Three-phase common-box GIL settlement fault detection method and system

Abstract

The invention discloses a three-phase common-box GIL settlement fault detection method and system, and the method comprises the steps: collecting the multi-source data of a GIL pipeline in real time through a heterogeneous sensor network, and carrying out the preprocessing of the multi-source data through the combination of an edge-cloud collaborative architecture, and performing multi-physics field coupling analysis on the preprocessed multi-source data based on a pre-constructed dynamic adaptive digital twinborn model, outputting a fault probability value, and triggering early warning when the fault probability value meets an early warning condition. The technical scheme provided by the embodiment of the invention is not influenced by environmental factors such as humidity, air pressure and the like, can widely cover different positions to comprehensively sense the settlement of the GIL pipeline bracket, and solves the problems that the measurement precision is poor and the settlement condition of the whole tunnel cannot be comprehensively and intuitively reflected in the prior art; the method has the beneficial effects of improving the measurement precision, the real-time performance of settlement detection, the reliability and the operation and maintenance efficiency.

Description

Technical Field

[0001] The present invention relates to the field of high-voltage power transmission technology, and in particular to a method and system for detecting a three-phase GIL settlement fault. Background Art

[0002] A three-phase gas-insulated transmission line (GIL) encloses three-phase conductors in a common metal casing and is filled with an insulating gas such as SF6. It boasts high transmission capacity and reliability and is widely used in high-voltage power transmission. During long-term operation, tunnel settlement can affect the transmission line piping structure within underground tunnels, potentially causing uneven stress on line components and interference with other facilities, threatening the long-term operational reliability of the equipment.

[0003] Existing technologies mainly measure tunnel settlement through static levels, which consist of multiple liquid cylinders. The height of the liquid in the cylinders changes with the settlement of the tunnel. However, static levels are sensitive to temperature changes. Temperature fluctuations can cause the liquid to expand or contract, resulting in measurement deviations. Environmental factors such as humidity and air pressure around the tunnel can also affect measurement accuracy. In addition, existing technologies can only measure settlement at specific locations and cannot fully and intuitively reflect the settlement of the entire tunnel. If you want to understand the overall settlement distribution of the tunnel, you need to install static levels at multiple locations, which will increase the measurement cost and difficulty. Existing digital twin technologies mostly use static models in GIL monitoring, which are difficult to adapt to complex environmental changes and lack the ability to couple and analyze multiple physical fields. In addition, the single data source of traditional sensors limits the comprehensiveness of the model, and data security and real-time performance are also challenged. Summary of the Invention

[0004] The present invention provides a three-phase common box GIL settlement fault detection method, system, electronic equipment, storage medium and program product to solve the problem that the existing technology has poor measurement accuracy and cannot fully and intuitively reflect the settlement status of the entire tunnel.

[0005] According to one aspect of the present invention, a method for detecting settlement faults of a three-phase common-chamber GIL is provided, characterized in that it is used in a three-phase common-chamber GIL settlement fault detection system, the system comprising: a GIL pipeline, a rubber gasket, a clamp, a strain gauge sensor, a vibration sensor, a displacement sensor, and a current sensor; the clamp is fixed to a bracket of the GIL pipeline, the rubber gasket is arranged between one end of the clamp and the lower contact surface of the GIL pipeline, the strain gauge sensor is fixed to the other end of the clamp, the current sensor, the vibration sensor, and the displacement sensor are respectively arranged on the lower contact surface of the GIL pipeline, and the strain gauge sensor, the current sensor, the vibration sensor, and the displacement sensor constitute a heterogeneous sensing network; the method comprises:

[0006] Collect multi-source data of the GIL pipeline in real time through the heterogeneous sensor network;

[0007] Preprocessing the multi-source data in combination with an edge-cloud collaborative architecture;

[0008] Based on the pre-built dynamic adaptive digital twin model, multi-physical field coupling analysis is performed on the pre-processed multi-source data, a fault probability value is output, and an early warning is triggered when the fault probability value meets the early warning conditions.

[0009] Optionally, before performing multi-physics field coupling analysis on the pre-processed multi-source data based on the pre-built dynamic adaptive digital twin model, outputting a fault probability value, and triggering an early warning when the fault probability value meets the early warning condition, the method further includes:

[0010] Build a dynamic and adaptive digital twin model based on transfer learning and federated learning.

[0011] Optionally, the dynamic adaptive digital twin model integrates a multi-physical field coupling analysis module, including mechanical field, thermal field and electromagnetic field simulation units, and outputs a fault probability value through joint optimization of finite element analysis and machine learning.

[0012] Optionally, the pre-built dynamic adaptive digital twin model performs multi-physics field coupling analysis on the pre-processed multi-source data, outputs a fault probability value, and triggers an early warning when the fault probability value meets the early warning condition, including:

[0013] Based on the pre-built dynamic adaptive digital twin model, multi-physical field coupling analysis is performed on the pre-processed multi-source data, and a fault probability value is output. When the fault probability value is greater than or equal to a preset threshold, an early warning is triggered.

[0014] According to another aspect of the present invention, a three-phase common-tank GIL settlement fault detection system is provided, comprising: a GIL pipeline, a rubber gasket, a clamp, a strain gauge sensor, a vibration sensor, a displacement sensor, and a current sensor; the clamp is fixed to a bracket of the GIL pipeline, the rubber gasket is disposed between one end of the clamp and the lower contact surface of the GIL pipeline, the strain gauge sensor is fixed to the other end of the clamp, and the current sensor, the vibration sensor, and the displacement sensor are respectively disposed on the lower contact surface of the GIL pipeline; the system further comprises a processor;

[0015] The processor is used to collect multi-source data of the GIL pipeline in real time through a heterogeneous sensor network;

[0016] The processor is further configured to pre-process the multi-source data in combination with an edge-cloud collaborative architecture;

[0017] The processor is also used to perform multi-physical field coupling analysis on the pre-processed multi-source data based on a pre-built dynamic adaptive digital twin model, output a fault probability value, and trigger an early warning when the fault probability value meets the early warning condition.

[0018] According to another aspect of the present invention, an electronic device is provided, comprising:

[0019] at least one processor; and

[0020] a memory communicatively connected to the at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the three-phase common tank GIL settlement fault detection method described in any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the three-phase common tank GIL settlement fault detection method described in any embodiment of the present invention when executed.

[0023] According to another aspect of the present invention, a computer program product is provided, comprising a computer program. When executed by a processor, the computer program implements the method for detecting settlement faults of a three-phase common tank GIL according to any embodiment of the present invention.

[0024] Embodiments of the present invention provide a method and system for detecting subsidence faults in a three-phase, common-chamber GIL pipeline. The method comprises: collecting multi-source data from the GIL pipeline in real time through a heterogeneous sensor network; preprocessing the multi-source data in conjunction with an edge-cloud collaborative architecture; performing multi-physics field coupling analysis on the preprocessed multi-source data based on a pre-built dynamic adaptive digital twin model; outputting a fault probability value; and triggering an early warning when the fault probability value meets early warning conditions. The technical solution provided by embodiments of the present invention collects multi-source data from the GIL pipeline in real time through a heterogeneous sensor network composed of multiple different types of sensors, each capable of accurately measuring specific parameters of the GIL pipeline. The mutual complementation and verification of different sensor types can reduce the potential errors inherent in individual sensors, improve data accuracy and reliability, and thus enhance the precision of GIL pipeline operating parameter measurements. Preliminary data cleaning and denoising preprocessing operations, such as cleaning and denoising, are performed on the edge to remove noise and interference introduced during data collection and improve data quality. The cloud can leverage its powerful computing power to perform more complex data fusion and correction processing, further improving data accuracy. This collaborative processing approach within the edge-cloud collaborative architecture ensures high accuracy of the data input into the digital twin model, thereby increasing the reliability of subsequent analysis results based on this data. The pre-built dynamic, adaptive digital twin model differs from traditional static models in that it automatically adjusts its parameters and structure based on real-time GIL pipeline operating data and changes in environmental conditions. In actual operation, the GIL pipeline's environment may undergo various complex changes, such as significant temperature fluctuations and changes in the surrounding geological structure. The dynamic, adaptive model can promptly adapt to these changes, maintaining accurate simulation and analysis of the GIL pipeline's operating status. Based on the pre-built dynamic, adaptive digital twin model, a multi-physics coupling analysis is performed on the pre-processed multi-source data, taking into account the interactions and influences between multiple physical fields, including electric, magnetic, mechanical, and thermal fields, during GIL pipeline operation. This analysis approach more realistically simulates the actual operation of the GIL pipeline, as these physical fields do not exist in isolation but are interconnected and mutually influential. Through multi-physics field coupling analysis, we can fully understand the coupling relationship between these physical fields, accurately assess the operating status and potential failure risks of the GIL pipeline, and provide more powerful support for fault diagnosis and prevention. The technical solution provided by the embodiment of the present invention is not affected by environmental factors such as humidity and air pressure. It can comprehensively perceive the settlement of GIL pipeline supports at different locations across a wide range of coverage areas. This solves the problem of poor measurement accuracy and the inability of existing technologies to fully and intuitively reflect the settlement status of the entire tunnel. It has the beneficial effect of improving measurement accuracy, the real-time performance of settlement detection, reliability, and operation and maintenance efficiency.

[0025] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0027] Figure 1 A flow chart of a method for detecting a settlement fault of a three-phase common-tank GIL provided in an embodiment of the present invention;

[0028] Figure 2 A schematic structural diagram of a three-phase common-tank GIL settlement fault detection system provided by an embodiment of the present invention;

[0029] Figure 3 A schematic structural diagram of an electronic device for a three-phase common-tank GIL settlement fault detection method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described 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 making creative efforts should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] Figure 1This is a flow chart of a three-phase common box GIL settlement fault detection method provided by an embodiment of the present invention. This embodiment is applicable to the detection of three-phase common box GIL settlement faults, and the method can be executed by a three-phase common box GIL settlement fault detection system. Figure 2 A schematic diagram of a three-phase common tank GIL settlement fault detection system provided by an embodiment of the present invention is shown in FIG. Figure 2 The three-phase common-chamber GIL settlement fault detection system includes: a GIL pipeline 1, a rubber gasket 2, a clamp 3, a strain gauge sensor 4, a vibration sensor 5, a displacement sensor 6, and a current sensor 7. The clamp 3 is fixed to the bracket of the GIL pipeline 1. A rubber gasket is provided between one end of the clamp 3 and the lower contact surface of the GIL pipeline 1. The strain gauge sensor 4 is fixed to the other end of the clamp 3. The current sensor 7, vibration sensor 5, and displacement sensor 6 are respectively provided on the lower contact surface of the GIL pipeline 1. The strain gauge sensor 4, current sensor 7, vibration sensor 5, and displacement sensor 6 constitute a heterogeneous sensing network. Figure 1 , the method comprising:

[0033] S110, collect multi-source data of the GIL pipeline in real time through a heterogeneous sensor network.

[0034] A heterogeneous sensing network is composed of multiple sensors of different types and characteristics. In this embodiment of the present invention, strain gauge sensors, current sensors, vibration sensors, and displacement sensors constitute the heterogeneous sensing network. These sensors differ in their operating principles, measurement ranges, data formats, and communication methods. For example, strain gauge sensors collect strain data on the GIL pipeline, current sensors collect current data flowing through the pipeline, vibration sensors collect vibration data, and displacement sensors collect displacement data caused by the strain-induced vibration. Each sensor is responsible for collecting information about a specific aspect of the GIL pipeline. Through network connectivity and collaboration, they jointly complete the task of comprehensive GIL pipeline status monitoring. Multi-source data refers to various data reflecting the operating status of the GIL pipeline from different perspectives, including but not limited to electrical parameters such as voltage, current, and power factor; physical parameters such as temperature, pressure, vibration, and displacement; and insulation parameters such as partial discharge and dielectric loss factor. Combined, these data can comprehensively describe the operating status of the GIL pipeline, providing a rich information foundation for subsequent analysis, diagnosis, and maintenance. During GIL pipeline operation, the sensor network continuously acquires data at a high frequency, enabling timely and accurate reflection of the pipeline's current operational status. This allows for the timely identification of potential issues and the implementation of appropriate measures. In summary, real-time multi-source data collection for GIL pipelines through heterogeneous sensor networks utilizes a network composed of multiple sensors to continuously and promptly acquire data reflecting various aspects of the GIL pipeline's operational status, providing data support for GIL pipeline status monitoring and management.

[0035] Strain gauge sensors can be installed at fixed intervals based on actual testing requirements to ensure coverage of settlement-sensitive areas. For example, the spacing can be ≤1.5 meters. The thickness and hardness of rubber gasket 2 can be selected based on actual engineering requirements to eliminate mechanical vibration interference. For example, the rubber gasket can be 2mm thick and have a Shore hardness of 60. The uniqueness of the fixture lies in its ability to provide micron-level accuracy for precision machining of semiconductor devices, using low thermal deformation materials or anti-backlash mechanisms. It also features an anti-vibration design, suppressing cutting vibrations through damping structures or materials to ensure high surface quality.

[0036] S120. Preprocess multi-source data in combination with the edge-cloud collaborative architecture.

[0037] The edge-cloud collaborative architecture consists of edge computing nodes and cloud servers. Edge computing nodes are a distributed computing model that places computation and data storage close to the data source or user. In GIL pipeline monitoring scenarios, edge computing nodes are typically deployed close to the GIL pipeline. They perform preliminary processing and analysis on the collected raw data, such as denoising, fusion, and feature extraction of multi-source data. Cloud servers are responsible for receiving the pre-processed data uploaded by edge computing nodes and performing more complex and in-depth analysis and processing, such as long-term data storage, big data analysis, and machine learning model training. Furthermore, cloud servers provide decision support and parameter configuration information to edge computing nodes, enabling collaborative operation between the two. The data collection process may be affected by various interference factors, such as electromagnetic interference and environmental noise, resulting in noisy data.

[0038] Specifically, preprocessing multi-source data using an edge-cloud collaborative architecture involves denoising, fusing, and extracting features from the data. Denoising involves applying various signal processing techniques, such as filtering and wavelet transforms, to remove noise from the data, improving its quality and reliability for subsequent analysis and processing. Fusion involves integrating data from different sensors and types, leveraging the complementary information from each data source to enhance overall awareness of the GIL pipeline's status. For example, fusing electrical and temperature data can more accurately determine whether the pipeline is experiencing abnormal conditions such as overload and overheating. Feature extraction involves extracting key features from the denoised and fused data that reflect the GIL pipeline's operating status. These features represent a high-level summary and abstraction of the original data, highlighting important information and reducing its dimensionality. This facilitates model training and fault diagnosis using machine learning and deep learning algorithms. For example, extracting harmonic features from current data and features such as discharge amplitude and frequency from partial discharge data can be used to determine insulation defects in the pipeline.

[0039] S130. Perform multi-physics field coupling analysis on the pre-processed multi-source data based on the pre-built dynamic adaptive digital twin model, output a fault probability value, and trigger an early warning when the fault probability value meets the early warning condition.

[0040] Digital twin models are used to simulate the state of GIL pipelines in real time. Dynamically adaptive digital twin models can automatically adjust model parameters and structures based on the GIL pipeline's real-time operating status and changing environmental conditions to better reflect the actual physical system, demonstrating dynamic adaptation and self-optimization capabilities. Multi-physics fields include, but are not limited to, electric, magnetic, mechanical, and thermal fields. These fields interact and influence each other. Multi-physics coupling analysis considers the coupling relationships between these different fields and utilizes digital twin models to comprehensively analyze pre-processed multi-source data to provide a more comprehensive and accurate understanding of the GIL pipeline's operating status. For example, by analyzing the coupling relationship between electric and thermal fields, it is possible to study the impact of heat generated by current passing through a conductor on insulation performance.

[0041] Specifically, based on a pre-built dynamic adaptive digital twin model, the operational status of the GIL pipeline is simulated in real time using multi-source data inputs, predicting settlement trends. The multi-source data includes strain signals collected by strain gauge sensors, ambient temperature monitored by temperature sensors, and load current parameters. The strain signals are preprocessed by a signal processing module (integrated with a differential amplifier circuit and a high-precision analog-to-digital converter chip, such as the ADS1256). The differential amplifier circuit suppresses common-mode noise interference, while the high-precision analog-to-digital converter accurately digitizes the tiny strain signals with 24-bit resolution. The processed digital signals are uploaded to a cloud server in real time via a wireless transmission module, such as the SIM7600, that supports 4G / 5G communications. After receiving the data, the cloud server performs multi-physics coupling analysis in conjunction with the multi-physics coupling simulation module within the digital twin model. Using an LSTM-GNN hybrid model, the temporal characteristics are analyzed and correlated with the sensor network topology, dynamically outputting a failure probability value. When the probability value exceeds a preset threshold, the system automatically triggers a tiered alert, such as an audible and visual alarm, or text message notification. The data is encrypted with SHA-256 and written to the blockchain for traceability and tamper-proofing. Furthermore, edge computing nodes locally perform lightweight model inference, fusing vibration and displacement sensor data through Kalman filtering to further optimize real-time performance and accuracy, creating a fully closed-loop monitoring system from data acquisition, transmission, analysis, to decision-making.

[0042] The technical solution provided by the embodiments of the present invention uses a heterogeneous sensor network to collect multi-source data from GIL pipelines in real time. The heterogeneous sensor network is composed of multiple different types of sensors, each capable of accurately measuring specific parameters of the GIL pipeline. The mutual complementation and verification of different sensor types can reduce the potential errors of a single sensor, improve the accuracy and reliability of the data, and thus enhance the precision of the measurement of GIL pipeline operating parameters. Preliminary data cleaning and denoising preprocessing operations are performed on the edge to remove noise and interference introduced during the data collection process, thereby improving data quality. The cloud can leverage powerful computing power to perform more complex data fusion and correction processing, further improving data accuracy. This collaborative processing approach within the edge-cloud collaborative architecture ensures high accuracy of the data input into the digital twin model, thereby increasing the reliability of subsequent analysis results based on this data. A pre-built dynamic and adaptive digital twin model, unlike traditional static models, can automatically adjust its parameters and structure based on changes in the real-time operating data and environmental conditions of the GIL pipeline. During actual operation, the environment surrounding a GIL pipeline may undergo various complex changes, such as large temperature fluctuations and changes in the surrounding geological structure. A dynamic adaptive model can promptly adapt to these changes, maintaining accurate simulation and analysis of the GIL pipeline's operating status. Based on a pre-built dynamic adaptive digital twin model, a multi-physics coupling analysis is performed on pre-processed multi-source data, taking into account the interactions and influences between multiple physical fields, including electric, magnetic, mechanical, and thermal fields, during GIL pipeline operation. This analysis method can more realistically simulate the actual operation of a GIL pipeline, because in reality, these physical fields do not exist in isolation but are interconnected and mutually influential. Through multi-physics coupling analysis, a comprehensive understanding of the coupling relationships between these physical fields can be achieved, accurately assessing the GIL pipeline's operating status and potential fault risks, and providing stronger support for fault diagnosis and prevention. The technical solution provided by the embodiments of the present invention is unaffected by environmental factors such as humidity and air pressure, and can comprehensively detect the settlement of GIL pipeline supports at various locations across a wide range of locations. This addresses the problem of poor measurement accuracy and the inability of existing technologies to fully and intuitively reflect the settlement status of the entire tunnel. It has the beneficial effect of improving measurement accuracy, the real-time performance of settlement detection, reliability, and operational efficiency.

[0043] In some other embodiments, optionally, before S130, the step further includes:

[0044] Build a dynamic and adaptive digital twin model based on transfer learning and federated learning.

[0045] Transfer learning is a machine learning technique that allows knowledge or model parameters learned on one task or dataset to be applied to another related, but not identical, task or dataset. When building digital twin models, transfer learning can leverage existing knowledge from similar models or data to quickly initialize and optimize new digital twin models, reducing training data requirements and time, and improving model generalization and learning efficiency. Federated learning is a distributed machine learning framework that allows model training to be conducted across multiple participants without centralizing data to a central server. Each participant stores and processes its own data locally and exchanges model parameters or gradient information with other participants using an encrypted communication protocol, collaboratively training a globally optimal model. When building digital twin models, federated learning can be used to integrate data from different sources, such as sensor data from different locations, while protecting data privacy and security. This leverages the data strengths of all parties and improves the accuracy and robustness of digital twin models without being limited by data fragmentation and privacy issues. In summary, building a dynamic and adaptive digital twin model based on transfer learning and federated learning means leveraging the advantages of these two technologies to create a digital twin model that can adjust and optimize itself in real time according to changes in the real world, and can effectively utilize existing knowledge and distributed data to more efficiently and accurately simulate and reflect the real dynamic behavior and characteristics of the GIL pipeline.

[0046] Optionally, the dynamic adaptive digital twin model integrates a multi-physics field coupling analysis module, including mechanical field, thermal field and electromagnetic field simulation units, and outputs the fault probability value through joint optimization of finite element analysis and machine learning.

[0047] In some other embodiments, optionally, S130 specifically includes:

[0048] Based on the pre-built dynamic adaptive digital twin model, multi-physics field coupling analysis is performed on the pre-processed multi-source data, the fault probability value is output, and an early warning is triggered when the fault probability value is greater than or equal to the preset threshold.

[0049] The preset threshold value may be pre-set based on actual engineering measurement accuracy requirements.

[0050] The technical solution provided by the embodiment of the present invention builds a dynamic adaptive digital twin model based on transfer learning and federated learning, performs multi-physics field coupling analysis on the pre-processed multi-source data based on the pre-built dynamic adaptive digital twin model, outputs a fault probability value, and triggers an early warning when the fault probability value is greater than or equal to a preset threshold. While improving the generalization ability and learning efficiency of the model, it protects the privacy and security of the data. The dynamic adaptive digital twin model integrates a multi-physics field coupling analysis module, performs a fusion analysis on multi-source data, and constructs a more complete GIL settlement state model, providing a richer data source for a comprehensive understanding of tunnel settlement. However, the static level works independently, making it difficult to achieve comprehensive analysis of the data.

[0051] Before installing the clamp, conduct a thorough assessment of the installation environment. Ensure the installation area is clear of obstructions and provides ample space for operation. Inspect the clamp and its materials to ensure quality and integrity. Use sandpaper or a grinder to remove rust, oil, and other impurities from the mounting surface of the GIL pipe bracket. After removing impurities, wipe the surface with a detergent to ensure no residual impurities remain. The cleaned surface should be dried to prevent moisture from affecting subsequent installation steps. Secure the clamp to the GIL pipe bracket according to the pre-designed installation location. When selecting a clamp, consider the bracket's shape, size, and weight, as well as the strain gauge sensor's installation requirements. The clamp should be securely fastened using appropriate screws or bolts. Before securing the clamp, mark the mounting location on the bracket to ensure accurate installation. Place the strain gauge sensor in the fixture's mounting slot, ensuring a tight fit between the strain gauge and the bracket surface. The fit of the strain gauge directly affects the accuracy of the monitoring data, so careful adjustment is required during installation. Place a silicone rubber pad between the strain gauge sensor and the clamp to provide cushioning and insulation. The thickness and hardness of the silicone rubber pad should be selected based on actual conditions to ensure effective buffering and insulation. Solder the strain gauge sensor's lead wires and connect them to the terminal blocks, ensuring a secure and reliable connection. After soldering, use insulating tape or heat shrink tubing to insulate the strain gauge sensor's lead wires and terminal blocks to prevent short circuits. The insulation should fully cover the lead wires and terminal blocks. The signal processing module should be installed in a location that facilitates connection to the strain gauge sensor and wireless transmission module, while also considering heat dissipation and ease of maintenance. Before securing the signal processing module, mark the installation location to ensure accurate installation. Connect the strain gauge sensor to the signal processing module, connecting the strain gauge sensor's lead wires to the analog input port of the signal processing module through the terminal blocks. Ensure the correct wiring sequence to ensure proper signal transmission. Before connecting, use a multimeter or other tool to test the connection between the lead wires and the port. Install the wireless transmission module in a suitable location within the control cabinet, ensuring its antenna can properly receive and transmit signals. Connect the wireless transmission module and the signal processing module. Use a data cable to connect them according to the module's interface type to ensure a stable communication connection with the cloud server. The selection of the wireless transmission module should take into account factors such as communication distance, signal strength, and stability to ensure that the monitoring data can be transmitted to the cloud server in a timely and accurate manner. Install the operating system on the cloud server, develop the digital twin model and data analysis program, and the data reception, processing, and analysis program to achieve communication with the wireless transmission module, receive monitoring data, update the digital twin model, and perform settlement fault analysis and early warning. The configuration of the cloud server should take into account factors such as data storage capacity, computing power, and security to ensure the stable operation of the monitoring system and the security and reliability of the data.

[0052] Continue to see Figure 2 The three-phase common-tank GIL settlement fault detection system includes: a GIL pipeline 1, a rubber gasket 2, a clamp 3, a strain gauge sensor 4, a vibration sensor 5, a displacement sensor 6, and a current sensor 7; the clamp 3 is fixed to the bracket of the GIL pipeline 1, a rubber gasket is provided between one end of the clamp 3 and the lower contact surface of the GIL pipeline 1, and the strain gauge sensor 4 is fixed to the other end of the clamp 3. The current sensor 7, the vibration sensor 5, and the displacement sensor 6 are respectively provided on the lower contact surface of the GIL pipeline 1; the system also includes a processor;

[0053] The processor is used to collect multi-source data of the GIL pipeline in real time through a heterogeneous sensor network;

[0054] The processor is also used to pre-process multi-source data in conjunction with the edge-cloud collaborative architecture;

[0055] The processor is also used to perform multi-physics field coupling analysis on the pre-processed multi-source data based on a pre-built dynamic adaptive digital twin model, output a fault probability value, and trigger an early warning when the fault probability value meets the early warning conditions.

[0056] The three-phase common box GIL settlement fault detection system provided by the embodiment of the present invention can execute the three-phase common box GIL settlement fault detection method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0057] Figure 3 A schematic diagram of the structure of an electronic device for a three-phase common-box GIL settlement fault detection method provided by an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0058] like Figure 3As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0059] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0060] Processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any other suitable processor, controller, microcontroller, etc. Processor 11 executes the various methods and processes described above, such as a method for detecting a three-phase common-tank GIL settlement fault.

[0061] In some embodiments, a three-phase common tank GIL settlement fault detection method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the three-phase common tank GIL settlement fault detection method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the three-phase common tank GIL settlement fault detection method in any other appropriate manner (e.g., via firmware).

[0062] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0063] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0064] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0065] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0066] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0067] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0068] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0069] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for detecting settlement failure of a three-phase common-tank GIL, characterized in that: A three-phase common-tank GIL settlement fault detection system, the system comprising: a GIL pipeline, a rubber gasket, a fixture, a strain gauge sensor, a vibration sensor, a displacement sensor, and a current sensor; the fixture is fixed to a bracket of the GIL pipeline, the rubber gasket is arranged between one end of the fixture and the lower contact surface of the GIL pipeline, the strain gauge sensor is fixed to the other end of the fixture, the current sensor, the vibration sensor, and the displacement sensor are respectively arranged on the lower contact surface of the GIL pipeline, and the strain gauge sensor, the current sensor, the vibration sensor, and the displacement sensor constitute a heterogeneous sensing network; the method comprises: Collect multi-source data of the GIL pipeline in real time through the heterogeneous sensor network; Preprocessing the multi-source data in combination with an edge-cloud collaborative architecture; Based on the pre-built dynamic adaptive digital twin model, multi-physical field coupling analysis is performed on the pre-processed multi-source data, a fault probability value is output, and an early warning is triggered when the fault probability value meets the early warning conditions.

2. The three-phase common tank GIL settlement fault detection method according to claim 1 is characterized in that: Before performing multi-physics field coupling analysis on the pre-processed multi-source data based on the pre-built dynamic adaptive digital twin model, outputting a fault probability value, and triggering an early warning when the fault probability value meets the early warning condition, the method further includes: Build a dynamic and adaptive digital twin model based on transfer learning and federated learning.

3. The three-phase common tank GIL settlement fault detection method according to claim 2, characterized in that: The dynamic adaptive digital twin model integrates a multi-physics field coupling analysis module, including mechanical field, thermal field and electromagnetic field simulation units, and outputs a fault probability value through joint optimization of finite element analysis and machine learning.

4. The method for detecting settlement failure of a three-phase common-tank GIL according to claim 1, characterized in that: The method of performing multi-physics field coupling analysis on pre-processed multi-source data based on the pre-built dynamic adaptive digital twin model, outputting a fault probability value, and triggering an early warning when the fault probability value meets the early warning condition includes: Based on the pre-built dynamic adaptive digital twin model, multi-physical field coupling analysis is performed on the pre-processed multi-source data, and a fault probability value is output. When the fault probability value is greater than or equal to a preset threshold, an early warning is triggered.

5. A three-phase common box GIL settlement fault detection system, characterized in that: include: A GIL pipe, a rubber gasket, a clamp, a strain gauge sensor, a vibration sensor, a displacement sensor, and a current sensor; the clamp is fixed to a bracket of the GIL pipe, the rubber gasket is arranged between one end of the clamp and the lower contact surface of the GIL pipe, the strain gauge sensor is fixed to the other end of the clamp, and the current sensor, the vibration sensor, and the displacement sensor are respectively arranged at the bottom of the GIL pipe; the system also includes a processor; The processor is used to collect multi-source data of the GIL pipeline in real time through a heterogeneous sensor network; The processor is further configured to pre-process the multi-source data in combination with an edge-cloud collaborative architecture; The processor is also used to perform multi-physical field coupling analysis on the pre-processed multi-source data based on a pre-built dynamic adaptive digital twin model, output a fault probability value, and trigger an early warning when the fault probability value meets the early warning condition.

6. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the three-phase common tank GIL settlement fault detection method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the three-phase common tank GIL settlement fault detection method according to any one of claims 1 to 4 when executed.

8. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the computer program implements the three-phase common tank GIL settlement fault detection method according to any one of claims 1 to 4.

Images