimization process; when the system encounters an abnormal situation, the user interaction module can be used to issue a consultation request and submit observation suggestions;

[0067] A differentiated feedback optimization strategy is proposed, which uses differentiated feedback optimization paths according to different types of GIS equipment, different operating environments, and different types of hidden dangers.

[0068] When it comes to equipment affected by the external environment, the system optimizes the data input of the external conditions and completes the detection.

[0069] In a preferred embodiment, a deep learning-based intelligent detection system for GIS equipment expansion joint hidden dangers includes:

[0070] S310: a construction module, which collects information source data from GIS devices, constructs an information source data set, and processes the constructed information source data set;

[0071] S320: A refinement module, after completing the processing of the information source data set, uses data processing technology to mine the information features of the information source data set and refine the data relationships of the information features;

[0072] S330: Evaluation module, which establishes a monitoring system, monitors the status of GIS equipment, and automatically evaluates the health status of GIS equipment according to preset rules;

[0073] S340: Detection module, which introduces feedback optimization process, improves the feedback optimization process through the processed information source data set, and completes the intelligent detection of hidden dangers in the expansion joints of GIS equipment.

[0074] The above-mentioned unit modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of the above-mentioned modules.

[0075] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0076] In summary, the present invention has significantly improved the efficiency and accuracy of hidden danger detection of expansion joints of GIS equipment through a series of innovative technical means. First, by integrating multi-source data and performing standardized processing, a high-quality information source data set is constructed, which lays a solid foundation for subsequent analysis. Then, a multi-level data analysis method is used to mine implicit information features and identify early signs of hidden dangers, greatly improving the detection accuracy. The established intelligent monitoring system can not only monitor the equipment status in real time and automatically evaluate the health status, but also support flexible configuration of early warning systems to ensure that operation and maintenance personnel can respond to potential problems in a timely manner. In addition, a continuous optimization mechanism based on a feedback loop is introduced, so that the system can continuously adjust itself according to actual operation results, thereby enhancing the adaptability and intelligence of the system. Finally, the present invention realizes efficient and accurate detection of hidden dangers of expansion joints of GIS equipment, greatly reduces the risk of power system failures, improves the safety and stability of the power grid, and at the same time reduces maintenance costs and time consumption. It has important application value and broad market prospects.

[0077] Example 2

[0078] Reference Figure 1 and Figure 2 This is the second embodiment of the present invention, which provides an intelligent detection method for hidden dangers of expansion joints of GIS equipment based on deep learning. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0079] Establish a monitoring system to monitor the status of GIS equipment and automatically assess its health status based on preset rules. Establishing a monitoring system includes constructing a monitoring system to monitor the status of GIS equipment and automatically assess its health status based on preset rules. The monitoring system is used to customize alarm thresholds based on different application scenarios and requirements in its flexible and configurable early warning system. It adopts a distributed architecture to process status monitoring requests for GIS equipment without affecting system performance. It integrates visualization tools to enable operation and maintenance personnel to view the development trend of GIS equipment status. When an abnormal situation is detected, the system triggers an alarm mechanism to notify relevant operation and maintenance personnel to take measures. The safety of the power system is ensured through monitoring, and the monitoring strategy and alarm thresholds are adjusted according to the scalability of the design.

[0080] Preferably, in the monitoring system of the present invention, setting alarm thresholds is a key step in ensuring timely assessment and response to the health status of GIS equipment. For example, when monitoring GIS equipment temperature parameters, the system presets a normal operating temperature range of -20°C to 40°C. When the temperature exceeds this range, different levels of alarms are triggered: if the temperature reaches 45°C, a low-level warning is triggered, prompting the attention of operation and maintenance personnel; if the temperature rises to 50°C, a medium-level alarm is triggered, recommending preventive maintenance measures; and once the temperature exceeds 60°C, a high-level emergency alarm is immediately triggered, requiring immediate inspection and treatment to prevent major failures. Similarly, for pressure parameters, a preset safety range of 0.1MPa to 0.5MPa is used. Exceeding this range will trigger corresponding early warning mechanisms based on the degree of excess. These thresholds can be customized based on multiple factors, such as the specific GIS equipment type, geographic location, environmental conditions, and historical data. As the system self-learns and optimizes, it can dynamically adjust to adapt to the changing power grid environment and technological advances, thereby achieving accurate monitoring and efficient management of GIS equipment status. This flexible and configurable early warning system not only improves the speed of problem response, but also greatly enhances the safety and stability of the power system.

[0081] The selection of the above temperature and pressure thresholds is based on an in-depth analysis of the operating characteristics and safety standards of GIS equipment. For temperature parameters, the normal operating range is set to -20°C to 40°C. This is because the insulating gas inside GIS equipment, such as SF6, can maintain optimal electrical performance and physical stability within this temperature range. When the temperature reaches 45°C, although still within the acceptable range, it is close to the upper limit. At this time, a low-level warning is triggered to alert operation and maintenance personnel to environmental changes or equipment load conditions to prevent further temperature increases. 50°C is the trigger point for the medium-level alarm because this temperature indicates that the equipment may have local overheating, requiring preventive maintenance to avoid potential failures. Once the temperature exceeds 60°C, it means a serious abnormality has occurred and immediate action must be taken to prevent damage to the insulation material or even a larger system failure.

[0082] As for the pressure parameters, the safety range is set to 0.1MPa to 0.5MPa. This is because this pressure range can ensure the effective insulation performance of the insulating gas inside the GIS equipment, and will not damage the equipment structure due to excessive pressure. Pressure fluctuations beyond this range often indicate possible leakage or sealing failure. For example, if the pressure drops below 0.1MPa, it may cause a decrease in insulation performance and increase the risk of arcing. On the contrary, if the pressure rises to more than 0.5MPa, it may cause the risk of deformation or even rupture of equipment components. Therefore, setting different levels of early warning thresholds based on these key points can ensure that potential problems are discovered and handled in a timely manner without affecting the normal operation of the equipment, thereby ensuring the safe and stable operation of the power grid. This refined threshold setting not only takes into account the specific working conditions of the equipment, but also combines long-term accumulated operating data and industry standards to provide the most optimized monitoring strategy. The comparison between the present invention and the prior art is shown in Table 1 below:

[0083] Table 1 Comparison between the present invention and the prior art

[0084]

[0085] As can be seen from Table 1, the present invention is significantly superior to existing technologies in terms of data processing, hidden danger detection accuracy, real-time monitoring and early warning mechanism, system adaptability, and maintenance cost, providing a more intelligent and efficient solution for detecting hidden dangers in expansion joints of GIS equipment.

[0086] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A deep learning-based intelligent detection method for hidden dangers in expansion joints of GIS equipment, characterized by: include, By collecting information source data from GIS equipment, constructing information source data sets, and processing the constructed information source data sets; After completing the processing of the information source data set, data processing technology is used to mine the information features of the information source data set and extract the data relationships of the information features; Establish a monitoring system to monitor the status of GIS equipment and automatically evaluate the health of GIS equipment based on preset rules; Introduce the feedback optimization process, improve the feedback optimization process through the processed information source data set, and complete the intelligent detection of hidden dangers in the expansion joints of GIS equipment.

2. The deep learning-based intelligent detection method for GIS equipment expansion joint hidden dangers according to claim 1 is characterized by: The construction of the information source data set includes integrating data from the operating parameters, historical maintenance records and environmental influencing factors of GIS equipment to form an information source data set, classifying the information source data set, eliminating inconsistencies between data from different sources, and introducing a dynamic time window mechanism to capture the trend of GIS equipment status changes over time.

3. The deep learning-based intelligent detection method for GIS equipment expansion joint hidden dangers according to claim 1 is characterized by: The data relationship of extracting information features includes, after completing the processing of the information source data set, using a multi-level data analysis method to mine the implicit information features in the data, focusing on the changes of single data points, and analyzing the cross-dimensional data correlation; The data correlation analysis includes the fluctuation pattern in the time series and the interaction between different parameters, extracts the characteristics that are indicative of the health status of the equipment from the data, designs an adaptive data screening mechanism, and automatically adjusts the analysis focus to improve the accuracy of detection.

4. The deep learning-based intelligent detection method for GIS equipment expansion joint hidden dangers according to claim 1 is characterized by: The establishment of the monitoring system includes constructing a monitoring system to monitor the status of GIS equipment and automatically assess its health status according to preset rules; The monitoring system is used to customize alarm thresholds according to different application scenarios and needs in its flexible and configurable early warning system. It adopts a distributed architecture to process status requests for monitoring GIS equipment without affecting system performance, and integrates visualization tools to enable operation and maintenance personnel to view the development trend of GIS equipment status; When an abnormal situation is detected, the system will trigger an alarm mechanism to notify relevant operation and maintenance personnel to take measures to ensure the safety of the power system through monitoring, and adjust the monitoring strategy and alarm thresholds based on the design scalability.

5. The deep learning-based intelligent detection method for GIS equipment expansion joint hidden dangers according to claim 1 is characterized by: The improved feedback optimization process includes introducing a continuous optimization mechanism based on a feedback loop to make improvements based on the results of the operation. The improvement includes automatically adjusting the internal logic of the GIS device based on the learning elements of the GIS device by comparing the predicted results with the actual situation to improve the accuracy of the prediction; A user interaction module was designed to directly participate in the optimization process, enhance the adaptability and intelligence of the system, and complete the intelligent detection of hidden dangers in the expansion joints of GIS equipment with the optimization of power grid environment technology.

6. The deep learning-based intelligent detection method for GIS equipment expansion joint hidden dangers according to claim 4 is characterized by: The monitoring system includes a dynamic adaptive monitoring network with an architectural design that automatically adjusts the location and density of monitoring nodes according to the layout and operating environment of GIS equipment, and seamlessly accesses various types of information through an integrated multi-dimensional data input interface; Analyze the massive data streams from GIS devices, identify specific patterns to determine the current working status of the equipment, and use a multi-level health scoring mechanism to assign corresponding weights to different types of hidden danger risks to generate a health index; Customize alarm thresholds based on application scenarios and requirements, and automatically recommend warning parameter combinations by combining machine learning technology and learning from historical data; Adopt a distributed architecture and take advantage of its edge capabilities to perform processing close to the data source, reducing the load on central servers. By introducing containerization technology, collaboration between components is expanded. Display the real-time status of GIS equipment, present the development trend of equipment status in the form of dashboard, and view the internal structure of GIS equipment through mobile devices.

7. The deep learning-based intelligent detection method for GIS equipment expansion joint hidden dangers according to claim 5 is characterized by: The automatic adjustment of the internal logic of the GIS device includes introducing a continuous optimization mechanism based on a feedback loop, designing a dynamic comparative analysis framework, collecting the actual operation data of the GIS device for a second time, and performing a multi-dimensional comparative analysis between it and the predicted results. The system automatically identifies the deviation pattern between the predicted value and the actual value, and infers the deficiencies of the current model. When the prediction of hidden dangers of a certain type is lower than the actual occurrence rate, the system will automatically adjust the actual operation data rules; Integrate intelligent learning elements to predict the learning of historical data; when using time series analysis technology, the system identifies the development pattern of hidden dangers over time, adjusts the internal logic of GIS equipment, and adopts adaptive learning strategies to automatically adjust learning methods according to changes in power grid environment and technology; Design user interaction modules to allow users to participate in the optimization process; When an abnormal situation occurs in the system, a consultation request is sent through the user interaction module to submit observation suggestions; A differentiated feedback optimization strategy is proposed, which uses differentiated feedback optimization paths according to different types of GIS equipment, different operating environments, and different types of hidden dangers. When it comes to equipment affected by the external environment, the system optimizes the data input of the external conditions and completes the detection.

8. A deep learning-based intelligent detection system for GIS equipment expansion joint hidden dangers, based on the deep learning-based intelligent detection method for GIS equipment expansion joint hidden dangers according to any one of claims 1 to 7, characterized in that: include, A construction module collects information source data from GIS equipment, constructs an information source data set, and processes the constructed information source data set; The extraction module, after completing the processing of the information source data set, uses data processing technology to mine the information features of the information source data set and extract the data relationships of the information features; The evaluation module establishes a monitoring system to monitor the status of GIS equipment and automatically evaluates the health of GIS equipment according to preset rules; The detection module introduces a feedback optimization process, improves the feedback optimization process through the processed information source data set, and completes the intelligent detection of hidden dangers in the expansion joints of GIS equipment.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the deep learning-based intelligent detection method for hidden dangers of expansion joints of GIS equipment described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the deep learning-based intelligent detection method for hidden dangers of expansion joints of GIS equipment according to any one of claims 1 to 7 are implemented.

Images